Air conditioner control method and device, air conditioner and computer readable storage medium

Abstract

The invention provides an air conditioner control method and device, an air conditioner and a computer readable storage medium. The method comprises the steps that a first voice control instruction is obtained; performing feature extraction on the first voice control instruction to determine a first volume feature, a first tone feature, a first timbre feature and a first speech speed feature; determining a target language type corresponding to the first voice control instruction according to the first volume feature, the first tone feature, the first timbre feature and the first speed feature; and broadcasting the target interaction voice according to a language corresponding to the target language type. According to the method provided by the invention, different types of features can be determined according to the voice control instruction of the user, and then the language type used by the user can be recognized according to the multiple types of features, so that the recognition accuracy of the language type can be improved. In addition, when the air conditioner carries out voice interaction with the user, the corresponding language the same as the user language type can be used for interaction, and the language interaction capacity of the air conditioner is improved.

Description

Technical Field

[0001] The present application relates to the field of electrical appliances, and in particular to an air conditioner control method, device, air conditioner and computer-readable storage medium. Background Art

[0002] With the rapid development of air conditioners, air conditioners are becoming more and more common in people's homes. In this case, since there are many types of dialects involved in Chinese, there are currently many dialect recognition technologies, and different dialect recognition uses different recognition engines. The current practice is to obtain the user's voice through the voice receiving module of the air conditioner to achieve simple dialect recognition or mixed recognition. This dialect recognition efficiency is low and there is a high possibility of recognition errors. Summary of the invention

[0003] The present application provides an air conditioner control method, which can effectively recognize different dialects.

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

[0005] Obtaining a first voice control instruction;

[0006] Extracting features of the first voice control instruction to determine a first volume feature, a first pitch feature, a first timbre feature, and a first speech speed feature;

[0007] determining a target language type corresponding to the first voice control instruction according to the first volume feature, the first pitch feature, the first timbre feature, and the first speech rate feature;

[0008] According to the language corresponding to the target language type, the target interactive voice is broadcasted.

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

[0010] Determine weight information corresponding to the first volume feature, the first tone feature, the first timbre feature, and the first speech rate feature, respectively, to obtain a first weighted volume feature, a first weighted tone feature, a first weighted timbre feature, and a first weighted speech rate feature;

[0011] determining first similarity information with various language types according to the first weighted volume feature, the first weighted pitch feature, the first weighted timbre feature, and the first weighted speech speed feature;

[0012] The target language type is determined according to each of the first similarity information.

[0013] In some implementations of the present application, determining the target language type according to each of the first similarity information includes:

[0014] If each of the first similarity information does not meet the first target similarity threshold, broadcasting a prompt voice to prompt the user to issue a second voice control instruction;

[0015] If the second voice control instruction is obtained, feature extraction is performed on the second voice control instruction to determine a second volume feature, a second pitch feature, a second timbre feature, and a second speech speed feature;

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

[0017] Determining second similarity information with various language types according to the average tone feature information, the average volume feature information, the average timbre feature information, and the average speech speed feature information;

[0018] The target language type is determined according to each of the second similarity information.

[0019] In some implementations of the present application, determining the target language type according to each of the second similarity information includes:

[0020] If each of the second similarity information does not meet the second target similarity threshold, broadcasting a prompt voice to prompt the user to issue a third voice control instruction;

[0021] The third voice control instruction is sent to a target server, so that the target server determines a target language type according to the third voice control instruction.

[0022] In some implementations of the present application, the target server determines the target language type according to the third voice control instruction, including:

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

[0024] The target server extracts features from the third voice control instruction to determine a third volume feature, a third pitch feature, a third timbre feature, and a third speech speed feature;

[0025] The target language type is determined according to the third volume feature, the third tone feature, the third timbre feature, the third speech speed feature, and the geographical location information.

[0026] In some embodiments of the present application, the method further comprises:

[0027] If the target language type cannot be identified, the target broadcast voice is used to broadcast, prompting the user to enter the adjustment mode, so as to prompt the user to input the training voice data and the corresponding label data;

[0028] A language recognition model for determining the target language type is adjusted according to the training speech data and the label data.

[0029] In some embodiments of the present application, the method further comprises:

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

[0031] According to the current correct recognition result, the weight information of the language recognition model is adjusted.

[0032] In a second aspect, the present application further provides an air conditioner control device, the device comprising:

[0033] An acquisition module, used to acquire a first voice control instruction;

[0034] A determination module, configured to extract features from the first voice control instruction to determine a first volume feature, a first pitch feature, a first timbre feature, and a first speech speed feature;

[0035] The determination module is further used to determine the target language type corresponding to the first voice control instruction according to the first volume feature, the first tone feature, the first timbre feature and the first speech speed feature;

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

[0037] In a third aspect, the present application also provides an air conditioner, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps in any one of the air conditioner control methods.

[0038] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and the computer program is executed by a processor to implement the steps in any one of the air conditioner control methods.

[0039] The air conditioner control method provided by the present application can extract different types of features from the first voice control instruction after obtaining the first voice control instruction, and obtain volume features, pitch features, timbre features, and speech speed features, so that the air conditioner itself can better identify the language type used by the user based on these features. Therefore, the present application can improve the recognition accuracy of the language type. In addition, when interacting with the user by voice, the corresponding language of the same language type as the user can be used for interaction, thereby improving the language interaction capability of the air conditioner. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the 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 work.

[0041] Figure 1 is a schematic diagram of a scene of an air conditioner control system provided in an embodiment of the present application;

[0042] Figure 2 is a flow chart of an embodiment of the air conditioner control method in the embodiment of the present application;

[0043] Figure 3 is a schematic structural diagram of an embodiment of an air conditioner control device in an embodiment of the present application;

[0044] Figure 4 It is a schematic structural diagram of an embodiment of an air conditioner in the embodiment of the present application. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work 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 understood as indicating or implying relative importance or implicitly indicating 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, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0047] In this application, the word "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described in this application as "exemplary" is not necessarily to be construed as being preferred or advantageous over other embodiments. The following description is given to enable any technician in the field to implement and use the present application. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present application can be implemented without using these specific details. In other instances, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present application with unnecessary details. Therefore, the present application is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0048] The present application provides an air conditioner control method, device, air conditioner and storage medium, which are described below respectively.

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

[0050] Air Conditioner: Generally includes cold source / heat source equipment, cold and hot medium distribution system, terminal device and other auxiliary equipment. Mainly includes refrigeration host, water pump, fan and pipeline system. The terminal device is responsible for using the cold and hot water distributed to specifically process the air state so that the air parameters of the target environment meet certain requirements.

[0051] See also Figure 1 , Figure 1 The scene diagram of the air conditioner control method provided in the embodiment of the present application is as follows. 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 may be connected to each other in any manner, including but not limited to signal communication through electronic circuits, communication through wireless signals, and the wireless signals may be computer network communications of the TCP / IP protocol suite (TCP / IP Protocol Suite, TCP / IP) and the User Datagram Protocol (User Datagram Protocol, UDP). The air conditioner 100 may receive control signals from a remote controller or a control panel to perform a series of air conditioner functions such as cooling, heating, dehumidification, and dust removal. The air conditioner 100 may also receive command information sent by the main control device 200. The air conditioner 100 may perform a series of operations such as cooling, heating, dehumidification, and dust removal according to the corresponding command information, such as the air conditioner control method in the present application.

[0052] In the embodiment of the present application, the air conditioner 100 includes but is not limited to a wall-mounted air conditioner, a cabinet air conditioner, a window air conditioner, a ceiling air conditioner, an embedded air conditioner, etc.

[0053] Those skilled in the art will understand that Figure 1 The application environment shown in the figure is only one application scenario of the present application solution and does not constitute a limitation on the application scenario of the present application solution. Other application environments may also include Figure 1 More or less air conditioners and air conditioners as shown in Figure 1 Only one air conditioner or air conditioner is shown in the figure. The air conditioner control system of the present application may also include one or more air conditioners and air conditioners for executing the air conditioner control method of the present application, which is not specifically limited here.

[0054] In addition, if 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 a single-chip microcomputer embedded in the air conditioner, and the specific details are not limited here.

[0055] It should be noted that Figure 1 The scene diagram of the air conditioner control system shown is only an example. The air conditioner control system and scene described in the embodiment of the present application are intended to more clearly illustrate the technical solution of the embodiment of the present application, and do not constitute a limitation on the technical solution provided in the embodiment of the present application. A person of ordinary skill in the art can know that with the evolution of the air conditioner control system and the emergence of new business scenarios, the technical solution provided in the embodiment of the present application is also applicable to similar technical problems.

[0056] like Figure 2 As shown, Figure 2 This is a flow chart of an embodiment of the air conditioner control method in the embodiment of the present application. The air conditioner control method may include the following steps 201 to 204:

[0057] 201. Obtain a first voice control instruction.

[0058] In the embodiment of the present application, the air conditioner can be installed with any voice receiving device, such as a microphone device. When the air conditioner is turned on, the microphone device is activated to collect voice commands. If the user sends any voice information, the air conditioner can analyze it, and if it is a command, it can be determined as the first voice control command.

[0059] For example, when receiving user voice information, the microphone device 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. Perform feature extraction on the first voice control instruction to determine a first volume feature, a first pitch feature, a first timbre feature, and a first speech speed feature.

[0061] When it is determined that the user's voice information is an instruction, that is, when the first voice control instruction is obtained, it is necessary to perform feature extraction on the first voice control instruction. In an embodiment of the present application, feature extraction can be performed from four aspects, namely volume features, pitch features, timbre features, and speech rate features. Among them, when performing these four feature extractions on the first voice control instruction, feature extraction can be performed separately by setting different neural network layers. For example: the first convolutional layer extracts volume features, the second convolutional layer extracts pitch features, the third convolutional layer extracts timbre features, the fourth convolutional layer extracts speech rate features, etc. The specific embodiments of the present application are not limited.

[0062] 203. Determine a target language type corresponding to the first voice control instruction according to the first volume feature, the first pitch feature, the first timbre feature, and the first speech rate feature.

[0063] After the four types of features are obtained, their corresponding language labels can be predicted respectively. For example, if the four corresponding labels predicted based on the four features are the same, then the speech types corresponding to the four same labels can be determined as the target language type.

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

[0065] 204. According to the language corresponding to the target language type, the target interactive voice is broadcasted.

[0066] When the target language type corresponding to the user's voice is determined, the corresponding language type can be used to respond to the user. For example, if the user issues a control command in Cantonese, the air conditioner can also respond to the user in Cantonese, "The command has been received." Alternatively, if the user issues a control command in English, the air conditioner can also respond to the user in English, "The command has been received."

[0067] The air conditioner control method provided by the present application can extract different types of features from the first voice control instruction after obtaining the first voice control instruction, and obtain volume features, pitch features, timbre features, and speech speed features, so that the air conditioner itself can better identify the language type used by the user based on these features. Therefore, the present application can improve the recognition accuracy of the language type. In addition, when interacting with the user by voice, the corresponding language of the same language type as the user can be used for interaction, thereby improving the language interaction capability of the air conditioner.

[0068] In order to better implement the method of the present application, in some embodiments of the present application, determining the target language type corresponding to the first voice control instruction according to the first volume feature, the first pitch feature, the first timbre feature, and the first speech rate feature includes:

[0069] Determine the weight information corresponding to the first volume feature, the first pitch feature, the first timbre feature and the first speaking speed feature respectively, and obtain the first weighted volume feature, the first weighted pitch feature, the first weighted timbre feature and the first weighted speaking speed feature; determine the first similarity information with various language types according to the first weighted volume feature, the first weighted pitch feature, the first weighted timbre feature and the first weighted speaking speed feature; determine the target language type according to each first similarity information.

[0070] In the embodiment of the present application, when determining the weight features corresponding to each of the volume features, pitch features, timbre features and speech speed features, the weights corresponding to each of them can be determined by means of an attention mechanism. For example: cross-attention mechanism, self-attention mechanism, etc., which are not limited in the embodiment of the present application. For example: the weight of the volume when determining the language type can be reduced, then the weight corresponding to the volume feature can be reduced. Therefore, in the embodiment of the present application, assuming that 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 speed feature is A, then two labels A and two labels B are included. Under normal circumstances, the model cannot determine the corresponding language type, but because the weight of the volume feature is reduced, the corresponding target language type can be determined according to label B.

[0071] It should be noted that in the embodiment of the present application, the label corresponding to the predicted feature can be predicted by similarity, for example, the timbre, volume, pitch and speech speed features of different languages ​​are stored. Afterwards, after acquiring different types of features, they are compared with the stored corresponding features respectively, and the similarity is calculated, so that the label corresponding to the feature with the highest similarity is regarded as the predicted label. In the embodiment of the present application, the method of calculating the similarity can be cosine similarity, Euclidean distance, etc., which is not limited in the embodiment of the present application.

[0072] In order to better implement the method of the present application, in some implementations of the present application, determining the target language type according to each piece of first similarity information includes:

[0073] If all the first similarity information do not meet the first target similarity threshold, a prompt voice is broadcast to prompt the user to issue a second voice control instruction; if the second voice control instruction is obtained, feature extraction is performed on the second voice control instruction to determine the second volume feature, the second pitch feature, the second timbre feature and the second speaking speed 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 speaking speed feature information of the first speaking speed feature and the second speaking speed feature are determined; the second similarity information with various language types is determined based on the average pitch feature information, the average volume feature information, the average timbre feature information and the average speaking speed feature information; and the target language type is determined based on each piece of second similarity information.

[0074] In actual situations, the user may be too far away from the air conditioner, resulting in unclear voice control instructions received by the air conditioner. At this time, although the air conditioner can obtain the similarity corresponding to each feature based on the user's first voice control instruction, the similarity value is low, for example, less than 50%. At this time, if the corresponding label is still determined based on the similarity information, it will obviously cause the failure of language type recognition. Therefore, in this case, the air conditioner can prompt the user to issue the voice control instruction again. The voice control instruction issued again is the second voice control instruction in the embodiment of the present application.

[0075] After obtaining the second voice control instruction, the second voice control instruction can be processed in the same manner to obtain four feature vectors corresponding to the second voice control instruction. It should be noted that in an embodiment of the present application, after obtaining the four feature vectors corresponding to the second voice control instruction, the four vectors corresponding to the first voice control vector can be averaged. Specifically, since the feature vector also includes a specific numerical value, in an embodiment of the present application, the first volume feature and the second volume feature can be added and averaged, the first timbre feature and the second timbre feature can be added and averaged, the first timbre feature and the second timbre feature can be added and averaged, and the first speech rate feature and the second speech rate feature can be added and averaged, and the similarity can be calculated based on the four average vectors, which can reduce errors and improve the accuracy of speech recognition. Among them, the method of calculating the corresponding target language type based on the second similarity information is the same as the above embodiment, and will not be repeated here.

[0076] In order to better implement the method of the present application, in some implementations of the present application, determining the target language type according to each second similarity information includes:

[0077] If each of the second similarity information does not meet the second target similarity threshold, a prompt voice is broadcast to prompt the user to issue a third voice control instruction; the third voice control instruction is sent to the target server, so that the target server determines the target language type according to the third voice control instruction.

[0078] Of course, in actual situations, the user's language may not be recognized. If the air conditioner itself cannot recognize the vector, the air conditioner can upload the user's voice command to the air conditioner manufacturer's server through the wifi module, and recognize it through the more powerful voice recognition model deployed in the server.

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

[0080] In order to better implement the method of the present application, in some implementations of the present application, the target server determines the target language type according to the third voice control instruction, including:

[0081] The target server determines the geographic location information for sending the third voice control instruction; the target server extracts features of the third voice control instruction to determine a third volume feature, a third pitch feature, a third timbre feature, and a third speech speed feature; and determines the target language type based on the third volume feature, the third pitch feature, the third timbre feature, the third speech speed feature, and the geographic location information.

[0082] The above embodiment provides a solution for determining the language type corresponding to a user by using a model in a server. Since the model computing capability involved in the server is more powerful and can involve more computing parameters, the server can also obtain the user's geographic location information for more comprehensive language identification.

[0083] Specifically, since the user's voice command is uploaded to the server through the air conditioner, the server can determine the geographical location information of the air conditioner that uploaded the voice according to the uploaded IP, so that the server obtains the geographical location information corresponding to the third voice control command. Since dialects are highly regional, a higher weight can be added to the geographical location information, so that the user's dialect can be identified based on the four features and combined with the geographical location information for prediction.

[0084] When the server recognizes the target language type of the user, the information of the target language type can be notified to the corresponding air conditioner through the network, so that the air conditioner can interact with the user according to the target language type.

[0085] In order to better implement the method of the present application, in some embodiments of the present application, the method further includes:

[0086] If the target language type cannot be identified, the target broadcast voice is used to announce the target language type, prompting the user to enter the adjustment mode to prompt the user to input the training voice data and the corresponding label data; based on the training voice data and the label data, the language recognition model to determine the target language type is adjusted.

[0087] However, in extreme cases, there may be a situation where it cannot be correctly recognized no matter what. At this time, the air conditioner can use the target broadcast voice to interact with the user. Among them, the voice type of the target broadcast voice can be a fixed voice type, such as Mandarin. At this time, the user can be prompted whether to enter the adjustment mode. If the user enters the adjustment mode, the user can first enter the dialect type through the air conditioner control device, such as a remote control panel or a control panel, as label data. After the user enters the dialect type, the user is prompted to speak freely to collect voice information under the corresponding dialect type for use as training voice data. After obtaining the label data and the trained voice data, the air conditioner can perform model training according to the label and training samples, thereby completing the adjustment of the model and realizing retraining.

[0088] Among them, the retraining method of the model can be any method, and the embodiments of the present application are not limited. For example: after collecting the user's language, unqualified data such as unclear data can be eliminated, and the voice module end performs pre-processing such as noise reduction and normalization on the N-time sound signal. Extract N times the acoustic signal features, combine the N-time sound signals with the currently used speech recognition model, fine-tune the recognition model, and finally complete the customization of the wake-up word. Finally, match the dialect parameters according to the highest matching value, and make corresponding dialect responses according to the recognized dialect type, and control the machine to enter the self-learning mode. In the self-learning mode, learn the user's dialect through the deep learning model.

[0089] In order to better implement the method of the present application, in some embodiments of the present application, the method further includes:

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

[0091] The above embodiment provides a solution for retraining the model when recognition fails. The embodiment of the present application also provides a solution for consolidating the recognition efficiency of the model after successful recognition.

[0092] Specifically, after correct recognition, the correct recognition result can be recorded and its weight value can be increased, so that it can respond quickly when the same recognition is performed in the future. The specific reason is that air conditioners are rarely resold second-hand. Therefore, the user's language usage habits usually do not change, so consolidating the weight of correct recognition will not cause the problem of a decrease in the accuracy of subsequent recognition.

[0093] Based on this, it can be inferred that the air conditioner system can continuously collect user interaction data, especially those language samples that were not correctly recognized at first but were successfully processed through the self-correction mechanism, and gradually optimize the performance of these language models. Through machine learning algorithms, the model parameters are continuously adjusted so that the model can better adapt to the user's actual dialect usage habits.

[0094] In order to better implement the air conditioner control method in the embodiment of the present application, in addition to the air conditioner control method, an air conditioner control device is also provided in the embodiment of the present application. The present application also provides an air conditioner control device, such as Figure 3 As shown, the device 300 includes:

[0095] An acquisition module 301 is used to acquire a first voice control instruction;

[0096] A determination module 302 is used to extract features from the first voice control instruction to determine a first volume feature, a first pitch feature, a first timbre feature, and a first speech rate feature;

[0097] The determination module 302 is further configured to determine the target language type corresponding to the first voice control instruction according to the first volume feature, the first pitch feature, the first timbre feature, and the first speech speed 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 by the present application can extract different types of features on the first voice control instruction through the determination module 302 after the acquisition module 301 acquires the first voice control instruction, and obtains volume features, pitch features, timbre features and speech speed features, so that the processing module 303 of the air conditioner can better identify the language type used by the user based on these features. Therefore, the present application can improve the recognition accuracy of the language type. In addition, when interacting with the user by voice, the corresponding language of the same language type as the user can be used for interaction, thereby improving the language interaction capability of the air conditioner.

[0100] In some implementations of the present application, the determination module 302 is specifically used to:

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

[0102] Determining first similarity information with various language types according to a first weighted volume feature, a first weighted pitch feature, a first weighted timbre feature, and a first weighted speech speed feature;

[0103] The target language type is determined according to each piece of first similarity information.

[0104] In some implementations of the present application, the determination module 302 is further configured to:

[0105] If each of the first similarity information does not meet the first target similarity threshold, a prompt voice is broadcasted to prompt the user to issue a second voice control instruction;

[0106] If a second voice control instruction is obtained, feature extraction is performed on the second voice control instruction to determine a second volume feature, a second pitch feature, a second timbre feature, and a second speech speed feature;

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

[0108] Determining second similarity information with various language types based on the average pitch feature information, the average volume feature information, the average timbre feature information, and the average speech speed feature information;

[0109] The target language type is determined according to each piece of second similarity information.

[0110] In some implementations of the present application, the determination module 302 is further configured to:

[0111] If each of the second similarity information does not meet the second target similarity threshold, a prompt voice is broadcasted to prompt the user to issue a third voice control instruction;

[0112] The third voice control instruction is sent to the target server, so that the target server determines the target language type according to the third voice control instruction.

[0113] In some implementations of the present application, the determination module 302 is further configured to:

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

[0115] The target server extracts features of the third voice control instruction to determine a third volume feature, a third pitch feature, a third timbre feature, and a third speech speed feature;

[0116] The target language type is determined according to the third volume feature, the third pitch feature, the third timbre feature, the third speech speed feature, and the geographical location information.

[0117] In some implementations of the present application, the determination module 302 is further configured to:

[0118] If the target language type cannot be identified, the target broadcast voice is used to broadcast, prompting the user to enter the adjustment mode, so as to prompt the user to input the training voice data and the corresponding label data;

[0119] According to the training speech data and the label data, the language recognition model is adjusted to determine the target language type.

[0120] In some implementations of the present application, the determination module 302 is further configured to:

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

[0122] According to the current correct recognition result, adjust the weight information of the language recognition model.

[0123] The embodiment of the present application also provides an air conditioner, which integrates any of the air conditioner control methods provided in the embodiment of the present application, such as Figure 4 As shown, it shows a schematic diagram of the structure of the air conditioner involved in the embodiment of the present application, specifically:

[0124] The air conditioner may include one or more processors 401 of processing cores, one or more computer-readable storage media storage devices 402, a power supply 403, an input unit 404 and other components. Those skilled in the art will appreciate that Figure 4 The air conditioner structure shown in the figure does not constitute a limitation on the air conditioner, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0125] in:

[0126] The processor 401 is the control center of the air conditioner, and uses various interfaces and lines to connect various parts of the entire air conditioner. By running or executing the software programs and / or modules stored in the storage device 402, and calling the data stored in the storage device 402, the processor 401 performs various functions of the air conditioner and processes data, thereby monitoring the air conditioner as a whole. 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 (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. Preferably, the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 401.

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

[0128] The air conditioner also includes a power supply 403 for supplying power to each component. Preferably, the power supply 403 can be logically connected to the processor 401 through a power management system, so that the power management system can manage charging, discharging, power consumption and other functions. The power supply 403 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators and other arbitrary components.

[0129] The air conditioner may further include an input unit 404, which may 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 controls.

[0130] Although not shown, the air conditioner may further include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 401 in the air conditioner will load 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 will run the application programs stored in the storage device 402, thereby realizing various functions, such as:

[0131] Obtaining a first voice control instruction;

[0132] Extracting features of the first voice control instruction to determine a first volume feature, a first pitch feature, a first timbre feature, and a first speech speed feature;

[0133] Determining a target language type corresponding to the first voice control instruction according to the first volume feature, the first pitch feature, the first timbre feature, and the first speech speed feature;

[0134] According to the language corresponding to the target language type, the target interactive voice is broadcast.

[0135] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0136] To this end, the embodiment of the present application provides a computer-readable storage medium, which may include: a read-only memory (ROM), a random access memory (RAM), a 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 the embodiment of the present application. For example, the computer program loaded by the processor can execute the following steps:

[0137] Obtaining a first voice control instruction;

[0138] Extracting features of the first voice control instruction to determine a first volume feature, a first pitch feature, a first timbre feature, and a first speech speed feature;

[0139] Determining a target language type corresponding to the first voice control instruction according to the first volume feature, the first pitch feature, the first timbre feature, and the first speech speed feature;

[0140] According to the language corresponding to the target language type, the target interactive voice is broadcast.

[0141] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the detailed description of other embodiments above, and will not be repeated here.

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

[0143] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0144] The air conditioner control method and device provided in the embodiment of the present application are introduced in detail above. The principles and implementation methods of the present application are explained in this article using specific examples. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for controlling an air conditioner, It is characterized in that The method comprises: Obtaining a first voice control instruction; Extracting features of the first voice control instruction to determine a first volume feature, a first pitch feature, a first timbre feature, and a first speech speed feature; determining a target language type corresponding to the first voice control instruction according to the first volume feature, the first pitch feature, the first timbre feature, and the first speech rate feature; According to the language corresponding to the target language type, the target interactive voice is broadcasted.

2. The air conditioner control method according to claim 1, It is characterized in that The determining, according to the first volume feature, the first tone feature, the first timbre feature, and the first speech rate feature, of the target language type corresponding to the first voice control instruction includes: Determine weight information corresponding to the first volume feature, the first tone feature, the first timbre feature, and the first speech rate feature, respectively, to obtain a first weighted volume feature, a first weighted tone feature, a first weighted timbre feature, and a first weighted speech rate feature; determining first similarity information with various language types according to the first weighted volume feature, the first weighted pitch feature, the first weighted timbre feature, and the first weighted speech speed feature; The target language type is determined according to each of the first similarity information.

3. The air conditioner control method according to claim 2, It is characterized in that The determining the target language type according to each of the first similarity information includes: If each of the first similarity information does not meet the first target similarity threshold, broadcasting a prompt voice to prompt the user to issue a second voice control instruction; If the second voice control instruction is obtained, feature extraction is performed on the second voice control instruction to determine a second volume feature, a second pitch feature, a second timbre feature, and a second speech speed feature; Determine average volume feature information of the first volume feature and the second volume feature, average tone feature information of the first tone feature and the second tone feature, average tone feature information of the first timbre feature and the second timbre feature, and average speech rate feature information of the first speech rate feature and the second speech rate feature; Determining second similarity information with various language types based on the average tone feature information, the average volume feature information, the average timbre feature information, and the average speech speed feature information; The target language type is determined according to each of the second similarity information.

4. The air conditioner control method according to claim 3, It is characterized in that The step of determining the target language type according to each of the second similarity information includes: If each of the second similarity information does not meet the second target similarity threshold, broadcasting a prompt voice to prompt the user to issue a third voice control instruction; The third voice control instruction is sent to a target server, so that the target server determines a target language type according to the third voice control instruction.

5. The air conditioner control method according to claim 4, It is characterized in that The target server determines the target language type according to the third voice control instruction, including: The target server determines the geographical location information for sending the third voice control instruction; The target server extracts features from the third voice control instruction to determine a third volume feature, a third pitch feature, a third timbre feature, and a third speech speed feature; The target language type is determined according to the third volume feature, the third tone feature, the third timbre feature, the third speech speed feature, and the geographical location information.

6. The air conditioner control method according to any one of claims 1 to 5, It is characterized in that The method further comprises: If the target language type cannot be identified, the target broadcast voice is used to broadcast, prompting the user to enter the adjustment mode, so as to prompt the user to input the training voice data and the corresponding label data; A language recognition model for determining the target language type is adjusted according to the training speech data and the label data.

7. The air conditioner control method according to any one of claims 1 to 5, It is characterized in that The method further comprises: If the target language type is correctly identified, the current correct recognition result is recorded; According to the current correct recognition result, the weight information of the language recognition model is adjusted.

8. An air conditioner control device, It is characterized in that The device comprises: An acquisition module, used to acquire a first voice control instruction; A determination module, configured to extract features from the first voice control instruction to determine a first volume feature, a first pitch feature, a first timbre feature, and a first speech speed feature; The determination module is further used to determine the target language type corresponding to the first voice control instruction according to the first volume feature, the first tone feature, the first timbre feature and the first speech speed feature; The processing module is used to broadcast the target interactive voice according to the language corresponding to the target language type.

9. An air conditioner, It is characterized in that The air conditioner comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the steps of the air conditioner control method according to any one of claims 1 to 7.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps in the air conditioner control method according to any one of claims 1 to 7.

Images