Laundry treating apparatus control method and device

Abstract

The application provides a control method and device of a clothes processing equipment, wherein the method comprises: acquiring a footstep audio signal of a user; performing feature extraction on the footstep audio signal of the user to obtain an extracted feature corresponding to the footstep audio signal; inputting the extracted feature into a first model pre-trained to represent a user straight walking towards the equipment to obtain a first probability value, inputting the extracted feature into a second model pre-trained to represent a user turning after straight walking towards the equipment to obtain a second probability value, and inputting the extracted feature into a third model pre-trained to represent a user passing by the equipment to obtain a third probability value; obtaining a recognition result of the footstep audio signal based on the first probability value, the second probability value and the third probability value, and sending a control instruction to the equipment according to the recognition result. The method of the application realizes accurate judgment of the intention of a user using the clothes processing equipment.

Description

Technical Field

[0001] This invention belongs to the field of smart home appliance technology, specifically relating to a control method and device for clothing processing equipment. Background Technology

[0002] Currently, smart home appliances possess various intelligent control functions through diverse control methods, greatly facilitating user operation.

[0003] Existing smart washing machine start-up control methods collect and identify user footsteps. If the footsteps are detected as close to the washing machine, it's determined that the user intends to use it, and the washing machine turns on. Conversely, if the footsteps are detected as far away, it's determined that the user does not intend to use it, and the washing machine remains off. Footstep sound identification primarily involves comparing the loudness of the footsteps with a preset threshold to determine their distance from the washing machine. Specifically, if the loudness of the footsteps is greater than or equal to the preset threshold, it's identified as the footsteps being close to the washing machine; conversely, if the loudness is less than the preset threshold, it's identified as the footsteps being far away.

[0004] Existing methods for controlling the power on of smart washing machines are not accurate in determining user intentions and may misjudge user intentions. Summary of the Invention

[0005] This invention provides a method and apparatus for controlling clothing processing equipment, which solves the problem that existing intelligent washing machine start-up control methods are not accurate in determining user intentions and may misjudge user intentions.

[0006] In a first aspect, the present invention provides a control method for a garment processing device, comprising:

[0007] Acquire the user's footstep audio signal;

[0008] Feature extraction is performed on the user's footstep audio signal to obtain the extracted features corresponding to the footstep audio signal;

[0009] The extracted features are input into a pre-trained first model representing a user moving straight toward the device to obtain a first probability value; the extracted features are input into a pre-trained second model representing a user turning around after moving straight toward the device to obtain a second probability value; and the extracted features are input into a pre-trained third model representing a user passing by the device to obtain a third probability value.

[0010] Based on the first probability value, the second probability value, and the third probability value, the recognition result of the footstep audio signal is obtained, and a control command is sent to the device according to the recognition result.

[0011] Optionally, the step of extracting features from the user's footstep audio signal to obtain the extracted features corresponding to the footstep audio signal includes:

[0012] Perform a short-time Fourier transform on the user's footstep audio signal to obtain the spectrogram corresponding to the footstep audio signal;

[0013] The spectrogram is input into a deep learning network to obtain the frequency variation features corresponding to the footstep audio signal.

[0014] Optionally, the frequency change feature is a curve showing the frequency changing over time after numerical linear fitting.

[0015] Optionally, the step of inputting the extracted features into a pre-trained first model representing a user moving straight toward the device to obtain a first probability value, inputting the extracted features into a pre-trained second model representing a user moving straight toward the device and then turning to obtain a second probability value, and inputting the extracted features into a pre-trained third model representing a user passing by the device to obtain a third probability value includes:

[0016] The extracted features are input into a pre-trained first model representing a user moving straight toward the device. The similarity probability between the extracted features and the first recognition features of the first model is calculated to obtain a first probability value of the extracted features relative to the first recognition features.

[0017] The extracted features are input into a pre-trained second model that represents a user turning around after walking straight toward the device. The similarity probability between the extracted features and the second recognition features of the second model is calculated to obtain a second probability value of the extracted features relative to the second recognition features.

[0018] The extracted features are input into a pre-trained third model representing a user passing by the device. The similarity probability between the extracted features and the third recognition features of the third model is calculated to obtain a third probability value of the extracted features relative to the third recognition features.

[0019] Optionally, obtaining the recognition result of the footstep audio signal based on the first probability value, the second probability value, and the third probability value, and sending a control command to the device according to the recognition result, includes:

[0020] The first probability value, the second probability value, and the third probability value are compared to obtain the maximum probability value. The maximum probability value is then compared with a preset threshold to obtain the following recognition result of the footstep audio signal, and the following corresponding control commands are sent to the device:

[0021] If the maximum probability value is greater than or equal to a preset threshold, and the maximum probability value is a first probability value, then the footstep audio signal is a signal representing the user walking straight toward the device. Accordingly, a first control command is sent to the device. The first control command is any one of the following: a power-on command, a power-on and door-opening command, or other function commands.

[0022] If the maximum probability value is greater than or equal to a preset threshold, and the maximum probability value is greater than the second probability value, then the footstep audio signal is a signal representing the user turning around after walking straight toward the device. Accordingly, a second control command is sent to the device, and the second control command is an empty data command.

[0023] If the maximum probability value is greater than or equal to a preset threshold, and the maximum probability value is greater than the third probability value, then the footstep audio signal is a signal representing the user passing by the device, and accordingly, the second control command is sent to the device;

[0024] If the maximum probability value is less than a preset threshold, then the second control command is sent to the device.

[0025] Optionally, after sending the second control command to the device if the maximum probability value is less than a preset threshold, the process includes:

[0026] The footstep audio signal is used as an audio training sample to train and update the pre-trained first model, second model, and third model.

[0027] Optionally, the acquisition of the user's footstep audio signal includes:

[0028] The device collects footstep audio signals within a preset threshold range.

[0029] In a second aspect, the present invention provides a signal processing apparatus, comprising:

[0030] Processor and memory;

[0031] The memory stores the processor-executable instructions;

[0032] The processor executes the executable instructions stored in the memory, causing the processor to perform the method described above.

[0033] Thirdly, the present invention provides a storage medium storing computer execution instructions, which, when executed by a processor, are used to implement the above-described method.

[0034] Fourthly, the present invention provides a program product including a computer program that, when executed by a processor, implements the above-described method.

[0035] The clothing processing equipment control method and apparatus provided by this invention acquires the user's footstep audio signal and extracts its features to obtain extracted features. Then, the extracted features are input into a pre-trained first model, a second model, and a third model that can represent different user intentions to obtain a first probability value, a second probability value, and a third probability value, respectively. Based on the first probability value, the second probability value, and the third probability value, the recognition result of the footstep audio signal is obtained, thereby accurately determining the user's intention to use the clothing processing equipment. This achieves precise control of the functional operation of the clothing processing equipment and avoids the user's footsteps from accidentally waking up the clothing processing equipment. Attached Figure Description

[0036] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. The drawings are as follows:

[0037] Figure 1 This is a diagram of an existing smart washing machine power-on control scenario;

[0038] Figure 2 This is a control system diagram of the clothing processing equipment provided in an embodiment of the present invention;

[0039] Figure 3 This is a schematic diagram illustrating the effect of the control method for the clothing processing equipment provided in this embodiment of the invention;

[0040] Figure 4 This is a flowchart of the control method for the clothing processing equipment provided in the embodiments of the present invention;

[0041] Figure 5 These are the fitted frequency-time curves corresponding to the three types of footstep audio signals provided in this embodiment of the invention;

[0042] Figure 6 This is a schematic diagram of the signal processing device provided in an embodiment of the present invention. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0044] Existing smart washing machine power-on control methods, to avoid accidental wake-up operations, often determine the user's intention to use the washing machine by collecting the user's footsteps and analyzing the loudness of the footsteps. For example, the loudness value of the collected footsteps is compared with a preset threshold of the washing machine. If the loudness value is greater than or equal to the preset threshold, it is assumed that the user intends to use the washing machine, and the machine is automatically turned on in advance; conversely, if the loudness value is less than the preset threshold, it is assumed that the user does not intend to use the washing machine, and the washing machine remains off even if the user's footsteps are detected.

[0045] Existing methods for controlling the power on of smart washing machines are not accurate in determining user intentions, and there are instances where user intentions are misinterpreted. For example... Figure 1 As shown, Figure 1 This is a diagram of an existing smart washing machine power-on control scenario. Figure 1 The diagram illustrates three exemplary scenarios, A, B, and C, when a user walks around the washing machine. Figure 1 In scenario A, when a user needs to use the washing machine, they will walk straight towards it. The closer the user gets to the washing machine, the louder the sound of their footsteps becomes, indicating the washing machine's intention to use the machine and prompting it to turn it on in advance. However, if the user walks straight towards the washing machine and then turns around, or if the user passes by the washing machine, such as... Figure 1 As shown in scenarios B and C, the user did not intend to use the washing machine; the machine was simply accidentally activated and turned on due to the user's proximity to it while walking. Based on existing smart washing machine start-up control methods, the washing machine collects... Figure 1 In scenarios B and C, the footsteps near the washing machine have a loudness value exceeding a preset threshold, causing the washing machine to turn on even if the user does not intend to use it. Furthermore, if the user moves away from the washing machine but still makes footsteps with a loudness value exceeding the preset threshold, the washing machine will also be falsely awakened and turned on. Therefore, the existing smart washing machine start-up control method suffers from inaccurate judgment of user intent.

[0046] Based on this, the present invention proposes a control method for clothing processing equipment to solve the problem that the existing intelligent washing machine start-up control method does not accurately determine the user's intention.

[0047] The following is combined with Figure 2 and Figure 3 The control method for the garment processing equipment proposed in this invention will be described. Figure 2 This is a control system diagram of the clothing processing equipment provided in an embodiment of the present invention. Figure 3 This is a schematic diagram illustrating the effect of the control method for the clothing processing equipment provided in an embodiment of the present invention. Figure 2As shown, the control system of the clothing processing equipment provided by the present invention includes: a clothing processing device 11 and a signal processing device 12, wherein the clothing processing device includes a controller 111 and a data acquisition unit 112. The signal processing device 12 can communicate with both the controller 111 and the data acquisition unit 112. Optionally, the signal processing device 12 can be located at the network edge cloud. The signal processing device 12 can also be installed on the clothing processing device 11. Preferably, when the signal processing device 12 is installed on the clothing processing device 11, the signal processing device 12 is wired to both the controller 111 and the data acquisition unit 112 to avoid abnormal network wireless signal interference blocking the communication between the signal processing device 12 and the controller 111 and the data acquisition unit 112. The data acquisition unit 112 collects user footstep audio signals around the clothing processing device 11. The signal processing device 12 obtains the user footstep audio signals from the data acquisition unit 112 and performs recognition processing on the user footstep audio signals to obtain recognition results. The signal processing device 12 determines the user's intention to use the clothing processing device 11 based on the recognition result, and sends the control command corresponding to the recognition result to the controller 111 to realize the corresponding function execution of the clothing processing device 11. Optionally, the clothing processing device 11 can be a washing machine or a clothes dryer, and the present invention does not specifically limit it.

[0048] Specifically, the signal processing device 12 acquires the user's footstep audio signal, then extracts features from the user's footstep audio signal to obtain extracted features corresponding to the footstep audio signal. Next, the signal processing device 12 inputs the extracted features into a pre-trained first model representing the user walking straight towards the device to obtain a first probability value, inputs the extracted features into a pre-trained second model representing the user walking straight towards the device and then turning to obtain a second probability value, and inputs the extracted features into a pre-trained third model representing the user passing by the device to obtain a third probability value. Finally, the signal processing device 12 obtains the recognition result of the footstep audio signal based on the first probability value, the second probability value, and the third probability value. Specifically, the recognition result includes, but is not limited to, the following results: the acquired user footstep audio signal is a signal of the user walking straight towards the device, the acquired user footstep audio signal is a signal of the user walking straight towards the device and then turning to obtain a signal, and the acquired user footstep audio signal is a signal of the user passing by the device. The signal of the user walking straight towards the device indicates that the user intends to use the device, while the signal of the user walking straight towards the device and then turning to obtain a signal, and the signal of the user passing by the device, both indicate that the user does not intend to use the device. Based on the recognition results, the signal processing device 12 sends control commands corresponding to the recognition results to the device, such as commands to power on the device or commands to prevent the device from performing functional operations, in order to achieve the following: Figure 3 The scene effect shown. For example, as shown... Figure 2As shown in scenario D, when a user walks straight towards the garment processing device 11, the garment processing device 11 is turned on under the function execution of the controller 111. When the user turns around after walking straight towards the garment processing device 11, the garment processing device 11 remains in the off state under the function execution of the controller 111, as shown in scenario D. Figure 2 As shown in scenario E, when a user passes by the clothing processing device 11, the clothing processing device 11 remains in the off state under the function execution of the controller 111, as follows. Figure 2 As shown in the F scenario.

[0049] The control method for a clothing processing device provided in this invention can accurately identify and determine a user's intention to use the device by recognizing footsteps around the device. This method achieves precise control over the device's functions and avoids accidental activation by footsteps.

[0050] The following is combined with Figure 4 The control method of the garment processing equipment provided by the present invention will be described in detail. Figure 4 This is a flowchart of the control method for the clothing processing equipment provided in the embodiments of the present invention. Figure 4 The execution subject of the embodiment shown is Figure 2 The signal processing device 12 in the illustrated embodiment, such as Figure 4 As shown, the method includes:

[0051] S101, Acquire the user's footstep audio signal;

[0052] Specifically, the signal processing device 12 acquires the user's footstep audio signal from the collector 112 and stores it in the signal processing device 12.

[0053] Optionally, the collector 112 collects footstep audio signals within a preset threshold range of the clothing processing device 11. For example, a monitoring space range, such as an infrared monitoring space range, can be preset on the clothing processing device 11. Once a user enters the monitoring space range, the collector 112 begins collecting the user's footstep audio signals, avoiding increased signal processing workload for the signal processing device 12 due to collecting footstep audio signals outside the monitoring space range, and preventing the collection of useless audio signals from occupying the storage space of the signal processing device 12.

[0054] S102. Extract features from the user's footstep audio signal to obtain the extracted features corresponding to the footstep audio signal;

[0055] Specifically, the signal processing device 12 performs feature extraction on the user's footstep audio signal obtained in step S101 to obtain the extracted features corresponding to the footstep audio signal.

[0056] Specifically, the signal processing device 12 performs a short-time Fourier transform on the user's footstep audio signal to obtain the spectrogram corresponding to the footstep audio signal. Since the spectrogram is the frequency spectrum of the sound signal, describing the relationship between the frequency, time, and intensity of the sound signal, it is easier to extract the frequency information of the sound signal subsequently. Next, the signal processing device 12 inputs the spectrogram into a deep learning network, and after local frequency feature extraction and local frequency feature clustering, obtains the frequency change features corresponding to the footstep audio signal.

[0057] Furthermore, this frequency variation characteristic can be a curve showing the frequency changing over time after numerical linear fitting. For example, Figure 5 These are the fitted frequency-time curves corresponding to the three types of footstep audio signals provided in this embodiment of the invention. For example... Figure 5 As shown, when a user walks straight toward the clothing processing device 11, because the user needs to use the device, their walking frequency remains constant as they move away from it, according to their walking habits. As they approach the device, the frequency decreases until it stops. When the user turns after walking straight toward the device, the frequency remains unchanged as they move away from it. As they approach the device and prepare to turn, the frequency decreases until they complete the turn and continue walking at a certain frequency. The walking frequency remains constant as the user passes the device. This frequency variation characteristic characterizes the frequency variation of the footsteps of a user needing to use the clothing processing device or avoiding obstacles (i.e., the clothing processing device) during walking. Therefore, using this frequency variation characteristic avoids the adverse effects of differences in the loudness of footsteps emitted by different users on the determination of user intent, as is present in existing technologies. This frequency variation characteristic is applicable to any user, eliminating the influence of differences in footstep sounds (such as loudness differences) on the accurate determination of a user's intent to use the clothing processing device.

[0058] S103. Input the extracted features into a pre-trained first model representing the user moving straight toward the device to obtain a first probability value; input the extracted features into a pre-trained second model representing the user turning after moving straight toward the device to obtain a second probability value; and input the extracted features into a pre-trained third model representing the user passing by the device to obtain a third probability value.

[0059] Specifically, the signal processing device 12 inputs the extracted features obtained in step 102 into a pre-trained first model representing the user moving straight toward the device to obtain a first probability value, inputs the extracted features into a pre-trained second model representing the user turning after moving straight toward the device to obtain a second probability value, and inputs the extracted features into a pre-trained third model representing the user passing by the device to obtain a third probability value.

[0060] Further, the signal processing device 12 inputs the frequency change features obtained in step 102 into a pre-trained first model representing the user moving straight toward the clothing processing device 11, and performs a similarity probability calculation between the frequency change features and the first recognition features of the first model to obtain a first probability value W1 of the frequency change features relative to the first recognition features.

[0061] Next, the signal processing device 12 inputs the frequency change features obtained in step 102 into a pre-trained second model representing the user moving straight toward the clothing processing device 11, and performs a similarity probability calculation between the frequency change features and the second recognition features of the second model to obtain a second probability value W2 of the frequency change features relative to the second recognition features.

[0062] Continuing, the signal processing device 12 inputs the frequency change features obtained in step 102 into the pre-trained third model representing the user moving straight toward the clothing processing device 11, and performs a similarity probability calculation between the frequency change features and the third recognition features of the third model to obtain the third probability value W3 of the frequency change features relative to the third recognition features.

[0063] For example, the first identification feature, the second identification feature, and the third identification feature can also be as follows: Figure 5 The frequency-time curve shown is the result of numerical linear fitting.

[0064] Optionally, the signal processing device 12 can synchronously input the frequency change features obtained in step 102 into the pre-trained first model, second model, and third model, and simultaneously perform similarity probability calculations between the frequency change features and the first, second, and third recognition features to obtain the first probability value W1, the second probability value W2, and the third probability value W3, respectively, so as to improve the timeliness of probability value calculation.

[0065] S104. Based on the first probability value, the second probability value, and the third probability value, obtain the recognition result of the footstep audio signal, and send control commands to the device according to the recognition result;

[0066] Specifically, the signal processing device 12 determines and obtains the recognition result of the footstep audio signal based on the first probability value W1, the second probability value W2, and the third probability value W3 obtained in step S103. Then, according to the recognition result, the signal processing device 12 sends a control command to the clothing processing device 11. Specifically, the signal processing device 12 sends a control command to the controller 111 of the clothing processing device 11 so that the controller 111 can perform corresponding functional operations.

[0067] Specifically, based on the first probability value W1, the second probability value W2, and the third probability value W3 obtained in step S103, the signal processing device 12 determines and obtains the recognition result of the footstep audio signal through the following steps:

[0068] First, the signal processing device 12 compares the first probability value W1, the second probability value W2, and the third probability value W3 obtained in step S103 to obtain the maximum probability value. Then, the signal processing device 12 compares the maximum probability value selected by the comparison with a preset threshold W0 to obtain the following recognition result of the footstep audio signal, and sends the following corresponding control command to the clothing processing device 11:

[0069] If the maximum probability value is greater than or equal to the preset threshold W0, and the maximum probability value is the first probability value W1, then the recognition result is: the footstep audio signal is a signal of the user walking straight towards the clothing processing device 11. Accordingly, the signal processing device 12 sends a first control command to the controller 111 of the clothing processing device 11. Based on the received first control command, the controller 111 controls the clothing processing device 11 to perform corresponding functional operations, such as enabling the clothing processing device 11 to achieve the following... Figure 3 Powering on the D scene.

[0070] Optionally, the first control instruction can be any one of the following: a power-on instruction, a power-on and door-opening instruction, or another function instruction. For example, the first control instruction can be a power-on instruction, a power-on and door-opening instruction, or another function instruction.

[0071] If the maximum probability value is greater than or equal to the preset threshold W0, and the maximum probability value is the second probability value W2, then the recognition result is: the footstep audio signal is a signal indicating that the user has turned around after walking straight towards the clothing processing device 11. Accordingly, the signal processing device 12 sends a second control command to the controller 111 of the clothing processing device 11. Specifically, the second control command is a null data command. Based on the received second control command, the controller 111 does not perform any functional operations on the clothing processing device 11, such as keeping the clothing processing device 11 in a certain position. Figure 3 The shutdown state in the E-scenario.

[0072] Similarly, if the maximum probability value is greater than or equal to the preset threshold W0, and the maximum probability value is the third probability value W3, then the recognition result is: the footstep audio signal is the signal of a user passing by the clothing processing device 11. Accordingly, the signal processing device 12 sends a second control command to the controller 111 of the clothing processing device 11. Based on the received second control command, the controller 111 does not perform any functional operations on the clothing processing device 11, such as keeping the clothing processing device 11 in a certain position. Figure 3 The shutdown state in the F scene.

[0073] If the maximum probability value is less than the preset threshold W0, it indicates that the footstep audio signal does not belong to any of the following signals: the signal of the user walking straight towards the clothing processing device 11, the signal of the user turning after walking straight towards the clothing processing device 11, or the signal of the user passing by the clothing processing device 11. Accordingly, the signal processing device 12 sends a second control command to the controller 111 of the clothing processing device 11. Based on the received second control command, the controller 111 does not perform any functional operation on the clothing processing device 11.

[0074] Furthermore, if the signal processing device 12 compares the probability value W1, the second probability value W2, and the third probability value W3 obtained in step S103, and the maximum probability value obtained is less than a preset threshold W0, then, correspondingly, after the signal processing device 12 sends a second control command to the controller 111 of the clothing processing device 11, the signal processing device 12 uses the footstep audio signal as an audio training and update sample to train and update the pre-trained first model, second model, and third model.

[0075] Optionally, the signal processing device 12 can directly train and update the pre-trained first model, second model, and third model based on the audio training update sample.

[0076] Furthermore, if the pre-trained first, second, and third models used in the signal processing device 12 are obtained from a model training device, then the signal processing device 12 can also send the audio training update sample to the model training device to train and update the first, second, and third models used by the signal processing device 12. The signal processing device 12 can then obtain updated first, second, and third models from the model training device for the recognition of footstep audio signals.

[0077] The control method for a clothing processing device provided in this invention determines the recognition result of the user's footstep audio signal by extracting the frequency variation features of user footsteps around the clothing processing device and calculating the similarity probability value between the extracted features and the recognition features in the model. Based on the recognition result, the user's intention to use the clothing processing device is accurately determined. Furthermore, the control method for a clothing processing device provided in this invention uses frequency variation features as the recognition feature, avoiding the adverse effects of differences in footstep sounds (such as loudness values) emitted by different users on the determination of user intention in existing technologies. Compared with existing intelligent washing machine power-on control methods, the control method for a clothing processing device provided in this invention is more accurate in recognizing and judging the user's intention to use the device, achieving precise control of the functional operation of the clothing processing device and avoiding false wake-up of the clothing processing device by user footsteps.

[0078] This invention also provides a signal processing device. Figure 6 This is a schematic diagram of the signal processing device provided in an embodiment of the present invention. Figure 6 As shown, the signal processing device includes a processor 61 and a memory 62. The memory 62 stores executable instructions for the processor 61, enabling the processor 61 to execute the technical solutions of the above-described method embodiments. The implementation principle and technical effects are similar, and will not be repeated here. It should be understood that the processor 61 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor. The memory 62 may include high-speed RAM, and may also include non-volatile memory (NVM), such as at least one disk storage device, or a USB flash drive, external hard drive, read-only memory, disk, or optical disc, etc.

[0079] This invention also provides a storage medium storing computer-executable instructions. When these instructions are executed by a processor, they implement the control method of the clothing processing device described above. The storage medium can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0080] An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Alternatively, the storage medium can be an integral part of the processor. Both the processor and the storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and storage medium can exist as discrete components in an electronic device or host device.

[0081] This invention also provides a program product, such as a computer program, which, when executed by a processor, implements the control method for the garment processing equipment covered by this invention.

[0082] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0083] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A control method of a laundry treating apparatus, characterized by, The method comprises: obtaining a footstep audio signal of a user; extracting features of the footstep audio signal of the user to obtain extracted features corresponding to the footstep audio signal; inputting the extracted features into a first model pre-trained to represent a user walking straight towards the device to obtain a first probability value, inputting the extracted features into a second model pre-trained to represent a user turning after walking straight towards the device to obtain a second probability value, and inputting the extracted features into a third model pre-trained to represent a user passing by the device to obtain a third probability value; based on the first probability value, the second probability value and the third probability value, obtaining a recognition result of the footstep audio signal, and sending a control instruction to the device according to the recognition result.

2. The method of claim 1, wherein, The method comprises: performing short-time Fourier transform on the footstep audio signal of the user to obtain a spectrogram corresponding to the footstep audio signal; inputting the spectrogram into a deep learning network to obtain a frequency change feature corresponding to the footstep audio signal.

3. The method of claim 2, wherein, The frequency change feature is a curve of frequency change over time after numerical linear fitting.

4. The method of claim 1, wherein, The method comprises: inputting the extracted features into the first model pre-trained to represent a user walking straight towards the device, performing similarity probability calculation on the extracted features and first recognition features of the first model to obtain a first probability value of the extracted features relative to the first recognition features; inputting the extracted features into the second model pre-trained to represent a user turning after walking straight towards the device, performing similarity probability calculation on the extracted features and second recognition features of the second model to obtain a second probability value of the extracted features relative to the second recognition features; inputting the extracted features into the third model pre-trained to represent a user passing by the device, performing similarity probability calculation on the extracted features and third recognition features of the third model to obtain a third probability value of the extracted features relative to the third recognition features.

5. The method according to any one of claims 1 to 4, characterized in that, The method comprises: comparing the first probability value, the second probability value and the third probability value to obtain a maximum probability value, comparing the maximum probability value with a preset threshold to obtain the following recognition result of the footstep audio signal and send the following corresponding control instruction to the device: If the maximum probability value is greater than or equal to a preset threshold value, and the maximum probability value is a first probability value, the footstep audio signal is a signal representing that the user is walking straight toward the device, and accordingly, a first control instruction is sent to the device, the first control instruction being any one of a power-on instruction, a power-on and door-opening instruction, and other function instructions; If the maximum probability value is greater than or equal to a preset threshold value, and the maximum probability value is a second probability value greater than, the footstep audio signal is a signal representing that the user is walking straight toward the device and then turns, and accordingly, a second control instruction is sent to the device, the second control instruction being a null data instruction; If the maximum probability value is greater than or equal to a preset threshold value, and the maximum probability value is a third probability value greater than, the footstep audio signal is a signal representing that the user is passing by the device, and accordingly, the second control instruction is sent to the device; If the maximum probability value is less than a preset threshold value, the second control instruction is sent to the device.

6. The method of claim 5, wherein, After the maximum probability value is less than a preset threshold value, the second control instruction is sent to the device, comprising: The footstep audio signal is used as an audio training sample to update the first model, the second model, and the third model.

7. The method according to any one of claims 1 to 4, characterized in that, The footstep audio signal of the user is obtained, comprising: Collecting the footstep audio signal within a preset range threshold of the device.

8. A signal processing device, characterized by Comprise: A processor and a memory; The memory stores executable instructions of the processor; The processor executes the executable instructions stored in the memory, so that the processor executes the method of any one of claims 1-7.

9. A storage medium, characterized by The storage medium stores computer execution instructions, and the computer execution instructions are executed by the processor to implement the method of any one of claims 1-7.

10. A program product, characterized by A computer program is executed by the processor to implement the method of any one of claims 1-7.

Images