Open noise reduction system and operation method thereof

Abstract

A noise reduction system (100) is provided. The system comprises: a sound receiving module disposed at a source (104) from which external noise enters so as to receive noise from an external uncontrolled noise source; a sound sensor (106) for recording the received noise; a noise model construction module (108) that constructs a plurality of artificial intelligence models based on a plurality of noise data definitions pre-stored in the database (110); an analysis module (114) that classifies and analyzes the recorded noise by using the plurality of artificial intelligence models and determines the intensity of the recorded noise; an acoustic wave release module (116) that releases a series of reverse acoustic waves and amplitudes based on the amplitudes of the noise; and a user interface (118) that detects continuous intermittent noise and enables a user to control the intensity of noise reduction and notify the user of noise indicative of an emergency situation.

Description

Technical Field

[0001] The embodiments disclosed herein relate to the field of electronics, and more specifically to a noise reduction system and its operating method. Background Technology

[0002] Many public spaces, homes, and business offices are open-plan environments where environmental noise pollution has become a major problem. Common noise sources include roads and highways, airplanes, industrial facilities, factories and plants, air conditioning systems, and swimming pool equipment. One of the disadvantages of open-plan office environments is the difficulty of working or making calls in noisy environments. Ambient noise can impair a user's ability to hear others clearly. Noisy environments can also prevent users from speaking clearly amidst other noise sources.

[0003] Alternatively, staff are forced to relocate to quieter environments free from noise sources. However, such spaces can be quite limited. Reducing ambient noise requires noise-canceling technologies. Some noise control techniques, such as earplugs, thick walls, and sound-absorbing ceiling tiles, are not ideal in many cases. In scenarios requiring noise reduction or suppression, these technologies can be uncomfortable, bulky, aesthetically unappealing, or ineffective. Furthermore, existing active noise-canceling technologies have limited applicability. They are only suitable for very small, enclosed spaces (such as headphones) or for continuous low-frequency sounds (such as mechanical noise). Additionally, noise-canceling headphones are unsuitable for newborns or other noise-sensitive individuals who cannot wear headphones for physical or medical reasons. Moreover, partly due to reliance on complex signal processing algorithms, existing technologies are limited to actively canceling noise within a small range of predictable frequencies.

[0004] For these reasons, existing active noise cancellation technologies are ineffective in many scenarios requiring noise reduction. There is a need for a noise cancellation system that is not limited to the ear and can be freely placed in open spaces like a speaker. Furthermore, there is a need for a noise cancellation system that can be controlled, adjusted, and modified wirelessly via a mobile device with an installed app. Further, there is a need for a system that identifies emergency noises such as smoke alarms without canceling them out.

[0005] Therefore, a noise reduction system and its operation method that can solve the above problems are needed.

[0006] Brief description

[0007] According to one embodiment of this disclosure, a noise reduction system is provided that achieves noise reduction by releasing sound waves to cancel and eliminate the movement paths of sound particles. The noise reduction system includes a sound receiving module, a noise model building module, an analysis module, a sound wave release module, and a user interface. The sound receiving module is located at the source of external noise and configured to receive noise from an external uncontrolled noise source. The sound receiving module includes a sound sensor for recording the noise received from the external uncontrolled noise source. The noise model building module is configured to build multiple artificial intelligence models based on multiple noise data definitions pre-stored in a database. The multiple noise data definitions are a set of frequently occurring noise records. The noise model building module stores the multiple artificial intelligence models back to a model repository. The analysis module is operatively coupled to the sound receiving module and the noise model building module. The analysis module is configured to classify and analyze the recorded noise using the multiple artificial intelligence models. The analysis of the recorded noise includes comparing the noise with multiple sound wave data stored in the database and determining the intensity of the recorded noise based on the analysis of the multiple sound wave data. The sound wave release module is operatively coupled to the analysis module. The acoustic wave release module is configured to release a series of reverse acoustic waves and their amplitudes based on the noise amplitude recorded by a sound sensor, thereby canceling out the received noise. This series of reverse acoustic waves distorts the motion paths of multiple noise particles. The user interface is operatively coupled to the analysis module and the acoustic wave release module. The user interface is configured to detect continuous intermittent noise and allow the user to control the intensity of the noise reduction. The user interface is also configured to notify the user when noise indicating an emergency is detected.

[0008] According to another embodiment, a method for operating a noise reduction system is provided. The method includes: receiving noise from an external uncontrolled noise source via a sound receiving module, and recording the noise received from the external uncontrolled noise source via a sound sensor. The method further includes: constructing multiple artificial intelligence models based on multiple noise data definitions pre-stored in a database via a noise model building module, wherein the multiple noise data definitions are a set of frequently occurring noise records. Further, the method includes: storing the multiple artificial intelligence models back to a model repository via the noise model building module. Additionally, the method includes: analyzing the recorded noise using the multiple artificial intelligence models via an analysis module, wherein the analysis of the recorded noise includes comparing the noise with multiple sound wave data stored in the database. Furthermore, the method includes: determining the intensity of the recorded noise based on the analysis of the multiple sound wave data via the analysis module. Furthermore, the method includes: releasing a series of reverse sound waves and amplitudes based on the amplitude of the noise recorded by the sound sensor via a sound wave release module, thereby canceling the received noise, wherein the series of reverse sound waves distorts the motion paths of multiple noise particles. Furthermore, the method includes: detecting continuous intermittent noise via a user interface, and enabling the user to control the intensity of the noise reduction. In addition, the method includes: notifying the user when noise indicating an emergency is detected through the user interface.

[0009] To further illustrate the advantages and features of this disclosure, a more detailed description of the disclosure will be provided below with reference to specific embodiments, which are illustrated in the accompanying drawings. It should be understood that these drawings depict only typical embodiments of the disclosure and should not be considered as limiting the scope of the disclosure. This disclosure will be described and explained in more specific and detailed manner in conjunction with the accompanying drawings.

[0010] Brief description of the attached figures

[0011] This disclosure will be described and explained in a more specific and detailed manner in conjunction with the accompanying drawings, wherein:

[0012] Figure 1 This is a block diagram illustrating a noise reduction system according to an embodiment of the present disclosure;

[0013] Figure 2 This indicates an embodiment according to the present disclosure. Figure 1 A block diagram of another embodiment of the noise reduction system shown;

[0014] Figure 3 This indicates an embodiment according to the present disclosure. Figure 1 A block diagram illustrating an exemplary embodiment of the noise reduction system architecture shown;

[0015] Figure 4a This indicates an embodiment according to the present disclosure. Figure 1A graphical representation of an exemplary embodiment of sound wave distortion shown;

[0016] Figure 4b This indicates an embodiment according to the present disclosure. Figure 1 A graph illustrating an exemplary embodiment of the sound wave shown;

[0017] Figure 5 This is a block diagram illustrating a computer or server for a noise reduction system according to an embodiment of the present disclosure; and

[0018] Figure 6 It is a flowchart showing the steps involved in the operation of the noise reduction system.

[0019] Furthermore, those skilled in the art will understand that the elements in the accompanying drawings are shown for simplicity and are not necessarily drawn to scale. Additionally, in terms of device construction, one or more components of the device may be represented by conventional symbols in the drawings, and the drawings may only show specific details relevant to understanding embodiments of this disclosure, so as not to obscure the drawings with details that will be readily understood by those skilled in the art upon benefiting from the description herein. Detailed Implementation Plan

[0020] To facilitate understanding of the principles of this disclosure, embodiments illustrated in the accompanying drawings will now be described using specific language. However, it should be understood that this is not intended to limit the scope of this disclosure. Such modifications and further alterations to the illustrated systems, as well as such further applications of the principles of this disclosure, as would normally occur to those skilled in the art, should be construed as falling within the scope of this disclosure.

[0021] The terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a process or method that includes a series of steps may include not only those steps but also other steps not expressly listed or inherent to the process or method. Similarly, a phrase beginning with “comprising…a” to include one or more devices, subsystems, elements, structures, or components does not exclude the presence of other devices, subsystems, elements, structures, components, additional devices, additional subsystems, additional elements, additional structures, or additional components, unless further limitations are desired. Phrases such as “in one embodiment,” “in another embodiment,” and similar expressions appearing throughout this specification may, but do not necessarily, refer to the same embodiment.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains. The systems, methods, and examples provided herein are illustrative only and are not intended to be limiting.

[0023] In the following description and claims, several terms will be used, which should be defined as having the following meanings. The singular forms “a / an” and “the” include plural references, unless the context clearly specifies otherwise.

[0024] Embodiments of this disclosure relate to a noise reduction system that achieves noise reduction by releasing sound waves to distort the path of sound particles. The noise reduction system includes a sound receiving module positioned at the source of external noise entry and configured to receive noise from an external uncontrolled noise source. The sound receiving module includes a sound sensor for recording the noise received from the external uncontrolled noise source. A noise model building module is configured to build multiple artificial intelligence models based on multiple noise data definitions pre-stored in a database. These multiple noise data definitions are sets of frequently occurring noise records. The noise model building module stores the multiple artificial intelligence models back to a model repository. An analysis module is operatively coupled to the sound receiving module and the noise model building module. The analysis module is configured to classify and analyze the recorded noise using the multiple artificial intelligence models. The analysis of the recorded noise includes comparing the noise with multiple sound wave data stored in the database and determining the intensity of the recorded noise based on the analysis of the multiple sound wave data. A sound wave release module and a user interface are operatively coupled to the analysis module. The acoustic wave release module is configured to release a series of reverse acoustic waves and their amplitudes based on the noise amplitude recorded by a sound sensor, thereby canceling out the received noise. This series of reverse acoustic waves distorts the motion paths of multiple noise particles. The user interface is operatively coupled to the analysis module and the acoustic wave release module. The user interface is configured to detect continuous intermittent noise and allow the user to control the intensity of the noise reduction. The user interface is also configured to notify the user when noise indicating an emergency is detected.

[0025] As used herein, the term "noise cancellation" refers to the use of active noise control to reduce unwanted ambient noise. Furthermore, the following... Figure 1 The system described herein is a noise reduction system and its operation method.

[0026] Figure 1This is a block diagram illustrating a noise reduction system (100) according to an embodiment of the present disclosure. The noise reduction system (100) achieves noise reduction by releasing sound waves to distort the path of sound particles. The noise reduction system (100) includes a sound receiving module (102), a noise model building module (108), an analysis module (114), a sound wave release module (116), and a user interface (118). The sound receiving module (102) is located at the source (104) of external noise entry and is configured to receive noise from the external uncontrolled noise source (104). The sound receiving module (102) includes a sound sensor (106) for recording the noise received from the external uncontrolled noise source (104).

[0027] The noise model building module (108) is configured to build multiple artificial intelligence models based on multiple noise data definitions pre-stored in a database (110). These multiple noise data definitions are sets of frequently occurring noise records. The noise model building module (108) saves these multiple artificial intelligence models back to a model repository (112). In one embodiment, the artificial intelligence updates the model repository (112) as different noise data emerges.

[0028] The analysis module (114) is operatively coupled to the sound receiving module (102) and the noise model building module (108). The analysis module (114) is configured to classify and analyze recorded noise using the multiple artificial intelligence models. The analysis of the recorded noise includes comparing the noise with multiple acoustic wave data stored in a database (110). The analysis module (114) is configured to determine the intensity of the recorded noise based on the analysis of the multiple acoustic wave data.

[0029] The acoustic wave release module (116) is operatively coupled to the analysis module (114), wherein the acoustic wave release module (116) is configured to release a series of reverse acoustic waves and amplitudes based on the amplitude of noise recorded by the sound sensor (106), thereby canceling the received noise, wherein the series of reverse acoustic waves distorts the motion paths of multiple noise particles. In one embodiment, the user can reduce external noise, rather than cancel all noise, through a mobile application interface.

[0030] The user interface (118) is operatively coupled to the analysis module (114) and the acoustic wave release module (116). The user interface (118) is configured to detect continuous intermittent noise and enable the user to control the intensity of noise reduction. The user is notified when noise indicating an emergency is detected. In one embodiment, the user interface (118) includes a mobile application interface.

[0031] In one embodiment, noise is recorded for future analysis, and the recorded noise is stored in a central database and subsequently used as a training set by an artificial intelligence model. In another embodiment, the recorded noise is stored in the user's local database. In one embodiment, the noise reduction system (100) may pre-store noise based on the user's residential area. For example, if the user lives near a train station or school, relevant noises are categorized and stored. If a new, unclassified noise is identified, it is automatically classified. The noise reduction device (100) notifies the user of newly incoming noise on the user's device. New incoming sound waves can be canceled or reduced according to the user's needs.

[0032] Figure 2 This indicates an embodiment according to the present disclosure. Figure 1 A block diagram of another embodiment of the noise reduction system (100) shown. This noise reduction system (100) achieves noise reduction by releasing sound waves to distort the path of sound particles. The noise reduction system (100) includes a sound receiving module (102), a noise model building module (108), an analysis module (114), a sound wave release module (116), and a user interface (118). The sound receiving module (102) is located at the source (104) of the external noise and is configured to receive noise from the external uncontrolled noise source (104). The sound receiving module (102) includes a sound sensor (106) for recording the noise received from the external uncontrolled noise source (104).

[0033] In one embodiment, the noise reduction system includes a decibel meter (120) operatively coupled to an analysis module (114) and configured to record residual sound after cancellation. The residual sound does not include human voices or speech. In one embodiment, the noise intensity is calculated on the decibel meter (120) and then controlled by a user interface (118). In one embodiment, the noise reduction system (100) includes an artificial intelligence module (122) configured to store multiple artificial intelligence models and multiple machine learning models. The multiple sound wave data are trained by one of the multiple machine learning models. Furthermore, in one embodiment, the noise reduction system (100) includes a notification module (124) configured to notify a user of an emergency based on the analyzed noise. In another embodiment, the noise reduction system (100) is configured to be installed in a digital device receiving the expected noise. In one embodiment, the noise reduction system (100) may be installed to provide services to various audio devices, such as Bluetooth audio devices, soundbars, headphones, earbuds, etc.

[0034] In one embodiment, the user interface (118) enables artificial intelligence to display the intensity of stored, recorded noise, wherein the display allows the user to control the intensity of noise reduction. In another embodiment, data on frequently incoming noise stored in a repository (112) can be accessed in the noise reduction system (100) to improve the user experience.

[0035] In one embodiment, the noise reduction device (100) is capable of controlling multiple types of noise during peak hours. In one embodiment, the noise reduction system (100) is capable of identifying known noise, such as train, airplane, and other noises pre-stored in the system based on user location. In another embodiment, the noise reduction system (100) can also identify unknown noise not stored in the system database (110). In one embodiment, known noise can be deployed from the cloud edge to the device. Examples of multiple types of noise in one embodiment are as follows:

[0036] • Continuous noise: Continuous noise comes from objects or machines that are constantly running. This type of noise is easily detected and can be seen everywhere in the environment. For example, in a car, the continuous noise from the engine can be heard.

[0037] • Intermittent noise: Intermittent noise occurs infrequently but regularly in daily life. It originates from sudden, loud noises, which are easily noticed but not surprising. For example, someone living near an airport might frequently hear planes taking off and landing. This is a loud noise, but it wouldn't surprise them.

[0038] • Impulsive noise: Impulsive noise has no fixed occurrence pattern and is difficult to predict, more like a sudden, startling sound. For example, when a restaurant waiter accidentally drops a plate, people usually look around to find the source of the noise (104), and the restaurant will temporarily become quiet as a result.

[0039] Low-frequency noise originates from objects in our daily environment. Even in seemingly quiet rooms, its sound level can still reach around 30-40 decibels. For example, in an office environment, noise may come from heating or ventilation systems; in a home, noise may come from the ticking of a clock.

[0040] • Hybrid Noise: Hybrid noise may be a combination of one or more of the four noise types mentioned above. It may also be a new noise type to be classified using artificial intelligence (AI) annotation and classification methods in the future. AI annotation can automatically identify and label objects in images, videos, and text. Classification methods, on the other hand, can annotate the entire image.

[0041] In one embodiment, the noise reduction system (100) includes a command module. This command module is configured to execute commands via voice instructions. In one embodiment, the instructions may include "reduce noise," "eliminate noise," "label noise," etc.

[0042] Figure 3 This indicates an embodiment according to the present disclosure. Figure 1 A block diagram illustrating an exemplary embodiment of the noise reduction system architecture is shown. In one embodiment, a central noise model builder (128) constructs a noise model based on a central noise definition database (126). In one embodiment, if a new type of noise that has not been classified is identified, the new noise is registered in the database (110). The classification of the new noise is done automatically. The noise reduction device (100) notifies the user of the newly incoming noise on the user's device. The new incoming sound wave can be canceled or reduced according to the user's needs. In one embodiment, the noise reduction system (100) includes a control center (130). In one embodiment, after the control center (130) identifies the sound wave on a mobile application, the system notifies the user of the new sound wave and recommends a corresponding reverse sound wave. If the user needs to use the reverse sound wave recommended by the artificial intelligence algorithm of the mobile application to cancel the noise, the reverse sound wave is released into the environment to cancel the noise. The released reverse sound wave cancels the newly registered noise.

[0043] In one embodiment, the incoming noise is analyzed by an analysis module (114). In one embodiment, the analysis module (114) includes an AI noise type classifier (132), an AI noise mathematical equation builder (134), and an AI emitted wave modeler (136). The AI ​​noise mathematical equation builder (134) constructs an equation based on the noise received from the AI ​​noise type classifier (132), and the AI ​​emitted wave modeler (136) determines the amount of sound waves to be emitted based on the equation.

[0044] The AI ​​noise type classifier is an AI model that uses artificial intelligence to classify the collected noise into one of the noise types already identified in the central noise model database (126).

[0045] o AI noise mathematical equation or AI model builder processes and uses acoustic data from AI noise type classifier (132) to create mathematical equations.

[0046] The AI ​​emission wave modeler (136) reverses the mathematical equation or AI model created by the AI ​​noise mathematical equation to generate a sound wave that is the opposite of the original noise wave.

[0047] The noise wave release module (118) is essentially a sound wave emitter that converts the inverse mathematical equation created by the AI ​​emission wave modeler back into an inverse sound wave and emits that sound wave into the surrounding environment to cancel out sound waves in the environment.

[0048] The noise model building module (108) includes:

[0049] o Resident noise definition database: It is a database that can be stored locally on the user's system, storing the most frequently occurring noise records (5 or 10 records).

[0050] The AI-driven continuous new noise learner acts as an observer and records new noise identified by the learner. This learner can also be used if the user wishes to manually label any surrounding sound as noise. It serves as a way to learn new noise through human intervention.

[0051] o Mobile Application Interface Communicator: This is the communication interface between home devices and mobile applications. The mobile application itself is an interface used by end users to customize requests to the device, such as adjusting noise reduction intensity and changing settings.

[0052] o Central Noise Definition Database (126): It is a cloud database that stores every observation data recorded by all individual devices.

[0053] The central AI noise model builder (128) periodically creates different AI models based on noise data definitions in the central noise definition database and saves these models back to the model repository (112) available in the central noise definition database (126). These models are eventually pushed to home devices via edge AI deployment for noise classification.

[0054] Figure 4a This indicates an embodiment according to the present disclosure. Figure 1 A graphical representation of an exemplary embodiment of sound wave distortion shown. Figure 4b This indicates an embodiment according to the present disclosure. Figure 1 A graph illustrating an exemplary embodiment of the sound wave is shown. The following is a non-limiting example of the operating principle of the noise reduction system (100). When sound wave "a)" is generated, the noise reduction system (100) understands and identifies the aforementioned sound category. The sound wave release module (116) releases sound wave b). In this case, the two sound waves cancel each other out, and the user's environment returns to quiet.

[0055] In one embodiment, if a user does not wish to completely cancel out the sound but instead wishes to reduce the volume of the sound / noise, this request can be communicated to the system via the user interface (118). The user interface (118) can provide options for the change request, allowing the user to reduce the sound wave intensity without completely canceling it out. The noise reduction system (100) emits a reverse sound wave with a relatively low amplitude, canceling only a small portion of the total noise, thereby reducing the sound wave intensity. The sound wave intensity can be controlled, adjusted, and changed via the user equipment, and the entire process operates seamlessly.

[0056] In one embodiment, the system also incorporates artificial intelligence, enabling it to perform tasks such as sensing and automatically adjusting to persistent intermittent noise, and sensing different types of noise. Since the noise reduction system (100) can identify and classify sounds, it can also identify important sounds such as smoke alarms. In scenarios where the user is not at home, the system can send a notification to the user interface (118) indicating that the system has detected the sound of a smoke alarm. In one embodiment, the system can be used in emergency situations such as fires, and its training will be of the highest quality, with no compromise on the quality of the training or test data to ensure that the software does not issue false alarm notifications.

[0057] In one embodiment, if the user equipment detects a sound wave and the user agrees to control or cancel the sound wave, the noise reduction system releases a reverse wave into the environment to cancel the noise. In one embodiment, the noise reduction system (100) includes a sound monitoring microphone located at a noise source (104), where the noise source (104) may be a window, door, etc.

[0058] Figure 5 This is a block diagram illustrating a computer or server (300) for a noise reduction system (100) according to an embodiment of the present disclosure. In one embodiment, the computer may be a home device or a digital device. The server (300) includes a processor (302) and a memory (306) operatively coupled to a bus (304).

[0059] As used herein, processor (302) means any type of computing circuit, such as, but not limited to, a microprocessor, a microcontroller, a complex instruction set computing microprocessor, a reduced instruction set computing microprocessor, a very long instruction word microprocessor, an explicit parallel instruction computing microprocessor, a digital signal processor, or any other type of processing circuit, or a combination thereof.

[0060] As used herein, bus (304) refers to an internal memory channel or computer network used to connect computer components and transfer data between them. Bus (304) includes serial bus or parallel bus, wherein serial bus transmits data in a bit-serial format and parallel bus transmits data over multiple lines. As used herein, bus (304) may include, but is not limited to, system bus, internal bus, external bus, expansion bus, front-side bus, back-side bus, etc.

[0061] The memory (306) includes multiple subsystems and modules stored in the form of executable programs that instruct the processor (302) to execute. Figure 1 The method steps are shown. Memory (306) and Figure 1 The noise reduction system (100) shown is basically similar. The noise reduction system (306) includes a sound receiving module (102), a noise model building module (108), an analysis module (114), a sound wave release module (116), and a user interface (118).

[0062] The noise model building module (108) is configured to build multiple artificial intelligence models based on multiple noise data definitions pre-stored in a database (110). These multiple noise data definitions are sets of frequently occurring noise records. The noise model building module (108) saves these multiple artificial intelligence models back to the model repository (112).

[0063] The analysis module (114) is operatively coupled to the sound receiving module (102) and the noise model building module (108). The analysis module (114) is configured to classify and analyze recorded noise using the multiple artificial intelligence models. The analysis of the recorded noise includes comparing the noise with multiple acoustic wave data stored in a database (110). The analysis module (114) is configured to determine the intensity of the recorded noise based on the analysis of the multiple acoustic wave data.

[0064] The acoustic wave release module (116) is operatively coupled to the analysis module (114), wherein the acoustic wave release module (116) is configured to release a series of reverse acoustic waves and amplitudes based on the amplitude of noise recorded by the sound sensor (106) to cancel the received noise, wherein the series of reverse acoustic waves distorts the motion paths of multiple noise particles.

[0065] Computer storage elements may include any suitable storage device for storing data and executable programs, such as read-only memory, random access memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, hard disk, removable media drive for handling memory cards, etc. Embodiments of this subject may be implemented in conjunction with program modules, including functions, procedures, data structures, and application programs for performing tasks or defining abstract data types or underlying hardware environments. Executable programs stored on any of the aforementioned storage media may be executed by a processor (302).

[0066] Figure 6 This is a flowchart illustrating the steps involved in a method (200) for operating a noise reduction system (100) according to an embodiment of the present disclosure. The method (200) includes, in step (202), receiving noise from an external uncontrolled noise source via a sound receiving module and recording the noise received from the external uncontrolled noise source via a sound sensor. The method also includes recording the canceled residual sound via a decibel meter. The residual sound does not include human voice and speech. The method further includes calculating the noise intensity via the decibel meter and controlling it via a user interface. The method also includes storing multiple artificial intelligence models and multiple machine learning models via an artificial intelligence module. The multiple sound wave data are trained by one of the multiple machine learning models. The method also includes notifying the user of an emergency based on the analyzed noise via a notification module. In one embodiment, the noise reduction system is configured to be installed in a digital system receiving the expected noise.

[0067] The method further includes, in step (204), constructing multiple artificial intelligence models based on multiple noise data definitions pre-stored in a database using a noise model building module, wherein the multiple noise data definitions are a set of frequently occurring noise records. The method also includes using the database as a training set for the artificial intelligence models. In another embodiment, the recorded noise is stored in a user's local database.

[0068] Furthermore, the method includes, in step (206), storing the multiple artificial intelligence models back to the model repository via the noise model building module. The method also includes updating the model repository via the artificial intelligence module as different noise data emerges.

[0069] Furthermore, the method includes, in step (208), analyzing the recorded noise using multiple artificial intelligence models via an analysis module, wherein the analysis of the recorded noise includes comparing the noise with multiple acoustic wave data stored in a database.

[0070] Furthermore, the method includes, in step (210), determining the intensity of the recorded noise by an analysis module based on the analysis of the plurality of acoustic wave data. The method also includes analyzing the acoustic waves based on a database storing the recorded noise.

[0071] Furthermore, the method includes, in step (212), releasing a series of reverse sound waves and amplitudes based on the amplitude of the noise recorded by the sound sensor through the sound wave release module, thereby canceling the received noise, wherein the series of reverse sound waves distorts the motion paths of multiple noise particles.

[0072] Furthermore, the method includes, in step (214), detecting continuous intermittent noise via a user interface and enabling the user to control the intensity of noise reduction. The method also includes displaying the intensity of stored, recorded noise, wherein the display enables the user to control the intensity of noise reduction.

[0073] Furthermore, the method includes, in step (216), notifying the user via the user interface when noise indicating an emergency is detected. The method also includes notifying the user via wireless communication. The method further includes notifying the user of the emergency and suggesting that the user control noise reduction.

[0074] In one embodiment, the steps for the artificial intelligence module (122) to identify different sounds are as follows:

[0075] - Sound is recorded by a sound recognition system using sensors that can detect sound. This step allows the model to lay the foundation for further sound processing, such as classifying sounds into different types.

[0076] - Analyze the recorded sound. This means comparing the recorded sound with the data used to train the model. A better training process and higher data quality can provide faster and more accurate predictions.

[0077] - By using a decibel meter to interpret the recorded sound wave type and its intensity, an output is provided to deliver an appropriate sound wave output. The system also stores the recorded sounds in a database (110), which can then be used to accurately locate the sound source (104), determine the sound type, etc., by referencing similar sounds using classification methods. This helps the system update the sound data in a timely manner without relying on training data. The output can use the recorded sounds as reference points.

[0078] Various embodiments of this disclosure enable users to hear clear sound by canceling uncontrolled environmental noise. The noise reduction systems disclosed herein reduce environmental noise on demand. This disclosure prioritizes user comfort, suppressing noise that is uncomfortable, bulky, unsightly, or ineffective. The systems disclosed herein are not limited in their applicability. The systems disclosed herein are suitable for large spaces, even in locations with low- or high-frequency sounds (such as mechanical sounds). The noise cancellation systems disclosed herein allow users to avoid noise in serious medical conditions (such as when headphones cannot be worn, or when patients are bedridden). Furthermore, this system covers a wide range of predictable and unpredictable frequencies.

[0079] Furthermore, the noise cancellation system of this disclosure identifies emergency noises such as smoke alarms without canceling them out. The system disclosed herein is not limited to ear use and can be freely placed in open areas. Moreover, this noise cancellation system can be controlled, adjusted, and modified wirelessly. Wireless devices may include remote controls, mobile phones, etc. Since noise is essentially a sound wave, the noise cancellation system of this disclosure can cancel or reduce it even if it is not detected. As more customers purchase this system, the noise cancellation system becomes increasingly sophisticated. Due to the existence of artificial intelligence, the noise cancellation system can learn and record more data through a universal cloud database. Each time a new sound or noise pattern is identified, the cloud database is updated, and all individual devices can access this cloud database.

[0080] Although this disclosure has been described in specific language, it is not intended to constitute any limitation. Those skilled in the art will understand that various practical modifications can be made to the methods to achieve the inventive concepts taught herein.

[0081] The accompanying drawings and the foregoing description provide examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements can be well combined into a single functional element. Alternatively, some elements can be divided into multiple functional elements. Elements of one embodiment can be added to another embodiment. For example, the order of processes described herein can be changed and is not limited to the manner described herein. Furthermore, the actions in the flowchart need not be performed in the order shown; nor is it necessary to perform all actions. Furthermore, actions that do not depend on other actions can be performed in parallel with other actions. The scope of the embodiments is by no means limited to these specific examples.

Claims

1. An open noise reduction system (100) for noise reduction by releasing sound waves to cancel and eliminate the path of sound particles, wherein, The noise reduction system (100) includes: A sound receiving module (102) is disposed at the source (104) where external noise enters and is configured to receive noise from an external uncontrolled noise source (104), wherein the sound receiving module (102) includes a sound sensor (106) for recording the noise received from the external uncontrolled noise source (104); A noise model building module (108) is configured to build multiple artificial intelligence models based on multiple noise data definitions pre-stored in a database (110). The multiple noise data definitions mentioned above are sets of frequently occurring noise records, and The noise model building module (108) saves the plurality of artificial intelligence models back to the model repository (112); Analysis module (114), which is operatively coupled to the sound receiving module (102) and the noise model building module (108), wherein the analysis module (114) is configured to: The recorded noise is classified and analyzed using the multiple artificial intelligence models, wherein the analysis of the recorded noise includes comparing the noise with multiple acoustic wave data stored in the database (110); and The intensity of the recorded noise is determined based on the analysis of the multiple acoustic wave data. A sound wave release module (116) is operatively coupled to the analysis module (114), wherein the sound wave release module (116) is configured to: Based on the amplitude of the noise recorded by the sound sensor (106), a series of reverse sound waves with varying amplitudes are released to cancel out the received noise, wherein the series of reverse sound waves distorts the motion paths of multiple noise particles; and A user interface (118) operatively coupled to the analysis module (114) and the acoustic wave release module (116), wherein the user interface (118) is configured to: Detects continuous intermittent noise and allows users to control the intensity of noise reduction; and The user is notified when noise indicating an emergency is detected.

2. The noise reduction system (100) of claim 1, comprising a decibel meter (120) operatively coupled to the analysis module (114) and configured to record residual sound after cancellation, wherein the residual sound does not include human voice and speech.

3. The noise reduction system (100) of claim 2, wherein the intensity of the noise is calculated on the decibel meter (120) and then controlled by the user interface (118).

4. The noise reduction system (100) of claim 1, comprising an artificial intelligence module (122), wherein the artificial intelligence module (122) is configured to store a plurality of artificial intelligence models and a plurality of machine learning models, wherein the plurality of acoustic wave data is trained by one of the plurality of machine learning models.

5. The noise reduction system (100) of claim 1, wherein the recorded noise is stored in a database (110) and subsequently used as a training set by the artificial intelligence model.

6. The noise reduction system (100) of claim 1, wherein the recorded noise is stored in the user's local database.

7. The noise reduction system (100) of claim 1, further comprising a notification module (124) configured to notify the user of an emergency based on analyzed noise.

8. The noise reduction system (100) of claim 1, wherein the noise reduction system (100) is configured to be installed in a digital device receiving intended noise.

9. The noise reduction system (100) of claim 1, wherein the user interface (118) enables artificial intelligence to display the intensity of stored recorded noise, wherein the display enables the user to control the intensity of noise reduction.

10. A method (200) for operating an open noise reduction system, wherein the method comprises: Noise is received from an external uncontrolled noise source via a sound receiving module, and the noise received from the external uncontrolled noise source is recorded via a sound sensor; (202) Multiple artificial intelligence models are constructed using a noise model building module based on multiple noise data definitions pre-stored in a database, wherein the multiple noise data definitions are sets of frequently occurring noise records; (204) The noise model building module saves the multiple artificial intelligence models back to the model repository. (206) The recorded noise is analyzed using the multiple artificial intelligence models through the analysis module, wherein the analysis of the recorded noise includes comparing the noise with multiple sound wave data stored in the database; (208) The intensity of the recorded noise is determined by the analysis module based on the analysis of the multiple acoustic wave data. (210) The acoustic wave release module releases a series of reverse acoustic waves and amplitudes based on the amplitude of the noise recorded by the sound sensor to cancel out the received noise, wherein the series of reverse acoustic waves distorts the motion paths of multiple noise particles; (212) Detect continuous intermittent noise through a user interface and enable the user to control the intensity of noise reduction; (214) and The user is notified via the user interface when noise indicating an emergency is detected. (216)

Images