Noise filtering method and device, computer readable storage medium and electronic equipment

Abstract

The invention provides a noise filtering method and device, a computer readable storage medium and electronic equipment. The method comprises the following steps: in a first preset environment, noise data of operation of the electrical equipment in each function mode is obtained, first noise data corresponding to each function mode is obtained, the first preset environment represents an environment without other sounds except the electrical equipment in a preset closed space before the electrical equipment leaves a factory, and the first noise data is sent to the electrical equipment; the first noise data comprises operation noise of the electrical equipment; in a second preset environment, noise data of operation of the electrical equipment in each function mode is obtained, and second noise data corresponding to each function mode is obtained; and filtering the first noise data and the second noise data to obtain target voice data. According to the invention, the problem of poor user experience caused by the fact that the voice function of the electrical equipment is greatly influenced by noise in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the technical field of device noise processing, and in particular to a noise filtering method, device, computer-readable storage medium and electronic device. Background Art

[0002] With the continuous development of electronic functions, voice functions are becoming more and more common in various products. They have tended to be used as one of the functions to improve product performance. Controlling products through voice functions frees up manpower, making it more convenient for users to use products and improving user experience.

[0003] In recent years, household appliances such as electric heaters have upgraded their voice functions as an important function. For example, traditional electric heaters generally require users to make commands and controls through key operations, but sometimes users are far away from the product, or it is inconvenient to directly operate the keys. At this time, voice control can solve the above problems very well. Users can directly wake up the voice control system with voice, and convey control commands through voice, realizing operation-free control, which greatly increases convenience.

[0004] In the prior art, the voice function of electrical appliances is generally combined with the conventional functions of the appliances to set up voice reception, dialogue and voice control logic. The specific settings of the voice functions of different products vary, and these differences will affect the user experience. According to the survey, the products such as electric heaters based on voice control in the prior art have the following problems, such as: the microphone is not sensitive to sound reception and is easily disturbed by other noises; the voice function sometimes speaks autonomously without receiving instructions; the interactive experience with users is not good, etc. Summary of the invention

[0005] The main purpose of the present application is to provide a noise filtering method, device, computer-readable storage medium and electronic device, so as to at least solve the problem in the prior art that the voice function of electrical equipment is greatly affected by noise, resulting in poor user experience.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a noise filtering method is provided, comprising: in a first preset environment, obtaining noise data of an electrical device operating in each functional mode, and obtaining first noise data corresponding to each of the functional modes, wherein the first preset environment represents an environment in which there is no other sound except the electrical device in a preset enclosed space before the electrical device leaves the factory, and the first noise data includes the operating noise of the electrical device; in a second preset environment, obtaining noise data of the electrical device operating in each of the functional modes, and obtaining second noise data corresponding to each of the functional modes, wherein the second preset environment represents an environment in which the electrical device includes operating noises of multiple other electrical devices in the preset enclosed space before leaving the factory, and the second noise data includes the operating noise of the electrical device and operating noises of multiple other electrical devices; filtering the first noise data and the second noise data to obtain target voice data, wherein the target voice data is voice data emitted by a user.

[0007] Optionally, noise data of the electrical device operating in each functional mode is obtained to obtain first noise data corresponding to each functional mode, including: receiving a first target operating instruction, controlling the electrical device to operate in the functional mode corresponding to the first target operating instruction, wherein the first target operating instruction is issued under the first preset environment; obtaining the first noise data corresponding to the functional mode through a microphone, wherein the microphone is included in the electrical device.

[0008] Optionally, the first noise data and the second noise data are filtered to obtain target voice data, including: converting the first noise data into first text data, and converting the second noise data into second text data; storing the first text data and the second text data in a text database; and when receiving user voice, filtering the first text data and the second text data from the user voice to obtain the target voice data, wherein the user voice represents audio data issued by the user to instruct the action of the electrical device.

[0009] Optionally, the first text data and the second text data are filtered from the user voice to obtain the target voice data, including: determining first spectrum data of the first text data, determining second spectrum data of the second text data, and determining third spectrum data of the user voice; calculating the difference between the third spectrum data and the first spectrum data to obtain fourth spectrum data, and calculating the difference between the fourth spectrum data and the second spectrum data to obtain fifth spectrum data; determining the voice data corresponding to the fifth spectrum data to obtain the target voice data.

[0010] Optionally, noise data of the electrical device operating in each of the functional modes is obtained to obtain second noise data corresponding to each of the functional modes, including: receiving a second target operation instruction, controlling the electrical device to operate in the functional mode corresponding to the second target operation instruction, wherein the second target operation instruction is issued under the second preset environment; and obtaining the second noise data corresponding to the functional mode through a microphone, wherein the microphone is included in the electrical device.

[0011] Optionally, after obtaining the target voice data, the method further includes: generating a voice signal control instruction based on the target voice data, and controlling the operation of the electrical device according to the voice signal control instruction, wherein the voice signal control instruction is a control instruction of the electrical device obtained by converting the voice data sent by the user.

[0012] Optionally, the method further includes: when receiving operating noise of other electrical devices, filtering the operating noise of the other electrical devices and not generating the voice signal control instruction.

[0013] According to another aspect of the present application, a noise filtering device is provided, comprising: a first acquisition unit, for acquiring noise data of the electrical device operating in each functional mode under a first preset environment, and obtaining first noise data corresponding to each of the functional modes, wherein the first preset environment represents an environment in which there is no other sound except the electrical device in a preset enclosed space before the electrical device leaves the factory, and the first noise data includes the operating noise of the electrical device; a second acquisition unit, for acquiring noise data of the electrical device operating in each functional mode under a second preset environment, and obtaining second noise data corresponding to each of the functional modes, wherein the second preset environment represents an environment in which the electrical device includes operating noises of multiple other electrical devices in the preset enclosed space before the electrical device leaves the factory, and the second noise data includes the operating noise of the electrical device and operating noises of multiple other electrical devices; a filtering unit, for filtering the first noise data and the second noise data to obtain target voice data, wherein the target voice data is voice data emitted by a user.

[0014] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute any one of the noise filtering methods.

[0015] According to another aspect of the present application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing any one of the noise filtering methods.

[0016] Applying the technical solution of the present application, in the first preset environment, the noise data of the electrical equipment running in each functional mode is obtained, and the first noise data corresponding to each functional mode is obtained, wherein the first preset environment represents an environment in which there is no other sound except the electrical equipment in the preset enclosed space before the electrical equipment leaves the factory, and the first noise data includes the running noise of the electrical equipment; in the second preset environment, the noise data of the electrical equipment running in each functional mode is obtained, and the second noise data corresponding to each functional mode is obtained, wherein the second preset environment represents an environment in which the electrical equipment includes the running noise of multiple other electrical equipment in the preset enclosed space before the electrical equipment leaves the factory, and the second noise data includes the running noise of the electrical equipment and the running noise of multiple other electrical equipment; the first noise data and the second noise data are filtered to obtain the target voice data. Compared with the existing technology, in which the electrical products based on voice control have problems such as insensitive sound reception and easy interference by other noises, the present application can record the noise data under two preset environments respectively before the electrical equipment leaves the factory, and filter out the above noise data when the electrical equipment is running, so as to achieve the purpose of filtering the running noise of the equipment itself and the running environment noise. Therefore, it can solve the problem that the voice function of the electrical equipment in the prior art is greatly affected by noise, resulting in poor user experience, and achieve the purpose of effectively filtering noise. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 A schematic diagram of a noise filtering method provided in an embodiment of the present application is shown;

[0019] Figure 2 A schematic diagram of a specific noise filtering method provided in an embodiment of the present application is shown;

[0020] Figure 3 A schematic flow chart of another specific noise filtering method provided in an embodiment of the present application is shown;

[0021] Figure 4 A structural block diagram of a noise filtering device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0022] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are 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 ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] As introduced in the background technology, products such as electric heaters based on voice control in the prior art have the following problems, such as: the microphone is not sensitive to sound reception and is easily disturbed by other noises; the voice function sometimes speaks autonomously without receiving any instructions; the interaction experience with users is not good, etc. In order to solve the problem in the prior art that the voice function of electrical equipment is greatly affected by noise, resulting in poor user experience, the embodiments of the present application provide a noise filtering method, device, computer-readable storage medium and electronic device.

[0026] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0027] In this embodiment, a noise filtering method running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0028] Figure 1is a flow chart of a noise filtering method according to an embodiment of the present application. Figure 1 As shown, the method comprises the following steps:

[0029] Step S201, in a first preset environment, obtaining noise data of the electrical device running in each functional mode, and obtaining first noise data corresponding to each functional mode, wherein the first preset environment represents an environment in which there is no other sound except the electrical device in a preset enclosed space before the electrical device leaves the factory, and the first noise data includes the operating noise of the electrical device;

[0030] Specifically, electrical products and equipment, such as electric heating equipment, are debugged in the factory before they are shipped out of the factory. This solves the problem of interference and misrecognition of user voices caused by the product's own noise during operation, and improves the product's voice human-computer interaction experience. When debugging and using it for the first time, place the product in a quiet environment, that is, the first preset environment mentioned above, and turn on the product to manually control all functional modes one by one. The microphone on the product receives the product's own noise or audio when it is running in each function and mode, and obtains the first noise data.

[0031] Step S202, in a second preset environment, obtaining noise data of the electrical device operating in each of the functional modes, and obtaining second noise data corresponding to each of the functional modes, wherein the second preset environment represents an environment in which the electrical device includes operating noises of multiple other electrical devices in the preset enclosed space before leaving the factory, and the second noise data includes the operating noise of the electrical device and the operating noises of multiple other electrical devices;

[0032] Specifically, after the first debugging, a second debugging is required. During the second debugging, the product is placed in an environment simulating the user's home use, such as an environment with noise or audio from other electrical appliances such as TVs, washing machines, and kitchen cooking. All functional modes of the product are manually controlled one by one, and the operating noise and audio of the electrical product in each mode are stored and memorized through the chip storage and filtering processor to obtain the second noise data.

[0033] Step S203: Filter the first noise data and the second noise data to obtain target voice data, wherein the target voice data is voice data uttered by a user.

[0034] Specifically, when the user is using it, the noise or audio information generated by the product's own operation and other electrical appliances in the house will be automatically filtered and processed by the chip filtering processor. That is to say, the first noise data and the second noise data will be automatically filtered and processed to reduce the interference of the product itself and the surrounding environment noise on the user's voice, and improve the product microphone reception sensitivity and the product human-computer interaction experience.

[0035] Through this embodiment, in the first preset environment, the noise data of the electrical equipment running in each functional mode is obtained, and the first noise data corresponding to each functional mode is obtained, wherein the first preset environment represents an environment in which there is no other sound except the electrical equipment in the preset enclosed space before the electrical equipment leaves the factory, and the first noise data includes the running noise of the electrical equipment; in the second preset environment, the noise data of the electrical equipment running in each functional mode is obtained, and the second noise data corresponding to each functional mode is obtained, wherein the second preset environment represents an environment in which the electrical equipment includes the running noise of multiple other electrical equipment in the preset enclosed space before the electrical equipment leaves the factory, and the second noise data includes the running noise of the electrical equipment and the running noise of multiple other electrical equipment; the first noise data and the second noise data are filtered to obtain the target voice data. Compared with the existing technology, in which the electrical products based on voice control have problems such as insensitive sound reception and easy interference by other noises, the present application can record the noise data under two preset environments respectively before the electrical equipment leaves the factory, and filter out the above noise data when the electrical equipment is running, so as to achieve the purpose of filtering the running noise of the equipment itself and the running environment noise. Therefore, it can solve the problem that the voice function of the electrical equipment in the existing technology is greatly affected by noise, resulting in poor user experience, and achieve the purpose of effectively filtering noise.

[0036] In the specific implementation process, the above step S201 obtains the noise data of the electrical device running in each functional mode, and obtains the first noise data corresponding to each functional mode, which can be achieved by the following steps: Step S2011: receiving a first target operation instruction, and controlling the electrical device to run in the functional mode corresponding to the first target operation instruction, wherein the first target operation instruction is issued under the first preset environment; Step S2012: obtaining the first noise data corresponding to the functional mode through a microphone, wherein the microphone is included in the electrical device. The method obtains the first noise data through the above steps, so that the noise of the device itself running in a quiet environment can be collected for noise filtering.

[0037] Specifically, the electrical device includes multiple modules, such as a voice chip storage filtering processor, etc., which receives the noise or audio of the product itself running in various functions and modes, that is, the first noise data, through the microphone on the product, and transmits it to the voice module, and the voice module transmits it to the voice chip processor. The chip processor converts the first noise data into a voice text command signal, and then transmits it to the chip storage filtering processor. The chip storage filtering processor stores and memorizes the first noise data of the product in various operating modes, and automatically filters and processes it, and will not convey the noise information instructions of the product operation itself to the speaker.

[0038] In some optional implementations, the above step S203 filters the first noise data and the second noise data to obtain the target voice data, which can be achieved by the following steps: step S2031: converting the first noise data into first text data, and converting the second noise data into second text data; step S2032: storing the first text data and the second text data in a text database; step S2033: in the case of receiving a user voice, filtering the first text data and the second text data from the user voice to obtain the target voice data, wherein the user voice represents the audio data issued by the user to indicate the action of the electrical device. The method stores the noise in advance through the above steps, and filters the noise when the electrical device is in use, so that the operating noise of the electrical device itself can be effectively and efficiently filtered out.

[0039] In the specific implementation process, two microphones are generally used in the prior art. When the device is running, one microphone is used to collect the device's own operating noise, and the other user collects all audio data (including user voice and device noise, etc.), and then filters them. This not only has a poor filtering effect, but also requires the installation of two microphones. The above steps of the present application simulate a quiet environment and the user's actual usage environment before the device leaves the factory, and collect noise data separately.

[0040] In some other optional implementations, step S2033 filters the first text data and the second text data from the user voice to obtain the target voice data, which can be achieved by the following steps: determining the first spectrum data of the first text data, determining the second spectrum data of the second text data, and determining the third spectrum data of the user voice; calculating the difference between the third spectrum data and the first spectrum data to obtain the fourth spectrum data, and calculating the difference between the fourth spectrum data and the second spectrum data to obtain the fifth spectrum data; determining the voice data corresponding to the fifth spectrum data to obtain the target voice data. The method obtains the target voice data by filtering through the above steps, thus filtering the noise data through the spectrum.

[0041] Specifically, the first text data corresponds to the first noise data, and the first noise data can be converted into corresponding spectrum data. The same is true for the second text data. At the same time, the user voice is converted into the corresponding third spectrum data. Then, the third spectrum data is subtracted from the second spectrum data and the first spectrum data to obtain the final difference, that is, the fifth spectrum data, which is then converted into voice data to obtain the target voice data.

[0042] In some optional embodiments, the above-mentioned step S202 obtains the noise data of the electrical device operating in each of the functional modes, and obtains the second noise data corresponding to each of the functional modes, which can be achieved by the following steps: receiving a second target operation instruction, controlling the electrical device to operate in the functional mode corresponding to the second target operation instruction, wherein the second target operation instruction is issued under the second preset environment; obtaining the second noise data corresponding to the functional mode through a microphone, wherein the microphone is included in the electrical device.

[0043] In the specific implementation process, by identifying the operation instructions in the second preset environment, the electrical device can intelligently adjust its operation mode to adapt to different usage scenarios, such as home, office or public places. The acquired second noise data can help the device automatically filter out noise interference in similar environments in subsequent operation, and improve the accuracy and response speed of voice recognition. This is crucial to improving the interactive experience between users and devices, especially in high-noise environments. By storing and learning noise characteristics in different environments, the device can provide users with a more personalized voice control experience. For example, in a kitchen environment, the device can filter out cooking noise, while in a living room environment, it can filter out the background sound of TV or music, making voice control more accurate. The device needs to have the ability to recognize and distinguish multiple preset environments. For example, it can automatically detect whether it is currently in a quiet bedroom or a noisy living room, so as to adjust the noise filtering strategy. This may involve classification learning of environmental noise and optimization of recognition algorithms. In order to filter noise more accurately, deep learning technology can be used to analyze and learn the noise data received by the microphone to establish a more complex noise feature model. This helps the device accurately distinguish between user voice commands and background noise in any environment. The device can be equipped with a user feedback system that allows users to manually correct errors when the device recognizes them. This feedback data can be collected and used to further optimize the noise filtering algorithm to make it more accurate. In addition to noise filtering in preset environments, the device should also be able to adapt to environmental changes in real time. For example, when the user moves from one environment to another, the device can quickly adjust its noise filtering strategy to maintain the efficiency of voice control. In some cases, if multiple voice commands are recognized at the same time, the device should be able to decide which command to execute first based on the preset priority rules, which can avoid command conflicts caused by environmental noise. The automatic filtering method of the voice electric heater's own noise can not only handle the noise generated by the operation of the electric heater, but also adapt to different usage scenarios more intelligently, providing a more accurate and personalized voice control experience. At the same time, the device's anti-interference ability has also been significantly improved, greatly enhancing the quality of interaction between users and devices.

[0044] In other optional embodiments, after obtaining the target voice data, the method further includes the following steps: generating a voice signal control instruction based on the target voice data, and controlling the operation of the electrical device according to the voice signal control instruction, wherein the voice signal control instruction is a control instruction of the electrical device obtained by converting the voice data sent by the user.

[0045] During the specific implementation process, after the microphone collects the voice signal, the voice chip processor first performs noise filtering to remove the noise generated by the operation of the electric heater itself and other environmental noise, retaining only the clear voice signal from the user. This filtering step is based on noise data collected and stored in advance in different environments to ensure that the user's voice commands can be accurately recognized even in a noisy environment. Next, the processor analyzes the filtered voice signal to identify key words or commands. This process may involve natural language processing technologies such as speech-to-text (STT) and keyword spotting (KWS) to convert the user's voice commands into text form. Instructions in text form are more easily processed by subsequent instruction conversion modules.

[0046] Once the voice command is converted into text, the control command generation module will match it according to the preset command library and convert the user's intention into specific operation instructions, such as "increase the temperature" and "reduce the brightness". This step may require a deep learning or rule matching algorithm to ensure the correctness and accuracy of the command.

[0047] Finally, according to the generated control instructions, the control system of the electrical equipment (such as the electric heater) will perform the corresponding operation and adjust the working state of the equipment. At the same time, the equipment should have a feedback mechanism to broadcast the execution results to the user through the speaker to confirm that the instructions have been executed correctly, thereby enhancing the interactive experience between the user and the equipment. For example, when the user says "increase the temperature", the electric heater should say "the temperature has been raised" after execution.

[0048] In some optional implementations, the method further comprises the following steps: when receiving the operating noise of other electrical devices, filtering the operating noise of the other electrical devices and not generating the voice signal control instruction. The method automatically filters out the noise of the device operation through the above steps, so that when there is only noise, no corresponding control instruction is generated, thereby avoiding the problem of inaccurate audio recognition caused by noise.

[0049] Specifically, the voice electric heater collects and learns the operating noise characteristics of other electrical appliances under different usage environments. This includes but is not limited to the typical noise of household appliances such as TVs, refrigerators, washing machines, and air conditioners. Through deep learning techniques, such as convolutional neural networks (CNN) or recurrent neural networks (RNN), a noise feature database is established to distinguish other electrical noise from user voice commands. When the microphone receives an audio signal, the voice chip processor performs noise detection in real time. The processor uses the previously established noise feature database to quickly classify the received audio signal through a pattern matching algorithm to determine whether it comes from the operating noise of other electrical equipment rather than a voice command issued by the user.

[0050] For signals identified as operating noise from other electrical equipment, the voice chip processor will apply a specific noise filtering algorithm. This may include technologies such as spectrum analysis, noise gate, and adaptive filters to eliminate or reduce the impact of these noises. By adjusting the parameters of the filter, noise in a specific frequency range or mode can be accurately filtered out to ensure the clarity of the user's voice commands. Based on the noise filtering algorithm, the system should also set the priority of the user's voice commands. Even in a complex environment, when the user issues a command, the processor can quickly identify and filter out background noise, prioritize user commands, generate correct voice signal control commands, and control the operation of the electric heater.

[0051] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the noise filtering method of the present application will be described in detail below in conjunction with specific embodiments.

[0052] This embodiment relates to a specific noise filtering method, such as Figure 2 As shown, the following steps are included:

[0053] Step S1: (electrical equipment) start up and run;

[0054] Step S2: The product is debugged in a quiet environment, and the noise or audio of the product running in various functions and modes is received through the microphone on the product, and transmitted to the voice module;

[0055] Step S3: The voice module is transmitted to the voice chip processor, and the chip processor converts the voice information into a voice text instruction signal, and then transmits it to the chip storage and filtering processor;

[0056] Step S4: The chip storage filter processor stores and memorizes the operating noise and audio of the product in each operating mode, and automatically filters and processes it, and will not convey the noise information instructions of the product operation itself to the speaker.

[0057] This embodiment relates to another specific noise filtering method, such as Figure 3 As shown, the following steps are included:

[0058] Step S5: placing the product in an environment simulating the user's home use, such as an environment with noise or audio such as a TV, washing machine, and kitchen cooking;

[0059] Step S6: Turn on the product and manually control all function modes one by one, receive the noise or audio of the product running in each function and mode through the microphone on the product, and transmit it to the voice module;

[0060] Step S7: The chip storage and filtering processor stores and memorizes the operating noise and audio of the product in each operating mode, and automatically filters and processes it, and does not transmit the noise information instructions of the product operation itself to the speaker.

[0061] The embodiment of the present application also provides a noise filtering device. It should be noted that the noise filtering device of the embodiment of the present application can be used to execute the noise filtering method provided by the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions thereof will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0062] The following is an introduction to the noise filtering device provided in the embodiments of the present application.

[0063] Figure 4 is a schematic diagram of a noise filtering device according to an embodiment of the present application. Figure 4 As shown, the device comprises:

[0064] A first acquisition unit 10 is used to acquire noise data of the electrical device running in each functional mode under a first preset environment, and obtain first noise data corresponding to each functional mode, wherein the first preset environment represents an environment in which there is no other sound except the electrical device in a preset enclosed space before the electrical device leaves the factory, and the first noise data includes the operating noise of the electrical device;

[0065] Specifically, electrical products and equipment, such as electric heating equipment, are debugged in the factory before they are shipped out of the factory. This solves the problem of interference and misrecognition of user voices caused by the product's own noise during operation, and improves the product's voice human-computer interaction experience. When debugging and using it for the first time, place the product in a quiet environment, that is, the first preset environment mentioned above, and turn on the product to manually control all functional modes one by one. The microphone on the product receives the product's own noise or audio when it is running in each function and mode, and obtains the first noise data.

[0066] A second acquisition unit 20 is used to acquire noise data of the electrical device operating in each of the functional modes under a second preset environment, and obtain second noise data corresponding to each of the functional modes, wherein the second preset environment represents an environment in which the electrical device includes operating noises of multiple other electrical devices in the preset enclosed space before leaving the factory, and the second noise data includes the operating noise of the electrical device and the operating noises of multiple other electrical devices;

[0067] Specifically, after the first debugging, a second debugging is required. During the second debugging, the product is placed in an environment simulating the user's home use, such as an environment with noise or audio from other electrical appliances such as TVs, washing machines, and kitchen cooking. All functional modes of the product are manually controlled one by one, and the operating noise and audio of the electrical product in each mode are stored and memorized through the chip storage and filtering processor to obtain the second noise data.

[0068] The filtering unit 30 is used to filter the first noise data and the second noise data to obtain target voice data, wherein the target voice data is voice data uttered by a user.

[0069] Specifically, when the user is using it, the noise or audio information generated by the product's own operation and other electrical appliances in the house will be automatically filtered and processed by the chip filtering processor. That is to say, the first noise data and the second noise data will be automatically filtered and processed to reduce the interference of the product itself and the surrounding environment noise on the user's voice, and improve the product microphone reception sensitivity and the product human-computer interaction experience.

[0070] Through this embodiment, in the first preset environment, the noise data of the electrical equipment running in each functional mode is obtained, and the first noise data corresponding to each functional mode is obtained, wherein the first preset environment represents an environment in which there is no other sound except the electrical equipment in the preset enclosed space before the electrical equipment leaves the factory, and the first noise data includes the running noise of the electrical equipment; in the second preset environment, the noise data of the electrical equipment running in each functional mode is obtained, and the second noise data corresponding to each functional mode is obtained, wherein the second preset environment represents an environment in which the electrical equipment includes the running noise of multiple other electrical equipment in the preset enclosed space before the electrical equipment leaves the factory, and the second noise data includes the running noise of the electrical equipment and the running noise of multiple other electrical equipment; the first noise data and the second noise data are filtered to obtain the target voice data. Compared with the existing technology, in which the electrical products based on voice control have problems such as insensitive sound reception and easy interference by other noises, the present application can record the noise data under two preset environments respectively before the electrical equipment leaves the factory, and filter out the above noise data when the electrical equipment is running, so as to achieve the purpose of filtering the running noise of the equipment itself and the running environment noise. Therefore, it can solve the problem that the voice function of the electrical equipment in the existing technology is greatly affected by noise, resulting in poor user experience, and achieve the purpose of effectively filtering noise.

[0071] In a specific implementation process, the first acquisition unit includes a first control module and a first acquisition module, wherein the first control module is used to receive a first target operation instruction and control the electrical device to operate in the functional mode corresponding to the first target operation instruction, wherein the first target operation instruction is issued under the first preset environment; and the first acquisition module is used to acquire the first noise data corresponding to the functional mode through a microphone, wherein the microphone is included in the electrical device. The device acquires the first noise data through the above steps, so that the noise of the device itself operating in a quiet environment can be collected for noise filtering.

[0072] Specifically, the electrical device includes multiple modules, such as a voice chip storage filtering processor, etc., which receives the noise or audio of the product itself running in various functions and modes, that is, the first noise data, through the microphone on the product, and transmits it to the voice module, and the voice module transmits it to the voice chip processor. The chip processor converts the first noise data into a voice text command signal, and then transmits it to the chip storage filtering processor. The chip storage filtering processor stores and memorizes the first noise data of the product in various operating modes, and automatically filters and processes it, and will not convey the noise information instructions of the product operation itself to the speaker.

[0073] In some optional embodiments, the filtering unit includes a conversion module, a storage module and a filtering module, wherein the conversion module is used to convert the first noise data into first text data and the second noise data into second text data; the storage module is used to store the first text data and the second text data in a text database; the filtering module is used to filter the first text data and the second text data from the user voice when receiving the user voice to obtain the target voice data, wherein the user voice represents the audio data issued by the user to indicate the action of the electrical device. The device stores the noise in advance through the above steps and filters the noise when the electrical device is in use, so that the operating noise of the electrical device itself can be effectively and efficiently filtered out.

[0074] In the specific implementation process, two microphones are generally used in the prior art. When the device is running, one microphone is used to collect the device's own operating noise, and the other user collects all audio data (including user voice and device noise, etc.), and then filters them. This not only has a poor filtering effect, but also requires the installation of two microphones. The above steps of the present application simulate a quiet environment and the user's actual usage environment before the device leaves the factory, and collect noise data separately.

[0075] In some other optional implementations, the filtering module includes a first determining submodule, a calculating submodule, and a second determining submodule, wherein the first determining submodule is used to determine the first spectrum data of the first text data, determine the second spectrum data of the second text data, and determine the third spectrum data of the user voice; the calculating submodule is used to calculate the difference between the third spectrum data and the first spectrum data to obtain the fourth spectrum data, and calculate the difference between the fourth spectrum data and the second spectrum data to obtain the fifth spectrum data; the second determining submodule is used to determine the speech data corresponding to the fifth spectrum data to obtain the target speech data. The device obtains the target speech data by filtering through the above steps, thereby filtering the noise data through the spectrum.

[0076] Specifically, the first text data corresponds to the first noise data, and the first noise data can be converted into corresponding spectrum data. The same is true for the second text data. At the same time, the user voice is converted into the corresponding third spectrum data. Then, the third spectrum data is subtracted from the second spectrum data and the first spectrum data to obtain the final difference, that is, the fifth spectrum data, which is then converted into voice data to obtain the target voice data.

[0077] In some optional embodiments, the above-mentioned second acquisition unit includes a second control module and a second acquisition module, the second control module is used to receive a second target operation instruction, and control the electrical device to operate in the functional mode corresponding to the second target operation instruction, wherein the second target operation instruction is issued under the second preset environment; the second acquisition module is used to obtain the second noise data corresponding to the functional mode through a microphone, wherein the microphone is included in the electrical device.

[0078] In the specific implementation process, by identifying the operation instructions in the second preset environment, the electrical device can intelligently adjust its operation mode to adapt to different usage scenarios, such as home, office or public places. The acquired second noise data can help the device automatically filter out noise interference in similar environments in subsequent operation, and improve the accuracy and response speed of voice recognition. This is crucial to improving the interactive experience between users and devices, especially in high-noise environments. By storing and learning noise characteristics in different environments, the device can provide users with a more personalized voice control experience. For example, in a kitchen environment, the device can filter out cooking noise, while in a living room environment, it can filter out the background sound of TV or music, making voice control more accurate. The device needs to have the ability to recognize and distinguish multiple preset environments. For example, it can automatically detect whether it is currently in a quiet bedroom or a noisy living room, so as to adjust the noise filtering strategy. This may involve classification learning of environmental noise and optimization of recognition algorithms. In order to filter noise more accurately, deep learning technology can be used to analyze and learn the noise data received by the microphone to establish a more complex noise feature model. This helps the device accurately distinguish between user voice commands and background noise in any environment. The device can be equipped with a user feedback system that allows users to manually correct errors when the device recognizes them. This feedback data can be collected and used to further optimize the noise filtering algorithm to make it more accurate. In addition to noise filtering in preset environments, the device should also be able to adapt to environmental changes in real time. For example, when the user moves from one environment to another, the device can quickly adjust its noise filtering strategy to maintain the efficiency of voice control. In some cases, if multiple voice commands are recognized at the same time, the device should be able to decide which command to execute first based on the preset priority rules, which can avoid command conflicts caused by environmental noise. The voice electric heater's own noise automatic filtering device can not only handle the noise generated by the operation of the electric heater, but also adapt to different usage scenarios more intelligently, providing a more accurate and personalized voice control experience. At the same time, the device's anti-interference ability has also been significantly improved, greatly enhancing the quality of interaction between users and devices.

[0079] In other optional embodiments, after obtaining the target voice data, the device also includes a control unit for generating a voice signal control instruction based on the target voice data, and controlling the operation of the electrical device according to the voice signal control instruction, wherein the voice signal control instruction is a control instruction of the electrical device obtained by converting the voice data sent by the user.

[0080] During the specific implementation process, after the microphone collects the voice signal, the voice chip processor first performs noise filtering to remove the noise generated by the operation of the electric heater itself and other environmental noise, retaining only the clear voice signal from the user. This filtering step is based on noise data collected and stored in advance in different environments to ensure that the user's voice commands can be accurately recognized even in a noisy environment. Next, the processor analyzes the filtered voice signal to identify key words or commands. This process may involve natural language processing technologies such as speech-to-text (STT) and keyword spotting (KWS) to convert the user's voice commands into text form. Instructions in text form are more easily processed by subsequent instruction conversion modules.

[0081] Once the voice command is converted into text, the control command generation module will match it according to the preset command library and convert the user's intention into specific operation instructions, such as "increase the temperature" and "reduce the brightness". This step may require a deep learning or rule matching algorithm to ensure the correctness and accuracy of the command.

[0082] Finally, according to the generated control instructions, the control system of the electrical equipment (such as the electric heater) will perform the corresponding operation and adjust the working state of the equipment. At the same time, the equipment should have a feedback mechanism to broadcast the execution results to the user through the speaker to confirm that the instructions have been executed correctly, thereby enhancing the interactive experience between the user and the equipment. For example, when the user says "increase the temperature", the electric heater should say "the temperature has been raised" after execution.

[0083] In some optional embodiments, the device further comprises a filtering unit for filtering the operating noise of other electrical devices when receiving the operating noise of the other electrical devices, and not generating the voice signal control instruction. The device automatically filters out the operating noise of the device through the above steps, so that when there is only noise, no corresponding control instruction is generated, thereby avoiding the problem of inaccurate audio recognition caused by noise.

[0084] Specifically, the voice electric heater collects and learns the operating noise characteristics of other electrical appliances under different usage environments. This includes but is not limited to the typical noise of household appliances such as TVs, refrigerators, washing machines, and air conditioners. Through deep learning techniques, such as convolutional neural networks (CNN) or recurrent neural networks (RNN), a noise feature database is established to distinguish other electrical noise from user voice commands. When the microphone receives an audio signal, the voice chip processor performs noise detection in real time. The processor uses the previously established noise feature database to quickly classify the received audio signal through a pattern matching algorithm to determine whether it comes from the operating noise of other electrical equipment rather than a voice command issued by the user.

[0085] For signals identified as operating noise from other electrical equipment, the voice chip processor will apply a specific noise filtering algorithm. This may include technologies such as spectrum analysis, noise gate, and adaptive filters to eliminate or reduce the impact of these noises. By adjusting the parameters of the filter, noise in a specific frequency range or mode can be accurately filtered out to ensure the clarity of the user's voice commands. Based on the noise filtering algorithm, the system should also set the priority of the user's voice commands. Even in a complex environment, when the user issues a command, the processor can quickly identify and filter out background noise, prioritize user commands, generate correct voice signal control commands, and control the operation of the electric heater.

[0086] The noise filtering device includes a processor and a memory, wherein the first acquisition unit, the second acquisition unit and the filtering unit are stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions. The modules are all located in the same processor; or, the modules are located in different processors in any combination.

[0087] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the problem of poor user experience caused by the voice function of electrical equipment being greatly affected by noise in the prior art can be solved by adjusting kernel parameters.

[0088] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0089] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the noise filtering method.

[0090] Specifically, the noise filtering method includes:

[0091] Step S201, in a first preset environment, obtaining noise data of the electrical device running in each functional mode, and obtaining first noise data corresponding to each functional mode, wherein the first preset environment represents an environment in which there is no other sound except the electrical device in a preset enclosed space before the electrical device leaves the factory, and the first noise data includes the operating noise of the electrical device;

[0092] Specifically, electrical products and equipment, such as electric heating equipment, are debugged in the factory before they are shipped out of the factory. This solves the problem of interference and misrecognition of user voices caused by the product's own noise during operation, and improves the product's voice human-computer interaction experience. When debugging and using it for the first time, place the product in a quiet environment, that is, the first preset environment mentioned above, and turn on the product to manually control all functional modes one by one. The microphone on the product receives the product's own noise or audio when it is running in each function and mode, and obtains the first noise data.

[0093] Step S202, in a second preset environment, obtaining noise data of the electrical device operating in each of the functional modes, and obtaining second noise data corresponding to each of the functional modes, wherein the second preset environment represents an environment in which the electrical device includes operating noises of multiple other electrical devices in the preset enclosed space before leaving the factory, and the second noise data includes the operating noise of the electrical device and the operating noises of multiple other electrical devices;

[0094] Specifically, after the first debugging, a second debugging is required. During the second debugging, the product is placed in an environment simulating the user's home use, such as an environment with noise or audio from other electrical appliances such as TVs, washing machines, and kitchen cooking. All functional modes of the product are manually controlled one by one, and the operating noise and audio of the electrical product in each mode are stored and memorized through the chip storage and filtering processor to obtain the second noise data.

[0095] Step S203: Filter the first noise data and the second noise data to obtain target voice data, wherein the target voice data is voice data uttered by a user.

[0096] Specifically, when the user is using it, the noise or audio information generated by the product's own operation and other electrical appliances in the house will be automatically filtered and processed by the chip filtering processor. That is to say, the first noise data and the second noise data will be automatically filtered and processed to reduce the interference of the product itself and the surrounding environment noise on the user's voice, and improve the product microphone reception sensitivity and the product human-computer interaction experience.

[0097] An embodiment of the present invention provides an electronic device, including a processor, a memory, and a program stored in the memory and executable on the processor, wherein when the processor executes the program, at least the following steps are implemented:

[0098] Step S201, in a first preset environment, obtaining noise data of the electrical device running in each functional mode, and obtaining first noise data corresponding to each functional mode, wherein the first preset environment represents an environment in which there is no other sound except the electrical device in a preset enclosed space before the electrical device leaves the factory, and the first noise data includes the operating noise of the electrical device;

[0099] Specifically, electrical products and equipment, such as electric heating equipment, are debugged in the factory before they are shipped out of the factory. This solves the problem of interference and misrecognition of user voices caused by the product's own noise during operation, and improves the product's voice human-computer interaction experience. When debugging and using it for the first time, place the product in a quiet environment, that is, the first preset environment mentioned above, and turn on the product to manually control all functional modes one by one. The microphone on the product receives the product's own noise or audio when it is running in each function and mode, and obtains the first noise data.

[0100] Step S202, in a second preset environment, obtaining noise data of the electrical device operating in each of the functional modes, and obtaining second noise data corresponding to each of the functional modes, wherein the second preset environment represents an environment in which the electrical device includes operating noises of multiple other electrical devices in the preset enclosed space before leaving the factory, and the second noise data includes the operating noise of the electrical device and the operating noises of multiple other electrical devices;

[0101] Specifically, after the first debugging, a second debugging is required. During the second debugging, the product is placed in an environment simulating the user's home use, such as an environment with noise or audio from other electrical appliances such as TVs, washing machines, and kitchen cooking. All functional modes of the product are manually controlled one by one, and the operating noise and audio of the electrical product in each mode are stored and memorized through the chip storage and filtering processor to obtain the second noise data.

[0102] Step S203: Filter the first noise data and the second noise data to obtain target voice data, wherein the target voice data is voice data uttered by a user.

[0103] Specifically, when the user is using it, the noise or audio information generated by the product's own operation and other electrical appliances in the house will be automatically filtered and processed by the chip filtering processor. That is to say, the first noise data and the second noise data will be automatically filtered and processed to reduce the interference of the product itself and the surrounding environment noise on the user's voice, and improve the product microphone reception sensitivity and the product human-computer interaction experience.

[0104] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0105] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the method described in each embodiment of the present application:

[0106] Step S201, in a first preset environment, obtaining noise data of the electrical device running in each functional mode, and obtaining first noise data corresponding to each functional mode, wherein the first preset environment represents an environment in which there is no other sound except the electrical device in a preset enclosed space before the electrical device leaves the factory, and the first noise data includes the operating noise of the electrical device;

[0107] Specifically, electrical products and equipment, such as electric heating equipment, are debugged in the factory before they are shipped out of the factory. This solves the problem of interference and misrecognition of user voices caused by the product's own noise during operation, and improves the product's voice human-computer interaction experience. When debugging and using it for the first time, place the product in a quiet environment, that is, the first preset environment mentioned above, and turn on the product to manually control all functional modes one by one. The microphone on the product receives the product's own noise or audio when it is running in each function and mode, and obtains the first noise data.

[0108] Step S202, in a second preset environment, obtaining noise data of the electrical device operating in each of the functional modes, and obtaining second noise data corresponding to each of the functional modes, wherein the second preset environment represents an environment in which the electrical device includes operating noises of multiple other electrical devices in the preset enclosed space before leaving the factory, and the second noise data includes the operating noise of the electrical device and the operating noises of multiple other electrical devices;

[0109] Specifically, after the first debugging, a second debugging is required. During the second debugging, the product is placed in an environment simulating the user's home use, such as an environment with noise or audio from other electrical appliances such as TVs, washing machines, and kitchen cooking. All functional modes of the product are manually controlled one by one, and the operating noise and audio of the electrical product in each mode are stored and memorized through the chip storage and filtering processor to obtain the second noise data.

[0110] Step S203: Filter the first noise data and the second noise data to obtain target voice data, wherein the target voice data is voice data uttered by a user.

[0111] Specifically, when the user is using it, the noise or audio information generated by the product's own operation and other electrical appliances in the house will be automatically filtered and processed by the chip filtering processor. That is to say, the first noise data and the second noise data will be automatically filtered and processed to reduce the interference of the product itself and the surrounding environment noise on the user's voice, and improve the product microphone reception sensitivity and the product human-computer interaction experience.

[0112] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0113] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0114] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0115] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0116] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0117] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0118] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0119] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0120] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0121] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0122] 1) In the noise filtering method of the present application, in the first preset environment, the noise data of the electrical equipment running in each functional mode is obtained, and the first noise data corresponding to each functional mode is obtained, wherein the first preset environment represents an environment in which there is no other sound except the electrical equipment in the preset enclosed space before the electrical equipment leaves the factory, and the first noise data includes the operating noise of the electrical equipment; in the second preset environment, the noise data of the electrical equipment running in each functional mode is obtained, and the second noise data corresponding to each functional mode is obtained, wherein the second preset environment represents an environment in which the electrical equipment includes the operating noise of multiple other electrical equipment in the preset enclosed space before the electrical equipment leaves the factory, and the second noise data includes the operating noise of the electrical equipment and the operating noise of multiple other electrical equipment; the first noise data and the second noise data are filtered to obtain the target voice data. Compared with the existing technology, where the electrical products based on voice control have problems such as insensitive sound reception and easy interference by other noises, the present application can record the noise data under two preset environments respectively before the electrical equipment leaves the factory, and filter out the above noise data when the electrical equipment is running, so as to achieve the purpose of filtering the equipment's own operating noise and the operating environment noise. Therefore, the problem in the prior art that the voice function of electrical equipment is greatly affected by noise, resulting in a poor user experience, can be solved, thereby achieving the purpose of effectively filtering noise.

[0123] 2) In the noise filtering device of the present application, in the first preset environment, the noise data of the electrical equipment running in each functional mode is obtained, and the first noise data corresponding to each functional mode is obtained, wherein the first preset environment represents an environment in which there is no other sound except the electrical equipment in the preset enclosed space before the electrical equipment leaves the factory, and the first noise data includes the operating noise of the electrical equipment; in the second preset environment, the noise data of the electrical equipment running in each functional mode is obtained, and the second noise data corresponding to each functional mode is obtained, wherein the second preset environment represents an environment in which the electrical equipment includes the operating noise of multiple other electrical equipment in the preset enclosed space before the electrical equipment leaves the factory, and the second noise data includes the operating noise of the electrical equipment and the operating noise of multiple other electrical equipment; the first noise data and the second noise data are filtered to obtain the target voice data. Compared with the existing technology, where the electrical products based on voice control have problems such as insensitive sound reception and easy interference by other noises, the present application can record the noise data under two preset environments before the electrical equipment leaves the factory, and filter out the above noise data when the electrical equipment is running, so as to achieve the purpose of filtering the equipment's own operating noise and the operating environment noise. Therefore, the problem in the prior art that the voice function of electrical equipment is greatly affected by noise, resulting in a poor user experience, can be solved, thereby achieving the purpose of effectively filtering noise.

[0124] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A noise filtering method, characterized in that: include: Under a first preset environment, noise data of the electrical device running in each functional mode is obtained to obtain first noise data corresponding to each functional mode, wherein the first preset environment represents an environment in which there is no other sound except the electrical device in a preset enclosed space before the electrical device leaves the factory, and the first noise data includes the operating noise of the electrical device; Under the second preset environment, noise data of the electrical device operating in each of the functional modes is obtained to obtain second noise data corresponding to each of the functional modes, wherein the second preset environment represents an environment in which the electrical device includes operating noises of multiple other electrical devices in the preset enclosed space before leaving the factory, and the second noise data includes the operating noise of the electrical device and the operating noises of multiple other electrical devices; The first noise data and the second noise data are filtered to obtain target voice data, wherein the target voice data is voice data uttered by a user.

2. The noise filtering method according to claim 1, characterized in that: Acquiring noise data of the electrical equipment running in each functional mode to obtain first noise data corresponding to each functional mode includes: receiving a first target operation instruction, and controlling the electrical device to operate in the functional mode corresponding to the first target operation instruction, wherein the first target operation instruction is issued under the first preset environment; The first noise data corresponding to the functional mode is acquired through a microphone, wherein the microphone is included in the electrical device.

3. The noise filtering method according to claim 1, characterized in that: Filtering the first noise data and the second noise data to obtain target speech data includes: Convert the first noise data into first text data, and convert the second noise data into second text data; storing the first text data and the second text data in a text database; When a user voice is received, the first text data and the second text data are filtered from the user voice to obtain the target voice data, wherein the user voice represents audio data issued by the user to instruct the action of the electrical device.

4. The noise filtering method according to claim 3, characterized in that: Filtering the first text data and the second text data from the user voice to obtain the target voice data includes: Determine first spectrum data of the first text data, determine second spectrum data of the second text data, and determine third spectrum data of the user voice; Calculating a difference between the third spectrum data and the first spectrum data to obtain fourth spectrum data, and calculating a difference between the fourth spectrum data and the second spectrum data to obtain fifth spectrum data; The speech data corresponding to the fifth spectrum data is determined to obtain the target speech data.

5. The noise filtering method according to claim 1, characterized in that: Acquiring noise data of the electrical device running in each of the functional modes to obtain second noise data corresponding to each of the functional modes includes: receiving a second target operation instruction, and controlling the electrical device to operate in the functional mode corresponding to the second target operation instruction, wherein the second target operation instruction is issued under the second preset environment; The second noise data corresponding to the functional mode is acquired through a microphone, wherein the microphone is included in the electrical device.

6. The noise filtering method according to claim 1, characterized in that: After obtaining the target voice data, the method further includes: A voice signal control instruction is generated according to the target voice data, and the operation of the electrical device is controlled according to the voice signal control instruction, wherein the voice signal control instruction is a control instruction of the electrical device obtained by converting the voice data sent by the user.

7. The noise filtering method according to claim 6, characterized in that: The method further comprises: When the operating noise of other electrical devices is received, the operating noise of the other electrical devices is filtered and the voice signal control instruction is not generated.

8. A noise filtering device, characterized in that: include: A first acquisition unit is used to acquire noise data of the electrical device running in each functional mode under a first preset environment, and obtain first noise data corresponding to each functional mode, wherein the first preset environment represents an environment in which there is no other sound except the electrical device in a preset enclosed space before the electrical device leaves the factory, and the first noise data includes the operating noise of the electrical device; A second acquisition unit is used to acquire noise data of the electrical device operating in each of the functional modes under a second preset environment, and obtain second noise data corresponding to each of the functional modes, wherein the second preset environment represents an environment in which the electrical device includes operating noises of multiple other electrical devices in the preset enclosed space before leaving the factory, and the second noise data includes the operating noise of the electrical device and the operating noises of multiple other electrical devices; A filtering unit is used to filter the first noise data and the second noise data to obtain target voice data, wherein the target voice data is voice data uttered by a user.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the noise filtering method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing the noise filtering method described in any one of claims 1 to 7.

Images