Clothes airing machine voice control method and device, electronic equipment and storage medium

Abstract

The invention relates to a clothes airing machine voice control method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining the user audio information of a clothes airing machine, carrying out the audio analysis of the user audio information, obtaining the noise level feature information and the audio feature information, and carrying out the voice analysis of the noise level feature information; preset feature information corresponding to the noise level feature information is determined as target feature information, the target feature information and the audio feature information are compared to obtain an audio feature comparison result, and then the clothes airing machine is controlled to respond to the user audio information according to the audio feature comparison result. According to the method, the clothes airing machine can analyze and process the user audio by adopting different target feature information according to different noise levels, so that the clothes airing machine is controlled to respond to obtain a clothes airing machine control result, the control precision of the clothes airing machine can be effectively improved, and the user experience is improved. The problem that the control precision is low due to much environmental noise in the voice control process of the clothes airing machine in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of clothes drying machines, and in particular to a method, device, electronic device and storage medium for voice control of clothes drying machines. Background Art

[0002] With the development of society, home appliances are also constantly developing towards intelligence, and people's requirements for the intelligence of home appliances are getting higher and higher. Clothes drying machines are commonly used in households for textile care. When users use clothes drying machines, they usually control the clothes drying machines while drying clothes. At this time, voice control becomes the most convenient control method for users. However, since clothes drying machines are usually installed in outdoor scenes such as balconies, there is usually a lot of environmental noise in outdoor scenes, which causes the user voice control of the clothes drying machine to be affected by environmental noise, resulting in low control accuracy. Summary of the invention

[0003] In order to solve the technical problem of low control accuracy due to high ambient noise during voice control of a clothes drying machine in the existing related technology, the present application provides a clothes drying machine voice control method, device, electronic device and storage medium.

[0004] In a first aspect, the present application provides a method for voice control of a clothes drying machine, comprising:

[0005] Get the user audio information of the clothes drying machine;

[0006] Performing audio analysis on the user audio information to obtain noise level feature information and audio feature information;

[0007] Determining preset characteristic information corresponding to the noise level characteristic information as target characteristic information;

[0008] Comparing the target feature information with the audio feature information to obtain an audio feature comparison result;

[0009] According to the audio feature comparison result, the clothes drying machine is controlled to respond to the user audio information to obtain a clothes drying machine control result.

[0010] Optionally, controlling the clothes drying machine to respond to the user audio information according to the audio feature comparison result to obtain a clothes drying machine control result includes:

[0011] When the audio feature comparison result is an audio feature matching result, performing text recognition on the user audio information to obtain user audio text information;

[0012] Determining a clothes drying machine control instruction according to the user audio text information;

[0013] Based on the clothes drying machine control instruction, the clothes drying machine is controlled to respond, and the clothes drying machine control result is obtained.

[0014] Optionally, determining the clothes drying machine control instruction according to the user audio text information includes:

[0015] Obtain at least one preset instruction text information;

[0016] In the case where the user audio text information matches the preset instruction text information, determining the preset instruction text information as the target instruction text information;

[0017] The clothes drying machine control instruction is generated according to the target instruction text information.

[0018] Optionally, controlling the clothes drying machine to respond based on the clothes drying machine control instruction to obtain the clothes drying machine control result includes:

[0019] In response to the clothes drying machine control instruction, acquiring execution status information of the clothes drying machine;

[0020] The clothes drying machine control result is generated according to the execution status information.

[0021] Optionally, determining preset characteristic information corresponding to the noise level characteristic information as target characteristic information includes:

[0022] Determine a noise level identifier corresponding to the noise level characteristic information;

[0023] Determine a preset noise identifier that matches the noise level identifier as a target noise identifier;

[0024] Obtaining preset characteristic information corresponding to the target noise identification;

[0025] The preset characteristic information is determined as the target characteristic information.

[0026] Optionally, performing audio analysis on the user audio information to obtain noise level feature information and audio feature information includes:

[0027] Performing audio analysis on the user audio information to obtain noise audio information and voice audio information;

[0028] Performing noise analysis on the noise audio information to obtain the noise level characteristic information;

[0029] Feature extraction is performed on the speech audio information to obtain the audio feature information.

[0030] Optionally, comparing the target feature information with the audio feature information to obtain an audio feature comparison result includes:

[0031] Determining a feature matching value between the target feature information and the audio feature information;

[0032] When the feature matching value does not reach a preset feature threshold, determining a preset audio feature mismatch result as the audio feature comparison result;

[0033] When the feature matching value reaches a preset feature threshold, a preset audio feature matching result is determined as the audio feature comparison result.

[0034] In a second aspect, the present application provides a voice control device for a clothes drying machine, comprising:

[0035] An acquisition module is used to obtain user audio information of the clothes drying machine;

[0036] An audio analysis module, used to perform audio analysis on the user audio information to obtain noise level feature information and audio feature information;

[0037] A determination module, used to determine preset characteristic information corresponding to the noise level characteristic information as target characteristic information;

[0038] A comparison module, used to compare the target feature information with the audio feature information to obtain an audio feature comparison result;

[0039] A response module is used to control the clothes drying machine to respond to the user audio information according to the audio feature comparison result to obtain a clothes drying machine control result.

[0040] In a third aspect, an electronic device is provided, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0041] Memory, used to store computer programs;

[0042] The processor is used to implement the voice control method for the clothes drying machine as described in any one of the first aspects when executing the program stored in the memory.

[0043] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the voice control method for a clothes drying machine as described in any one of the first aspects is implemented.

[0044] The clothes drying machine voice control method, device, electronic device and storage medium provided in the embodiments of the present application obtain user audio information of the clothes drying machine, perform audio analysis on the user audio information, obtain noise level characteristic information and audio characteristic information, determine preset characteristic information corresponding to the noise level characteristic information as target characteristic information, and compare the target characteristic information and the audio characteristic information to obtain an audio characteristic comparison result, and then control the clothes drying machine to respond to the user audio information based on the audio characteristic comparison result, so that the clothes drying machine can use different target characteristic information according to different noise levels to analyze and process the user audio, and thereby control the clothes drying machine to respond, and obtain a clothes drying machine control result, thereby effectively improving the control accuracy of the clothes drying machine, and solving the problem of low control accuracy due to high ambient noise in the existing related technology during voice control of the clothes drying machine. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0047] Figure 1 A flow chart of a method for voice control of a clothes drying machine provided in an embodiment of the present application;

[0048] Figure 2 A schematic flow chart of a method for voice controlling a clothes drying machine provided in another embodiment of the present application;

[0049] Figure 3 A schematic diagram of the structure of a voice control device for a clothes drying machine provided in an embodiment of the present application;

[0050] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0052] With the development and maturity of voice recognition technology, voice recognition functions can now be configured on various products. The accuracy of voice recognition mainly depends on the collection and analysis of user voice. Voice collection usually requires the user to be closer to the voice collection device or the user to increase the volume to improve the integrity and accuracy of voice collection, while the accuracy of voice analysis mainly depends on the noise in the user's voice, that is, the more noise in the voice, the lower the accuracy of voice analysis. It can be seen from this that in the existing related technologies, if the accuracy of voice recognition needs to be improved, the user is usually required to input voice at a close distance and find an environment with less noise to input voice, etc.; however, the above problems are particularly prominent for clothes drying machines. On the one hand, because clothes drying machines are usually installed outdoors such as balconies, and the noise in the outdoor environment is usually more, users cannot actively avoid these noises. On the other hand, the installation location of clothes drying machines is mainly installed on the ceiling of the house, that is, the distance between the clothes drying machine and the user is far, and it is difficult for the user to further close the distance; therefore, due to the use environment and installation location of the clothes drying machine, the user cannot input voice at a close distance and find an environment with less noise to input voice, etc., resulting in the problem of low accuracy of voice control of the clothes drying machine.

[0053] In order to solve the technical problem of low control accuracy due to high ambient noise in the voice control process of a clothes drying machine in the existing related technology, the present application provides a method, device, electronic device and storage medium for voice control of a clothes drying machine, by obtaining user audio information of the clothes drying machine, performing audio analysis on the user audio information, obtaining noise level characteristic information and audio characteristic information, determining preset characteristic information corresponding to the noise level characteristic information as target characteristic information, and comparing the target characteristic information with the audio characteristic information to obtain an audio feature comparison result, and then controlling the clothes drying machine to respond to the user audio information based on the audio feature comparison result, so that the clothes drying machine can use different target characteristic information to analyze and process the user audio according to different noise levels, and thereby control the clothes drying machine to respond, to obtain a clothes drying machine control result, thereby effectively improving the control accuracy of the clothes drying machine, and solving the problem of low control accuracy due to high ambient noise in the voice control process of the clothes drying machine in the existing related technology.

[0054] Figure 1 A flow chart of a method for voice controlling a clothes drying machine provided in an embodiment of the present application.

[0055] like Figure 1 As shown, a method for voice controlling a clothes drying machine provided in an embodiment of the present application may specifically include the following steps:

[0056] S110: Acquire user audio information of the clothes drying machine.

[0057] Among them, the clothes drying machine can represent a clothes drying device with a voice collection function, such as a clothes drying device equipped with an audio collection device, and the user audio information can represent the audio information collected by the clothes drying machine, for example, it can be the audio information emitted by the user collected by the clothes drying machine through the audio collection device. This embodiment does not make specific limitations on this.

[0058] It should be noted that in the process of obtaining the user audio information of the clothes drying machine, the environmental audio information collected by the clothes drying machine can be obtained, and user voice recognition can be performed on the environmental audio information to identify whether there is user voice information in the environmental audio. The user voice information can represent the voice information emitted by the user. In the case of whether there is user voice information in the environmental audio information, the environmental audio information is determined as the user audio information. In the case of no user voice information in the environmental audio information, the environmental audio information can be discarded and the environmental audio information can continue to be collected; thus, the subsequent steps can be executed only when the voice information emitted by the user is collected, thereby improving the effect of voice collection. Of course, the above is only an example for illustration, and this embodiment does not make specific limitations on this.

[0059] S120: Performing audio analysis on the user audio information to obtain noise level feature information and audio feature information.

[0060] Specifically, after obtaining the user audio information of the clothes drying machine, audio analysis can be performed on the user audio information to obtain noise level feature information and audio feature information; the audio analysis can represent the process of performing various analysis and processing on the user audio information, such as noise recognition and audio feature extraction; and the noise level feature information can represent the level of noise features contained in the user audio information, such as no noise level, moderate noise level, severe noise level, rainy day noise level, typhoon noise level, etc.; the audio feature information can represent the audio features of the user voice contained in the user audio information, such as audio amplitude, audio frequency, frequency cepstrum coefficients, zero crossing rate, energy and other features, which are not specifically limited in this embodiment.

[0061] S130: Determine the preset characteristic information corresponding to the noise level characteristic information as the target characteristic information.

[0062] Specifically, after obtaining the noise level characteristic information, the preset characteristic information corresponding to the noise level characteristic information can be determined as the target characteristic information; wherein the preset characteristic information can represent the characteristic information pre-configured for audio feature comparison, and the target characteristic information can represent the preset characteristic information that matches the current noise level characteristic information.

[0063] It should be noted that in this embodiment, a variety of different preset characteristic information can be pre-configured according to different noise levels. For example, when the preset characteristic information A is configured for the no noise level, the preset characteristic information B is configured for the moderate noise level, the preset characteristic information C is configured for the severe noise level, the preset characteristic information D is configured for the rainy day noise level, and the preset characteristic information E is configured for the typhoon noise level; by performing audio analysis on the user audio information, when the obtained noise level characteristic information is the no noise level, the preset characteristic information A can be determined as the target characteristic information, when the obtained noise level characteristic information is the moderate noise level, the preset characteristic information B can be determined as the target characteristic information, and when the obtained noise level characteristic information is the rainy day noise level, the preset characteristic information D can be determined as the target characteristic information. Of course, the above is only an example, and this embodiment does not make specific limitations on this.

[0064] S140: Compare the target feature information and the audio feature information to obtain an audio feature comparison result.

[0065] Specifically, after determining the target feature information, the target feature information and the audio feature information can be compared to obtain an audio feature comparison result, which can indicate whether the target feature information and the audio feature information match; that is, the audio feature comparison result can be an audio feature mismatch result or an audio feature match result, the audio feature mismatch result indicating that the target feature information and the audio feature information do not match, and the audio feature match result indicating that the target feature information and the audio feature information match.

[0066] It can be seen that in the process of analyzing the audio feature information corresponding to the user audio information, this embodiment combines the target feature information corresponding to the noise level feature information for comparative analysis, that is, different target feature information can be used for comparative analysis according to the different noise level feature information of the user audio information; therefore, when analyzing the audio feature information, it is no longer limited to using noise reduction and audio extraction to improve the audio recognition accuracy, but it is possible to perform targeted comparative analysis by pre-configuring the target feature information corresponding to different noise level feature information, thereby achieving the effect of improving the audio recognition accuracy.

[0067] S150: Based on the audio feature comparison result, control the clothes drying machine to respond to the user audio information to obtain a clothes drying machine control result.

[0068] Specifically, after obtaining the audio feature comparison result, the clothes drying machine can be controlled to respond to the user audio information based on the audio feature comparison result to obtain the clothes drying machine control result; wherein the clothes drying machine control result can indicate the state result after the clothes drying machine responds to the user audio information, such as raising the drying rod, turning on the drying mode, etc.

[0069] It should be noted that in the process of controlling the clothes drying machine to respond to the user audio information, this embodiment may include generating a control instruction based on the audio feature comparison result combined with the user audio information, and controlling the clothes drying machine to perform a corresponding operation through the generated control instruction to obtain the execution result of the clothes drying machine, and generating a clothes drying machine control result based on the execution result. Of course, the above is only an example, and this embodiment does not make any specific limitation on this.

[0070] It can be seen that the present application obtains user audio information of the clothes dryer, performs audio analysis on the user audio information, obtains noise level characteristic information and audio characteristic information, determines the preset characteristic information corresponding to the noise level characteristic information as the target characteristic information, and compares the target characteristic information and the audio characteristic information to obtain the audio feature comparison result, and then controls the clothes dryer to respond to the user audio information based on the audio feature comparison result, so that the clothes dryer can use different target characteristic information to analyze and process the user audio according to different noise levels, and thereby control the clothes dryer to respond, and obtain the clothes dryer control result, thereby effectively improving the control accuracy of the clothes dryer, and solving the problem of low control accuracy due to the high ambient noise in the voice control process of the clothes dryer in the existing related technology.

[0071] like Figure 2 As shown, in an optional embodiment of the present application, step S150 controls the clothes drying machine to respond to the user audio information according to the audio feature comparison result to obtain the clothes drying machine control result, which may specifically include the following sub-steps:

[0072] S151: When the audio feature comparison result is an audio feature matching result, perform text recognition on the user audio information to obtain user audio text information;

[0073] S152: Determine a clothes drying machine control instruction according to the user audio text information;

[0074] S153: Based on the clothes drying machine control instruction, control the clothes drying machine to respond and obtain a clothes drying machine control result.

[0075] In the process of controlling the clothes drying machine to respond to the user audio information and obtaining the clothes drying machine control result based on the audio feature comparison result, this embodiment can determine whether the audio feature comparison result is an audio feature matching result; when the audio feature comparison result is an audio feature matching result, it means that the current audio feature information and the target feature information match, which means that the current user voice intends to control the clothes drying machine; thereby, text recognition can be performed on the user audio information to obtain user audio text information, and the user audio text information can represent the text content recognized in the user audio information; further, the clothes drying machine control instruction can be determined based on the user audio text information, and the clothes drying machine control instruction can represent the instruction for controlling the clothes drying machine to perform an operation; then, based on the clothes drying machine control instruction, the clothes drying machine can be controlled to respond and the clothes drying machine control result can be obtained.

[0076] It should be noted that, in the process of determining the clothes drying machine control instructions based on the user audio text information, this embodiment may perform semantic analysis, intention recognition, etc. on the user audio text information to determine the user control demand information, and then determine the clothes drying machine control instructions corresponding to the user control demand information; or it may compare the user audio text information with the pre-configured preset instruction text information, and generate the clothes drying machine control instructions based on the preset instruction text information that matches the user audio text information; of course, other methods of determining the clothes drying machine control instructions based on the user audio text information may also be used, and this embodiment does not specifically limit this.

[0077] In an optional embodiment of the present application, determining the clothes drying machine control instruction based on the user audio text information may specifically include the following sub-steps: obtaining at least one preset instruction text information; when the user audio text information matches the preset instruction text information, determining the preset instruction text information as the target instruction text information; generating the clothes drying machine control instruction based on the target instruction text information.

[0078] In the process of determining the clothes drying machine control instruction based on the user audio text information, this embodiment can obtain at least one preset instruction text information, and the preset instruction text information can indicate that the clothes drying machine is pre-configured with text content that can execute instructions; thereby, the user audio text information can be compared with each preset instruction text information, and it can be determined whether the user audio text information matches each preset instruction text information. When the user audio text information matches the preset instruction text information, the preset instruction text information can be determined as the target instruction text information; and based on the target instruction text information, a clothes drying machine control instruction is generated, specifically, the control instruction corresponding to the target instruction text information can be determined as the clothes drying machine control instruction, and this embodiment does not make any specific limitation on this.

[0079] It should be noted that, in the process of comparing the user audio text information with each preset instruction text information and determining whether the user audio text information matches each preset instruction text information, the user audio text information may be semantically analyzed to obtain user intent information, and the user intent information may be compared with the instruction intent information corresponding to the preset instruction text information to obtain intent similarity; if the intent similarity does not reach the preset intent familiarity threshold, the next preset instruction text information may be compared; if the intent similarity reaches the preset intent familiarity threshold, it may be determined that the user audio text information matches the preset instruction text information. Of course, the above is only an example, and this embodiment does not specifically limit this.

[0080] In addition, if there is no preset instruction text information that matches the user audio text information, it means that the clothes drying machine cannot be controlled to execute the text content contained in the response user audio text information. At this time, a voice instruction abnormality prompt information can be generated. The voice instruction abnormality prompt information can indicate information used to prompt the user that there is an abnormality in the current input voice instruction. Specifically, it can be playing the voice instruction abnormality prompt information through a speaker, displaying the voice instruction abnormality prompt information through an application, and displaying the output voice instruction abnormality prompt information on a display screen. This embodiment does not make specific limitations on this.

[0081] In an optional embodiment of the present application, based on the clothes drying machine control instruction, the clothes drying machine is controlled to respond to obtain a clothes drying machine control result, which may specifically include the following sub-steps: in response to the clothes drying machine control instruction, the execution status information of the clothes drying machine is obtained; based on the execution status information, the clothes drying machine control result is generated.

[0082] In the process of controlling the clothes dryer to respond based on the clothes dryer control instruction and obtaining the clothes dryer control result, this embodiment can respond to the clothes dryer control instruction, that is, control the clothes dryer to respond according to the clothes dryer control instruction, and execute the operation corresponding to the clothes dryer control instruction; and obtain the execution status information of the clothes dryer, and the execution status information can indicate the state of the clothes dryer after executing the operation corresponding to the clothes dryer control instruction; thereby, the clothes dryer control result can be generated based on the execution status information.

[0083] Specifically, for example, when the clothes drying machine control instruction is an instruction to turn on the drying mode, in response to the clothes drying machine control instruction, the clothes drying machine can be controlled to respond to turn on the drying mode of the clothes drying machine. At this time, the execution status information of the clothes drying machine is the drying function status. According to the drying function status, it can be determined whether the drying mode is turned on, and then the clothes drying machine control result is generated; if the drying mode is successfully turned on, a clothes drying machine control success result can be generated, and when the drying mode fails to be turned on, a clothes drying machine control abnormality result can be generated; that is, when the clothes drying machine control result is a clothes drying machine control abnormality result, clothes drying machine control abnormality prompt information can also be generated according to the clothes drying machine control abnormality result, and the user is prompted by the clothes drying machine control abnormality prompt information that the current clothes drying machine has a control abnormality. Of course, the above is only an example, and this embodiment does not make specific limitations on this.

[0084] In an optional embodiment of the present application, step S130 determines the preset characteristic information corresponding to the noise level characteristic information as the target characteristic information, which may specifically include the following sub-steps: determining the noise level identifier corresponding to the noise level characteristic information; determining the preset noise identifier that matches the noise level identifier as the target noise identifier; obtaining the preset characteristic information corresponding to the target noise identifier; and determining the preset characteristic information as the target characteristic information.

[0085] In the process of determining preset characteristic information corresponding to noise level characteristic information as target characteristic information, this embodiment may determine a noise level identifier corresponding to the noise level characteristic information, and the noise level identifier may indicate an identifier of the noise level to which the noise level characteristic information belongs, such as a no-noise identifier, a moderate-noise identifier, a severe-noise identifier, a rainy-day noise identifier, a typhoon noise identifier, etc.; thereby, the noise level identifier may be compared one by one with a pre-configured preset noise identifier, and the preset noise identifier may indicate an identifier pre-configured for marking different noise environments, such as a no-noise identifier, a moderate-noise identifier, a severe-noise identifier, a rainy-day noise identifier, a typhoon noise identifier, etc.; when the noise level identifier matches the preset noise identifier, the preset noise identifier matching the noise level identifier may be determined as the target noise identifier; after determining the target noise identifier, the preset characteristic information corresponding to the target noise identifier may be acquired, and the preset characteristic information may be determined as the target characteristic information.

[0086] It should be noted that the preset noise identifier and the preset feature information in this embodiment can be a pre-configured one-to-one correspondence, and different preset feature information is used to represent the feature information of audio in different noise environments. For example, the rainy day preset feature information corresponding to the rainy day noise identifier can include the characteristics of rain sound audio, so that when the rainy day preset feature information is used as the target feature information to be compared with the audio feature information corresponding to the user audio information, the audio feature information that is the same as the ambient noise in which the user audio information is located is used for comparison, thereby weakening the recognition error caused by the ambient noise, which can effectively improve the accuracy of speech recognition.

[0087] In an optional embodiment of the present application, step S120 performs audio analysis on the user audio information to obtain noise level characteristic information and audio characteristic information, which may specifically include the following sub-steps: performing audio analysis on the user audio information to obtain noise audio information and voice audio information; performing noise analysis on the noise audio information to obtain noise level characteristic information; performing feature extraction on the voice audio information to obtain audio characteristic information.

[0088] After obtaining the user audio information, this embodiment can perform audio analysis on the user audio information to obtain noise audio information and voice audio information, wherein the audio analysis may include but is not limited to analysis and processing methods such as noise recognition, voice recognition, noise extraction, and voice extraction, and the noise audio information may represent the noise audio contained in the user audio information, and the voice audio information may represent the user voice audio contained in the user audio information; thereby, noise analysis can be performed on the noise audio information to obtain noise level feature information, wherein the noise analysis may be to extract the noise features in the noise audio information and determine the noise level feature information corresponding to the noise features; then, feature extraction can be performed on the voice audio information to obtain audio feature information, wherein the feature extraction may represent user voice feature extraction, such as extraction of features such as audio amplitude, audio frequency, frequency cepstrum coefficients, zero crossing rate, energy, etc., which is not specifically limited in this embodiment.

[0089] Specifically, in the process of performing noise analysis on the noise audio information, the noise feature in the noise audio information can be extracted, and the noise type of the noise feature can be determined. When the noise type belongs to the preset noise type, the noise level feature information can be determined according to the noise level corresponding to the preset noise type. For example, when the preset noise type can be a rain noise type, the noise level feature information can be determined according to the rain noise level, or when the preset noise type is a typhoon noise type, the noise level feature information can be determined according to the typhoon noise type, etc.; and when the noise type does not belong to the preset noise type, the noise decibel value can be determined according to the noise feature, and the preset noise decibel interval corresponding to the noise decibel value is determined as the target noise decibel interval, and then the noise level feature information can be determined according to the noise level corresponding to the target noise decibel interval. For example, the target noise decibel interval corresponding to the noise decibel value is a severe noise decibel interval, and the noise level feature information can be determined according to the severe noise level corresponding to the severe noise decibel interval. Of course, the above is only an example for illustration, and this embodiment does not make specific limitations on this.

[0090] In an optional embodiment of the present application, step S140 compares the target feature information and the audio feature information to obtain an audio feature comparison result, which may specifically include the following sub-steps: determining a feature matching value between the target feature information and the audio feature information; when the feature matching value does not reach a preset feature threshold, determining a preset audio feature non-matching result as the audio feature comparison result; when the feature matching value reaches a preset feature threshold, determining a preset audio feature matching result as the audio feature comparison result.

[0091] In the process of comparing the target feature information and the audio feature information to obtain the audio feature comparison result, the present embodiment can determine the feature matching value between the target feature information and the audio feature information. The feature matching value can indicate the matching of specific features of the target feature information and the audio feature information. Specifically, each feature information in the target feature information is compared with each feature information in the audio feature information to obtain feature matching information, and the feature matching value is determined according to the feature matching information. Thus, it can be judged whether the feature matching value reaches a preset feature threshold. The preset feature threshold can indicate a threshold when the matching degree between the pre-configured target feature information and the audio feature information meets the requirement. That is, when the feature matching value does not reach the preset feature threshold, it means that the matching degree between the current target feature information and the audio feature information does not meet the preset matching requirement. At this time, the preset audio feature non-matching result can be determined as the audio feature comparison result. When the feature matching value reaches the preset feature threshold, it means that the matching degree between the current target feature information and the audio feature information meets the preset matching requirement. At this time, the preset audio feature matching result can be determined as the audio feature comparison result.

[0092] Specifically, in the process of comparing each feature information in the target feature information with each feature information in the audio feature information and determining the feature matching value according to the feature matching information, the target frequency cepstral coefficient feature, target zero crossing rate feature, target energy feature, target amplitude feature and target frequency feature can be extracted from the target feature information, and the audio frequency cepstral coefficient feature, audio zero crossing rate feature, audio energy feature, audio amplitude feature and audio frequency feature can be extracted from the audio feature information, and the target frequency cepstral coefficient feature can be compared with the audio frequency cepstral coefficient feature, the target zero crossing rate feature can be compared with the audio zero crossing rate feature and the target energy feature, the target amplitude feature can be compared with the audio amplitude feature, and the target frequency feature can be compared with the audio frequency feature to obtain feature matching information, so as to generate a feature matching value based on the feature matching information. The feature matching value can be a percentage value or a matching degree value, which is not specifically limited in this embodiment.

[0093] like Figure 3 As shown, the present application also discloses an embodiment, providing a voice control device for a clothes drying machine, comprising:

[0094] An acquisition module 310 is used to acquire user audio information of the clothes drying machine;

[0095] The audio analysis module 320 is used to perform audio analysis on the user audio information to obtain noise level feature information and audio feature information;

[0096] A determination module 330, configured to determine preset characteristic information corresponding to the noise level characteristic information as target characteristic information;

[0097] A comparison module 340 is used to compare the target feature information with the audio feature information to obtain an audio feature comparison result;

[0098] The response module 350 is used to control the clothes drying machine to respond to the user audio information according to the audio feature comparison result, and obtain the clothes drying machine control result.

[0099] In an optional embodiment of the present application, the response module 350 may include:

[0100] A text recognition unit, configured to perform text recognition on the user audio information to obtain user audio text information when the audio feature comparison result is an audio feature matching result;

[0101] A first determining unit, configured to determine a clothes drying machine control instruction according to the user audio text information;

[0102] The control unit is used to control the clothes drying machine to respond based on the clothes drying machine control instruction to obtain the clothes drying machine control result.

[0103] In an optional embodiment of the present application, the first determining unit may include:

[0104] A first acquisition subunit, used to acquire at least one preset instruction text information;

[0105] A first determining subunit is used to determine the preset instruction text information as the target instruction text information when the user audio text information matches the preset instruction text information;

[0106] The first generating subunit is used to generate the clothes drying machine control instruction according to the target instruction text information.

[0107] In an optional embodiment of the present application, the control unit may include:

[0108] a second acquisition subunit, configured to acquire execution status information of the clothes drying machine in response to the clothes drying machine control instruction;

[0109] The second generating subunit is used to generate the clothes drying machine control result according to the execution status information.

[0110] In an optional embodiment of the present application, the determination module 330 may include:

[0111] A second determining unit, configured to determine a noise level identifier corresponding to the noise level characteristic information;

[0112] A third determining unit, configured to determine a preset noise identifier that matches the noise level identifier as a target noise identifier;

[0113] An acquisition unit, used to acquire preset characteristic information corresponding to the target noise identification;

[0114] The fourth determining unit is configured to determine the preset characteristic information as the target characteristic information.

[0115] In an optional embodiment of the present application, the audio analysis module 320 may include:

[0116] An audio analysis unit, used to perform audio analysis on the user audio information to obtain noise audio information and voice audio information;

[0117] A noise analysis unit, configured to perform noise analysis on the noise audio information to obtain the noise level characteristic information;

[0118] The feature extraction unit is used to extract features from the speech audio information to obtain the audio feature information.

[0119] In an optional embodiment of the present application, the comparison module 340 may include:

[0120] a fifth determining unit, configured to determine a feature matching value between the target feature information and the audio feature information;

[0121] a sixth determining unit, configured to determine a preset audio feature mismatch result as the audio feature comparison result if the feature matching value does not reach a preset feature threshold;

[0122] The seventh determination unit is used to determine a preset audio feature matching result as the audio feature comparison result when the feature matching value reaches a preset feature threshold.

[0123] The implementation process of the functions and effects of each module in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, which will not be repeated here.

[0124] like Figure 4 As shown, an embodiment of the present application provides an electronic device, including a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other through the communication bus 440;

[0125] Memory 430, for storing computer programs;

[0126] In one embodiment of the present application, the processor 410, when executing the program stored in the memory 430, implements the clothes drying machine voice control method provided by any of the aforementioned method embodiments, by acquiring user audio information of the clothes drying machine, performing audio analysis on the user audio information, obtaining noise level characteristic information and audio characteristic information, and determining preset characteristic information corresponding to the noise level characteristic information as target characteristic information, and comparing the target characteristic information and the audio characteristic information to obtain an audio feature comparison result, and then controlling the clothes drying machine to respond to the user audio information based on the audio feature comparison result, so that the clothes drying machine can use different target characteristic information according to different noise levels to analyze and process the user audio, and thereby control the clothes drying machine to respond, and obtain a clothes drying machine control result, thereby effectively improving the control accuracy of the clothes drying machine, and solving the problem of low control accuracy due to high ambient noise in the existing related technology during the voice control of the clothes drying machine.

[0127] The embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a clothes drying machine voice control method as provided in any of the aforementioned method embodiments, by acquiring user audio information of the clothes drying machine, performing audio analysis on the user audio information, obtaining noise level characteristic information and audio characteristic information, determining preset characteristic information corresponding to the noise level characteristic information as target characteristic information, and comparing the target characteristic information with the audio characteristic information to obtain an audio characteristic comparison result, and then controlling the clothes drying machine to respond to the user audio information based on the audio characteristic comparison result, so that the clothes drying machine can use different target characteristic information to analyze and process the user audio according to different noise levels, and thereby control the clothes drying machine to respond, to obtain a clothes drying machine control result, thereby effectively improving the control accuracy of the clothes drying machine, and solving the problem of low control accuracy due to high ambient noise in the existing related technology during the voice control of the clothes drying machine.

[0128] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0129] The above describes specific embodiments of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0130] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for voice control of a clothes drying machine, characterized in that: include: Get the user audio information of the clothes drying machine; Performing audio analysis on the user audio information to obtain noise level feature information and audio feature information; Determining preset characteristic information corresponding to the noise level characteristic information as target characteristic information; Comparing the target feature information with the audio feature information to obtain an audio feature comparison result; According to the audio feature comparison result, the clothes drying machine is controlled to respond to the user audio information to obtain a clothes drying machine control result.

2. The method for voice control of a clothes drying machine according to claim 1, characterized in that: The step of controlling the clothes drying machine to respond to the user audio information based on the audio feature comparison result to obtain a clothes drying machine control result includes: When the audio feature comparison result is an audio feature matching result, performing text recognition on the user audio information to obtain user audio text information; Determining a clothes drying machine control instruction according to the user audio text information; Based on the clothes drying machine control instruction, the clothes drying machine is controlled to respond, and the clothes drying machine control result is obtained.

3. The method for voice control of a clothes drying machine according to claim 2, characterized in that: The step of determining the clothes drying machine control instruction according to the user audio text information includes: Obtain at least one preset instruction text information; In the case where the user audio text information matches the preset instruction text information, determining the preset instruction text information as the target instruction text information; The clothes drying machine control instruction is generated according to the target instruction text information.

4. The method for voice control of a clothes drying machine according to claim 2, characterized in that: The controlling the clothes drying machine to respond based on the clothes drying machine control instruction to obtain the clothes drying machine control result includes: In response to the clothes drying machine control instruction, acquiring execution status information of the clothes drying machine; The clothes drying machine control result is generated according to the execution status information.

5. The voice control method for a clothes drying machine according to claim 1, characterized in that: The step of determining the preset characteristic information corresponding to the noise level characteristic information as the target characteristic information includes: Determine a noise level identifier corresponding to the noise level characteristic information; Determine a preset noise identifier that matches the noise level identifier as a target noise identifier; Obtaining preset characteristic information corresponding to the target noise identification; The preset characteristic information is determined as the target characteristic information.

6. The method for voice control of a clothes drying machine according to claim 1, characterized in that: The performing audio analysis on the user audio information to obtain noise level feature information and audio feature information includes: Performing audio analysis on the user audio information to obtain noise audio information and voice audio information; Performing noise analysis on the noise audio information to obtain the noise level characteristic information; Feature extraction is performed on the speech audio information to obtain the audio feature information.

7. The voice control method for a clothes drying machine according to any one of claims 1 to 6, characterized in that: The comparing the target feature information with the audio feature information to obtain an audio feature comparison result includes: Determining a feature matching value between the target feature information and the audio feature information; When the feature matching value does not reach a preset feature threshold, determining a preset audio feature mismatch result as the audio feature comparison result; When the feature matching value reaches a preset feature threshold, a preset audio feature matching result is determined as the audio feature comparison result.

8. A voice control device for a clothes drying machine, characterized in that: include: An acquisition module is used to obtain user audio information of the clothes drying machine; An audio analysis module, used to perform audio analysis on the user audio information to obtain noise level feature information and audio feature information; A determination module, used to determine preset characteristic information corresponding to the noise level characteristic information as target characteristic information; A comparison module, used to compare the target feature information with the audio feature information to obtain an audio feature comparison result; A response module is used to control the clothes drying machine to respond to the user audio information according to the audio feature comparison result to obtain a clothes drying machine control result.

9. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor is used to implement the voice control method for the clothes drying machine as described in any one of claims 1 to 7 when executing the program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the voice control method for a clothes drying machine as described in any one of claims 1 to 7 is implemented.

Images