Barrel collision noise identification method and device, equipment and storage medium

Abstract

The invention provides a barrel collision noise identification method and device, equipment and a storage medium, and relates to the technical field of intelligent household appliances. According to the recognition method for the barrel collision noise, when clothes are dewatered, before clothes processing equipment is about to enter a next speed-up dewatering stage, whether the clothes processing equipment is controlled to enter the next speed-up dewatering stage or not is judged according to the similarity between a current dewatering audio frequency and a pre-stored reference audio frequency collected when barrel collision just occurs in the state. By means of the method, whether the clothes processing equipment collides with the barrel or not can be judged in the process that the clothes processing equipment enters the high-speed dewatering stage, processing is conducted in time, and meanwhile the use experience 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 a method, device, equipment and storage medium for identifying barrel collision noise. Background Art

[0002] When the clothes are being dehydrated, it is generally necessary to first shake them loose or rotate them at a constant speed to evenly distribute the clothes. If the clothes are not evenly distributed, they are prone to hitting the barrel during the high-speed dehydration process of the clothes processing device, generating a large noise.

[0003] In the face of the above-mentioned problem of uneven distribution of clothes, the prior art commonly uses the following means: during the dehydration process, the barrel displacement of the outer barrel of the clothing processing device is obtained at a relatively low speed, and it is judged whether the clothing processing device has a barrel collision phenomenon at this time based on the barrel displacement of the outer barrel. Specifically, if the barrel displacement exceeds a preset threshold, it is determined that a barrel collision may occur, and the load is redistributed. If it does not exceed the threshold, high-speed dehydration is performed.

[0004] However, the above method currently only determines whether the drum collision phenomenon occurs when the rotation speed of the clothing processing device is low, and the solution is relatively imperfect. Summary of the invention

[0005] In order to solve the above problems in the prior art, the present application provides a barrel collision noise recognition method, device, equipment and storage medium.

[0006] In a first aspect, the present application provides a method for identifying barrel collision noise, the method comprising:

[0007] When the clothes processing device enters the dehydration program, the load weight of the clothes to be processed is obtained, and when the rotation speed of the clothes processing device reaches a first rotation speed, the current dehydration audio is collected, wherein the first rotation speed is determined according to the initial rotation speed corresponding to each of the multiple speed-up dehydration stages in the dehydration program;

[0008] Acquiring a pre-stored reference audio according to the first rotation speed and the load weight, wherein the reference audio is audio collected when the clothes processing device pre-dehydrates the clothes of the load weight at the first rotation speed and hits the tub;

[0009] The similarity between the reference audio and the dehydration audio is obtained, and if the similarity is less than the first similarity, the clothing processing device is controlled to enter the next speed-up dehydration stage, wherein the similarity is used to determine whether the clothing processing device hits the barrel.

[0010] In a possible implementation manner, after controlling the laundry processing device to enter the next dehydration stage, the method further includes:

[0011] If the similarity is less than the first similarity and greater than or equal to the second similarity, new dehydration audio is acquired at the first time interval, and the type of the new dehydration audio is acquired through the audio classification model, and whether the clothes processing device hits the barrel is determined according to the type;

[0012] If the similarity is less than the second similarity and greater than or equal to the third similarity, new dehydration audio is acquired at the second time interval, and the type of the new dehydration audio is acquired through the audio classification model, and whether the clothes processing device hits the barrel is determined according to the type;

[0013] If the similarity is less than the third similarity, acquiring new dehydration audio when the rotation speed of the clothes processing device reaches the second rotation speed, and determining whether the clothes processing device hits the tub according to the second rotation speed and the new dehydration audio;

[0014] The second speed is an initial speed corresponding to a next speed-up dehydration stage after the speed-up dehydration stage corresponding to the first speed, and the first time interval is smaller than the second time interval.

[0015] In a possible implementation manner, acquiring a pre-stored reference audio according to the first rotation speed and the load weight includes:

[0016] A corresponding reference audio is acquired from a preset relationship according to the first rotational speed and the load weight, wherein the preset relationship is used to indicate a relationship between a rotational speed, a load weight and a reference audio of the laundry processing device.

[0017] In a possible implementation manner, obtaining the similarity between the reference audio and the dehydrated audio includes:

[0018] Acquire at least one reference short-term feature of the reference audio and at least one short-term feature of the dehydrated audio;

[0019] The similarity between the reference audio and the dehydrated audio is obtained according to the at least one reference short-term feature and the corresponding short-term feature.

[0020] In a possible implementation, acquiring the similarity between the reference audio and the dehydrated audio according to the at least one reference short-term feature and the corresponding short-term feature includes:

[0021] Obtaining candidate similarities between the short-term feature and the corresponding reference short-term feature, wherein the number of the candidate similarities is the same as the number of the short-term features or the reference short-term features;

[0022] The similarity between the reference audio and the dehydrated audio is obtained according to the weight of each short-term feature and the candidate similarity.

[0023] In a possible implementation manner, obtaining at least one short-term feature of the dehydrated audio includes:

[0024] At least one short-term feature is extracted according to the dehydrated audio, and the short-term feature is smoothed by first-order filtering.

[0025] In a possible implementation, the method further includes:

[0026] If the similarity is greater than or equal to the first similarity, the clothes processing device is controlled to shake out the clothes to be processed and re-enter the dehydration program.

[0027] In a second aspect, the present application provides a device for identifying and controlling barrel collision noise, including: a collection module, an acquisition module, and a control module, wherein:

[0028] The acquisition module is used to acquire the load weight of the clothes to be processed when the clothes processing device enters the dehydration program, and to acquire the current dehydration audio when the rotation speed of the clothes processing device reaches a first rotation speed, wherein the first rotation speed is determined according to the initial rotation speeds corresponding to the multiple speed-up dehydration stages in the dehydration program;

[0029] The acquisition module is used to acquire a pre-stored reference audio according to the first rotation speed and the load weight, wherein the reference audio is the audio collected when the clothes processing device dehydrates the clothes of the load weight at the first rotation speed and just hits the barrel;

[0030] The control module is used to obtain the similarity between the reference audio and the dehydration audio, and if the similarity is less than the first similarity, control the clothing processing device to enter the next speed-up dehydration stage, wherein the similarity is used to determine whether the clothing processing device sends a barrel collision.

[0031] In a possible implementation manner, the acquisition module is further used to:

[0032] If the similarity is less than the first similarity and greater than or equal to the second similarity, new dehydration audio is acquired at the first time interval, and the type of the new dehydration audio is acquired through the audio classification model, and whether the clothes processing device hits the barrel is determined according to the type;

[0033] If the similarity is less than the second similarity and greater than or equal to the third similarity, new dehydration audio is acquired at the second time interval, and the type of the new dehydration audio is acquired through the audio classification model, and whether the clothes processing device hits the barrel is determined according to the type;

[0034] If the similarity is less than the third similarity, acquiring new dehydration audio when the rotation speed of the clothes processing device reaches the second rotation speed, and determining whether the clothes processing device hits the tub according to the second rotation speed and the new dehydration audio;

[0035] The second speed is an initial speed corresponding to a next speed-up dehydration stage after the speed-up dehydration stage corresponding to the first speed, and the first time interval is smaller than the second time interval.

[0036] In a possible implementation manner, the acquisition module is further used to:

[0037] A corresponding reference audio is acquired from a preset relationship according to the first rotational speed and the load weight, wherein the preset relationship is used to indicate a relationship between a rotational speed, a load weight and a reference audio of the laundry processing device.

[0038] In a possible implementation manner, the acquisition module is further used to:

[0039] Acquire at least one reference short-term feature of the reference audio and at least one short-term feature of the dehydrated audio;

[0040] The similarity between the reference audio and the dehydrated audio is obtained according to the at least one reference short-term feature and the corresponding short-term feature.

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

[0042] Obtaining candidate similarities between the short-term feature and the corresponding reference short-term feature, wherein the number of the candidate similarities is the same as the number of the short-term features or the reference short-term features;

[0043] The similarity between the reference audio and the dehydrated audio is obtained according to the weight of each short-term feature and the candidate similarity.

[0044] In a possible implementation manner, the control module is further used to:

[0045] At least one short-term feature is extracted according to the dehydrated audio, and the short-term feature is smoothed by first-order filtering.

[0046] In a possible implementation manner, the control module is further used to:

[0047] If the similarity is greater than or equal to the first similarity, the clothes processing device is controlled to shake out the clothes to be processed and re-enter the dehydration program.

[0048] In a third aspect, the present application provides a clothes processing device, comprising: at least one processor and a memory, wherein:

[0049] The memory is used to store computer-executable instructions;

[0050] The at least one processor is used to execute the computer-executable instructions stored in the memory, so that the at least one processor performs the barrel collision noise recognition method as described in any one of the first aspects.

[0051] 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 method for identifying barrel collision noise as described in any one of the first aspects.

[0052] 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 method for identifying barrel collision noise as described in any of the above items.

[0053] The present application provides a method, device, equipment and storage medium for identifying barrel collision noise. When the clothes are being dehydrated, before the clothes processing device is about to enter the next high-speed dehydration stage, it is determined whether to control the clothes processing device to enter the next high-speed dehydration stage based on the similarity between the current dehydration audio and the pre-stored reference audio collected when the barrel collision just occurred in this state. Through the above method, it is possible to determine whether the clothes processing device has a barrel collision during the process of the clothes processing device entering the high-speed dehydration stage, and to deal with it in time, while improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] 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.

[0055] Figure 1 A schematic diagram of a method for identifying barrel noise provided in an embodiment of the present application Figure 1 ;

[0056] Figure 2 A schematic diagram of a method for identifying barrel noise provided in an embodiment of the present application Figure 2 ;

[0057] Figure 3 A schematic diagram of a method for identifying barrel noise provided in an embodiment of the present application Figure 3 ;

[0058] Figure 4 A schematic diagram of the structure of a barrel collision noise recognition and control device provided in an embodiment of the present application;

[0059] Figure 5 A schematic structural diagram of a clothing processing device provided in an embodiment of the present application.

[0060] 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

[0061] 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.

[0062] 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.

[0063] 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.

[0064] When the clothes processing device is dehydrating clothes, in order to avoid the clothes processing device hitting the barrel when rotating at high speed, the clothes are generally evenly distributed by shaking or rotating at a constant speed before the high-speed dehydration stage. At the same time, when rotating at a low speed, the barrel displacement of the outer barrel of the clothes processing device is obtained, and it is determined whether the clothes processing device hits the barrel at this time according to the barrel displacement of the outer barrel.

[0065] However, the above method can only determine whether the drum collision phenomenon occurs according to the displacement of the outer drum of the clothing processing device when the rotation speed of the clothing processing device is low, and the solution is relatively imperfect.

[0066] The present application provides a method for identifying barrel collision noise. When the clothes are being dehydrated, before the clothes processing device is about to enter the next high-speed dehydration stage, it is determined whether to control the clothes processing device to enter the next high-speed dehydration stage based on the similarity between the current dehydration audio and the pre-stored reference audio collected when the barrel collision just occurred in this state. Through the above method, it is possible to determine whether the clothes processing device has a barrel collision during the process of the clothes processing device entering the high-speed dehydration stage, and to deal with it in time, while improving the user experience.

[0067] 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.

[0068] Figure 1 A schematic diagram of a method for identifying barrel noise provided in an embodiment of the present application Figure 1 The method comprises:

[0069] S101. When the clothes processing device enters a dehydration program, the load weight of the clothes to be processed is obtained, and when the rotation speed of the clothes processing device reaches a first rotation speed, the current dehydration audio is collected.

[0070] In this step, the first rotation speed is determined according to an initial rotation speed corresponding to each of a plurality of speed-up dehydration stages in the dehydration procedure.

[0071] Specifically, when the clothes processing device dehydrates clothes, it will first accelerate to a uniform speed and run for a period of time to make the clothes to be processed in the barrel evenly distributed. After judging that the clothes to be processed in the barrel are evenly distributed, it enters the high-speed dehydration stage. The clothes processing device needs to go through multiple speed-up dehydration stages to increase the speed from uniform speed to high speed, and it is very easy to hit the barrel when the speed of the clothes processing device increases. Therefore, it is necessary to judge whether the clothes processing device can enter the next speed-up dehydration stage before each speed-up dehydration stage.

[0072] Specifically, when it is detected that the clothing processing device has entered the dehydration program, the load weight of the clothing processing device and the rotational speed of the clothing processing device are obtained. When the rotational speed reaches the first rotational speed, the current dehydration audio is collected, and based on the obtained dehydration audio, it is determined whether to control the clothing processing device to enter the next speed-up dehydration stage.

[0073] S102: Acquire pre-stored reference audio according to the first rotation speed and the load weight.

[0074] In this step, the reference audio is the audio collected when the clothes processing device dehydrates the clothes of the load weight at the first speed in advance and hits the barrel.

[0075] Furthermore, this embodiment does not impose any limitation on how to obtain the pre-stored reference audio according to the first rotation speed and the load weight, and the operation can be selected according to actual conditions.

[0076] In a possible implementation, a corresponding reference audio is acquired from a preset relationship according to the first rotational speed and the load weight, wherein the preset relationship is used to indicate a relationship between a rotational speed, a load weight and a reference audio of the laundry processing device.

[0077] S103, obtaining the similarity between the reference audio and the dehydration audio, and if the similarity is less than a first similarity, controlling the clothing processing device to enter a next speed-up dehydration stage.

[0078] In this step, the similarity is used to indicate the closeness between the reference audio and the dehydration audio, that is, the higher the similarity, the closer the reference audio and the dehydration audio are. The first similarity is used to determine whether the laundry processing device has a barrel collision, that is, when the similarity is greater than or equal to the first similarity, it is determined that the laundry processing device has a barrel collision and cannot enter the next speed-up dehydration stage.

[0079] In a possible implementation, the reference audio may be converted into a reference spectrum, the dehydrated audio may be converted into a dehydrated spectrum, and the similarity between the reference audio and the dehydrated audio may be determined based on the overlap between the reference spectrum and the dehydrated spectrum.

[0080] Optionally, reference audio features of the reference audio and audio features of the dehydrated audio are obtained, and the similarity between the reference audio features and the audio features is obtained based on the reference audio features and the audio features, that is, the similarity between the reference audio and the dehydrated audio is obtained based on the reference audio features and the audio features.

[0081] Exemplarily, the similarity is 50%, the first similarity is 77%, and the similarity 50% is less than the first similarity 77%. It is judged that the proximity between the dehydration audio and the reference audio is not high, that is, the clothing processing device did not hit the barrel, and the clothing processing device is controlled to enter the next speed-up dehydration stage.

[0082] The present application provides a method for identifying barrel collision noise. When the clothes are being dehydrated, before the clothes processing device is about to enter the next high-speed dehydration stage, it is determined whether to control the clothes processing device to enter the next high-speed dehydration stage based on the similarity between the current dehydration audio and the pre-stored reference audio collected when the barrel collision just occurred in this state. Through the above method, it is possible to determine whether the clothes processing device has a barrel collision during the process of the clothes processing device entering the high-speed dehydration stage, and to deal with it in time, while improving the user experience.

[0083] Figure 2 A schematic diagram of a method for identifying barrel noise provided in an embodiment of the present application Figure 2The embodiment of the present application provides a detailed description of the steps for obtaining the similarity between the reference audio and the dehydrated audio. The method includes:

[0084] S201. Obtain at least one reference short-term feature of the reference audio and at least one short-term feature of the dehydrated audio.

[0085] In this step, the short-term features and the reference short-term features are used to obtain the similarity between the reference audio and the dehydrated audio. This embodiment does not impose any restrictions on the number of short-term features and reference short-term features to be obtained, and they can be selected according to actual conditions. For example, the short-term features can be: zero crossing rate, energy.

[0086] Specifically, audio contains long-term features and short-term features. The long-term feature waveform changes greatly and has an irregular period; the short-term feature waveform changes little and has a regular period. In order to make the similarity obtained based on audio features more accurate, the short-term features of dehydrated audio are selected to obtain the similarity between the reference audio and the dehydrated audio.

[0087] Furthermore, when it is determined that the dehydration audio of the clothing processing device needs to be obtained, the clothing processing device triggers the audio data acquisition program, and cuts the collected audio through a sliding window to obtain the dehydration audio. The window size and step size of the sliding window are selected according to actual conditions.

[0088] Furthermore, since the dehydrated audio may contain other noises, the short-term features obtained from the dehydrated audio may also be affected by other noises. In order to make the similarity obtained based on the short-term features more accurate, this embodiment processes the extracted short-term features. The specific operations are as follows:

[0089] At least one short-term feature is extracted according to the dehydrated audio, and the short-term feature is smoothed by first-order filtering.

[0090] S202: Obtain candidate similarities between the short-term feature and the corresponding reference short-term feature, wherein the number of the candidate similarities is the same as the number of the short-term features or the reference short-term features.

[0091] In this step, when the number of short-term features obtained is multiple, in order to make the similarity calculated based on the short-term features more accurate, the candidate similarity is obtained based on each short-term feature and its corresponding reference short-term feature, and then the similarity between the final reference audio and the dehydrated audio is obtained based on the candidate similarity.

[0092] Furthermore, since the short-term features of audio are changing, the candidate similarity obtained based only on the short-term features of a certain moment and the reference short-term features will have errors and cannot be used to determine the similarity between the reference audio and the dehydrated audio. Therefore, this embodiment obtains the similarity based on the short-term features of the entire audio time of the dehydrated audio.

[0093] Specifically, after obtaining the short-term features and the reference short-term features, each short-term feature and each reference short-term feature are converted into a spectrum, and then the candidate similarity between the short-term feature and the corresponding reference short-term feature is obtained based on the overlap between the spectrum corresponding to the reference short-term feature and the spectrum corresponding to the short-term feature.

[0094] S203: Obtain the similarity between the reference audio and the dehydrated audio according to the weight of each short-term feature and the candidate similarity.

[0095] In this step, in order to make the final similarity obtained according to multiple candidate similarities more accurate, a corresponding weight is obtained according to each short-term feature, and then the similarity between the reference audio and the dehydrated audio is obtained according to the weight and the corresponding candidate similarity.

[0096] For example, three short-term features are obtained: short-time energy, short-time zero-crossing rate, and short-time power. The candidate similarity corresponding to short-time energy is 0.8, and the weight is 0.3; the candidate similarity corresponding to short-time zero-crossing rate is 0.6, and the weight is 0.3; the candidate similarity corresponding to short-time power is 0.9, and the weight is 0.4. Similarity = 0.6*0.3+0.8*0.3+0.4*0.9=0.78.

[0097] Furthermore, the similarity is used to indicate the closeness between the reference audio and the dehydrated audio. The higher the similarity, the closer the reference audio and the dehydrated audio are. Therefore, after obtaining the similarity between the reference audio and the dehydrated audio, the magnitude relationship between the similarity and the first similarity is obtained.

[0098] Specifically, if the similarity is greater than or equal to the first similarity, the clothes processing device is controlled to shake out the clothes to be processed and re-enter the dehydration program.

[0099] The present application provides a method for identifying barrel collision noise, extracting short-term features based on dehydration audio, extracting reference short-term features based on reference audio, and obtaining the similarity between the reference audio and the dehydration audio based on the short-term features and the reference short-term features. In the above manner, the similarity between the reference audio and the dehydration audio is judged by the short-term features, making the similarity judgment more accurate, thereby improving the accuracy of the judgment of the barrel collision of the clothing processing device.

[0100] Figure 3 A schematic diagram of a method for identifying barrel noise provided in an embodiment of the present application Figure 3The embodiment of the present application provides a detailed description of the operation steps of how to determine whether a barrel collision occurs during each speed-up and dehydration stage according to the similarity. The method includes:

[0101] S301: Obtain the magnitude relationship between the similarity and the first similarity, the second similarity, and the third similarity.

[0102] In this step, when the similarity between the reference audio and the dehydration audio is obtained and it is determined that the similarity is less than the first similarity, the clothing treatment device is controlled to enter the next speed-up dehydration stage. During the speed-up dehydration process, the rotation speed of the clothing treatment device will continue to increase, and the clothes to be treated in the barrel will still be entangled and cause the risk of hitting the barrel. Therefore, it is necessary to continue to determine whether the clothing treatment device hits the barrel during the speed-up dehydration process.

[0103] Furthermore, after obtaining the similarity, the magnitude relationship between the similarity and the first similarity, the second similarity and the third similarity is obtained, and according to the magnitude relationship, it is determined how to continue to determine whether the clothing processing device hits the barrel during the speed-up dehydration process.

[0104] S302: If the similarity is less than the first similarity and greater than or equal to the second similarity, new dehydration audio is obtained at the first time interval, and the type of the new dehydration audio is obtained through the audio classification model, and whether the clothing processing device hits the barrel is determined according to the type.

[0105] In this step, the closer the similarity is to the first similarity, the more likely the clothing processing device is to collide with the barrel.

[0106] Furthermore, if the similarity is less than the first similarity and greater than or equal to the second similarity, it means that the clothing processing device has not hit the barrel at this time, but the barrel displacement is large and it is very easy to hit the barrel. During the speed-up dehydration process, it is necessary to frequently monitor the dehydration audio of the clothing processing device to determine whether the clothing processing device has hit the barrel at this time.

[0107] Specifically, when it is determined that the similarity is less than the first similarity and greater than or equal to the second similarity, new dehydrated audio is obtained at the first time interval, and new short-term features are extracted from the new dehydrated audio. How to obtain new dehydrated audio and how to extract short-term features from the new dehydrated audio have been described in detail in the above embodiments, and will not be described in detail here.

[0108] Specifically, since the rotation speed of the clothing processing device changes greatly during the speed-up dehydration process, in order to more accurately determine whether the clothing processing device hits the barrel, the extracted new short-term features are input into the audio classification model to obtain the type of new dehydration audio output.

[0109] It should be noted that the audio classification model needs to be pre-trained based on the audio data of the clothing processing equipment. The specific operations are as follows:

[0110] The audio of the clothing processing equipment at different speeds and loads is simulated and collected, the collected audio is labeled as "barrel collision" and "non-barrel collision", and the audio classification model is trained with the short-term features of the collected audio.

[0111] S303: If the similarity is less than the second similarity and greater than or equal to the third similarity, new dehydration audio is obtained at the second time interval, and the type of the new dehydration audio is obtained through the audio classification model, and whether the clothing processing device hits the barrel is determined according to the type.

[0112] In this step, if the similarity is less than the second similarity and greater than or equal to the third similarity, it means that the clothing processing device has not hit the barrel at this time, and the barrel displacement is small, and the probability of hitting the barrel is low. However, since the speed will continue to increase during the speed-up dehydration process, there is still a probability of hitting the barrel, so it is still necessary to monitor the dehydration audio of the clothing processing device to determine whether the clothing processing device has hit the barrel at this time.

[0113] Specifically, when it is determined that the similarity is less than the second similarity and greater than or equal to the third similarity, new dehydrated audio is acquired at the second time interval, and new short-term features are extracted from the new dehydrated audio. The extracted new short-term features are input into the audio classification model to obtain the type of the output new dehydrated audio.

[0114] S304: If the similarity is less than the third similarity, a new dehydration audio is obtained when the rotation speed of the clothes processing device reaches a second rotation speed, and it is determined whether the clothes processing device hits the tub according to the second rotation speed and the new dehydration audio.

[0115] In this step, if the similarity is less than the third similarity, it means that the clothing processing device has not hit the barrel at this time, and the barrel displacement is small, and it is extremely difficult to hit the barrel. Although the speed will continue to increase during the speed-up dehydration process, the probability of hitting the barrel is still small, so it is only necessary to obtain the dehydration audio of the clothing processing device when the speed reaches the second speed to determine whether the clothing processing device has hit the barrel at this time.

[0116] Specifically, when it is determined that the similarity is less than the third similarity, a new dehydration audio is obtained when the rotation speed reaches the second rotation speed, and a new reference audio is obtained according to the second rotation speed and the load weight, and a new short-term feature is extracted from the new dehydration audio, and a new reference short-term feature is obtained from the new reference audio. It is determined whether the laundry processing device has hit the barrel based on the similarity between the new short-term feature and the new reference short-term feature.

[0117] The present application provides a method for identifying barrel collision noise, and selects a barrel collision judgment method during the current speed-up spin stage according to the similarity between the dehydration audio and the reference audio at the beginning of each speed-up spin stage. Through the above method, the similarity between the obtained dehydration audio and the reference audio can be made more accurate, thereby improving the accuracy of the barrel collision judgment of the clothing processing device and improving the user experience.

[0118] Figure 4 This is a schematic diagram of the structure of a barrel collision noise recognition and control device provided in an embodiment of the present application. Figure 4 As shown, the device includes: a collection module 401, an acquisition module 402 and a control module 403, wherein:

[0119] The acquisition module 401 is used to acquire the load weight of the clothes to be processed when the clothes processing device enters the dehydration program, and to acquire the current dehydration audio when the rotation speed of the clothes processing device reaches a first rotation speed, wherein the first rotation speed is determined according to the initial rotation speeds corresponding to the multiple speed-up dehydration stages in the dehydration program;

[0120] The acquisition module 402 is used to acquire a pre-stored reference audio according to the first rotation speed and the load weight, wherein the reference audio is the audio collected when the clothes processing device dehydrates the clothes of the load weight at the first rotation speed and just hits the barrel;

[0121] The control module 403 is used to obtain the similarity between the reference audio and the dehydration audio, and if the similarity is less than the first similarity, control the clothing processing device to enter the next speed-up dehydration stage, wherein the similarity is used to determine whether the clothing processing device sends a barrel collision.

[0122] In a possible implementation manner, the acquisition module 402 is further configured to:

[0123] If the similarity is less than the first similarity and greater than or equal to the second similarity, new dehydration audio is acquired at the first time interval, and the type of the new dehydration audio is acquired through the audio classification model, and whether the clothes processing device hits the barrel is determined according to the type;

[0124] If the similarity is less than the second similarity and greater than or equal to the third similarity, new dehydration audio is acquired at the second time interval, and the type of the new dehydration audio is acquired through the audio classification model, and whether the clothes processing device hits the barrel is determined according to the type;

[0125] If the similarity is less than the third similarity, acquiring new dehydration audio when the rotation speed of the clothes processing device reaches the second rotation speed, and determining whether the clothes processing device hits the tub according to the second rotation speed and the new dehydration audio;

[0126] The second speed is an initial speed corresponding to a next speed-up dehydration stage after the speed-up dehydration stage corresponding to the first speed, and the first time interval is smaller than the second time interval.

[0127] In a possible implementation manner, the acquisition module 402 is further configured to:

[0128] A corresponding reference audio is acquired from a preset relationship according to the first rotational speed and the load weight, wherein the preset relationship is used to indicate a relationship between a rotational speed, a load weight and a reference audio of the laundry processing device.

[0129] In a possible implementation manner, the acquisition module 402 is further configured to:

[0130] Acquire at least one reference short-term feature of the reference audio and at least one short-term feature of the dehydrated audio;

[0131] The similarity between the reference audio and the dehydrated audio is obtained according to the at least one reference short-term feature and the corresponding short-term feature.

[0132] In a possible implementation manner, the acquisition module 402 is further configured to:

[0133] Obtaining candidate similarities between the short-term feature and the corresponding reference short-term feature, wherein the number of the candidate similarities is the same as the number of the short-term features or the reference short-term features;

[0134] The similarity between the reference audio and the dehydrated audio is obtained according to the weight of each short-term feature and the candidate similarity.

[0135] In a possible implementation manner, the control module 403 is further configured to:

[0136] At least one short-term feature is extracted according to the dehydrated audio, and the short-term feature is smoothed by first-order filtering.

[0137] In a possible implementation manner, the control module 403 is further configured to:

[0138] If the similarity is greater than or equal to the first similarity, the clothes processing device is controlled to shake out the clothes to be processed and re-enter the dehydration program.

[0139] Figure 5 The schematic diagram of the structure of a clothes processing device provided in an embodiment of the present application. The clothes processing device 50 comprises: at least one processor 501 and a memory 502, wherein:

[0140] The memory 502 is used to store computer-executable instructions;

[0141] The at least one processor 501 is used to execute the computer-executable instructions stored in the memory 502, so that the at least one processor 501 performs the barrel collision noise recognition method as described in any one of the above.

[0142] Among them, at least one processor 501 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.

[0143] Optionally, in a specific implementation, the processor 501 and the memory 502 are implemented independently, and the processor 501 and the memory 502 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.

[0144] Optionally, in a specific implementation, if the processor 501 and the memory 502 are integrated on a chip, the processor 501 and the memory 502 can communicate through an internal interface.

[0145] 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 above-mentioned barrel collision noise recognition method is implemented.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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 make equivalent replacements for some or all of the technical features therein. 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 method for identifying barrel collision noise, characterized in that: The method comprises: When the clothes processing device enters the dehydration program, the load weight of the clothes to be processed is obtained, and when the rotation speed of the clothes processing device reaches a first rotation speed, the current dehydration audio is collected, wherein the first rotation speed is determined according to the initial rotation speed corresponding to each of the multiple speed-up dehydration stages in the dehydration program; Acquiring a pre-stored reference audio according to the first rotation speed and the load weight, wherein the reference audio is audio collected when the clothes processing device pre-dehydrates the clothes of the load weight at the first rotation speed and hits the tub; The similarity between the reference audio and the dehydration audio is obtained, and if the similarity is less than the first similarity, the clothing processing device is controlled to enter the next speed-up dehydration stage, wherein the similarity is used to determine whether the clothing processing device hits the barrel.

2. The method according to claim 1, characterized in that After controlling the laundry processing device to enter the next dehydration stage, the method further includes: If the similarity is less than the first similarity and greater than or equal to the second similarity, new dehydration audio is acquired at the first time interval, and the type of the new dehydration audio is acquired through the audio classification model, and whether the clothes processing device hits the barrel is determined according to the type; If the similarity is less than the second similarity and greater than or equal to the third similarity, new dehydration audio is acquired at the second time interval, and the type of the new dehydration audio is acquired through the audio classification model, and whether the clothes processing device hits the barrel is determined according to the type; If the similarity is less than the third similarity, acquiring new dehydration audio when the rotation speed of the clothes processing device reaches the second rotation speed, and determining whether the clothes processing device hits the tub according to the second rotation speed and the new dehydration audio; The second speed is an initial speed corresponding to a next speed-up dehydration stage after the speed-up dehydration stage corresponding to the first speed, and the first time interval is smaller than the second time interval.

3. The method according to claim 2, characterized in that The obtaining of a pre-stored reference audio according to the first rotation speed and the load weight includes: A corresponding reference audio is acquired from a preset relationship according to the first rotational speed and the load weight, wherein the preset relationship is used to indicate a relationship between a rotational speed, a load weight and a reference audio of the laundry processing device.

4. The method according to claim 3, characterized in that The obtaining the similarity between the reference audio and the dehydrated audio includes: Acquire at least one reference short-term feature of the reference audio and at least one short-term feature of the dehydrated audio; The similarity between the reference audio and the dehydrated audio is obtained according to the at least one reference short-term feature and the corresponding short-term feature.

5. The method according to claim 4, characterized in that The obtaining, according to the at least one reference short-term feature and the corresponding short-term feature, the similarity between the reference audio and the dehydrated audio includes: Obtaining candidate similarities between the short-term feature and the corresponding reference short-term feature, wherein the number of the candidate similarities is the same as the number of the short-term features or the reference short-term features; The similarity between the reference audio and the dehydrated audio is obtained according to the weight of each short-term feature and the candidate similarity.

6. The method according to claim 5, characterized in that The obtaining of at least one short-term feature of the dehydrated audio comprises: At least one short-term feature is extracted according to the dehydrated audio, and the short-term feature is smoothed by first-order filtering.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: If the similarity is greater than or equal to the first similarity, the clothes processing device is controlled to shake out the clothes to be processed and re-enter the dehydration program.

8. A device for identifying and controlling barrel collision noise, characterized in that: include: Acquisition module, acquisition module and control module, wherein: The acquisition module is used to acquire the load weight of the clothes to be processed when the clothes processing device enters the dehydration program, and to acquire the current dehydration audio when the rotation speed of the clothes processing device reaches a first rotation speed, wherein the first rotation speed is determined according to the initial rotation speeds corresponding to the multiple speed-up dehydration stages in the dehydration program; The acquisition module is used to acquire a pre-stored reference audio according to the first rotation speed and the load weight, wherein the reference audio is the audio collected when the clothes processing device dehydrates the clothes of the load weight at the first rotation speed and just hits the barrel; The control module is used to obtain the similarity between the reference audio and the dehydration audio, and if the similarity is less than the first similarity, control the clothing processing device to enter the next speed-up dehydration stage, wherein the similarity is used to determine whether the clothing processing device sends a barrel collision.

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