Air conditioner control method, apparatus, air conditioner and computer-readable storage medium

Abstract

This application provides an air conditioner control method, apparatus, air conditioner, and computer-readable storage medium. The method includes: acquiring a first voice control command; extracting features from the first voice control command to determine a first volume feature, a first tone feature, a first timbre feature, and a first speech rate feature; determining the target language type corresponding to the first voice control command based on the first volume feature, first tone feature, first timbre feature, and first speech rate feature; and broadcasting the target interactive voice according to the language corresponding to the target language type. The method provided by this application can determine different types of features based on the user's voice control command, and then identify the language type used by the user based on multiple types of features, thus improving the accuracy of language type recognition. Furthermore, when interacting with the user via voice, the corresponding language of the same type as the user's language can be used for interaction, improving the language interaction capability of the air conditioner.

Description

Technical Field

[0001] This application relates to the field of electrical appliances, specifically to an air conditioner control method, device, air conditioner, and computer-readable storage medium. Background Technology

[0002] With the rapid development of air conditioning, it has become increasingly common in people's homes. Given the many dialects within Chinese, and the existence of various dialect recognition technologies, different recognition engines are used for different dialects. Current methods involve using the air conditioner's voice receiver module to acquire the user's voice, achieving simple dialect recognition or mixed recognition. However, this method is inefficient and carries a significant risk of errors. Summary of the Invention

[0003] This application provides an air conditioner control method that can effectively identify different dialects.

[0004] In a first aspect, this application provides an air conditioner control method, the method comprising:

[0005] Obtain the first voice control command;

[0006] Feature extraction is performed on the first voice control command to determine the first volume feature, the first tone feature, the first timbre feature, and the first speech rate feature;

[0007] Based on the first volume feature, the first tone feature, the first timbre feature, and the first speech rate feature, the target language type corresponding to the first voice control command is determined.

[0008] The target interactive voice is broadcast according to the language corresponding to the target language type.

[0009] In some embodiments of this application, determining the target language type corresponding to the first voice control command based on the first volume feature, the first pitch feature, the first timbre feature, and the first speech rate feature includes:

[0010] The weight information corresponding to the first volume feature, the first pitch feature, the first timbre feature, and the first speech rate feature is determined respectively to obtain the first weighted volume feature, the first weighted pitch feature, the first weighted timbre feature, and the first weighted speech rate feature.

[0011] Based on the first weighted volume feature, the first weighted pitch feature, the first weighted timbre feature, and the first weighted speech rate feature, first similarity information with various language types is determined.

[0012] Based on the first similarity information, the target language type is determined.

[0013] In some embodiments of this application, determining the target language type based on each of the first similarity information includes:

[0014] If none of the first similarity information satisfies the first target similarity threshold, a prompt voice is played to prompt the user to issue a second voice control command.

[0015] If the second voice control command is obtained, feature extraction is performed on the second voice control command to determine the second volume feature, the second tone feature, the second timbre feature, and the second speech rate feature;

[0016] Determine the average volume feature information of the first volume feature and the second volume feature, the average pitch feature information of the first tone feature and the second tone feature, the average timbre feature information of the first timbre feature and the second timbre feature, and the average speech rate feature information of the first speech rate feature and the second speech rate feature.

[0017] Based on the average pitch feature information, the average volume feature information, the average timbre feature information, and the average speech rate feature information, a second similarity information with various language types is determined;

[0018] The target language type is determined based on the second similarity information.

[0019] In some embodiments of this application, determining the target language type based on each of the second similarity information includes:

[0020] If none of the second similarity information meets the second target similarity threshold, a prompt voice will be played to prompt the user to issue a third voice control command.

[0021] The third voice control command is sent to the target server so that the target server can determine the target language type based on the third voice control command.

[0022] In some embodiments of this application, the target server determines the target language type based on the third voice control command, including:

[0023] The target server determines the geographical location information for sending the third voice control command;

[0024] The target server extracts features from the third voice control command to determine the third volume feature, the third tone feature, the third timbre feature, and the third speech rate feature.

[0025] The target language type is determined based on the third volume feature, the third tone feature, the third timbre feature, the third speech rate feature, and the geographical location information.

[0026] In some embodiments of this application, the method further includes:

[0027] If the target language type cannot be identified, the target speech will be used to broadcast the message, prompting the user to enter the adjustment mode and prompting the user to input training speech data and corresponding label data.

[0028] Based on the training speech data and the label data, the language recognition model for determining the target language type is adjusted.

[0029] In some embodiments of this application, the method further includes:

[0030] If the target language type is correctly identified, record the current correct identification result;

[0031] Based on the current correct recognition result, adjust the weight information of the language recognition model.

[0032] Secondly, this application also provides an air conditioner control device, the device comprising:

[0033] The acquisition module is used to acquire the first voice control command;

[0034] The determination module is used to extract features from the first voice control command and determine the first volume feature, the first tone feature, the first timbre feature, and the first speech rate feature;

[0035] The determining module is further configured to determine the target language type corresponding to the first voice control command based on the first volume feature, the first tone feature, the first timbre feature, and the first speech rate feature.

[0036] The processing module is used to broadcast the target interactive voice according to the language corresponding to the target language type.

[0037] Thirdly, this application also provides an air conditioner, the air conditioner including a processor, a memory, and a computer program stored in the memory and executable on the processor, the processor executing the computer program to implement the steps in any of the air conditioner control methods described above.

[0038] Fourthly, this application also provides a computer-readable storage medium storing a computer program that is executed by a processor to implement the steps in any of the air conditioner control methods described above.

[0039] The air conditioner control method provided in this application can extract different types of features from the first voice control command after it is acquired, obtaining volume features, pitch features, timbre features, and speech rate features. This allows the air conditioner to better identify the language type used by the user based on these features. Therefore, this application can improve the accuracy of language type recognition. Furthermore, when interacting with the user via voice, the air conditioner can use a corresponding language of the same type as the user's language, improving its language interaction capabilities. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a schematic diagram of a scenario for the air conditioner control system provided in the embodiments of this application;

[0042] Figure 2 This is a schematic flowchart of one embodiment of the air conditioner control method in this application.

[0043] Figure 3 This is a schematic diagram of one embodiment of the air conditioner control device in this application.

[0044] Figure 4 This is a schematic diagram of the structure of an embodiment of the air conditioner in this application. Detailed Implementation

[0045] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0046] In the description of this application, it should be understood that the terms "a" and "an" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "a" or "an" may explicitly or implicitly include one or more features. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0047] In this application, the term "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0048] This application provides an air conditioner control method, apparatus, air conditioner, and storage medium, which are described below.

[0049] The following section first introduces some basic concepts involved in the embodiments of this application:

[0050] An air conditioner generally consists of several main parts, including a cold / heat source unit, a cold / heat medium distribution system, terminal units, and other auxiliary equipment. The main components include the refrigeration unit, water pump, fan, and piping system. The terminal units are responsible for utilizing the distributed cold or heat to specifically process the air, ensuring that the air parameters of the target environment meet certain requirements.

[0051] Please see Figure 1 , Figure 1 This is a schematic diagram illustrating a scenario of the air conditioner control method provided in this application. The air conditioner control system may include an air conditioner 100 and a main control device 200. The air conditioner 100 and the main control device 200 can communicate with each other in any way, including but not limited to signal communication via electronic circuits or wireless signals. The wireless signals can be computer network communication using the TCP / IP protocol suite (TCP / IP) or User Datagram Protocol (UDP). The air conditioner 100 can receive control signals from a remote control or control panel to perform a series of air conditioner functions such as cooling, heating, dehumidification, and dust removal. The air conditioner 100 can also receive instruction information sent by the main control device 200. The air conditioner 100 can perform a series of operations such as cooling, heating, dehumidification, and dust removal according to the corresponding instruction information, such as the air conditioner control method in this application.

[0052] In this embodiment of the application, the air conditioner 100 includes, but is not limited to, wall-mounted air conditioners, floor-standing air conditioners, window air conditioners, ceiling-mounted air conditioners, and recessed air conditioners.

[0053] Those skilled in the art will understand that Figure 1 The application environment shown is merely one application scenario of the solution in this application and does not constitute a limitation on the application scenario of the solution in this application. Other application environments may include those that are more specific to this application. Figure 1 The number of more or fewer air conditioners and air conditioners shown, for example Figure 1 Only one air conditioner or air conditioner is shown in the figure. The air conditioner control system of this application may also include one or more air conditioners and air conditioners for performing the air conditioner control method of this application. The specific details are not limited here.

[0054] In addition, such as Figure 1 As shown, the main control device 200 may include any hardware device capable of data processing and instruction sending, such as a CPU or microcontroller embedded inside the air conditioner; no specific limitation is made here.

[0055] It should be noted that, Figure 1 The schematic diagram of the air conditioner control system shown is merely an example. The air conditioner control system and scenario described in this application embodiment are for the purpose of more clearly illustrating the technical solutions of this application embodiment and do not constitute a limitation on the technical solutions provided in this application embodiment. As those skilled in the art will know, with the evolution of air conditioner control systems and the emergence of new business scenarios, the technical solutions provided in this application embodiment are also applicable to similar technical problems.

[0056] like Figure 2 As shown, Figure 2 This is a schematic flowchart of one embodiment of the air conditioner control method in this application. The air conditioner control method may include the following steps 201 to 204:

[0057] 201. Obtain the first voice control command.

[0058] In this embodiment, the air conditioner can be equipped with any type of voice receiving device, such as a microphone. When the air conditioner is turned on, the microphone is activated to collect voice commands. If the user emits any voice information, the air conditioner can analyze it; if it is a command, it is identified as the first voice control command.

[0059] For example, when a microphone device receives a user's voice information, it can perform vector conversion on the user's voice information and compare the converted vector with the stored instruction vector to determine whether the current user's voice information is an instruction.

[0060] 202. Extract features from the first voice control command to determine the first volume feature, the first tone feature, the first timbre feature, and the first speech rate feature.

[0061] When the user's voice information is determined to be a command, i.e., a first voice control command is obtained, feature extraction needs to be performed on the first voice control command. In this embodiment, feature extraction can be performed from four aspects: volume features, pitch features, timbre features, and speech rate features. When extracting these four features from the first voice control command, different neural network layers can be used for feature extraction. For example, the first convolutional layer extracts volume features, the second convolutional layer extracts pitch features, the third convolutional layer extracts timbre features, and the fourth convolutional layer extracts speech rate features, etc. Specific embodiments of this application are not limited to these.

[0062] 203. Determine the target language type corresponding to the first voice control command based on the first volume feature, the first tone feature, the first timbre feature, and the first speech rate feature.

[0063] After obtaining the four types of features, their corresponding language labels can be predicted for each. For example, if the four labels predicted from the four features are all the same, then the speech type corresponding to the four identical labels can be determined as the target language type.

[0064] It should be noted that the language type mentioned in this application may refer to dialect type or language type, and the specific embodiments of this application are not limited.

[0065] 204. Broadcast the target interactive voice according to the language corresponding to the target language type.

[0066] Once the target language of the user's voice is determined, the air conditioner can respond to the user in that language. For example, if the user issues a control command in Cantonese, the air conditioner can also respond in Cantonese with "Instruction received." Similarly, if the user issues a control command in English, the air conditioner can also respond in English with "Instruction received."

[0067] The air conditioner control method provided in this application can extract different types of features from the first voice control command after it is acquired, obtaining volume features, pitch features, timbre features, and speech rate features. This allows the air conditioner to better identify the language type used by the user based on these features. Therefore, this application can improve the accuracy of language type recognition. Furthermore, when interacting with the user via voice, the air conditioner can use a corresponding language of the same type as the user's language, improving its language interaction capabilities.

[0068] To better implement the method of this application, in some embodiments of this application, the target language type corresponding to the first voice control command is determined based on a first volume feature, a first pitch feature, a first timbre feature, and a first speech rate feature, including:

[0069] The weight information corresponding to the first volume feature, first pitch feature, first timbre feature, and first speech rate feature is determined respectively to obtain the first weighted volume feature, first weighted pitch feature, first weighted timbre feature, and first weighted speech rate feature; based on the first weighted volume feature, first weighted pitch feature, first weighted timbre feature, and first weighted speech rate feature, the first similarity information with various language types is determined; based on each first similarity information, the target language type is determined.

[0070] In this embodiment, when determining the weighted features corresponding to volume, pitch, timbre, and speech rate, an attention mechanism can be used to determine their respective weights. For example, cross-attention or self-attention mechanisms are not limited in this embodiment. For instance, the weight of volume in determining language type can be reduced by lowering the weight corresponding to the volume feature. Therefore, in this embodiment, assuming the predicted label corresponding to the first weighted volume feature is A, the predicted label corresponding to the first weighted pitch feature is B, the predicted label corresponding to the first weighted timbre feature is B, and the predicted label corresponding to the first weighted speech rate feature is A, there are two labels A and two labels B. Normally, the model cannot determine the corresponding language type, but because the weight of the volume feature is reduced, the target language type can be determined based on label B.

[0071] It should be noted that, in this embodiment, the label corresponding to the predicted feature can be predicted using a similarity method. For example, the timbre, volume, pitch, and speech rate features of different language types can be stored. Then, after obtaining different types of features, they are compared with the corresponding stored features to calculate the similarity. The label corresponding to the feature with the highest similarity is then taken as the predicted label. In this embodiment, the similarity can be calculated using methods such as cosine similarity or Euclidean distance; this embodiment does not limit the specific methods used.

[0072] To better implement the method of this application, in some embodiments of this application, the target language type is determined based on each first similarity information, including:

[0073] If none of the first similarity information meets the first target similarity threshold, a prompt voice is played to prompt the user to issue a second voice control command. If the second voice control command is obtained, features are extracted from the second voice control command to determine the second volume feature, the second pitch feature, the second timbre feature, and the second speech rate feature. The average volume feature information of the first volume feature and the second volume feature, the average pitch feature information of the first pitch feature and the second pitch feature, the average timbre feature information of the first timbre feature and the second timbre feature, and the average speech rate feature information of the first speech rate feature and the second speech rate feature are determined. Based on the average pitch feature information, the average volume feature information, the average timbre feature information, and the average speech rate feature information, the second similarity information with various language types is determined. Based on each of the second similarity information, the target language type is determined.

[0074] In practice, users may be too far from the air conditioner, resulting in unclear voice control commands received by the air conditioner. In this case, although the air conditioner can calculate the similarity of various features based on the user's first voice control command, the similarity value is low, for example, below 50%. If the corresponding label is still determined based on the similarity information, it will obviously lead to a failure in language recognition. Therefore, in this situation, the air conditioner can prompt the user to issue the voice control command again. The reissued voice control command is the second voice control command in this embodiment of the application.

[0075] After obtaining the second voice control command, it can be processed in the same way to obtain four feature vectors corresponding to the second voice control command. It should be noted that in this embodiment, after obtaining the four feature vectors corresponding to the second voice control command, the four vectors corresponding to the first voice control command can be averaged. Specifically, since feature vectors also include specific numerical values, in this embodiment, the first volume feature and the second volume feature can be added together and averaged, the first timbre feature and the second timbre feature can be added together and averaged, and the first speech rate feature and the second speech rate feature can be added together and averaged. The similarity is then calculated based on the four average vectors. This reduces errors and improves the accuracy of speech recognition. The method for determining the corresponding target language type based on the second similarity information is the same as in the above embodiment and will not be repeated here.

[0076] To better implement the method of this application, in some embodiments of this application, the target language type is determined based on each second similarity information, including:

[0077] If none of the second similarity information meets the second target similarity threshold, a prompt voice is played to prompt the user to issue a third voice control command; the third voice control command is sent to the target server so that the target server can determine the target language type based on the third voice control command.

[0078] Of course, in practice, there may be instances where the user's language cannot be recognized. If the air conditioner itself cannot recognize the user's voice commands based on the voice vector, it can upload the user's voice commands to the air conditioner manufacturer's server via Wi-Fi, where a more powerful voice recognition model is deployed for recognition.

[0079] In this embodiment, the number of network layers in the speech recognition model deployed on the server can be more than the number of network layers in the model deployed locally on the air conditioner, and more calculation parameters are involved. The specific embodiment of this application does not limit its model structure.

[0080] To better implement the method of this application, in some embodiments of this application, the target server determines the target language type based on a third voice control command, including:

[0081] The target server determines the geographical location information of the third voice control command; the target server extracts features from the third voice control command to determine the third volume feature, third tone feature, third timbre feature, and third speech rate feature; based on the third volume feature, third tone feature, third timbre feature, third speech rate feature, and geographical location information, the target language type is determined.

[0082] The above embodiments provide a scheme for determining a user's corresponding language type using a model within a server. Because the model involved in the server has more powerful computational capabilities and can handle more computational parameters, the server can also obtain the user's geographical location information for more comprehensive language type identification.

[0083] Specifically, since the user's voice commands are uploaded to the server via the air conditioner, the server can determine the geographical location of the air conditioner from which the voice commands were uploaded based on the uploaded IP address. This allows the server to obtain the geographical location information corresponding to the third voice control command. Because dialects are highly regional, geographical location information can be given significant weight. Therefore, based on the four main characteristics and combined with geographical location information, predictions can be made to identify the user's dialect.

[0084] When the server identifies the user's target language type, it can transmit that target language type information to the corresponding air conditioner via the network, enabling the air conditioner to interact with the user based on the target language type.

[0085] To better implement the method of this application, in some embodiments of this application, the method further includes:

[0086] If the target language type cannot be identified, the target speech will be used to prompt the user to enter the adjustment mode, which will then prompt the user to input training speech data and corresponding label data. Based on the training speech data and label data, the language recognition model that determines the target language type will be adjusted.

[0087] However, in extreme cases, there might be situations where correct recognition is impossible. In such cases, the air conditioner can interact with the user using a target voice prompt. The target voice prompt can be a fixed voice type, such as Mandarin. The user can then be prompted to enter adjustment mode. If the user enters adjustment mode, they can first input their dialect type via the air conditioner's control device, such as a remote or control panel, as label data. After the user inputs their dialect type, they are prompted to speak freely to collect speech information in that dialect type for use as training speech data. After obtaining the label data and training speech data, the air conditioner can train a model based on the labels and training samples, thus adjusting the model and achieving retraining.

[0088] The retraining method for the model can be any method, and this application embodiment does not limit it. For example: after collecting the user's speech, unqualified data such as unclear speech can be removed. The voice module performs preprocessing such as noise reduction and normalization on the Nth sound signal. The Nth acoustic signal features are extracted, and the Nth sound signal is combined with the currently used speech recognition model to fine-tune the recognition model. Finally, the wake word is customized, and the dialect parameters are matched according to the highest matching value. The corresponding dialect response is given according to the recognized dialect type, and the machine is controlled to enter the self-learning mode. In the self-learning mode, the user's dialect is learned through a deep learning model.

[0089] To better implement the method of this application, in some embodiments of this application, the method further includes:

[0090] If the target language type is correctly identified, record the current correct identification result; adjust the weight information of the language recognition model based on the current correct identification result.

[0091] The above embodiments provide a scheme for model retraining when recognition fails. This application also provides a scheme for consolidating the model's recognition efficiency after successful recognition.

[0092] Specifically, after a correct identification, the result can be recorded and its weight increased to facilitate a quick response when performing the same identification in the future. The reason for this is that air conditioners are rarely resold. Therefore, users' language habits usually do not change, and reinforcing the weight of correct identification will not cause a decrease in the accuracy of subsequent identifications.

[0093] Based on this, it can be deduced that air conditioning systems can continuously collect user interaction data, especially language samples that were initially not correctly identified but were successfully processed through a self-correction mechanism, gradually optimizing the performance of these language models. Through machine learning algorithms, model parameters are continuously adjusted so that the model can better adapt to users' actual dialect usage habits.

[0094] To better implement the air conditioner control method in the embodiments of this application, an air conditioner control device is also provided in the embodiments of this application, such as... Figure 3 As shown, the device 300 includes:

[0095] Acquisition module 301 is used to acquire the first voice control command;

[0096] The determination module 302 is used to extract features from the first voice control command and determine the first volume feature, the first tone feature, the first timbre feature, and the first speech rate feature;

[0097] The determining module 302 is also used to determine the target language type corresponding to the first voice control command based on the first volume feature, the first tone feature, the first timbre feature and the first speech rate feature;

[0098] The processing module 303 is used to broadcast the target interactive voice according to the language corresponding to the target language type.

[0099] The air conditioner control device provided in this application, after the acquisition module 301 acquires the first voice control command, can perform different types of feature extraction on the first voice control command through the determination module 302 to obtain volume features, pitch features, timbre features, and speech rate features. This allows the air conditioner's processing module 303 to better identify the language type used by the user based on these features. Therefore, this application can improve the accuracy of language type recognition. Furthermore, when interacting with the user via voice, the device can use a corresponding language of the same type as the user's language, improving the air conditioner's language interaction capabilities.

[0100] In some embodiments of this application, the determining module 302 is specifically used for:

[0101] The weight information corresponding to the first volume feature, the first pitch feature, the first timbre feature, and the first speech rate feature is determined respectively to obtain the first weighted volume feature, the first weighted pitch feature, the first weighted timbre feature, and the first weighted speech rate feature;

[0102] Based on the first weighted volume feature, the first weighted pitch feature, the first weighted timbre feature, and the first weighted speech rate feature, the first similarity information with various language types is determined.

[0103] The target language type is determined based on the first similarity information.

[0104] In some embodiments of this application, the determining module 302 is further configured to:

[0105] If none of the first similarity information meets the first target similarity threshold, a prompt voice will be played to prompt the user to issue a second voice control command.

[0106] If a second voice control command is obtained, feature extraction is performed on the second voice control command to determine the second volume feature, the second tone feature, the second timbre feature, and the second speech rate feature.

[0107] Determine the average volume feature information of the first volume feature and the second volume feature, the average pitch feature information of the first pitch feature and the second pitch feature, the average timbre feature information of the first timbre feature and the second timbre feature, and the average speech rate feature information of the first speech rate feature and the second speech rate feature;

[0108] Based on the average pitch feature information, average volume feature information, average timbre feature information, and average speech rate feature information, the second similarity information with various language types is determined;

[0109] The target language type is determined based on the second similarity information.

[0110] In some embodiments of this application, the determining module 302 is further configured to:

[0111] If none of the second similarity information meets the second target similarity threshold, a prompt voice will be played to prompt the user to issue a third voice control command.

[0112] The third voice control command is sent to the target server so that the target server can determine the target language type based on the third voice control command.

[0113] In some embodiments of this application, the determining module 302 is further configured to:

[0114] The target server determines the geographical location information for sending the third voice control command;

[0115] The target server extracts features from the third voice control command to determine the third volume feature, third tone feature, third timbre feature, and third speech rate feature;

[0116] The target language type is determined based on the third volume feature, third tone feature, third timbre feature, third speech rate feature, and geographical location information.

[0117] In some embodiments of this application, the determining module 302 is further configured to:

[0118] If the target language type cannot be identified, the target speech will be used to broadcast the message, prompting the user to enter the adjustment mode and prompting the user to input training speech data and corresponding label data.

[0119] Based on the training speech data and label data, the language recognition model for determining the target language type is adjusted.

[0120] In some embodiments of this application, the determining module 302 is further configured to:

[0121] If the target language type is correctly identified, record the current correct identification result;

[0122] Adjust the weight information of the language recognition model based on the current correct recognition results.

[0123] This application also provides an air conditioner that integrates any of the air conditioner control methods provided in this application, such as... Figure 4 As shown, it illustrates a structural schematic diagram of the air conditioner involved in the embodiments of this application, specifically:

[0124] The air conditioner may include components such as a processor 401 with one or more processing cores, a storage device 402 with one or more computer-readable storage media, a power supply 403, and an input unit 404. Those skilled in the art will understand that... Figure 4 The air conditioner structure shown does not constitute a limitation on the air conditioner and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0125] in:

[0126] The processor 401 is the control center of the air conditioner. It connects to various parts of the air conditioner via various interfaces and lines. By running or executing software programs and / or modules stored in the storage device 402, and by calling data stored in the storage device 402, it performs various functions and processes data, thereby providing overall monitoring of the air conditioner. Optionally, the processor 401 may include one or more processing cores. The processor 401 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. Preferably, the processor 401 may integrate an application processor and a modem processor. The application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 401.

[0127] Storage device 402 can be used to store software programs and modules. Processor 401 executes various functional applications and data processing by running the software programs and modules stored in storage device 402. Storage device 402 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created based on the use of the air conditioner, etc. In addition, storage device 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, storage device 402 may also include a memory controller to provide processor 401 with access to storage device 402.

[0128] The air conditioner also includes a power supply 403 that supplies power to the various components. Preferably, the power supply 403 can be logically connected to the processor 401 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 403 may also include one or more DC or AC power supplies, a recharging system, a power fault detection circuit, a power converter or inverter, a power status indicator, or any other components.

[0129] The air conditioner may also include an input unit 404, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0130] Although not shown, the air conditioner may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 401 in the air conditioner loads the executable files corresponding to the processes of one or more application programs into the storage device 402 according to the following instructions, and the processor 401 runs the application programs stored in the storage device 402 to realize various functions, such as:

[0131] Obtain the first voice control command;

[0132] Feature extraction is performed on the first voice control command to determine the first volume feature, the first tone feature, the first timbre feature, and the first speech rate feature;

[0133] Based on the first volume feature, the first tone feature, the first timbre feature, and the first speech rate feature, determine the target language type corresponding to the first voice control command;

[0134] Play the target interactive voice according to the language corresponding to the target language type.

[0135] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0136] Therefore, embodiments of this application provide a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk, etc. A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in any of the air conditioner control methods provided in embodiments of this application. For example, the computer program loaded by the processor can execute the following steps:

[0137] Obtain the first voice control command;

[0138] Feature extraction is performed on the first voice control command to determine the first volume feature, the first tone feature, the first timbre feature, and the first speech rate feature;

[0139] Based on the first volume feature, the first tone feature, the first timbre feature, and the first speech rate feature, determine the target language type corresponding to the first voice control command;

[0140] Play the target interactive voice according to the language corresponding to the target language type.

[0141] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the detailed descriptions of other embodiments above, which will not be repeated here.

[0142] In practice, each of the above units or structures can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units or structures, please refer to the previous method embodiments, which will not be repeated here.

[0143] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0144] The above provides a detailed description of an air conditioner control method and apparatus provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. An air conditioner control method, characterized in that, The method includes: Obtain the first voice control command; Feature extraction is performed on the first voice control command to determine the first volume feature, the first tone feature, the first timbre feature, and the first speech rate feature; Based on the first volume feature, the first tone feature, the first timbre feature, and the first speech rate feature, the target language type corresponding to the first voice control command is determined. The step of determining the target language type corresponding to the first voice control command based on the first volume feature, the first pitch feature, the first timbre feature, and the first speech rate feature includes: The weight information corresponding to the first volume feature, the first pitch feature, the first timbre feature, and the first speech rate feature is determined respectively to obtain the first weighted volume feature, the first weighted pitch feature, the first weighted timbre feature, and the first weighted speech rate feature. Based on the first weighted volume feature, the first weighted pitch feature, the first weighted timbre feature, and the first weighted speech rate feature, first similarity information with various language types is determined. Based on the first similarity information, the target language type is determined; The target interactive voice is broadcast according to the language corresponding to the target language type.

2. The air conditioner control method according to claim 1, characterized in that, The step of determining the target language type based on each of the first similarity information includes: If none of the first similarity information satisfies the first target similarity threshold, a prompt voice is played to prompt the user to issue a second voice control command. If the second voice control command is obtained, feature extraction is performed on the second voice control command to determine the second volume feature, the second tone feature, the second timbre feature, and the second speech rate feature; Determine the average volume feature information of the first volume feature and the second volume feature, the average pitch feature information of the first tone feature and the second tone feature, the average timbre feature information of the first timbre feature and the second timbre feature, and the average speech rate feature information of the first speech rate feature and the second speech rate feature. Based on the average pitch feature information, the average volume feature information, the average timbre feature information, and the average speech rate feature information, a second similarity information with various language types is determined; The target language type is determined based on the second similarity information.

3. The air conditioner control method according to claim 2, characterized in that, The step of determining the target language type based on each of the second similarity information includes: If none of the second similarity information meets the second target similarity threshold, a prompt voice will be played to prompt the user to issue a third voice control command. The third voice control command is sent to the target server so that the target server can determine the target language type based on the third voice control command.

4. The air conditioner control method according to claim 3, characterized in that, The target server determines the target language type based on the third voice control command, including: The target server determines the geographical location information for sending the third voice control command; The target server extracts features from the third voice control command to determine the third volume feature, the third tone feature, the third timbre feature, and the third speech rate feature. The target language type is determined based on the third volume feature, the third tone feature, the third timbre feature, the third speech rate feature, and the geographical location information.

5. The air conditioner control method according to any one of claims 1 to 4, characterized in that, The method further includes: If the target language type cannot be identified, the target speech will be used to broadcast the message, prompting the user to enter the adjustment mode and prompting the user to input training speech data and corresponding label data. Based on the training speech data and the label data, the language recognition model for determining the target language type is adjusted.

6. The air conditioner control method according to any one of claims 1 to 4, characterized in that, The method further includes: If the target language type is correctly identified, record the current correct identification result; Based on the current correct recognition result, adjust the weight information of the language recognition model.

7. An air conditioner control device, characterized in that, The device includes: The acquisition module is used to acquire the first voice control command; The determination module is used to extract features from the first voice control command and determine the first volume feature, the first tone feature, the first timbre feature, and the first speech rate feature; The determining module is further configured to determine the target language type corresponding to the first voice control command based on the first volume feature, the first tone feature, the first timbre feature, and the first speech rate feature. The step of determining the target language type corresponding to the first voice control command based on the first volume feature, the first pitch feature, the first timbre feature, and the first speech rate feature includes: The weight information corresponding to the first volume feature, the first pitch feature, the first timbre feature, and the first speech rate feature is determined respectively to obtain the first weighted volume feature, the first weighted pitch feature, the first weighted timbre feature, and the first weighted speech rate feature. Based on the first weighted volume feature, the first weighted pitch feature, the first weighted timbre feature, and the first weighted speech rate feature, first similarity information with various language types is determined. Based on the first similarity information, the target language type is determined; The processing module is used to broadcast the target interactive voice according to the language corresponding to the target language type.

8. An air conditioner, characterized in that, The air conditioner includes a processor, a memory, and a computer program stored in the memory and executable on the processor, the processor executing the computer program to implement the steps of the air conditioner control method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is executed by a processor to implement the steps of the air conditioner control method according to any one of claims 1 to 6.

Images