Voice control method of intelligent household electrical appliance and intelligent household electrical appliance

Abstract

The invention relates to the technical field of voice control of household electrical appliances, particularly provides a voice control method of an intelligent household electrical appliance and the intelligent household electrical appliance, and aims to solve the problem that an existing voice control system cannot accurately recognize an effective voice instruction in a noisy environment. In order to achieve the purpose, the voice control method of the intelligent household electrical appliance comprises the following steps: after a voice control function is started, collecting audio data within a preset duration; environment noise and voice instructions of the surrounding environment in the audio data are recognized; when the environmental noise is greater than or equal to a preset noise threshold value, acquiring a voice keyword in the voice instruction; according to the voice control method disclosed by the invention, when the surrounding environment noise is greater than the preset noise threshold value, the environment noise and the voice instruction in the acquired audio data can be identified, and the intelligent household electrical appliance is controlled by identifying the keyword in the voice instruction; the accuracy of recognizing the voice instruction in the audio data is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of voice control of household appliances, and specifically provides a voice command voice control method and a smart household appliance thereof. Background Art

[0002] The voice control function of smart terminals is widely used in various smart terminal devices, allowing users to control smart devices through voice, so that users can control smart devices more conveniently and improve user satisfaction.

[0003] However, in the voice control system of smart home appliances, there is a noisy operating environment, such as the sound of TV, music, children playing and crying, etc. The voice control system will receive many useful and useless commands in this environment and cannot recognize effective voice commands, which affects the accuracy of the voice control system in recognizing voice commands.

[0004] Accordingly, the art needs a new technical solution to solve the above problems. Summary of the invention

[0005] The present invention aims to solve the above technical problem, that is, to solve the problem that the existing voice control system receives many useful and useless instructions in a noisy environment, cannot accurately recognize effective voice instructions, and affects the accuracy of the voice control system in recognizing voice instructions.

[0006] In a first aspect, the present invention provides a voice control method for a smart home appliance, wherein the smart home appliance has a voice control function, and after the voice control function is activated, the smart home appliance supports real-time voice control, and the voice control method comprises:

[0007] After the voice control function is activated, collecting audio data within a preset time period;

[0008] identifying ambient noise of the surrounding environment and voice commands in the audio data;

[0009] When the environmental noise is greater than or equal to a preset noise threshold, parsing the voice command to obtain voice keywords in the voice command;

[0010] The smart home appliance is controlled according to the voice keyword.

[0011] In the preferred technical solution of the voice control method for smart home appliances, the number of the sound sources is at least two, and the step of identifying the ambient noise and voice commands in the surrounding environment in the audio data includes:

[0012] Acquire a plurality of first positions and a plurality of first voiceprint information corresponding to a plurality of sound sources emitting sounds in the audio data;

[0013] The environmental noise and the voice command in the audio data are identified according to the plurality of the first positions and the plurality of the first voiceprint information.

[0014] In the preferred technical solution of the voice control method of the smart home appliance, the step of identifying the environmental noise in the audio data according to the plurality of the first positions and the plurality of the voiceprint information includes:

[0015] Matching the plurality of first positions and the plurality of first voiceprint information having corresponding relationships with a pre-stored mapping relationship table storing corresponding relationships between a plurality of second positions and a plurality of second voiceprint information;

[0016] The multiple sound sources corresponding to the multiple first positions and the multiple first voiceprint information that have a corresponding relationship and match the multiple second positions and the multiple second voiceprint information that have a corresponding relationship are taken as multiple noise sources, and the multiple sounds emitted by the multiple noise sources are taken as the environmental noise.

[0017] In the preferred technical solution of the voice control method of the smart home appliance, the step of identifying the ambient noise of the surrounding environment in the audio data further includes:

[0018] Determining a plurality of distances between a plurality of the sound sources and the smart home appliance according to the plurality of the first positions;

[0019] The multiple distances are compared with a preset distance threshold, and the sound source corresponding to the distance greater than the distance threshold is taken as the noise sound source.

[0020] In the preferred technical solution of the voice control method of the smart home appliance, before the step of using the multiple sound sources corresponding to the multiple first positions and the multiple first voiceprint information corresponding to the multiple second positions and the multiple second voiceprint information as multiple noise sources, and using the multiple sounds emitted by the multiple noise sources as the ambient noise, the step further includes:

[0021] After the plurality of first voiceprint information are matched with the plurality of second voiceprint information in the mapping relationship table, the plurality of first voiceprint information matched with the plurality of second voiceprint information are used as the plurality of voiceprints to be verified;

[0022] Acquire a plurality of first positions corresponding to the plurality of voiceprints to be verified, and use the plurality of first positions corresponding to the plurality of voiceprints to be verified as a plurality of positions to be matched;

[0023] Acquire a plurality of second positions corresponding to the plurality of positions to be matched according to the plurality of positions to be matched and the mapping relationship table;

[0024] When the distance between the plurality of second positions and the plurality of to-be-matched positions corresponding to the plurality of second positions is less than or equal to a preset second distance threshold, the plurality of second positions in the mapping relationship table are not adjusted;

[0025] When the distance between the plurality of second positions and the plurality of positions to be matched that have a corresponding relationship with the plurality of second positions is greater than a preset second distance threshold, taking the plurality of second positions among the plurality of second positions corresponding to the plurality of positions to be matched whose distance between the plurality of second positions is greater than the second distance threshold as the position information to be adjusted;

[0026] The second position corresponding to the position information to be adjusted is adjusted to the first position corresponding to the position to be matched corresponding to the position information to be adjusted.

[0027] In the preferred technical solution of the above-mentioned voice control method for smart home appliances, the step of controlling the smart home appliances according to the voice keywords includes:

[0028] Matching the voice keyword with a pre-stored control instruction containing a preset keyword;

[0029] Acquire a pre-stored control instruction corresponding to the voice keyword, and use the pre-stored control instruction corresponding to the voice keyword as a target control instruction;

[0030] The smart home appliance is controlled according to the target control instruction.

[0031] In the preferred technical solution of the above-mentioned voice control method for smart home appliances, the step of controlling the smart home appliances according to the pre-stored control instructions includes:

[0032] When the number of times the voice keyword corresponding to the target control instruction appears once, generating first prompt information, wherein the first prompt information is used to indicate a first execution content corresponding to the target control instruction;

[0033] Controlling the smart home appliance to send the first prompt information;

[0034] After the smart home appliance sends the first prompt information, if the smart home appliance receives a cancellation instruction to cancel the execution of the target control instruction within a preset first time threshold, the smart home appliance abandons the execution;

[0035] If the smart home appliance receives a first confirmation instruction confirming the execution of the target control instruction within the first time threshold, or the smart home appliance does not receive a first confirmation instruction confirming the execution of the target control instruction within the first time threshold, the smart home appliance is controlled to execute the target control instruction.

[0036] In the preferred technical solution of the above-mentioned voice control method for smart home appliances, the number of the target control instructions is at least one, and the step of controlling the smart home appliance according to the pre-stored control instructions further includes:

[0037] When the voice keyword corresponding to the target control instruction appears at least twice, obtaining the number of the target control instructions corresponding to the voice keyword that appears at least twice;

[0038] When the number of the target control instructions corresponding to the voice keyword that appears at least twice is one, controlling the smart home appliance to execute the target control instruction corresponding to the voice keyword that appears at least twice;

[0039] When the number of the target control instructions corresponding to the voice keyword that appears at least twice is at least two, using the multiple target control instructions corresponding to the voice keyword that appears at least twice as multiple candidate control instructions;

[0040] generating second prompt information, wherein the second prompt information is used to indicate a plurality of second execution contents corresponding to the plurality of candidate control instructions;

[0041] Controlling the smart home appliance to send the second prompt information;

[0042] After the smart home appliance sends the second prompt information, if the smart home appliance does not receive a second confirmation instruction corresponding to one of the multiple candidate control instructions within a preset second time threshold, the smart home appliance abandons execution;

[0043] If the smart home appliance receives a second confirmation instruction corresponding to one of the multiple alternative control instructions within the second time threshold, the smart home appliance is controlled to execute the alternative control instruction corresponding to the second confirmation instruction.

[0044] In the preferred technical solution of the above-mentioned voice control method for smart home appliances, the voice control method further includes:

[0045] When the environmental noise is less than a preset noise threshold, parsing all third execution contents contained in the voice instruction;

[0046] The smart home appliance is controlled based on all the third execution contents.

[0047] In a second aspect, the present invention further provides a smart home appliance, comprising a controller, wherein the controller is configured to execute the above-mentioned voice control method.

[0048] When the above-mentioned technical scheme is adopted, the voice control method of the smart home appliance of the present invention can identify the environmental noise and voice commands in the collected audio data when the surrounding environmental noise is greater than the preset noise threshold, so as to improve the accuracy of recognizing the voice commands in the audio data. Moreover, the voice control method of the present invention can also control the smart home appliance by recognizing the keywords in the voice commands when the environmental noise is greater than the preset noise threshold, so as to further improve the accuracy of the smart home appliance in recognizing the voice commands, thereby improving the user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings, in which:

[0050] Figure 1 is a schematic diagram of a scenario of a method for voice control of a smart home appliance of the present invention;

[0051] Figure 2 is a main flow chart of an embodiment of a method for voice control of a smart home appliance of the present invention;

[0052] Figure 3 is a flow chart of another implementation of an embodiment of the method for voice control of a smart home appliance of the present invention;

[0053] Figure 4 is a flow chart of another implementation of an embodiment of the method for voice control of a smart home appliance of the present invention;

[0054] Figure 5 is a flow chart of another implementation of an embodiment of the method for voice control of a smart home appliance of the present invention;

[0055] Figure 6 is a flow chart of another implementation of an embodiment of the method for voice control of a smart home appliance of the present invention;

[0056] Figure 7 is a flow chart of another implementation of an embodiment of the method for voice control of a smart home appliance of the present invention;

[0057] Figure 8 is a flow chart of another implementation of an embodiment of the method for voice control of a smart home appliance of the present invention;

[0058] Fig. 9 is a flow chart of another implementation of an embodiment of the method for voice control of a smart home appliance of the present invention;

[0059] Fig.10 It is a flow chart of another implementation of an embodiment of the voice control method for smart home appliances of the present invention. DETAILED DESCRIPTION

[0060] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not used to limit the scope of protection of the present invention. Those skilled in the art can make adjustments to them as needed to adapt to specific application scenarios.

[0061] It should be noted that in the description of the present invention, the terms "upper", "lower", "inner" and "outer" and other terms indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings, which are only for the convenience of description, and do not indicate or imply that the device or element must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second" and "third" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first", "second" and "third" may explicitly or implicitly include one or more features. In the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0062] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0063] Figure 1 It is a scene schematic diagram of the voice control method of the smart home appliance of the present invention. Figure 2 It is a main flow chart of an embodiment of the voice control method for smart home appliances of the present invention. Figure 3 It is a flow chart of another implementation of an embodiment of the voice control method for smart home appliances of the present invention. Figure 4 It is a flow chart of another implementation of an embodiment of the voice control method for smart home appliances of the present invention. Figure 5 It is a flow chart of another implementation of an embodiment of the voice control method for smart home appliances of the present invention. Figure 6 It is a flow chart of another implementation of an embodiment of the voice control method for smart home appliances of the present invention. Figure 7 It is a flow chart of another implementation of an embodiment of the voice control method for smart home appliances of the present invention. Figure 8 It is a flow chart of another implementation of an embodiment of the voice control method for smart home appliances of the present invention. Fig. 9It is a flow chart of another implementation of an embodiment of the voice control method for smart home appliances of the present invention. Fig.10 It is a flow chart of another implementation of an embodiment of the voice control method for smart home appliances of the present invention.

[0064] The existing voice control system will receive many useful and useless commands in this environment and cannot recognize effective voice commands, which affects the accuracy of the voice control system in recognizing voice commands.

[0065] In view of the above problems, the present invention provides a voice control method for smart home appliances. Figure 1 It is a scene schematic diagram of the voice control method for smart home appliances provided by the present invention. Figure 1 The smart home appliance has a voice interaction module, which has a voice control function. After the voice control function of the interaction module is started, the smart home appliance supports real-time voice control, which is used to receive audio data collected after the voice function is started, and parse and process the received audio data, so that the smart home appliance executes the corresponding processing program according to the voice data sent by the user.

[0066] Figure 1 The following is a schematic diagram of a scenario in which a smart home appliance interacts with a user via voice in a noisy environment. Figure 1 As shown, the smart home appliance can receive audio data within a preset time after the voice control function is turned on, wherein the number of sound sources generating the audio data can be multiple. The smart home appliance can also parse the audio data to obtain the location and voiceprint information of the sound source. Specifically, the smart home appliance is equipped with a speaker with a multi-microphone array and a voiceprint recognition device. More specifically, by analyzing the time difference between the sound reaching different microphones, the approximate direction and distance of the sound source can be determined, and then the sound input focused on a specific direction is calculated by beamforming technology to improve the accuracy of capturing the target sound, so as to obtain the location information of the sound source that issued the voice command. The voiceprint information of the sound source can be determined by a microphone or a voiceprint collector with a voiceprint information recognition function.

[0067] It should be noted that although the smart home appliance described above determines the position information of the sound source by installing a speaker with a multi-microphone array, this is not restrictive. In other embodiments of the present invention, a UWB sensor can also be installed on the smart home appliance, so that the smart home appliance of the present invention can locate the sound source of the indoor sound through ultra-wideband technology.

[0068] In the present invention, the smart home appliance also includes a controller (not shown), which is connected to the voiceprint recognition device and the speaker of the multi-microphone array, so that the controller can parse the voice commands issued by the user and received by the smart home appliance. It should be noted that the controller can be a control chip of the smart home appliance itself, or a control module specifically used to execute the voice control method of the present invention, or a functional unit of the control module.

[0069] Refer to the following Figure 2-Figure 10 To illustrate the implementation of the voice control method for smart home appliances of the present invention.

[0070] like Figure 2 As shown, in a possible implementation manner, the voice control method of the smart home appliance of the present invention includes the following steps:

[0071] S101: After the voice control function is activated, audio data within a preset time period is collected;

[0072] S102: Identify ambient noise and voice commands in the surrounding environment in the audio data;

[0073] S103: When the ambient noise is greater than or equal to a preset noise threshold, parsing the voice command to obtain voice keywords in the voice command;

[0074] S104: Controlling smart home appliances according to voice keywords.

[0075] In S101, after the voice control function is activated, the smart home appliance can collect audio data emitted by the sound source within a preset time length through a multi-array microphone and a device with a voiceprint information recognition function, wherein the number of sound sources is at least one, and the location of the sound source can be indoors or outdoors. It should be noted that the preset time length can be determined by the designer based on experience, experiments, calculations, etc. For example, the preset time length can be set to 10 seconds, so that the smart home appliance can obtain audio data within 10 seconds after the voice control function is activated. Obviously, the preset time length can also be set to 8 seconds, 9 seconds or 11 seconds. This adjustment does not deviate from the principle of the present invention and therefore will fall within the scope of protection of the present invention.

[0076] In S102: the smart home appliance can identify the ambient noise and voice commands of the surrounding environment in the audio data, wherein the ambient noise can be the sound of a TV, music, children playing and crying, door closing, car horn outside, etc., and the voice command can be issued by the user. This can prevent the smart home appliance from recognizing the audio content in the ambient noise so as to interfere with the smart home appliance's recognition of the content in the voice command, thereby ensuring the accuracy of the smart home appliance's recognition of the voice command.

[0077] In S103, when the smart home appliance detects that the ambient noise is greater than or equal to a preset noise threshold, it parses the voice command to obtain the voice keywords in the voice command. In this way, even when the ambient noise is loud, the smart home appliance can obtain the voice keywords in the voice command to determine the execution content contained in the voice command, thereby further reducing the situation where the smart home appliance has errors in recognizing voice commands due to ambient noise.

[0078] It should be noted that the noise threshold is the decibel threshold of the ambient noise, and the noise threshold is determined by designers based on experience, experiments, calculations, etc. The specific decibel threshold value is not the focus of the present invention and will not be repeated here.

[0079] like Figure 3 As shown, in a possible implementation manner, the voice control method of the smart home appliance of the present invention includes the following steps:

[0080] S201: Acquire multiple first positions and multiple first voiceprint information corresponding to multiple sound sources emitting sounds in the audio data;

[0081] S202: Identify environmental noise and voice commands in audio data according to the multiple first positions and the multiple first voiceprint information.

[0082] In S201, in a specific implementation of the present invention, when the number of sound sources is one and the sound source is a user issuing a voice command, the smart home appliance can execute the voice command. When the number of sound sources is at least two, at least one of which is a noise source, a multi-microphone array installed inside the smart home appliance obtains a plurality of first positions corresponding to the plurality of sound sources emitting sound in the audio data, and a voiceprint recognition device installed in the smart home appliance obtains a plurality of first voiceprint information corresponding to the plurality of sound sources emitting sound in the audio data. Moreover, when the smart home appliance processes the audio data through the multi-microphone array and the voiceprint recognition device, When performing recognition, a multi-microphone array can be used to assist the voiceprint recognition device in recognizing the voiceprint information in the audio data. In this way, when the smart home appliance recognizes the multiple first positions of multiple sound sources and the multiple first voiceprint information in the audio data, a corresponding relationship can be established between the multiple first positions of the multiple sound sources and the multiple first voiceprints. In this way, after the smart home appliance obtains the multiple first voiceprint information of the multiple sound sources, the smart home appliance can correspondingly determine the multiple first positions of the multiple sound sources. Conversely, after the smart home appliance obtains the multiple first positions of the multiple sound sources, the smart home appliance can correspondingly determine the multiple first voiceprint information of the multiple sound sources.

[0083] In S202, the smart home appliance can identify the ambient noise and voice commands in the audio data based on multiple first positions and multiple first voiceprint information. This can prevent the smart home appliance from identifying the audio content in the ambient noise to interfere with the smart home appliance's recognition of the content in the voice commands, thereby ensuring the accuracy of the smart home appliance's recognition of the voice commands.

[0084] like Figure 4 As shown, in a possible implementation manner, the voice control method of the smart home appliance of the present invention includes the following steps:

[0085] S301: Matching a plurality of first positions and a plurality of first voiceprint information having a corresponding relationship with a pre-stored corresponding relationship table storing a plurality of second positions and a plurality of second voiceprint information;

[0086] S302: multiple sound sources corresponding to multiple first positions and multiple first voiceprint information that correspond to multiple second positions and multiple second voiceprint information that correspond to each other are regarded as multiple noise sources, and multiple sounds emitted by the multiple noise sources are regarded as environmental noise.

[0087] In S301, when the smart home appliance identifies the audio data emitted by multiple sound sources, it can obtain multiple first positions and multiple first voiceprint information corresponding to the multiple sound sources. When the controller obtains the multiple first positions and multiple first voiceprint information corresponding to the multiple sound sources, the controller establishes a correspondence between the multiple first positions and multiple first voiceprint information corresponding to the multiple sound sources, and the controller matches the multiple first positions and multiple first voiceprint information corresponding to the multiple sound sources with the pre-stored multiple second positions and multiple second voiceprint information with corresponding relationships, wherein the correspondence between the multiple second positions and the multiple second voiceprints is stored in a mapping relationship table, and the mapping relationship table is stored in the controller. It should be noted that although the mapping relationship table described above is pre-stored in the controller, this is not restrictive, and the controller can also be configured to match the corresponding mapping relationship table in a local database, a cloud database, or a network database according to the received pre-stored control instructions.

[0088] In S302, after the controller matches the multiple first positions and multiple first voiceprint information corresponding to the multiple sound sources with the pre-stored multiple second positions and multiple second voiceprint information with corresponding relationships, the controller regards the multiple sound sources corresponding to the multiple first positions and multiple first voiceprint information with corresponding relationships that match the multiple second positions and multiple second voiceprint information with corresponding relationships as multiple noise sources, and regards the multiple sounds emitted by the multiple noise sources as ambient noise. Specifically, when the present invention is implemented, when a user performs voice control on a smart home appliance in a noisy environment, for example, when a user performs voice control on an indoor air conditioner, if the indoor TV is playing a TV program, or the indoor speaker is playing music, then the air conditioner will receive the voice command issued by the user and the program sound emitted by the TV or the music played by the speaker, and the position of the indoor TV or speaker is usually fixed. Then, the second position information and second voiceprint information of the indoor home appliance that can make sound are correspondingly stored in the mapping relationship table. In this way, when the controller matches the multiple first positions and multiple first voiceprint information corresponding to the multiple sound sources with the pre-stored multiple second positions and multiple second voiceprint information with corresponding relationships, if the first position and the first voiceprint information with corresponding relationships and the second position and the second voiceprint information corresponding to the TV are successfully matched, it means that the sound source at the first position corresponding to the second position of the TV in the audio data is the TV, so that the sound source corresponding to the second position of the TV can be determined as the noise source, so that the smart home appliance can identify the noise source and voice command in the audio data.

[0089] It should be noted that, although the above description of multiple sound sources includes a TV and a speaker, this is not restrictive. In the specific implementation of the present invention, the multiple sound sources may also include a washing machine, a sweeping robot, a refrigerator or a child. It should be noted that the second position information corresponding to the second voiceprint information of the sweeping robot in the pre-stored mapping relationship table is the position that the sweeping robot can reach indoors. When the first voiceprint information corresponding to the second voiceprint information of the sweeping robot is identified among the multiple first voiceprint information, no matter where the first position corresponding to the sweeping robot is identified, the sound emitted by the sound source of the first voiceprint information corresponding to the sweeping robot is environmental noise. Similarly, the second position information corresponding to the second voiceprint information of the child in the pre-stored mapping relationship table is the position that the child can reach indoors. When the first voiceprint information corresponding to the second voiceprint information of the child is identified among the multiple first voiceprint information, no matter where the first position corresponding to the child is identified, the sound emitted by the sound source of the first voiceprint information corresponding to the child is environmental noise.

[0090] like Figure 5 As shown, in a possible implementation manner, the voice control method of the smart home appliance of the present invention includes the following steps:

[0091] S401: Determine multiple distances between multiple sound sources and the smart home appliance according to multiple first positions;

[0092] S402: Compare the multiple distances with a preset distance threshold, and take the sound source corresponding to the distance greater than the distance threshold as the noise source.

[0093] In S401, the controller determines multiple distances of multiple sound sources from the smart home appliances according to the multiple first positions. It should be noted that after the multi-microphone array obtains multiple first positions corresponding to the multiple sound sources, the controller establishes a corresponding relationship with the multiple first voiceprint information of the multiple sound sources corresponding to the multiple first positions. In this way, after the controller calculates the multiple distances of the multiple sound sources from the smart home appliances according to the multiple first position information, it can determine the multiple distances of the multiple sound sources from the smart home appliances when emitting sounds according to the multiple first voiceprints corresponding to the multiple first position information.

[0094] In S402, the controller compares multiple distances with a preset distance threshold, and uses the sound source corresponding to the distance greater than the distance threshold as a noise source. For example, the distance threshold may be a distance at which the smart home appliance can effectively receive voice commands. In this way, when the distance between the location where the sound source emits the sound and the smart home appliance is greater than the distance threshold, the sound source corresponding to the distance greater than the distance threshold is determined as the noise source, so that the smart home appliance can effectively filter out the sound source that emits ambient noise, thereby further improving the accuracy of the smart home appliance in recognizing voice commands.

[0095] like Figure 6 As shown, in a possible implementation manner, the voice control method of the smart home appliance of the present invention includes the following steps:

[0096] S501: after a plurality of first voiceprint information is matched with a plurality of second voiceprint information in a mapping relationship table, the plurality of first voiceprint information matched with the plurality of second voiceprint information is used as a plurality of voiceprints to be verified;

[0097] S502: Acquire multiple first positions corresponding to multiple voiceprints to be verified, and use the multiple first positions corresponding to the multiple voiceprints to be verified as multiple positions to be matched;

[0098] S503: Acquire a plurality of second positions corresponding to the plurality of positions to be matched according to the plurality of positions to be matched and the mapping relationship table;

[0099] S504: when the distance between the plurality of second positions and the plurality of to-be-matched positions corresponding to the plurality of second positions is less than or equal to a preset second distance threshold, the plurality of second positions in the mapping relationship table are not adjusted;

[0100] S505: When the distance between the plurality of second positions and the plurality of to-be-matched positions corresponding to the plurality of second positions is greater than a preset second distance threshold, taking the plurality of second positions among the plurality of second positions corresponding to the plurality of to-be-matched positions having a distance greater than the second distance threshold as the position information to be adjusted;

[0101] S506: Adjust the second position corresponding to the position information to be adjusted to the first position corresponding to the position to be matched corresponding to the position information to be adjusted.

[0102] In S501, during the specific implementation of the present invention, after the controller matches the multiple first voiceprint information with the multiple second voiceprint information in the mapping relationship table, the multiple first voiceprint information matched with the multiple second voiceprint information are used as voiceprints to be verified, so that the controller can further verify the multiple voiceprints to be verified.

[0103] In S502, the controller obtains multiple first positions corresponding to the multiple voiceprints to be verified, and uses the multiple first positions corresponding to the multiple voiceprints to be verified as multiple positions to be matched, so that the controller can verify the multiple positions to be matched corresponding to the multiple voiceprints to be verified.

[0104] In S503, the controller obtains multiple second positions corresponding to the multiple positions to be matched according to the multiple positions to be matched and the mapping relationship table. In the specific implementation of the present invention, the multiple positions to be matched include the first voiceprint information and the first position corresponding to the first voiceprint information, and the mapping relationship table stores the multiple second voiceprint information and the multiple second positions having the corresponding relationship. Then, after the multiple first voiceprint information of the multiple positions to be matched are matched with the multiple second voiceprint information in the mapping relationship table, the multiple first positions corresponding to the multiple positions to be matched and the mapping relationship table are obtained and the multiple second positions corresponding to the multiple second voiceprint information are matched with the multiple first voiceprint information.

[0105] In S504, when the distance between the multiple second positions and the multiple positions to be matched that have a corresponding relationship with the multiple second positions is less than or equal to a preset second distance threshold, the multiple second positions in the mapping relationship table are not adjusted, which means that the position corresponding to the sound source emitting the ambient noise in the room has not changed or the distance of the position adjustment is small.

[0106] In S505, when the distance between multiple second positions and multiple positions to be matched that have a corresponding relationship with the multiple second positions is greater than a preset second distance threshold, it means that the position of the household appliance that can make sound in the room has been adjusted. At this time, in order to accurately identify the position of the sound source that can make ambient noise in the room, it is necessary to update the information of the second position corresponding to the ambient noise that has been adjusted in the mapping relationship table. Therefore, when the distance between multiple second positions and multiple positions to be matched that have a corresponding relationship with the multiple second positions is greater than a preset second distance threshold, it is necessary to use multiple second positions in the multiple second positions corresponding to the distance between the multiple positions to be matched that is greater than the preset second distance as the position information to be adjusted.

[0107] In S506, the controller adjusts the second position corresponding to the position information to be adjusted to the first position corresponding to the position to be matched corresponding to the position information to be adjusted. Specifically, in the process of determining the position information to be adjusted of the present invention, since there is a corresponding relationship between the position information to be adjusted and the position to be matched, and the position to be matched contains information of the first position, the controller can also determine the first position corresponding to the position to be adjusted based on the position information to be adjusted.

[0108] like Figure 7 As shown, in a possible implementation manner, the voice control method of the smart home appliance of the present invention includes the following steps:

[0109] S601: Matching the voice keyword with a pre-stored control instruction containing a preset keyword;

[0110] S602: Acquire a pre-stored control instruction corresponding to the voice keyword, and use the pre-stored control instruction corresponding to the voice keyword as a target control instruction;

[0111] S603: Control the smart home appliance according to the target control instruction.

[0112] In S601, the controller matches the parsed voice keywords with pre-stored control instructions containing preset keywords, wherein the preset keywords are pre-stored in the controller, and specifically, the preset keywords include: cooling, heating, humidification, temperature reduction, humidity reduction, humidification, mute, 17 degrees, 18 degrees, 20 degrees, 23 degrees, 25 degrees, 30 degrees, etc. The pre-stored control instructions include: power on, power off, cooling, heating, cooling, dehumidification, humidification, etc. Based on this, after the controller parses the voice keywords contained in the user instructions, the controller matches the voice keywords with the preset keywords. After the voice keywords are successfully matched with the preset keywords, the voice keywords correspond to the pre-stored control instructions containing the preset keywords.

[0113] In S602, the controller obtains the pre-stored control instruction corresponding to the voice keyword, and uses the pre-stored control instruction corresponding to the voice keyword as the target control instruction, so that the controller can control the smart home appliance according to the determined target control instruction.

[0114] like Figure 8 As shown, in a possible implementation manner, the voice control method of the smart home appliance of the present invention includes the following steps:

[0115] S701: When the voice keyword corresponding to the target control instruction appears once, generate first prompt information;

[0116] S702: Control the smart home appliance to send a first prompt message;

[0117] S703: After the smart home appliance sends the first prompt information, if the smart home appliance receives a cancellation instruction for canceling the execution of the target control instruction within a preset first time threshold, the smart home appliance abandons the execution;

[0118] S704: If the smart home appliance receives a first confirmation instruction for confirming the execution of the target control instruction within the first time threshold, or the smart home appliance does not receive the first confirmation instruction for confirming the execution of the target control instruction within the first time threshold, the smart home appliance is controlled to execute the target control instruction.

[0119] In S701, when the present invention is implemented specifically, if the voice keyword corresponding to the target control instruction appears once in the audio data, a first prompt message corresponding to the target control instruction is generated, and the first prompt message is used to indicate the first execution content corresponding to the target control instruction. In this way, after the smart home appliance receives the audio data containing environmental noise and voice instructions and parses the content of the voice instructions, it can send a first prompt message to the user for confirmation, thereby further improving the accuracy of the smart home appliance in recognizing voice instructions and improving the user's satisfaction.

[0120] In S703, after the smart home appliance sends out the first prompt message, if the smart home appliance receives a cancellation command to cancel the execution of the target control command within the preset first time threshold, the controller abandons the execution of the target control command. Through the above-mentioned setting method, after the smart home appliance sends out the first prompt message corresponding to the target control command, if the user finds that the execution content of the target control command to be executed by the smart home appliance is inconsistent with the control content of the voice command issued by the user, a cancellation command to cancel the execution of the target control command can be sent to the smart home appliance to avoid the smart home appliance from executing voice commands that do not meet user needs, thereby making the control of the smart home appliance more intelligent and improving the user experience.

[0121] It should be noted that the first time threshold can be determined by the designer based on experience, experiments, calculations, etc. For example, the first time threshold can be set to 5 seconds. Obviously, the first time threshold can also be set to 3 seconds, 4 seconds or 6 seconds. This adjustment does not deviate from the principle of the present invention and therefore will fall within the scope of protection of the present invention.

[0122] like Fig. 9 As shown, in a possible implementation manner, the voice control method of the smart home appliance of the present invention includes the following steps:

[0123] S801: When a voice keyword corresponding to a target control instruction appears at least twice, obtaining the number of target control instructions corresponding to the voice keyword that appears at least twice;

[0124] S802: When the number of target control instructions corresponding to the voice keyword that appears at least twice is one, control the smart home appliance to execute the target control instruction corresponding to the voice keyword that appears at least twice;

[0125] S803: When the number of target control instructions corresponding to the voice keyword that appears at least twice is at least two, use multiple target control instructions corresponding to the voice keyword that appears at least twice as multiple candidate control instructions;

[0126] S804: Generate second prompt information, where the second prompt information is used to indicate a plurality of second execution contents corresponding to the plurality of candidate control instructions;

[0127] S805: Control the smart home appliance to send a second prompt message;

[0128] S806: After the smart home appliance sends the second prompt information, if the smart home appliance does not receive a second confirmation instruction corresponding to one of the multiple candidate control instructions within a preset second time threshold, the smart home appliance abandons execution;

[0129] S807: If the smart home appliance receives a second confirmation instruction corresponding to one of the multiple alternative control instructions within the second time threshold, the smart home appliance is controlled to execute the alternative control instruction corresponding to the second confirmation instruction.

[0130] During the specific implementation of the present invention, if a voice keyword corresponding to a target control instruction appears at least twice, the controller obtains the number of target instructions corresponding to the voice keyword that appears at least twice. When the number of target control instructions corresponding to the voice keyword that appears at least twice is one, the controller controls the smart home appliance to execute the target control instruction corresponding to the voice keyword that appears at least twice. In this way, there is no need for the user to manually input the first confirmation instruction to the smart home appliance, thereby further improving the intelligence of the smart home appliance.

[0131] In the specific implementation of the present invention, there may be a situation where at least two users issue voice commands at the same time, and the number of target control commands may be at least two. Then, if the number of target control commands corresponding to the voice keywords that appear at least twice is at least two, the multiple target control commands corresponding to the voice keywords that appear at least twice are used as multiple alternative control commands, so that the smart home appliance can select multiple alternative control commands from the multiple target control commands for the user to select. Then, when the number of alternative control commands is multiple, the controller generates a second prompt message, wherein the second prompt message is used to indicate multiple second execution contents corresponding to the multiple alternative control commands, and the controller controls the smart home appliance to issue the second prompt message. Specifically, the way in which the smart home appliance issues the second prompt message can be a voice broadcast or a way of sending it to the user's mobile terminal. After the smart home appliance issues the second prompt message, if the smart home appliance does not receive a second confirmation command corresponding to one of the multiple alternative control commands within a preset second time threshold, the voice control program executed on the smart home appliance is abandoned. If the smart home appliance receives a second confirmation instruction corresponding to one of the multiple alternative control instructions within a second time threshold, the controller controls the smart home appliance to execute the alternative control instruction corresponding to the second confirmation instruction. In this way, when multiple users send voice commands to the smart home appliance, the smart home appliance can also recognize it and send a prompt message to the user for the user to choose to confirm, thereby reducing the risk of errors in the smart home appliance's recognition of voice commands, thereby further improving the accuracy of the smart home appliance's recognition of voice commands, and thereby improving user satisfaction.

[0132] like Fig.10 As shown, in a possible implementation manner, the voice control method of the smart home appliance of the present invention includes the following steps:

[0133] S901: When the ambient noise is less than a preset noise threshold, analyzing all third execution contents contained in the voice instruction;

[0134] S902: Control the smart home appliances based on all the third execution contents.

[0135] In the specific implementation of the present invention, when the controller recognizes that the ambient noise is less than the preset noise threshold, it means that the ambient noise has little interference with the voice command. At this time, the controller parses all the third execution contents contained in the voice command, and then controls the smart home appliances based on all the third execution contents.

[0136] Preferably, the present invention further provides a smart home appliance, the smart home appliance includes a controller, the controller of the smart home appliance includes a memory and a voice control program stored in the memory and executable on a processor, and the voice control program implements the voice control method of the aromatherapy module when executed by the processor. The smart home appliance can be an air conditioner, a washing machine, a smart TV, a smart fan, and other home appliances with voice control functions.

[0137] Those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present application and form different embodiments. For example, in the claims of the present application, any one of the claimed embodiments may be used in any combination.

[0138] It should be noted that although the detailed steps of the method of the present application are described in detail above, without departing from the basic principles of the present application, technical personnel in this field can combine, split and change the order of the above steps. The modified technical solution does not change the basic concept of the present application and therefore falls within the scope of protection of the present application.

[0139] So far, the technical solutions of the present invention have 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 invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A voice control method for smart home appliances, characterized in that: The smart home appliance has a voice control function. After the voice control function is activated, the smart home appliance supports real-time voice control. The voice control method includes: After the voice control function is activated, collecting audio data within a preset time period; identifying ambient noise of the surrounding environment and voice commands in the audio data; When the environmental noise is greater than or equal to a preset noise threshold, parsing the voice command to obtain voice keywords in the voice command; The smart home appliance is controlled according to the voice keyword.

2. The voice control method according to claim 1, characterized in that: The number of sound sources is at least two, and the step of "identifying ambient noise and voice instructions in the surrounding environment in the audio data" includes: Acquire a plurality of first positions and a plurality of first voiceprint information corresponding to a plurality of sound sources emitting sounds in the audio data; The environmental noise and the voice command in the audio data are identified according to the plurality of the first positions and the plurality of the first voiceprint information.

3. The voice control method according to claim 2, characterized in that: The step of “identifying the environmental noise in the audio data according to the plurality of the first positions and the plurality of the voiceprint information” comprises: Matching the plurality of first positions and the plurality of first voiceprint information having corresponding relationships with a pre-stored mapping relationship table storing corresponding relationships between a plurality of second positions and a plurality of second voiceprint information; The multiple sound sources corresponding to the multiple first positions and the multiple first voiceprint information that have a corresponding relationship and match the multiple second positions and the multiple second voiceprint information that have a corresponding relationship are taken as multiple noise sources, and the multiple sounds emitted by the multiple noise sources are taken as the environmental noise.

4. The voice control method according to claim 3, characterized in that: The step of "identifying ambient noise of the surrounding environment in the audio data" also includes: Determining a plurality of distances between a plurality of the sound sources and the smart home appliance according to the plurality of the first positions; The multiple distances are compared with a preset distance threshold, and the sound source corresponding to the distance greater than the distance threshold is taken as the noise sound source.

5. The voice control method according to claim 3, characterized in that: Before the step of "taking the plurality of sound sources corresponding to the plurality of first positions and the plurality of first voiceprint information that have a corresponding relationship and match the plurality of second positions and the plurality of second voiceprint information that have a corresponding relationship as the plurality of noise sound sources, and taking the plurality of sounds emitted by the plurality of noise sound sources as the environmental noise", the method further includes: After the plurality of first voiceprint information are matched with the plurality of second voiceprint information in the mapping relationship table, the plurality of first voiceprint information matched with the plurality of second voiceprint information are used as the plurality of voiceprints to be verified; Acquire a plurality of first positions corresponding to the plurality of voiceprints to be verified, and use the plurality of first positions corresponding to the plurality of voiceprints to be verified as a plurality of positions to be matched; Acquire a plurality of second positions corresponding to the plurality of positions to be matched according to the plurality of positions to be matched and the mapping relationship table; When the distance between the plurality of second positions and the plurality of to-be-matched positions corresponding to the plurality of second positions is less than or equal to a preset second distance threshold, the plurality of second positions in the mapping relationship table are not adjusted; When the distance between the plurality of second positions and the plurality of positions to be matched that have a corresponding relationship with the plurality of second positions is greater than a preset second distance threshold, taking the plurality of second positions among the plurality of second positions corresponding to the plurality of positions to be matched whose distance between the plurality of second positions is greater than the second distance threshold as the position information to be adjusted; The second position corresponding to the position information to be adjusted is adjusted to the first position corresponding to the position to be matched corresponding to the position information to be adjusted.

6. The voice control method according to claim 1, characterized in that: The step of "controlling the smart home appliance according to the voice keyword" includes: Matching the voice keyword with a pre-stored control instruction containing a preset keyword; Acquire a pre-stored control instruction corresponding to the voice keyword, and use the pre-stored control instruction corresponding to the voice keyword as a target control instruction; The smart home appliance is controlled according to the target control instruction.

7. The voice control method according to claim 6, characterized in that: The step of "controlling the smart home appliance according to the target control instruction" includes: When the number of times the voice keyword corresponding to the target control instruction appears once, generating first prompt information, wherein the first prompt information is used to indicate a first execution content corresponding to the target control instruction; Controlling the smart home appliance to send the first prompt information; After the smart home appliance sends the first prompt information, if the smart home appliance receives a cancellation instruction to cancel the execution of the target control instruction within a preset first time threshold, the smart home appliance abandons the execution; If the smart home appliance receives a first confirmation instruction confirming the execution of the target control instruction within the first time threshold, or the smart home appliance does not receive a first confirmation instruction confirming the execution of the target control instruction within the first time threshold, the smart home appliance is controlled to execute the target control instruction.

8. The voice control method according to claim 6, characterized in that: The number of the target control instructions is at least one, and the step of "controlling the smart home appliance according to the target control instruction" further includes: When the voice keyword corresponding to the target control instruction appears at least twice, obtaining the number of the target control instructions corresponding to the voice keyword that appears at least twice; When the number of the target control instructions corresponding to the voice keyword that appears at least twice is one, controlling the smart home appliance to execute the target control instruction corresponding to the voice keyword that appears at least twice; When the number of the target control instructions corresponding to the voice keyword that appears at least twice is at least two, using the multiple target control instructions corresponding to the voice keyword that appears at least twice as multiple candidate control instructions; generating second prompt information, wherein the second prompt information is used to indicate a plurality of second execution contents corresponding to the plurality of candidate control instructions; Controlling the smart home appliance to send the second prompt information; After the smart home appliance sends the second prompt information, if the smart home appliance does not receive a second confirmation instruction corresponding to one of the multiple candidate control instructions within a preset second time threshold, the smart home appliance abandons execution; If the smart home appliance receives a second confirmation instruction corresponding to one of the multiple alternative control instructions within the second time threshold, the smart home appliance is controlled to execute the alternative control instruction corresponding to the second confirmation instruction.

9. The voice control method according to claim 1, characterized in that: The voice control method further includes: When the environmental noise is less than a preset noise threshold, parsing all third execution contents contained in the voice instruction; The smart home appliance is controlled based on all the third execution contents.

10. A smart home appliance, characterized in that: The smart home appliance includes a controller configured to execute the voice control method according to any one of claims 1 to 9.

Images