Human body detection method, device and equipment based on ultrasonic waves and storage medium

Abstract

The invention provides a human body detection method and device based on ultrasonic waves, equipment and a storage medium, and relates to the technical field of intelligent household appliances. The invention discloses a human body detection method based on ultrasonic waves, and the method comprises the steps: judging whether a reflected wave is reflected by a human body or not according to the similarity between a vector feature of a high-gamete sub-band in the reflected wave and a vector feature of a high-frequency sub-band in a pre-stored human body reflected wave. Through the mode, the accuracy of human body detection is improved, the probability of misoperation of the clothes processing equipment is reduced, and the use experience feeling of a user is improved.

Description

Technical Field

[0001] The present application belongs to the technical field of smart home appliances, and specifically relates to an ultrasonic-based human body detection method, device, equipment and storage medium. Background Art

[0002] With the continuous improvement of production technology, all clothing processing equipment currently includes voice interaction functions. Users can remotely control the clothing processing equipment to turn on or perform corresponding operations through voice commands. However, voice commands are generally common, which causes clothing processing equipment to misrecognize commands, resulting in unnecessary waste of resources.

[0003] In the prior art, in the face of the problem of misidentification of commands by the above-mentioned laundry processing device, the commonly used means are: when the laundry processing device receives a voice command, it sends ultrasonic waves in that direction and receives reflected waves, and determines whether the user is within the preset range of the laundry processing device according to the reflected waves. It also determines whether to execute the voice command based on the distance between the user and the laundry processing device.

[0004] However, the method of detecting the human body through ultrasound may be interfered by other objects, resulting in misidentification, thereby reducing the human body recognition rate and affecting the user experience. Summary of the invention

[0005] In order to solve the above problems in the prior art, the present application provides an ultrasound-based human body detection method, device, equipment and storage medium.

[0006] In a first aspect, the present application provides a human body detection method based on ultrasound, the method comprising:

[0007] Acquiring a sound source position according to a voice command received by the laundry processing device, and controlling the laundry processing device to send ultrasonic waves toward the sound source position and receive reflected waves;

[0008] Decomposing the reflected wave to obtain a contrast subband, obtaining a feature vector according to the contrast subband, and obtaining a similarity between the feature vector and a reference vector, wherein the reference vector is obtained in advance according to an echo reflected by a user at a reference position corresponding to the sound emission position;

[0009] According to the similarity, it is determined whether a user is detected within a preset range of the laundry processing device, wherein the reference position is within the preset range.

[0010] In a possible implementation manner, decomposing the reflected wave to obtain a comparison subband, obtaining a feature vector according to the comparison subband, and obtaining a similarity between the feature vector and a reference vector includes:

[0011] Decomposing the reflected wave by wavelet packet to obtain the contrast subband;

[0012] Vectorizing the contrast subband to obtain a characteristic vector of the reflected wave;

[0013] The similarity between the feature vector and the reference vector is obtained according to the cosine similarity calculation.

[0014] In a possible implementation manner, decomposing the reflected wave by using a wavelet packet to obtain the contrast sub-band includes:

[0015] Decomposing the reflected wave by wavelet packets to obtain a plurality of sub-bands with different frequencies, and dividing each sub-band into a high-frequency sub-band area or a low-frequency sub-band area according to the frequency of each sub-band;

[0016] According to the magnitude relationship between the target frequency and the boundary frequency, the comparison sub-band is obtained from the corresponding sub-band area;

[0017] The boundary frequency is used to divide the high-frequency sub-band area and the low-frequency sub-band area, and the comparison sub-band is the sub-band closest to the target frequency.

[0018] In a possible implementation, judging, according to the similarity, whether a user is detected within a preset range of the laundry processing device includes:

[0019] If the similarity is greater than or equal to the first similarity, it is determined that a user is detected within a preset range of the laundry processing device;

[0020] If the similarity is less than the first similarity and greater than or equal to the second similarity, then acquiring the echo time;

[0021] According to the echo time and the reference time, it is determined whether a user is detected within a preset range of the clothing processing device, wherein the reference time is obtained in advance based on an echo reflected by the user when ultrasonic waves are emitted to a reference position.

[0022] In a possible implementation manner, judging whether a user is detected within a preset range of the laundry processing device according to the echo time and the reference time includes:

[0023] If the ratio of the echo time to the reference time is less than or equal to a preset ratio, it is determined that a user is detected within a preset range of the laundry processing device.

[0024] In a possible implementation manner, before acquiring the sound position according to the voice instruction, the method further includes:

[0025] Dividing a preset area of ​​the laundry processing device into a plurality of reference areas, and acquiring a reference position corresponding to each of the reference areas;

[0026] Controlling the laundry processing device to transmit ultrasonic waves toward each reference area, and receiving echoes reflected back by the user at the corresponding reference position;

[0027] Decomposing the echo by wavelet packets, obtaining a reference subband corresponding to each echo, and vectorizing the reference subband to obtain a reference vector corresponding to each reference position;

[0028] The reference time corresponding to each reference position is obtained according to the interval time from when the laundry processing device sends the ultrasonic wave to when each echo is received.

[0029] In a possible implementation, obtaining the sound position according to the voice instruction includes:

[0030] According to the order in which the multi-channel microphones of the voice module of the laundry processing device receive the voice command, obtaining a target microphone, wherein the target microphone is the first microphone to receive the voice command;

[0031] amplifying the received signal of the target microphone and combining it with the received signals of other microphones;

[0032] The sound emission position is obtained according to the combined signal.

[0033] In a second aspect, the present application provides an ultrasonic-based human body detection control device, comprising: an acquisition module, a calculation module and a judgment module, wherein:

[0034] The acquisition module is used to acquire a sound source position according to a voice instruction received by the clothes processing device, and control the clothes processing device to send ultrasonic waves toward the sound source position and receive reflected waves;

[0035] The calculation module is used to decompose the reflected wave to obtain a contrast sub-band, obtain a feature vector according to the contrast sub-band, and obtain a similarity between the feature vector and a reference vector, wherein the reference vector is obtained in advance according to an echo reflected by the user at a reference position corresponding to the sound emission position;

[0036] The judgment module is used to judge whether a user is detected within a preset range of the clothing processing device according to the similarity, wherein the reference position is within the preset range.

[0037] In a possible implementation manner, the calculation module is further used to:

[0038] Decomposing the reflected wave by wavelet packet to obtain the contrast subband;

[0039] Vectorizing the contrast subband to obtain a characteristic vector of the reflected wave;

[0040] The similarity between the feature vector and the reference vector is obtained according to the cosine similarity calculation.

[0041] In a possible implementation manner, the calculation module is further used to:

[0042] Decomposing the reflected wave by wavelet packets to obtain a plurality of sub-bands with different frequencies, and dividing each sub-band into a high-frequency sub-band area or a low-frequency sub-band area according to the frequency of each sub-band;

[0043] According to the magnitude relationship between the target frequency and the boundary frequency, the comparison sub-band is obtained from the corresponding sub-band area;

[0044] The boundary frequency is used to divide the high-frequency sub-band area and the low-frequency sub-band area, and the comparison sub-band is the sub-band closest to the target frequency.

[0045] In a possible implementation manner, the determination module is further configured to:

[0046] If the similarity is greater than or equal to the first similarity, it is determined that a user is detected within a preset range of the laundry processing device;

[0047] If the similarity is less than the first similarity and greater than or equal to the second similarity, then acquiring the echo time;

[0048] According to the echo time and the reference time, it is determined whether a user is detected within a preset range of the clothing processing device, wherein the reference time is obtained in advance based on an echo reflected by the user when ultrasonic waves are emitted to a reference position.

[0049] In a possible implementation manner, the determination module is further configured to:

[0050] If the ratio of the echo time to the reference time is less than or equal to a preset ratio, it is determined that a user is detected within a preset range of the laundry processing device.

[0051] In a possible implementation manner, the acquisition module is further used to:

[0052] Dividing a preset area of ​​the laundry processing device into a plurality of reference areas, and acquiring a reference position corresponding to each of the reference areas;

[0053] Controlling the laundry processing device to transmit ultrasonic waves toward each reference area, and receiving echoes reflected back by the user at the corresponding reference position;

[0054] Decomposing the echo by wavelet packets, obtaining a reference subband corresponding to each echo, and vectorizing the reference subband to obtain a reference vector corresponding to each reference position;

[0055] The reference time corresponding to each reference position is obtained according to the interval time from when the laundry processing device sends the ultrasonic wave to when each echo is received.

[0056] In a possible implementation manner, the acquisition module is further used to:

[0057] According to the order in which the multi-channel microphones of the voice module of the laundry processing device receive the voice command, obtaining a target microphone, wherein the target microphone is the first microphone to receive the voice command;

[0058] amplifying the received signal of the target microphone and combining it with the received signals of other microphones;

[0059] The sound emission position is obtained according to the combined signal.

[0060] In a third aspect, the present application provides a clothes processing device, comprising: at least one processor and a memory, wherein:

[0061] The memory is used to store computer-executable instructions;

[0062] The at least one processor is used to execute the computer-executable instructions stored in the memory, so that the at least one processor executes the ultrasound-based human body detection method as described in any one of the first aspects.

[0063] In a fourth aspect, the present application provides a computer storage medium, wherein the computer storage medium stores computer execution instructions, and when the computer execution instructions are executed by a processor, they are used to implement the ultrasound-based human body detection method as described in any of the above items.

[0064] In a fifth aspect, the present application also provides a computer program product, including a computer program, which, when executed by a processor, can implement the steps of the ultrasound-based human body detection method as described in any of the above items.

[0065] The present application provides a human body detection method, device, equipment and storage medium based on ultrasound, which determines whether the reflected wave is reflected by the human body according to the similarity between the vector features of the high-frequency subband in the reflected wave and the vector features of the high-frequency subband in the pre-stored human body reflected wave. Through the above method, the accuracy of human body detection is increased, the probability of misoperation of clothing processing equipment is reduced, and the user experience is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0067] Figure 1A schematic diagram of the reference position division of the laundry treatment equipment;

[0068] Figure 2 A schematic diagram of a human body detection method based on ultrasound provided in an embodiment of the present application Figure 1 ;

[0069] Figure 3 A schematic diagram of a human body detection method based on ultrasound provided in an embodiment of the present application Figure 2 ;

[0070] Figure 4 A schematic diagram of a human body detection method based on ultrasound provided in an embodiment of the present application Figure 3 ;

[0071] Figure 5 A schematic diagram of the structure of an ultrasonic-based human body detection control device provided in an embodiment of the present application;

[0072] Figure 6 A schematic structural diagram of a clothing processing device provided in an embodiment of the present application.

[0073] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0074] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0075] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in sequences other than those illustrated or described herein, for example.

[0076] In the embodiments of the present application, the words "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0077] In order to increase the interaction between smart home appliances and users, most smart home appliances can interact with users' voices and perform corresponding operations according to users' voice commands. Similar to clothing processing equipment, due to the function of the equipment, the voice commands are relatively simple and easy to be misjudged. The existing technology adds a process of judging the distance between the user and the clothing processing equipment. When a user is detected in the clothing processing equipment, the voice command received by the clothing processing equipment is executed.

[0078] However, the method of detecting the human body through ultrasound may be interfered by other objects, resulting in misidentification, thereby reducing the human body recognition rate and affecting the user experience.

[0079] The present application provides a human body detection method, device, equipment and storage medium based on ultrasound, which determines whether the reflected wave is reflected by the human body according to the similarity between the vector features of the high-frequency subband in the reflected wave and the vector features of the high-frequency subband in the pre-stored human body reflected wave. Through the above method, the accuracy of human body detection is increased, the probability of misoperation of clothing processing equipment is reduced, and the user experience is improved.

[0080] Next, the technical solution shown in the present application is described in detail through specific embodiments. It should be noted that the following embodiments can exist independently or in combination with each other, and the same or similar contents will not be described repeatedly in different embodiments.

[0081] Figure 1 This is a schematic diagram of the reference position division of the clothing processing equipment. As shown in the figure:

[0082] The preset range of the device is divided into 4 reference areas, each of which has a reference position. When the clothing treatment device receives the reflected wave, the sound position A is obtained based on the reflected wave, and then the reference information of the reference position A corresponding to the reference area to which the sound position A belongs needs to be obtained. By comparing the information of the reflected wave with the reference information of the reference position A, it is determined whether the user is detected within the preset range of the clothing treatment device.

[0083] Figure 2 A schematic diagram of a human body detection method based on ultrasound provided in an embodiment of the present application Figure 1 .like Figure 2 As shown, the method includes:

[0084] S201. Acquire a sound source position according to a voice instruction received by a clothes processing device, and control the clothes processing device to send ultrasonic waves toward the sound source position and receive reflected waves.

[0085] In this step, the specific steps of obtaining the sound position are:

[0086] According to the order in which the multi-channel microphones of the voice module of the laundry processing device receive the voice command, obtaining a target microphone, wherein the target microphone is the first microphone to receive the voice command;

[0087] The received signal of the target microphone is amplified and combined with the received signals of other microphones, and the sound position is obtained according to the combined signal.

[0088] Furthermore, after the reflected wave is received, relevant information is obtained according to the reflected wave to determine whether the reflected wave is a reflected wave passing through the human body.

[0089] S202: Decompose the reflected wave to obtain a comparison sub-band, obtain a feature vector according to the comparison sub-band, and obtain a similarity between the feature vector and a reference vector.

[0090] In this step, different body shapes and positions of users have an impact on the reflected wave. Therefore, it is possible to determine whether the reflected wave is reflected by the user based on the similarity between the reflected wave and the reference wave reflected back by the user within the pre-stored preset range. However, considering the impact of the position on the reflected wave, it is necessary to select the reference wave at the position closest to the direction of the sound. Since the position of the user cannot be determined within the preset range of the clothing processing equipment, a large number of reference waves need to be acquired in advance. Therefore, it is difficult to compare the waveform similarity. Taking into account the characteristics of the vector, the present application chooses to determine whether the reflected wave is reflected by the human body by the similarity between the characteristic vector of the reflected wave and the reference vector of the reference wave.

[0091] The reference vector is obtained in advance based on the echo reflected by the user at the reference position corresponding to the sound emission position.

[0092] Furthermore, although the size of the characteristic vector of the ultrasonic wave reflected back by the user at different positions within the preset range is not much different, the vector has a direction in addition to the size, and the direction also affects the similarity of the vector, so it is necessary to divide the preset range into multiple reference areas and obtain the reference vector corresponding to each reference area. The process of obtaining the reference vector is:

[0093] Dividing a preset area of ​​the laundry processing device into a plurality of reference areas, and acquiring a reference position corresponding to each of the reference areas;

[0094] Controlling the laundry processing device to transmit ultrasonic waves toward each reference area, and receiving echoes reflected back by the user at the corresponding reference position;

[0095] Decomposing the echo by wavelet packets, obtaining a reference subband corresponding to each echo, and vectorizing the reference subband to obtain a reference vector corresponding to each reference position;

[0096] The reference time corresponding to each reference position is obtained according to the interval time from when the laundry processing device sends the ultrasonic wave to when each echo is received.

[0097] S203. Determine, based on the similarity, whether a user is detected within a preset range of the laundry processing device, wherein the reference position is within the preset range.

[0098] In this step, the similarity is used to determine whether the reflected wave is likely to be reflected by the human body, that is, the higher the similarity, the greater the possibility that the reflected wave is reflected by the human body. When the similarity is too high, it is determined that the reflected wave is reflected by the user, that is, the user is detected within the preset range of the clothing processing device.

[0099] Exemplarily, the similarity between the feature vector and the reference vector is 0.99, and it is considered that the reflected wave is very similar to the reference wave, that is, the reflected wave is reflected back by the user, and the user is detected within the preset range of the clothing processing device.

[0100] The present application provides a human body detection method, device, equipment and storage medium based on ultrasound, which determines whether the reflected wave is reflected by the human body according to the similarity between the vector features of the high-frequency subband in the reflected wave and the vector features of the high-frequency subband in the pre-stored human body reflected wave. Through the above method, the accuracy of human body detection is increased, the probability of misoperation of clothing processing equipment is reduced, and the user experience is improved.

[0101] Figure 3 A schematic diagram of a human body detection method based on ultrasound is provided for the present application embodiment. Figure 2 The present application embodiment provides a detailed description of the steps for obtaining the similarity between the reference vector and the feature vector. Figure 3 As shown, the method includes:

[0102] S301 , decomposing the reflected wave by wavelet packets to obtain a plurality of sub-bands with different frequencies, and dividing each sub-band into a high-frequency sub-band area or a low-frequency sub-band area according to the frequency of each sub-band.

[0103] In this step, when the wavelet packet decomposes the reflected wave, the reflected wave is decomposed into multiple sub-bands with different frequencies. Since the number of sub-bands is uncertain, in order to facilitate the screening of the required comparison sub-bands from multiple sub-bands, the multiple sub-bands can be divided into different areas first.

[0104] Specifically, according to the size relationship between the sub-band frequency and the boundary frequency, each sub-band is divided into a high-frequency sub-band area or a low-frequency sub-band area, that is, if the sub-band frequency is less than the boundary frequency, the sub-band should be divided into the low-frequency sub-band area; if the sub-band frequency is greater than or equal to the boundary frequency, the sub-band should be divided into the high-frequency sub-band area.

[0105] Optionally, if the number of sub-bands is too large, additional sub-band areas may be added to further facilitate subsequent screening, for example, a high-frequency sub-band area, a medium-frequency sub-band area, and a low-frequency sub-band area.

[0106] S302: Acquire the comparison sub-band from the corresponding sub-band area according to the magnitude relationship between the target frequency and the boundary frequency.

[0107] In this step, the sub-band frequency also affects the attenuation. The higher the sub-band frequency, the smaller the attenuation of the sub-band during the retransmission process. Therefore, the sub-band with the highest frequency is selected, and the accuracy of the feature vector obtained from it is higher. Therefore, the target frequency is required to be greater than or equal to the sub-band with the highest frequency in the reflected wave. The target frequency can be selected according to the clothing processing equipment. For example, the target frequency can be 400.

[0108] The boundary frequency is used to divide the high-frequency sub-band area and the low-frequency sub-band area, and the comparison sub-band is the sub-band closest to the target frequency.

[0109] Furthermore, considering that the sub-band with the highest frequency may still belong to the low-frequency sub-band area, if the comparison sub-band closest to the target frequency is directly selected from the high-frequency sub-band area, there will be a situation where there is no sub-band to choose from. Therefore, this embodiment obtains the corresponding sub-band area according to the target frequency, and obtains the comparison sub-band closest to the target frequency from the corresponding sub-band area.

[0110] Exemplarily, the wavelet packet decomposes the reflected wave into: sub-band A with a frequency of 200, sub-band B with a frequency of 244, sub-band C with a frequency of 555, and sub-band D with a frequency of 600, the demarcation frequency is 400, and the target frequency is 655. Then the high-frequency sub-band area includes sub-band C with a frequency of 555 and sub-band D with a frequency of 600, and the low-frequency sub-band area includes sub-band A with a frequency of 200 and sub-band B with a frequency of 244. If the target frequency is greater than the demarcation frequency, the comparison sub-band is obtained from the high-frequency sub-band area, because the frequency of sub-band D is closer to the target frequency, so the comparison sub-band is sub-band D.

[0111] S303: vectorize the comparison subband to obtain a feature vector of the reflected wave, and obtain the similarity between the feature vector and the reference vector based on cosine similarity calculation.

[0112] In this step, the similarity is calculated as follows: feature vector * reference vector / feature vector modulus * reference vector modulus. For example, if the feature vector is (1, 2, 2) and the reference vector is (2, 1, 2), the corresponding similarity is:

[0113] The present application provides a method, device, equipment and storage medium for human body detection based on ultrasound, which decomposes the reflected wave and screens out high-frequency sub-bands, vectorizes the high-frequency sub-bands to obtain feature vectors, and then obtains the similarity between the feature vectors and reference vectors. Through the above methods, the accuracy of human body detection is increased, the probability of misoperation of clothing processing equipment is reduced, and the user experience is improved.

[0114] Figure 4 A schematic diagram of a human body detection method based on ultrasound is provided for the present application embodiment. Figure 3 The embodiment of the present application provides a detailed description of the steps of determining whether a user is detected based on similarity. Figure 4 As shown, the method includes:

[0115] S401: Obtain the magnitude relationship between the similarity, the first similarity, and the second similarity.

[0116] In this step, the similarity is used to determine whether the reflected wave is reflected by the user, that is, the greater the similarity, the greater the similarity between the reflected wave and the reference wave.

[0117] The first similarity and the second similarity are used to determine the degree of proximity between the characteristic vector of the reflected wave and the reference vector, and the first similarity is greater than the second similarity.

[0118] Furthermore, the first similarity is used to determine whether the reference vector and the feature vector are consistent. If they are consistent, it is considered that the reference wave and the reflected wave are almost the same. The second similarity is used to determine whether the feature vector and the reference vector are similar. Therefore, after obtaining the similarity between the feature vector and the reference vector, it is necessary to obtain the magnitude relationship between the similarity and the first similarity and the second similarity.

[0119] S402: If the similarity is greater than or equal to a first similarity, it is determined that a user is detected within a preset range of the clothing processing device.

[0120] In this step, the first similarity is used to determine whether the reference vector and the feature vector are consistent. If they are consistent, the reference wave and the reflected wave are considered to be almost the same. That is, when the similarity is greater than the first similarity, the feature vector and the reference vector are considered to be almost the same, and the reflected wave and the reference wave are considered to be almost the same, and it is determined that the reflected wave is reflected by the user. When the similarity is less than the first similarity and greater than the second similarity, it is considered that the feature vector and the reference vector are highly similar, which may be affected by the environment or the distance from the sound source, so other factors need to be used to assist in the judgment.

[0121] S403: If the similarity is less than the first similarity and greater than or equal to the second similarity, then acquire the echo time.

[0122] In this step, since the distance between the sound source and the clothing processing device has an attenuation effect on the reflected wave, when the sound source is close to the edge of the preset range, the reflected wave attenuates more, affecting the feature vector obtained based on the reflected wave, and the corresponding similarity will also be significantly reduced. Therefore, other judgment factors can be added. This embodiment uses the echo time to assist in determining whether the reflected wave is reflected by the user.

[0123] Specifically, the echo time is the interval time from the emission of ultrasonic waves to the reception of reflected waves by the clothing treatment device, and can be used to determine the distance between the sound source and the clothing treatment device. When the distance between the sound source and the clothing treatment device is far, the similarity between the feature vector obtained based on the reflected wave and the reference vector is high, but not completely consistent, so the second similarity is set to determine the similarity between the reference vector and the feature vector. That is, when the similarity is less than the first similarity and greater than or equal to the second similarity, the similarity between the feature vector and the reference vector is high, which can assist the echo time, that is, the distance between the sound source and the clothing treatment device to assist in the judgment.

[0124] Furthermore, if the distance between the sound source and the clothes processing device is too far, it may cause excessive loss of the reflected wave, and the similarity obtained based on the characteristic vector of the reflected wave is not very useful for reference. Therefore, there are requirements for the distance between the sound source and the clothes processing device, that is, there are requirements for the echo time. Therefore, when the similarity is less than the first similarity and greater than or equal to the second similarity, the echo time is obtained.

[0125] S404: If the ratio of the echo time to the reference time is less than or equal to a preset ratio, it is determined that a user is detected within a preset range of the laundry processing device.

[0126] In this step, the echo time is used to determine the distance between the sound source and the clothing processing device. The echo time is proportional to the distance, that is, the longer the echo time, the farther the distance between the sound source and the clothing processing device.

[0127] Specifically, when obtaining the echo time, the ratio of the echo time to the reference time is obtained. If the ratio is less than or equal to the preset ratio, it is determined that the distance between the sound source position and the laundry processing device is within a reasonable range, and it is considered that the reflected wave is reflected by the user. This embodiment does not impose any limitation on the preset ratio. For example, the preset ratio may be 1.3.

[0128] Exemplarily, the echo time is 120 s, the reference time is 100 s, the ratio of the echo time to the reference time is 1.2, and if 1.2 is less than the preset ratio of 1.3, it is considered that the reflected wave is reflected by the user.

[0129] Further, when it is determined that the reflected wave is reflected by the user, the clothes processing device is controlled to execute according to the received voice command.

[0130] The present application provides a method, device, equipment and storage medium for human body detection based on ultrasound, which determines whether a user is detected within a preset range of a clothing treatment device according to the similarity between a feature vector and a reference vector, and the ratio between an echo time and a reference time. In this way, the accuracy of human body detection is increased, the probability of misoperation of the clothing treatment device is reduced, and the user experience is improved.

[0131] Figure 5 The schematic diagram of the structure of a human body detection control device based on ultrasound provided in an embodiment of the present application. The device comprises: an acquisition module 501, a calculation module 502 and a judgment module 503, wherein:

[0132] The acquisition module 501 is used to acquire a sound source position according to a voice instruction received by the clothes processing device, and control the clothes processing device to send ultrasonic waves toward the sound source position and receive reflected waves;

[0133] The calculation module 502 is used to decompose the reflected wave to obtain a contrast sub-band, obtain a feature vector according to the contrast sub-band, and obtain a similarity between the feature vector and a reference vector, wherein the reference vector is obtained in advance according to an echo reflected by the user at a reference position corresponding to the sound emission position;

[0134] The determination module 503 is configured to determine whether a user is detected within a preset range of the clothing processing device according to the similarity, wherein the reference position is within the preset range.

[0135] In a possible implementation manner, the calculation module 502 is further configured to:

[0136] Decomposing the reflected wave by wavelet packet to obtain the contrast subband;

[0137] Vectorizing the contrast subband to obtain a characteristic vector of the reflected wave;

[0138] The similarity between the feature vector and the reference vector is obtained according to the cosine similarity calculation.

[0139] In a possible implementation manner, the calculation module 502 is further configured to:

[0140] Decomposing the reflected wave by wavelet packets to obtain a plurality of sub-bands with different frequencies, and dividing each sub-band into a high-frequency sub-band area or a low-frequency sub-band area according to the frequency of each sub-band;

[0141] According to the magnitude relationship between the target frequency and the boundary frequency, the comparison sub-band is obtained from the corresponding sub-band area;

[0142] The boundary frequency is used to divide the high-frequency sub-band area and the low-frequency sub-band area, and the comparison sub-band is the sub-band closest to the target frequency.

[0143] In a possible implementation manner, the determining module 503 is further configured to:

[0144] If the similarity is greater than or equal to the first similarity, it is determined that a user is detected within a preset range of the laundry processing device;

[0145] If the similarity is less than the first similarity and greater than or equal to the second similarity, then acquiring the echo time;

[0146] According to the echo time and the reference time, it is determined whether a user is detected within a preset range of the clothing processing device, wherein the reference time is obtained in advance based on an echo reflected by the user when ultrasonic waves are emitted to a reference position.

[0147] In a possible implementation manner, the determining module 503 is further configured to:

[0148] If the ratio of the echo time to the reference time is less than or equal to a preset ratio, it is determined that a user is detected within a preset range of the laundry processing device.

[0149] In a possible implementation manner, the acquisition module 501 is further configured to:

[0150] Dividing a preset area of ​​the laundry processing device into a plurality of reference areas, and acquiring a reference position corresponding to each of the reference areas;

[0151] Controlling the laundry processing device to transmit ultrasonic waves toward each reference area, and receiving echoes reflected back by the user at the corresponding reference position;

[0152] Decomposing the echo by wavelet packets, obtaining a reference subband corresponding to each echo, and vectorizing the reference subband to obtain a reference vector corresponding to each reference position;

[0153] The reference time corresponding to each reference position is obtained according to the interval time from when the laundry processing device sends the ultrasonic wave to when each echo is received.

[0154] In a possible implementation manner, the acquisition module 501 is further configured to:

[0155] According to the order in which the multi-channel microphones of the voice module of the laundry processing device receive the voice command, obtaining a target microphone, wherein the target microphone is the first microphone to receive the voice command;

[0156] amplifying the received signal of the target microphone and combining it with the received signals of other microphones;

[0157] The sound emission position is obtained according to the combined signal.

[0158] Figure 6 The schematic diagram of the structure of a clothes processing device provided in an embodiment of the present application is as follows. The clothes processing device 60 comprises: at least one processor 601 and a memory 602, wherein:

[0159] The memory 602 is used to store computer-executable instructions;

[0160] The at least one processor 601 is used to execute the computer-executable instructions stored in the memory 602, so that the at least one processor 601 executes the ultrasound-based human body detection method as described in any one of the first aspects.

[0161] Among them, at least one processor 601 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0162] Optionally, in a specific implementation, the processor 601 and the memory 602 are implemented independently, and the processor 601 and the memory 602 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc., but it does not mean that there is only one bus or one type of bus.

[0163] Optionally, in a specific implementation, if the processor 601 and the memory 602 are integrated on a chip, the processor 601 and the memory 602 can communicate through an internal interface.

[0164] The present application also provides a computer storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the technical solution of the aforementioned ultrasonic-based human body detection method is implemented.

[0165] The computer-readable storage medium may be implemented by 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 memory, flash memory, magnetic disk or optical disk. The computer-readable storage medium may be any available medium that can be accessed by a general or special purpose computer.

[0166] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in the control device of the clothing processing device.

[0167] The division of the units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, which may be electrical, mechanical or other forms.

[0168] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0169] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0170] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0171] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0172] So far, the technical solution of the present application has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments, and the above embodiments are only used to illustrate the technical solution of the present application rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements 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 application.

Claims

1. A human body detection method based on ultrasound, characterized in that: The method comprises: Acquiring a sound source position according to a voice command received by the laundry processing device, and controlling the laundry processing device to send ultrasonic waves toward the sound source position and receive reflected waves; Decomposing the reflected wave to obtain a contrast subband, obtaining a feature vector according to the contrast subband, and obtaining a similarity between the feature vector and a reference vector, wherein the reference vector is obtained in advance according to an echo reflected by a user at a reference position corresponding to the sound emission position; According to the similarity, it is determined whether a user is detected within a preset range of the laundry processing device, wherein the reference position is within the preset range.

2. The method according to claim 1, characterized in that The decomposing the reflected wave to obtain a contrast subband, obtaining a feature vector according to the contrast subband, and obtaining a similarity between the feature vector and a reference vector includes: Decomposing the reflected wave by wavelet packet to obtain the contrast subband; Vectorizing the contrast subband to obtain a characteristic vector of the reflected wave; The similarity between the feature vector and the reference vector is obtained according to the cosine similarity calculation.

3. The method according to claim 2, characterized in that Decomposing the reflected wave by wavelet packet to obtain the contrast sub-band includes: Decomposing the reflected wave by wavelet packets to obtain a plurality of sub-bands with different frequencies, and dividing each sub-band into a high-frequency sub-band area or a low-frequency sub-band area according to the frequency of each sub-band; According to the magnitude relationship between the target frequency and the boundary frequency, the comparison sub-band is obtained from the corresponding sub-band area; The boundary frequency is used to divide the high-frequency sub-band area and the low-frequency sub-band area, and the comparison sub-band is the sub-band closest to the target frequency.

4. The method according to claim 3, characterized in that: The determining, based on the similarity, whether a user is detected within a preset range of the laundry processing device includes: If the similarity is greater than or equal to the first similarity, it is determined that a user is detected within a preset range of the laundry processing device; If the similarity is less than the first similarity and greater than or equal to the second similarity, then acquiring the echo time; According to the echo time and the reference time, it is determined whether a user is detected within a preset range of the clothing processing device, wherein the reference time is obtained in advance based on an echo reflected by the user when ultrasonic waves are emitted to a reference position.

5. The method according to claim 4, characterized in that The determining, based on the echo time and the reference time, whether a user is detected within a preset range of the laundry processing device comprises: If the ratio of the echo time to the reference time is less than or equal to a preset ratio, it is determined that a user is detected within a preset range of the laundry processing device.

6. The method according to claim 5, characterized in that Before obtaining the sound position according to the voice instruction, the method further includes: Dividing a preset area of ​​the laundry processing device into a plurality of reference areas, and acquiring a reference position corresponding to each of the reference areas; Controlling the laundry processing device to transmit ultrasonic waves toward each reference area, and receiving echoes reflected back by the user at the corresponding reference position; Decomposing the echo by wavelet packets, obtaining a reference subband corresponding to each echo, and vectorizing the reference subband to obtain a reference vector corresponding to each reference position; The reference time corresponding to each reference position is obtained according to the interval time from when the laundry processing device sends the ultrasonic wave to when each echo is received.

7. The method according to any one of claims 1 to 6, characterized in that: The obtaining of the sound position according to the voice instruction comprises: Acquire a target microphone according to the order in which the multi-channel microphones of the voice module of the laundry processing device receive the voice command, wherein the target microphone is the first microphone to receive the voice command; amplifying the received signal of the target microphone and combining it with the received signals of other microphones; The sound emission position is obtained according to the combined signal.

8. A human body detection control device based on ultrasonic wave, characterized in that: include: Acquisition module, calculation module and judgment module, where: The acquisition module is used to acquire a sound source position according to a voice instruction received by the clothes processing device, and control the clothes processing device to send ultrasonic waves toward the sound source position and receive reflected waves; The calculation module is used to decompose the reflected wave to obtain a contrast sub-band, obtain a feature vector according to the contrast sub-band, and obtain a similarity between the feature vector and a reference vector, wherein the reference vector is obtained in advance according to an echo reflected by the user at a reference position corresponding to the sound emission position; The judgment module is used to judge whether a user is detected within a preset range of the clothing processing device according to the similarity, wherein the reference position is within the preset range.

9. A clothes processing device, characterized in that: include: at least one processor and memory, wherein: The memory is used to store computer-executable instructions; The at least one processor is configured to execute the computer-executable instructions stored in the memory, so that the at least one processor performs the method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that: The computer storage medium stores computer executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

Images