Household appliances, cloud servers, and voice interaction methods, devices, and systems

Abstract

The present invention discloses a household appliance, a cloud server and a voice interaction method, device and system. The voice interaction method of the household appliance includes the following steps: obtaining the regional information of the household appliance; controlling the household appliance to inquire whether the current user is a user of a preset area based on the regional information; if the current user is a user of the preset area, controlling the household appliance to obtain a dialect learning list corresponding to the preset area, and controlling the household appliance to play the content of the dialect learning list; based on the content of the dialect learning list played by the household appliance, collecting the voice information of the current user through the household appliance, and sending the voice information of the current user to the cloud server, so that the cloud server optimizes the voice recognition model based on the voice information of the current user and the content of the dialect learning list to improve the user experience.

Description

Technical Field

[0001] The present invention relates to the technical field of household appliances, and in particular to a household appliance, a cloud server, and a voice interaction method, device, and system. Background Art

[0002] In related technologies, the voice recognition and voice control functions of home appliances can effectively improve the convenience of users' lives. In order to improve the convenience of using home appliances, how to improve the dialect recognition rate of home appliances so that home appliances can recognize multiple pronunciations expressing the same usage needs in different regions has become one of the development directions of home appliances. Summary of the Invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, one object of the present invention is to provide a voice interaction method for home appliances. The voice interaction method can control the home appliance to match and learn the dialect based on the user's region, thereby enabling the home appliance to accurately recognize the local dialect and improving the convenience of use of the home appliance.

[0004] The present invention further provides a computer-readable storage medium.

[0005] The present invention also provides a voice control system for household appliances.

[0006] According to the first aspect of the present invention, the voice interaction method for household appliances includes the following steps: obtaining geographical information of the household appliance; controlling the household appliance to inquire whether the current user is a user of a preset area based on the geographical information; if the current user is a user of the preset area, controlling the household appliance to obtain a dialect learning list corresponding to the preset area, and controlling the household appliance to play the content of the dialect learning list; based on the content of the dialect learning list played by the household appliance, collecting the voice information of the current user through the household appliance, and sending the voice information of the current user to a cloud server, so that the cloud server optimizes the voice recognition model based on the voice information of the current user and the content of the dialect learning list.

[0007] According to the voice interaction method of a home appliance device in an embodiment of the present invention, regional information is first obtained, so that when the user is a local, the home appliance device is controlled to learn the dialect to optimize the voice recognition model of the home appliance device, so that the home appliance device can accurately recognize the dialect of the area where the home appliance device is used, thereby improving the dialect recognition rate of the home appliance device and improving the user experience.

[0008] According to some embodiments of the present invention, the contents of the dialect learning lists corresponding to different regions are different.

[0009] Furthermore, the content of the dialect learning list includes instruction words whose regional pronunciation is significantly different from the standard dialect.

[0010] According to the computer-readable storage medium of the second embodiment of the present invention, a voice control program for a home appliance is stored thereon, and when the voice control program is executed by a processor, a voice interaction method for the home appliance is implemented.

[0011] According to the third aspect of the present invention, the voice interaction device of the household appliance includes: an acquisition module for acquiring the geographical information of the household appliance; a voice interaction control module for controlling the household appliance to inquire whether the current user is a user of a preset area according to the geographical information, and controlling the household appliance to obtain the dialect learning list corresponding to the preset area when the current user is a user of the preset area, and controlling the household appliance to play the content of the dialect learning list, and collecting the voice information of the current user through the household appliance according to the content of the dialect learning list played by the household appliance; a first sending module for sending the voice information of the current user to a cloud server, so that the cloud server optimizes the voice recognition model according to the voice information of the current user and the content of the dialect learning list.

[0012] The household appliance according to an embodiment of the present invention includes the voice interaction device described in the above embodiment.

[0013] According to an embodiment of the present invention, a household appliance includes a memory, a processor, and a voice interaction program for the household appliance stored in the memory and runnable on the processor. When the processor executes the voice interaction program, a voice interaction method for the household appliance is implemented.

[0014] According to an embodiment of the present invention, the cloud server includes: a second sending module, which is used to send a dialect learning list corresponding to a preset area to the home appliance according to a request instruction of the home appliance, wherein the home appliance sends the request instruction to the cloud server when inquiring whether the current user is a user of the preset area based on the geographical information; a model optimization module, which is used to optimize the speech recognition model according to the voice information of the current user and the content of the dialect learning list, wherein the home appliance plays the content of the dialect learning list, collects the voice information of the current user according to the content of the played dialect learning list, and sends the voice information of the current user to the cloud server.

[0015] Furthermore, the contents of the dialect learning lists corresponding to different regions are different.

[0016] Furthermore, the content of the dialect learning list includes instruction words whose regional pronunciation is significantly different from the standard dialect.

[0017] The voice interaction system for a home appliance according to an embodiment of the present invention includes a home appliance and a cloud server, wherein:

[0018] The home appliance obtains regional information, and inquires whether the current user is a user of a preset area based on the regional information, and if the current user is a user of the preset area, obtains a dialect learning list corresponding to the preset area, and plays the content of the dialect learning list;

[0019] The home appliance is further configured to collect voice information of the current user according to the content of the played dialect learning list, and send the voice information of the current user to a cloud server;

[0020] The cloud server optimizes the speech recognition model according to the voice information of the current user and the content of the dialect learning list.

[0021] According to some embodiments of the present invention, voice control of the home appliance device is performed based on the optimized voice recognition model, including: receiving the voice control instructions of the current user through the home appliance device, and sending the voice control instructions of the current user to the cloud server; the cloud server recognizes the voice control instructions of the current user based on the optimized voice recognition model, and feeds back the recognition results to the home appliance device to perform voice control on the home appliance device.

[0022] In some embodiments, when the current user is a non-local, the home appliance is directly controlled to enter a voice recognition control mode so that the cloud server can recognize the voice control instructions of the current user.

[0023] Furthermore, when the home appliance enters the dialect learning wizard mode, the home appliance is controlled to send a dialect learning instruction to the cloud server, so that the cloud server feeds back the dialect learning list to the home appliance according to the dialect learning instruction.

[0024] Optionally, the content of the dialect learning list varies according to dialect and region, and includes instruction words whose local pronunciation is significantly different from the standard dialect.

[0025] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned by practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments with reference to the accompanying drawings, in which:

[0027] Figure 1 is a flowchart of a speech recognition model generation process according to a speech interaction method for a home appliance device according to an embodiment of the present invention;

[0028] Figure 2 is a flow chart of a voice recognition control process of a voice interaction method for a home appliance according to an embodiment of the present invention;

[0029] Figure 3 is a block diagram of a voice control system for a home appliance according to an embodiment of the present invention;

[0030] Figure 4 is a block diagram of a household appliance according to an embodiment of the present invention;

[0031] Figure 5 is a block diagram of a cloud server according to an embodiment of the present invention.

[0032] Reference numerals:

[0033] Voice control system 1000,

[0034] Home appliance 100, cloud server 200,

[0035] Voice interaction control module 110, first sending module 120,

[0036] The second sending module 210 and the model optimization module 220 . DETAILED DESCRIPTION

[0037] The following describes embodiments of the present invention in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended only to explain the present invention and are not to be construed as limiting the present invention.

[0038] Reference below Figure 1-Figure 3 The home appliance 100, the cloud server 200, and the voice interaction method, device, and system according to the embodiments of the present invention are described.

[0039] First of all, it should be pointed out that the language used by a region or an ethnic group is called a dialect (that is, the language of a certain region). However, the dialects of a certain region, based on the geographical span and soil and water conditions, lead to pronunciation differences in some words in dialects of different regions within the same dialect region. For example, there are great differences in pronunciation between different cities in the dialect region where Minnan dialect and Cantonese are located.

[0040] Based on this, the present application proposes a voice interaction method for a home appliance 100 , so as to establish a corresponding voice recognition model on a cloud server 200 through the learning function of the home appliance 100 , thereby improving the voice recognition rate of the home appliance 100 .

[0041] According to the voice interaction method of the home appliance 100 of the first embodiment of the present invention, Figure 1 As shown, the voice interaction method includes the following steps: obtaining the regional information of the home appliance 100.

[0042] Specifically, the home appliance 100 includes but is not limited to common household electronic devices such as air conditioners and televisions. With the realization of the smart home concept and the introduction of the Internet of Things, the home appliance 100 can be connected to the Internet through voice, remote control, etc., and then when the home appliance 100 is initially configured for the network or under user operation, the home appliance 100 can obtain its own regional information and determine the type of dialect in the region (for example, Cantonese, Hokkien, Northeastern dialect, etc.) through the regional information.

[0043] Of course, the home appliance 100 can also obtain regional information through GPS, etc., and is not limited to obtaining regional information after the above-mentioned network configuration.

[0044] The home appliance 100 is controlled according to the regional information to inquire whether the current user is a user in a preset area.

[0045] After the home appliance 100 obtains the regional information, it inquires whether the user who is using the home appliance 100 is a user of a preset area, so as to determine whether the home appliance 100 needs to learn the dialect.

[0046] It can be understood that the preset area is an area corresponding to a certain type of dialect.

[0047] If the current user is a user of a preset area, the home appliance 100 is controlled to obtain a dialect learning list corresponding to the preset area, and the home appliance 100 is controlled to play the content of the dialect learning list.

[0048] That is to say, under the premise that the current user is a user in the preset area, the home appliance device 100 can obtain the corresponding dialect learning list. The dialect learning list obtained on the cloud server 200 contains a series of dialect voices related to the operating instructions of the home appliance device 100, and then controls the home appliance device 100 to voice play the content of the dialect learning list to interact with the current user by voice, and in the process of voice interaction with the current user, collects the current user's voice information through the home appliance device 100.

[0049] Thus, according to the content of the dialect learning list played by the home appliance 100, the voice information of the current user is collected through the home appliance 100, and the voice information of the current user is sent to the cloud server 200 through the home appliance 100, so that the cloud server 200 can optimize the voice recognition model according to the voice information of the current user and the dialect learning list, so as to perform voice control on the home appliance 100 according to the optimized voice recognition model.

[0050] In summary, the home appliance device 100 of the present application can obtain regional information when it is first configured for the network or when the user needs it. When the current user is a user in a preset area (that is, the area where the home appliance is used), the home appliance device 100 obtains the dialect learning list through the cloud server 200, plays the dialect voice in the dialect learning list, interacts with the current user, collects the current user's voice information, and then optimizes the current user's voice information based on the current user's voice information and the voice in the dialect learning list, thereby generating an optimized voice recognition model.

[0051] According to the voice interaction method of the home appliance 100 in an embodiment of the present invention, the regional information is first obtained, so that when the user is a user in a preset area, the home appliance 100 is controlled to perform dialect learning to optimize the voice recognition model of the home appliance 100, so that the home appliance 100 can accurately recognize the dialect of the area where the home appliance 100 is used, thereby improving the dialect recognition rate of the home appliance 100 and improving the user experience.

[0052] It is understandable that the contents of the dialect learning lists corresponding to different regions are different, and the contents of the dialect learning lists include instruction words whose regional pronunciations are significantly different from the standard dialect.

[0053] Specifically, the content of the dialect learning lists varies according to dialect and region, and includes instruction words whose local pronunciation differs significantly from the standard dialect.

[0054] It can be understood that the standard dialect refers to the pronunciation of a certain dialect officially recorded, such as Cantonese and Hokkien. For example, locals in a Cantonese-speaking area may all speak Cantonese, but the Cantonese pronunciation of individual words or some words in the area where the current user is located (the scope is smaller than the area) is different from the officially recorded Cantonese pronunciation. Therefore, in the dialect learning list, the command words with obvious differences (i.e., individual words and some words) are recorded, and during the learning process, the above-mentioned command words are played through the home appliance 100 to obtain the command word voice (i.e., voice information) issued by the current user, thereby realizing the optimization of the speech recognition model.

[0055] Among them, the optimization of the speech recognition model of the present application is not limited to obtaining the voice of the current user corresponding to the home appliance device 100. Based on the same dialect and the same region, comprehensive calculations can be performed based on the big data in the cloud server 200 to make the recognition accuracy of the speech recognition model of the home appliance device 100 higher.

[0056] In some embodiments, as Figure 2 As shown, when the current user is not a user in the preset area, the home appliance 100 is directly controlled to enter the voice recognition control mode so that the cloud server 200 can recognize the voice control instructions of the current user.

[0057] In this way, the cloud server 200 stores dialect data packets of multiple regions and Mandarin (official standard language) data packets, and all of them correspond to a speech recognition model. Then, when the current user is not a user in the preset area, and when the voice emitted by the current user corresponds to Mandarin, the cloud server 200 can directly recognize the voice emitted by the current user according to the Mandarin speech recognition model, so that the scope of application of the home appliance device 100 is larger, and it can at least be controlled by local dialect and Mandarin voice, making the voice control of the home appliance device 100 simpler and more convenient.

[0058] Here, it should be pointed out that when the current user is a dialect user, and the dialect used by the current user is different from the current user's dialect, the dialect learning list of the current user's own dialect can be selected on the home appliance 100 and the above-mentioned speech recognition model optimization operation can be performed so that the home appliance 100 can be controlled by the current user's dialect, further improving the user experience.

[0059] According to the computer-readable storage medium of the second embodiment of the present invention, a voice control program of the home appliance 100 is stored thereon, and when the voice control program is executed by the processor, a voice interaction method of the home appliance 100 is implemented.

[0060] According to the computer-readable storage medium of an embodiment of the present invention, by executing the voice control program stored thereon corresponding to the voice interaction method of the above-mentioned home appliance 100, the voice recognition success rate of the home appliance 100 can be improved, so that the home appliance 100 can recognize dialects, thereby improving the user experience of the home appliance 100.

[0061] The voice interaction device according to the third embodiment of the present invention includes: an acquisition module, a voice interaction control module 110 and a first sending module 120.

[0062] The acquisition module is used to acquire the regional information of the home appliance 100 .

[0063] The voice interaction control module 110 is used to control the home appliance 100 to inquire whether the current user is a user of the preset area based on the geographical information, and when the current user is a user of the preset area, control the home appliance 100 to obtain the dialect learning list corresponding to the preset area, and control the home appliance 100 to play the content of the dialect learning list, and collect the current user's voice information through the home appliance 100 based on the content of the dialect learning list played by the home appliance 100.

[0064] The first sending module 120 is used to send the voice information of the current user to the cloud server 200, so that the cloud server 200 can optimize the voice recognition model according to the voice information of the current user and the content of the dialect learning list.

[0065] Therefore, the voice interaction device according to the embodiment of the present invention can be set in any home appliance 100 to realize dialect learning of the home appliance 100 through the interaction between the voice interaction device and the cloud server, which can improve the intelligence level of the home appliance 100 and improve the success rate of dialect recognition.

[0066] This application further proposes a home appliance 100 having the above-mentioned voice interaction device. The technical effects of the home appliance 100 are consistent with those of the above-mentioned voice interaction device, and will not be described in detail here.

[0067] The present application also proposes a household appliance, comprising a memory, a processor, and a voice interaction program of the household appliance 100 stored in the memory and runnable on the processor. When the processor executes the voice interaction program, the voice interaction method of the household appliance 100 in the above embodiment is implemented.

[0068] The present invention also proposes a cloud server 200 that can interact with the home appliance 100 for data.

[0069] The cloud server 200 includes: a second sending module 210, which is used to send a dialect learning list corresponding to a preset area to the home appliance 100 according to a request instruction of the home appliance 100.

[0070] Among them, when the home appliance device 100 inquires based on the regional information whether the current user is a user in the preset area, it sends a request instruction to the cloud server 200, that is, the first sending module 120 sends the request instruction to the cloud server 200, and then the cloud server 200 retrieves the dialect learning list and sends the dialect learning list to the home appliance device 100 through the second sending module 210.

[0071] The model optimization module 220 is used to optimize the speech recognition model based on the current user's voice information and the content of the dialect learning list, wherein the home appliance device 100 plays the content of the dialect learning list, collects the current user's voice information based on the content of the played dialect learning list, and sends the current user's voice information to the cloud server 200.

[0072] In other words, the first sending module 120 sends the current user's voice information to the cloud server 200, and the cloud server 200 generates an optimized speech recognition model based on the big data algorithm and the content of the dialect learning list and the user's voice information.

[0073] In summary, the optimized speech recognition model has a higher matching degree with the current user's voice, which can effectively improve the speech recognition rate of the home appliance 100.

[0074] According to some embodiments of the present invention, Figure 2 As shown, voice control of the home appliance 100 is performed according to the optimized voice recognition model, including:

[0075] The home appliance 100 receives the current user's voice control instructions and sends the current user's voice control instructions to the cloud server 200; the cloud server 200 recognizes the current user's voice control instructions based on the optimized voice recognition model, and feeds back the recognition results to the home appliance 100 to perform voice control on the home appliance 100.

[0076] For example, the home appliance 100 is an air conditioner. When the air conditioner is turned on, the current user issues a corresponding voice control command (for example, cooling, temperature 22°C). After receiving the voice control command, the home appliance 100 sends the voice control command to the cloud server 200. The cloud server 200 recognizes the voice in the voice control command and feeds back the recognition result (i.e., the air conditioner switches to cooling mode, and the cooling temperature is 22°C) to the home appliance 100, thereby realizing control of the home appliance 100 (i.e., voice control of the home appliance 100).

[0077] In this way, when the current user uses the dialect for voice control, after the current user's voice control instructions are uploaded to the cloud server 200, the cloud service area performs voice recognition based on the optimized voice recognition model to accurately identify the current user's usage needs (control intentions), thereby achieving precise voice control of the home appliance 100 and improving the user's usage experience.

[0078] The dialect learning list includes: at least some operating instructions corresponding to the home appliance 100 (for example: power on, power off, temperature adjustment range, mode switching, etc.).

[0079] The voice control system 1000 of the home appliance 100 according to the embodiment of the present invention is as follows: Figure 3 As shown, the voice control system 1000 includes a home appliance 100 and a cloud server 200 .

[0080] Among them, the home appliance 100 obtains regional information, and inquires whether the current user is a user of the preset area based on the regional information, and when the current user is a user of the preset area, obtains the dialect learning list corresponding to the preset area and plays the content of the dialect learning list.

[0081] The home appliance 100 is also used to collect the voice information of the current user based on the content of the played dialect learning list, and send the voice information of the current user to the cloud server 200.

[0082] Specifically, the home appliance 100 obtains the dialect learning list through the cloud server 200; the home appliance 100 plays the content of the dialect learning list through voice to interact with the current user, and in the process of voice interaction with the current user, collects the current user's voice information, and sends the current user's voice information to the cloud server 200; the cloud server 200 optimizes the voice recognition model according to the current user's voice information and the dialect learning list, and performs voice control on the home appliance 100 according to the optimized voice recognition model.

[0083] According to the voice control system 1000 of the embodiment of the present invention, regional information is obtained, a dialect learning list is played, user voice is collected, and user voice is uploaded through the home appliance 100; the voice recognition model is optimized and the user voice is recognized through the cloud server 200, and the home appliance 100 is controlled to perform operations corresponding to the recognized user voice, so that the voice control system 1000 can accurately control the home appliance 100 to perform the operations expected by the current user, thereby improving the user experience.

[0084] See below. Figure 1 and Figure 2 , taking the home appliance 100 as a specific embodiment of an air conditioner, the voice interaction method of the home appliance 100 of the present application is specifically described.

[0085] like Figure 1 As shown, after the air conditioner is turned on, it automatically performs network configuration, and after the network configuration is completed, it obtains its own regional information.

[0086] The air conditioner sends a query based on the regional information to determine whether the current user is a local of the region represented by the regional information.

[0087] If the current user is a local (i.e., a user of the preset area), the air conditioner enters the direction learning wizard mode and sends a dialect learning instruction to the cloud server 200. The cloud server 200 obtains the corresponding dialect learning list based on the regional information and the dialect learning instruction, and sends the corresponding dialect learning list to the air conditioner. The air conditioner plays the voice content in the dialect learning list and interacts with the current user by voice. During the interaction, the voice of the current user is collected and the collected voice information is uploaded to the cloud server 200. The cloud server 200 optimizes the voice recognition model based on the voice information and the dialect learning list.

[0088] Then, after the current user speaks in dialect, the air conditioner uploads the current user's voice control command to the cloud server 200. The cloud server 200 recognizes the voice control command, generates a corresponding recognition result, and performs voice control on the home appliance 100 through the recognition result.

[0089] like Figure 2 As shown, if the current user is not a local, the air conditioner directly enters the voice recognition control mode, and the cloud server 200 performs voice recognition based on the dialect list and Mandarin voice recognition model stored in the cloud server 200, and controls the air conditioner according to the recognition results.

[0090] In summary, the air conditioner's voice recognition rate is higher, and the recognition accuracy and precision are higher, thereby improving the user experience.

[0091] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like to indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0092] In the description of the present invention, "first feature" or "second feature" may include one or more of the features.

[0093] In the description of the present invention, "plurality" means two or more.

[0094] In the description of the present invention, a first feature being “on” or “under” a second feature may include the first and second features being in direct contact with each other, or the first and second features not being in direct contact with each other but being in contact with each other via another feature therebetween.

[0095] In the description of the present invention, “on”, “above” and “above” a first feature of a second feature include the first feature being directly above and obliquely above the second feature, or simply means that the first feature is horizontally higher than the second feature.

[0096] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, illustrative uses of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0097] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

Claims

1. A voice interaction method for a household appliance (100), characterized in that: The following steps are involved: Acquiring regional information of the household appliance (100); Controlling the home appliance (100) to inquire whether the current user is a user in a preset area according to the regional information; If the current user is a user of a preset area, the home appliance (100) enters a dialect learning wizard mode, controls the home appliance (100) to obtain a dialect learning list corresponding to the preset area, and controls the home appliance (100) to play the content of the dialect learning list, wherein the content of the dialect learning list includes instruction words whose regional pronunciation is significantly different from the standard dialect; According to the content of the dialect learning list played by the home appliance (100), voice information of the current user is collected through the home appliance (100), and the voice information of the current user is sent to a cloud server (200), so that the cloud server (200) optimizes a speech recognition model according to the voice information of the current user and the content of the dialect learning list; If the current user is a user in a non-preset area, the home appliance (100) directly enters a voice recognition control mode, the cloud server (200) performs voice recognition based on a dialect list and a Mandarin voice recognition model stored in the cloud server (200), and controls the home appliance (100) based on the recognition result.

2. The voice interaction method of the household appliance (100) according to claim 1, characterized in that: The contents of the dialect learning lists corresponding to different regions are different.

3. A computer-readable storage medium, characterized in that A voice interaction program of a household appliance (100) is stored thereon, and when the voice interaction program is executed by a processor, a voice interaction method of a household appliance (100) as described in any one of claims 1 to 2 is implemented.

4. A voice interaction device for household appliances, characterized in that: include: An acquisition module, used for acquiring regional information of the household appliance (100); A voice interaction control module (110) is configured to control the home appliance (100) to inquire whether the current user is a user of a preset area based on the regional information, and when the current user is a user of the preset area, control the home appliance (100) to enter a dialect learning wizard mode, and control the home appliance (100) to obtain a dialect learning list corresponding to the preset area, and control the home appliance (100) to play the content of the dialect learning list, wherein the content of the dialect learning list includes instruction words whose regional pronunciation is significantly different from the standard dialect, and collect the voice information of the current user through the home appliance (100) based on the content of the dialect learning list played by the home appliance (100); A first sending module (120) is used to send the voice information of the current user to a cloud server (200), so that the cloud server (200) optimizes the voice recognition model according to the voice information of the current user and the content of the dialect learning list; If the current user is a user in a non-preset area, the home appliance (100) directly enters a voice recognition control mode, the cloud server (200) performs voice recognition based on a dialect list and a Mandarin voice recognition model stored in the cloud server (200), and controls the home appliance (100) based on the recognition result.

5. A household appliance (100), characterized in that: A voice interaction device comprising the household appliance (100) as claimed in claim 4.

6. A household appliance (100), characterized in that: The invention relates to a household appliance (100) comprising a memory, a processor, and a voice interaction program stored in the memory and operable on the processor. When the processor executes the voice interaction program, the voice interaction method of the household appliance (100) as described in any one of claims 1 to 2 is implemented.

7. A cloud server (200), characterized in that: include: The second sending module (210) is configured to send a dialect learning list corresponding to a preset area to the home appliance (100) according to a request instruction of the home appliance (100), wherein the home appliance (100) sends the request instruction to the cloud server (200) when the current user is a user in the preset area according to the regional information, and the home appliance (100) enters a dialect learning wizard mode, controls the home appliance (100) to obtain the dialect learning list corresponding to the preset area, and controls the home appliance (100) to play the content of the dialect learning list, wherein the content of the dialect learning list includes instruction words whose regional pronunciation is significantly different from the standard dialect; a model optimization module (220) for optimizing a speech recognition model based on the speech information of the current user and the contents of the dialect learning list, wherein the home appliance (100) plays the contents of the dialect learning list, collects the speech information of the current user based on the played contents of the dialect learning list, and sends the speech information of the current user to a cloud server (200); If the current user is a user in a non-preset area, the home appliance (100) directly enters a voice recognition control mode, the cloud server (200) performs voice recognition based on a dialect list and a Mandarin voice recognition model stored in the cloud server (200), and controls the home appliance (100) based on the recognition result.

8. The cloud server (200) according to claim 7, characterized in that: The contents of the dialect learning lists corresponding to different regions are different.

9. A voice interaction system for a household appliance (100), characterized in that: It includes a home appliance (100) and a cloud server (200), wherein: The home appliance (100) acquires regional information and inquires whether a current user is a user of a preset region based on the regional information; and when the current user is a user of the preset region, controls the home appliance (100) to enter a dialect learning wizard mode to acquire a dialect learning list corresponding to the preset region and plays the contents of the dialect learning list, wherein the contents of the dialect learning list include instruction words whose regional pronunciation is significantly different from the standard dialect; The home appliance (100) is further configured to collect voice information of the current user based on the content of the played dialect learning list, and send the voice information of the current user to a cloud server (200); The cloud server (200) optimizes the speech recognition model according to the speech information of the current user and the content of the dialect learning list; If the current user is a user in a non-preset area, the home appliance (100) directly enters a voice recognition control mode, the cloud server (200) performs voice recognition based on a dialect list and a Mandarin voice recognition model stored in the cloud server (200), and controls the home appliance (100) based on the recognition result.

Images