Sound detection method and device, voice system, air conditioner and storage medium

Abstract

The application discloses a sound detection method and device, a voice system, an air conditioner and a storage medium, and belongs to the technical field of sound detection. The method comprises the following steps: acquiring environmental audio in a current environment; determining whether the environmental audio contains noise of a preset type according to a first preset identification model to obtain a first credibility; when the first credibility is less than a first preset credibility threshold value and a difference between the first credibility and the first preset credibility threshold value is less than a preset difference threshold value, prompting information is shown to a user; when a confirmation instruction input by the user based on the prompting information is received, it is determined that the environmental audio contains the noise of the preset type, and the first preset credibility threshold value is updated according to the first credibility. Thus, the default threshold value can be adaptively updated under specific conditions, so that it can be more suitable for the use environment of the user, and the sound detection precision is improved.

Description

Technical Field

[0001] This invention relates to the field of sound detection technology, and in particular to a sound detection method, apparatus, voice system, air conditioner, and storage medium. Background Technology

[0002] Because each user's home layout, decoration, and space size may differ, and users may also use different brands or models of appliances, a default threshold is usually used to identify special types of sounds during sound detection. However, due to these differences, in certain usage scenarios, using the default threshold for identifying special types of sounds may affect the accuracy of sound detection, thereby impacting normal user experience. Summary of the Invention

[0003] The main objective of this invention is to provide a sound detection method, device, voice system, air conditioner, and storage medium, aiming to solve the technical problem that using default thresholds for special types of sound determination in the prior art may affect the accuracy of sound detection.

[0004] To achieve the above objectives, the present invention provides a sound detection method, the sound detection method comprising:

[0005] Get the ambient audio in the current environment;

[0006] Based on the first preset recognition model, it is determined whether the environmental audio contains a preset type of noise to obtain the first confidence level;

[0007] When the first credibility is less than the first preset credibility threshold and the difference between the first credibility and the first preset credibility threshold is less than the preset difference threshold, a prompt message is displayed to the user;

[0008] Upon receiving a confirmation instruction input by the user based on the prompt information, it is determined that the ambient audio contains noise of the preset type, and the first preset confidence threshold is updated according to the first confidence level.

[0009] Optionally, after obtaining the first level of confidence, the method further includes:

[0010] When the first confidence level is greater than or equal to the first preset confidence level threshold, the environmental audio is uploaded to the server so that the server can determine whether the environmental audio contains a preset type of noise according to the second preset recognition model, and obtain the second confidence level. When the second confidence level is greater than or equal to the second preset confidence level threshold, the server will return the first preset result, where the second preset confidence level threshold is greater than the first preset confidence level threshold.

[0011] Upon receiving the first preset result from the server, it is determined that the ambient audio contains noise of the preset type.

[0012] Optionally, after obtaining the first level of confidence, the method further includes:

[0013] When the first confidence level is greater than or equal to the first preset confidence level threshold, the environmental audio is uploaded to the server so that the server can determine whether the environmental audio contains a preset type of noise according to the second preset recognition model and obtain the second confidence level. When the second confidence level is less than the second preset confidence level threshold and the difference between the second confidence level and the second preset confidence level threshold is less than the preset difference threshold, the second preset result is fed back.

[0014] Upon receiving the second preset result from the server, a prompt message is displayed to the user;

[0015] Upon receiving a confirmation instruction input by the user based on the prompt information, it is determined that the ambient audio contains noise of the preset type, and the second preset confidence threshold is updated according to the second confidence level.

[0016] Optionally, after updating the second preset confidence threshold based on the second confidence level, the method further includes:

[0017] The first target value is determined based on the second confidence level and the preset confidence level reduction value;

[0018] The first preset confidence threshold is updated based on the first target value.

[0019] Optionally, after updating the first preset confidence threshold based on the first confidence level, the method further includes:

[0020] The second target value is determined based on the first confidence level and the preset confidence level increment value;

[0021] The second preset confidence threshold is updated based on the second target value.

[0022] Optionally, the method further includes:

[0023] When the ambient audio contains noise of the preset type, an electronic control command is generated according to a preset control strategy.

[0024] The operating status of the air conditioner is adjusted according to the electronic control command.

[0025] Furthermore, to achieve the above objectives, the present invention also proposes a sound detection device, the sound detection device comprising:

[0026] The information acquisition module is used to acquire ambient audio within the current environment;

[0027] A noise recognition module is used to determine whether the ambient audio contains a preset type of noise based on a first preset recognition model, and to obtain a first confidence level.

[0028] The information prompt module is used to display prompt information to the user when the first credibility is less than a first preset credibility threshold and the difference between the first credibility and the first preset credibility threshold is less than a preset difference threshold.

[0029] The threshold update module is used to determine that the ambient audio contains the preset type of noise when it receives a confirmation instruction input by the user based on the prompt information, and to update the first preset confidence threshold according to the first confidence level.

[0030] In addition, to achieve the above objectives, the present invention also proposes a voice system, which includes: a memory, a processor, and a sound detection program stored in the memory and executable on the processor. When the sound detection program is executed by the processor, it implements the sound detection method described above.

[0031] In addition, to achieve the above objectives, the present invention also proposes an air conditioner that includes the voice system described above.

[0032] In addition, to achieve the above objectives, the present invention also proposes a storage medium storing a sound detection program, which, when executed by a processor, implements the sound detection method described above.

[0033] The sound detection method proposed in this invention involves: acquiring ambient audio in the current environment; determining whether the ambient audio contains noise of a preset type based on a first preset recognition model to obtain a first confidence level; displaying a prompt message to the user when the first confidence level is less than a first preset confidence level threshold and the difference between the first confidence level and the first preset confidence level threshold is less than a preset difference threshold; and upon receiving a confirmation command input by the user based on the prompt message, determining that the ambient audio contains noise of the preset type and updating the first preset confidence level threshold based on the first confidence level. This allows for adaptive updates to the default threshold under specific circumstances, making it more suitable for the user's environment and improving the accuracy of sound detection. Attached Figure Description

[0034] Figure 1 This is a schematic diagram of the voice system structure of the hardware operating environment involved in the embodiments of the present invention;

[0035] Figure 2This is a flowchart illustrating the first embodiment of the sound detection method of the present invention;

[0036] Figure 3 This is a flowchart illustrating the second embodiment of the sound detection method of the present invention;

[0037] Figure 4 This is a schematic diagram of the overall judgment logic of an embodiment of the sound detection method of the present invention;

[0038] Figure 5 This is a flowchart illustrating the third embodiment of the sound detection method of the present invention;

[0039] Figure 6 This is a schematic diagram of the functional modules of the first embodiment of the sound detection device of the present invention.

[0040] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0041] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0042] Reference Figure 1 , Figure 1 This is a schematic diagram of the voice system structure of the hardware operating environment involved in the embodiment of the present invention.

[0043] like Figure 1 As shown, the voice system may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and input units such as buttons; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed random access memory (RAM) or non-volatile memory, such as a disk drive. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0044] Those skilled in the art will understand that Figure 1 The device structure shown does not constitute a limitation on the voice system and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0045] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a sound detection program.

[0046] exist Figure 1 In the voice system shown, the network interface 1004 is mainly used to connect to the external network and communicate with other network devices; the user interface 1003 is mainly used to connect to the user equipment and communicate with the user equipment; the device of the present invention calls the sound detection program stored in the memory 1005 through the processor 1001 and executes the sound detection method provided in the embodiment of the present invention.

[0047] Based on the above hardware structure, an embodiment of the sound detection method of the present invention is proposed.

[0048] Reference Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the sound detection method of the present invention.

[0049] In the first embodiment, the sound detection method includes:

[0050] Step S10: Obtain the ambient audio in the current environment.

[0051] It should be noted that the execution entity in this embodiment may be a voice system, which may include a processor and at least one sound detection device. The sound detection device can acquire ambient audio, and the processor can analyze the ambient audio to perform special types of sound detection. This embodiment does not limit this.

[0052] It is understood that the sound detection device in this embodiment may include, but is not limited to, a microphone, and this embodiment does not impose any restrictions on it.

[0053] It should be noted that the voice system in this embodiment can be used in conjunction with the air conditioner to adjust the operating status of the air conditioner based on the sound detection results, thereby controlling the operation of the air conditioner in a way that better suits the user's current usage scenario.

[0054] In one embodiment, the voice system can be separated from the air conditioner; that is, the voice system can be a separate external device, and the air conditioner can be an air conditioner without a voice module. The external voice system performs special types of sound detection and generates electronic control commands based on the sound detection results. These commands are then transmitted to the air conditioner's controller via Bluetooth, wireless network, or wired network, enabling the controller to operate the air conditioner according to the commands.

[0055] In another embodiment, the voice system can be integrated with the air conditioner; that is, the voice system can be a built-in device within the air conditioner, and the air conditioner can be an air conditioner containing a voice module. In this case, the microphone of the voice system can be a microphone installed on the air conditioner, and the processor of the voice system can be integrated on the motherboard corresponding to the air conditioner's controller. The built-in voice system performs characteristic-type sound detection and generates electronic control commands based on the sound detection results. These electronic control commands are then transmitted to the air conditioner's controller via circuit connections on the motherboard, enabling the controller to operate the air conditioner according to the electronic control commands.

[0056] It should be understood that since the voice system in this embodiment needs to be used in conjunction with the air conditioner, sound detection is meaningless if the air conditioner is not turned on. Therefore, in order to avoid wasting resources and improve the user experience, the voice system can be set to automatically start when the air conditioner is turned on and automatically turn off when the air conditioner is turned off, so that the voice system can be turned on or off synchronously with the air conditioner. This embodiment does not impose any restrictions on this.

[0057] It is understandable that the voice system can be activated simultaneously after the air conditioner is turned on. It can use a microphone to record the current environment in real time and send the detected ambient audio to the processor for analysis. The microphone can send the detected ambient audio to the processor in real time, or it can send it at preset intervals. This embodiment does not limit this; in this embodiment, we will use the example of the microphone sending the recorded ambient audio to the processor every 5 seconds as an example.

[0058] It is understood that the current environment can be the space where the air conditioner and voice system are located. For example, the current environment can include, but is not limited to, various spaces that conform to the user's air conditioner usage scenario, such as the kitchen space, the dining space, and the living room space. This embodiment does not limit this. In this embodiment, the current environment is taken as the kitchen space as an example for explanation.

[0059] Step S20: Determine whether the ambient audio contains a preset type of noise based on the first preset recognition model to obtain the first confidence level.

[0060] It should be noted that the first preset recognition model can be a noise recognition model set locally in the voice system. It can determine whether the ambient audio contains a preset type of noise by judging whether the ambient audio has a certain regular relationship between frequency and loudness, and output the first confidence level. In this embodiment, the descriptions of "first" and "second" are only for the convenience of distinguishing different objects and do not constitute other limitations.

[0061] It is understood that the preset type of noise can include, but is not limited to, various types of noise such as the noise of a range hood and the noise of children playing. This embodiment does not limit this. In this embodiment, the noise of a range hood is used as an example of the preset type of noise for explanation.

[0062] Step S30: When the first credibility is less than the first preset credibility threshold and the difference between the first credibility and the first preset credibility threshold is less than the preset difference threshold, a prompt message is displayed to the user.

[0063] It should be noted that the first preset confidence threshold in this embodiment can be a threshold associated with the first preset recognition model. Both the first preset confidence threshold and the preset difference threshold can be preset default thresholds, and this embodiment does not impose any restrictions on them.

[0064] It should be understood that after obtaining the first confidence level, it can be compared with a first preset confidence threshold. If the first confidence level is greater than or equal to a second preset confidence threshold, it indicates that the ambient audio contains noise of a preset type, and the air conditioner needs to be adjusted. If the first confidence level is less than the first preset confidence threshold, it indicates that the ambient audio may not contain noise of the preset type.

[0065] It is understandable that, given the differences in layout, decoration, and space size of each user's home, and the different brands or models of appliances used by users, the thresholds preset at the factory may not be suitable for the current user's usage scenario. Therefore, to avoid affecting the accuracy of sound detection and improve the effect of detecting special sounds, if the first confidence level is less than the first preset confidence level threshold, the difference between the first confidence level and the first preset confidence level threshold can be further calculated and compared with a preset difference threshold.

[0066] If the difference is greater than the preset difference threshold, it means that the gap between the first confidence level and the first preset confidence level threshold is large, and the recognition result is relatively accurate. Therefore, in this case, it can be determined that the ambient audio does not contain the preset type of noise, and there is no need to adjust the air conditioner.

[0067] If the difference is less than the preset difference threshold, it means that the gap between the first confidence level and the first preset confidence level threshold is small, and the first confidence level and the first preset confidence level threshold are relatively close. There may be a situation where the detection is inaccurate due to differences in usage scenarios. Therefore, a prompt message can be displayed to the user so that the user can confirm whether the range hood has been turned on based on the prompt message.

[0068] Step S40: Upon receiving the confirmation instruction input by the user based on the prompt information, determine that the ambient audio contains noise of the preset type, and update the first preset confidence threshold according to the first confidence level.

[0069] It should be understood that if the user denies turning on the range hood, it can be determined that the ambient audio does not contain the preset type of noise, and no adjustment of the air conditioner is required. If the user confirms that the range hood is turned on, it can be determined that the ambient audio contains the preset type of noise, and the air conditioner needs to be adjusted. In this case, the first preset confidence threshold does not conform to the user's usage scenario. Therefore, the original first preset confidence threshold can be replaced based on the first confidence level, thereby achieving the effect of adaptively updating and adjusting the first preset confidence threshold according to the user's actual usage scenario. This makes the voice system more suitable for the user's actual usage scenario and improves the accuracy of sound detection.

[0070] In this embodiment, ambient audio within the current environment is acquired; a first confidence level is obtained by determining whether the ambient audio contains noise of a preset type based on a first preset recognition model; when the first confidence level is less than a first preset confidence level threshold, and the difference between the first confidence level and the first preset confidence level threshold is less than a preset difference threshold, a prompt message is displayed to the user; upon receiving a confirmation command input by the user based on the prompt message, it is determined that the ambient audio contains noise of the preset type, and the first preset confidence level threshold is updated based on the first confidence level. This allows for adaptive updates to the default threshold under specific circumstances, making it more suitable for the user's environment and improving the accuracy of sound detection.

[0071] In one embodiment, such as Figure 3 As shown, based on the first embodiment, a second embodiment of the sound detection method of the present invention is proposed. After step S20, it further includes:

[0072] Step S01: When the first confidence level is greater than or equal to the first preset confidence level threshold, the environmental audio is uploaded to the server so that the server determines whether the environmental audio contains a preset type of noise according to the second preset recognition model, and obtains the second confidence level. When the second confidence level is greater than or equal to the second preset confidence level threshold, the server feeds back the first preset result, where the second preset confidence level threshold is greater than the first preset confidence level threshold.

[0073] It should be noted that, due to cost considerations, the local storage space and processor processing power of the voice system are limited, which may prevent it from supporting overly complex speech recognition models. However, to improve the sound detection effect, this embodiment can also set a second preset recognition model on the server. This second preset recognition model can be a noise recognition model set on the server associated with the voice system. It can determine whether the ambient audio contains a preset type of noise by judging whether the ambient audio has a certain regular relationship between frequency and loudness, and output a second confidence level. The accuracy of the second preset recognition model can be higher than that of the first preset recognition model. More training samples are needed when training the model, but this embodiment does not impose any restrictions on this. Furthermore, the second preset confidence level threshold is also greater than the first preset confidence level threshold, but this embodiment does not impose any restrictions on this either.

[0074] It should be understood that, as Figure 4 As shown, Figure 4 As shown in the overall judgment logic diagram, if the first confidence level is greater than or equal to the first preset confidence level threshold, the voice system's processor can upload the ambient audio to the associated server for secondary detection. The server can analyze the ambient audio using a second preset recognition model and output a second confidence level.

[0075] It should be noted that the second preset confidence threshold in this embodiment can be a threshold associated with the second preset recognition model. Both the second preset confidence threshold and the preset difference threshold can be preset default thresholds, and this embodiment does not impose any restrictions on them.

[0076] It should be understood that after obtaining the second confidence level, the second confidence level can be compared with the second preset confidence level threshold. If the second confidence level is greater than or equal to the second preset confidence level threshold, it means that the ambient audio contains noise of a preset type, and the air conditioner needs to be adjusted. Therefore, the server can feed back a first preset result containing confirmation of the result to the voice system.

[0077] Step S02: Upon receiving the first preset result from the server, determine that the ambient audio contains noise of the preset type.

[0078] It should be understood that if the second confidence level is less than the second preset confidence level threshold, it indicates that the ambient audio may not contain the preset type of noise. However, since the layout, decoration, and space size of each user's home may differ, and users may also use different brands or models of appliances, the thresholds preset at the factory may not be suitable for the current user's usage scenario. Therefore, to avoid affecting the accuracy of sound detection and improve the effect of special sound detection, if the second confidence level is less than the second preset confidence level threshold, the difference between the second confidence level and the second preset confidence level threshold can be further calculated and compared with a preset difference threshold.

[0079] If the difference is greater than the preset difference threshold, it means that the gap between the second confidence level and the second preset confidence level threshold is large, and the recognition result is relatively accurate. Therefore, in this case, it can be determined that the ambient audio does not contain the preset type of noise, and there is no need to adjust the air conditioner. The server can feed back the second preset result containing the result denial to the voice system.

[0080] If the difference is less than the preset difference threshold, it means that the gap between the second confidence level and the second preset confidence level threshold is small, and the second confidence level and the second preset confidence level threshold are relatively close. There may be a situation where the detection is inaccurate due to differences in usage scenarios. Therefore, a prompt message can be displayed to the user so that the user can confirm whether the range hood has been turned on based on the prompt message.

[0081] It should be understood that if the user denies turning on the range hood, it can be determined that the ambient audio does not contain the preset type of noise, and no adjustment of the air conditioner is required. The server can then provide the voice system with a second preset result indicating denial. If the user confirms that the range hood is turned on, it can be determined that the ambient audio contains the preset type of noise, requiring adjustment of the air conditioner. The server can then provide the voice system with a first preset result indicating confirmation. In this case, the second preset confidence threshold does not conform to the user's usage scenario. Therefore, the original second preset confidence threshold can be replaced based on the second confidence threshold, thereby achieving the effect of adaptively updating and adjusting the second preset confidence threshold according to the user's actual usage scenario. This makes the voice system more suitable for the user's actual usage scenario and improves the accuracy of sound detection.

[0082] Understandably, the voice system can perform different operations based on different results from the server. If the server returns a first preset result that confirms the result, it is determined that the ambient audio contains noise of a preset type, and the air conditioner's operating status needs to be adjusted. If the server returns a second preset result that denies the result, it is determined that the ambient audio does not contain noise of a preset type, and the air conditioner's operating status does not need to be adjusted.

[0083] Furthermore, since the sound detection control logic in this solution combines local and cloud detection, as well as manual confirmation by the user when necessary, to improve the accuracy of sound detection, the first preset confidence threshold and the second preset confidence threshold are both important threshold parameters. Therefore, after updating and adjusting one threshold, the other threshold can also be updated and adjusted synchronously, and subsequent sound detection will be based on the updated threshold.

[0084] It should be noted that, when updating and adjusting the first preset credibility threshold, a second target value can be determined based on the first credibility and the preset credibility increment, and then the second preset credibility threshold can be updated and adjusted based on the second target value. Similarly, when updating and adjusting the second preset credibility threshold, a first target value can be determined based on the second credibility and the preset credibility decrement value, and then the first preset credibility threshold can be updated and adjusted based on the first target value.

[0085] In a specific implementation, for example, suppose the first preset confidence threshold is 0.5, the second preset confidence threshold is 0.6, the preset confidence increment is +0.1, and the preset confidence decrement is -0.1.

[0086] If it is necessary to update and adjust the first preset confidence threshold, and the first confidence level is 0.45, then the first preset confidence threshold can be adjusted to 0.45. At the same time, the second target value of 0.55 can be calculated, and the second preset confidence threshold can be adaptively adjusted to 0.55.

[0087] If it is necessary to update and adjust the second preset confidence threshold, and the second confidence level is 0.55, then the second preset confidence threshold can be adjusted to 0.55. Simultaneously, the first target value can be calculated to be 0.45, and the first preset confidence threshold can be adaptively adjusted to 0.45.

[0088] It is understandable that, in addition to the aforementioned methods of updating and adjusting the threshold, to further improve accuracy, after obtaining several reasonably adjusted values, the final value can be determined based on the average of these values. Furthermore, based on the obtained average value, at least one more test can be performed to verify the average value; if the verification passes, this average value can then be used as the final value. This embodiment does not impose any limitations on this approach.

[0089] In this embodiment, when the first confidence level is greater than or equal to a first preset confidence threshold, the environmental audio is uploaded to a server. The server then uses a second preset recognition model to determine whether the environmental audio contains a preset type of noise, obtaining a second confidence level. When the second confidence level is greater than or equal to the second preset confidence threshold, a first preset result is fed back, where the second preset confidence threshold is greater than the first preset confidence threshold. Upon receiving the first preset result from the server, it is determined that the environmental audio contains the preset type of noise. This allows for local analysis of the environmental audio using the first preset recognition model to identify potential preset types of noise, followed by secondary analysis via the cloud. This not only improves the accuracy of sound detection but also saves on equipment costs.

[0090] In one embodiment, such as Figure 5 As shown, a third embodiment of the sound detection method of the present invention is proposed based on the first or second embodiment. In this embodiment, the description is based on the first embodiment. After step S40, the method further includes:

[0091] Step S50: When the ambient audio contains noise of the preset type, generate an electronic control command according to a preset control strategy.

[0092] It's worth noting that controlling the air conditioner in the kitchen has always been a pain point for users. On one hand, kitchens are noisy, and voice recognition is often ineffective. On the other hand, hands are frequently occupied with utensils and other items in the kitchen, making remote control inconvenient.

[0093] The aforementioned sound detection scheme can detect whether the ambient audio in the kitchen contains noise from the range hood when the air conditioner is on. If so, it indicates that the range hood is running, meaning the user is cooking. In this case, the system can automatically adjust the air conditioner's operating parameters, such as mode, temperature, and fan speed. Furthermore, while traditional linkage control systems only guarantee compatibility between appliances of the same brand or protocol, this invention, through special sound detection, actively issues a power control command upon detecting noise from the range hood, regardless of the brand of the air conditioner or range hood, making it universally applicable.

[0094] It should be understood that preset control strategies can be automatically generated based on the user's historical usage, or users can set personalized preset control strategies themselves; this embodiment does not impose any restrictions on this. For example, when noise from the range hood is detected in a kitchen setting, the corresponding preset control strategy can be set to adjust to cooling mode, set the temperature to 18 degrees Celsius, and set the fan speed to maximum.

[0095] Step S60: Adjust the operating status of the air conditioner according to the electronic control command.

[0096] Understandably, after the above-mentioned tests, the voice system can send the generated electronic control commands to the air conditioner's controller, so that the controller can adjust the air conditioner's operating status according to the electronic control commands, enabling the air conditioner to meet the user's needs in the current scenario.

[0097] In practical implementation, to address the issue of unresponsive voice systems in noisy spaces such as kitchens, this method utilizes the built-in microphone of the voice-activated air conditioner. By monitoring ambient noise, if the range hood in the kitchen is detected as being on, the air conditioner automatically switches to cooling mode, sets the temperature to 18 degrees Celsius, and sets the fan speed to maximum.

[0098] In this embodiment, when the ambient audio contains noise of the preset type, an electronic control command is generated according to a preset control strategy; the operating state of the air conditioner is adjusted according to the electronic control command. This allows sound detection to be associated with air conditioner control, and when noise of the preset type is detected, the operating state of the air conditioner is adaptively adjusted. This not only better meets the user's needs, but also demonstrates universal applicability to various brands of air conditioners and range hoods.

[0099] Furthermore, this embodiment of the invention also proposes a storage medium storing a sound detection program, which, when executed by a processor, implements the steps of the sound detection method described above.

[0100] Since this storage medium adopts all the technical solutions of all the above embodiments, it has at least all the beneficial effects brought about by the technical solutions of the above embodiments, which will not be repeated here.

[0101] In addition, refer to Figure 6 The present invention also proposes a sound detection device, the sound detection device comprising:

[0102] The information acquisition module 10 is used to acquire ambient audio within the current environment.

[0103] It is understood that the sound detection device in this embodiment may include, but is not limited to, a microphone, and this embodiment does not impose any restrictions on it.

[0104] It should be noted that the voice system in this embodiment can be used in conjunction with the air conditioner to adjust the operating status of the air conditioner based on the sound detection results, thereby controlling the operation of the air conditioner in a way that better suits the user's current usage scenario.

[0105] In one embodiment, the voice system can be separated from the air conditioner; that is, the voice system can be a separate external device, and the air conditioner can be an air conditioner without a voice module. The external voice system performs special types of sound detection and generates electronic control commands based on the sound detection results. These commands are then transmitted to the air conditioner's controller via Bluetooth, wireless network, or wired network, enabling the controller to operate the air conditioner according to the commands.

[0106] In another embodiment, the voice system can be integrated with the air conditioner; that is, the voice system can be a built-in device within the air conditioner, and the air conditioner can be an air conditioner containing a voice module. In this case, the microphone of the voice system can be a microphone installed on the air conditioner, and the processor of the voice system can be integrated on the motherboard corresponding to the air conditioner's controller. The built-in voice system performs characteristic-type sound detection and generates electronic control commands based on the sound detection results. These electronic control commands are then transmitted to the air conditioner's controller via circuit connections on the motherboard, enabling the controller to operate the air conditioner according to the electronic control commands.

[0107] It should be understood that since the voice system in this embodiment needs to be used in conjunction with the air conditioner, sound detection is meaningless if the air conditioner is not turned on. Therefore, in order to avoid wasting resources and improve the user experience, the voice system can be set to automatically start when the air conditioner is turned on and automatically turn off when the air conditioner is turned off, so that the voice system can be turned on or off synchronously with the air conditioner. This embodiment does not impose any restrictions on this.

[0108] It is understandable that the voice system can be activated simultaneously after the air conditioner is turned on. It can use a microphone to record the current environment in real time and send the detected ambient audio to the processor for analysis. The microphone can send the detected ambient audio to the processor in real time, or it can send it at preset intervals. This embodiment does not limit this; in this embodiment, we will use the example of the microphone sending the recorded ambient audio to the processor every 5 seconds as an example.

[0109] It is understood that the current environment can be the space where the air conditioner and voice system are located. For example, the current environment can include, but is not limited to, various spaces that conform to the user's air conditioner usage scenario, such as the kitchen space, the dining space, and the living room space. This embodiment does not limit this. In this embodiment, the current environment is taken as the kitchen space as an example for explanation.

[0110] The noise recognition module 20 is used to determine whether the ambient audio contains a preset type of noise based on a first preset recognition model, and to obtain a first confidence level.

[0111] It should be noted that the first preset recognition model can be a noise recognition model set locally in the voice system. It can determine whether the ambient audio contains a preset type of noise by judging whether the ambient audio has a certain regular relationship between frequency and loudness, and output the first confidence level. In this embodiment, the descriptions of "first" and "second" are only for the convenience of distinguishing different objects and do not constitute other limitations.

[0112] It is understood that the preset type of noise can include, but is not limited to, various types of noise such as the noise of a range hood and the noise of children playing. This embodiment does not limit this. In this embodiment, the noise of a range hood is used as an example of the preset type of noise for explanation.

[0113] The information prompt module 30 is used to display prompt information to the user when the first credibility is less than a first preset credibility threshold and the difference between the first credibility and the first preset credibility threshold is less than a preset difference threshold.

[0114] It should be noted that the first preset confidence threshold in this embodiment can be a threshold associated with the first preset recognition model. Both the first preset confidence threshold and the preset difference threshold can be preset default thresholds, and this embodiment does not impose any restrictions on them.

[0115] It should be understood that after obtaining the first confidence level, it can be compared with a first preset confidence threshold. If the first confidence level is greater than or equal to a second preset confidence threshold, it indicates that the ambient audio contains noise of a preset type, and the air conditioner needs to be adjusted. If the first confidence level is less than the first preset confidence threshold, it indicates that the ambient audio may not contain noise of the preset type.

[0116] It is understandable that, given the differences in layout, decoration, and space size of each user's home, and the different brands or models of appliances used by users, the thresholds preset at the factory may not be suitable for the current user's usage scenario. Therefore, to avoid affecting the accuracy of sound detection and improve the effect of detecting special sounds, if the first confidence level is less than the first preset confidence level threshold, the difference between the first confidence level and the first preset confidence level threshold can be further calculated and compared with a preset difference threshold.

[0117] If the difference is greater than the preset difference threshold, it means that the gap between the first confidence level and the first preset confidence level threshold is large, and the recognition result is relatively accurate. Therefore, in this case, it can be determined that the ambient audio does not contain the preset type of noise, and there is no need to adjust the air conditioner.

[0118] If the difference is less than the preset difference threshold, it means that the gap between the first confidence level and the first preset confidence level threshold is small, and the first confidence level and the first preset confidence level threshold are relatively close. There may be a situation where the detection is inaccurate due to differences in usage scenarios. Therefore, a prompt message can be displayed to the user so that the user can confirm whether the range hood has been turned on based on the prompt message.

[0119] The threshold update module 40 is used to determine that the ambient audio contains the preset type of noise when it receives the confirmation instruction input by the user based on the prompt information, and to update the first preset confidence threshold according to the first confidence level.

[0120] It should be understood that if the user denies turning on the range hood, it can be determined that the ambient audio does not contain the preset type of noise, and no adjustment of the air conditioner is required. If the user confirms that the range hood is turned on, it can be determined that the ambient audio contains the preset type of noise, and the air conditioner needs to be adjusted. In this case, the first preset confidence threshold does not conform to the user's usage scenario. Therefore, the original first preset confidence threshold can be replaced based on the first confidence level, thereby achieving the effect of adaptively updating and adjusting the first preset confidence threshold according to the user's actual usage scenario. This makes the voice system more suitable for the user's actual usage scenario and improves the accuracy of sound detection.

[0121] In this embodiment, ambient audio within the current environment is acquired; a first confidence level is obtained by determining whether the ambient audio contains noise of a preset type based on a first preset recognition model; when the first confidence level is less than a first preset confidence level threshold, and the difference between the first confidence level and the first preset confidence level threshold is less than a preset difference threshold, a prompt message is displayed to the user; upon receiving a confirmation command input by the user based on the prompt message, it is determined that the ambient audio contains noise of the preset type, and the first preset confidence level threshold is updated based on the first confidence level. This allows for adaptive updates to the default threshold under specific circumstances, making it more suitable for the user's environment and improving the accuracy of sound detection.

[0122] Other embodiments or specific implementation methods of the sound detection device described in this invention can refer to the above-described method embodiments, and will not be repeated here.

[0123] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0124] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0125] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This estimation machine software product is stored in an estimation machine readable storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a smart device (which may be a mobile phone, estimation machine, voice system, or network voice system, etc.) to execute the methods described in the various embodiments of the present invention.

[0126] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A sound detection method, characterized in that, The sound detection method includes: Get the ambient audio in the current environment; The first preset recognition model is used to determine whether the ambient audio contains a preset type of noise based on a first preset recognition model, thereby obtaining a first confidence level. The first preset recognition model is used to determine whether the ambient audio contains a preset type of noise by judging whether there is a regular relationship between frequency and loudness. The preset type of noise includes the noise of a range hood. When the first credibility level is less than a first preset credibility threshold, and the difference between the first credibility level and the first preset credibility threshold is less than a preset difference threshold, a prompt message is displayed to the user; and Upon receiving a confirmation instruction input by the user based on the prompt information, it is determined that the ambient audio contains noise of the preset type, and the first preset confidence threshold is updated according to the first confidence level. After obtaining the first level of confidence, the process also includes: When the first confidence level is greater than or equal to the first preset confidence level threshold, the environmental audio is uploaded to the server, so that the server determines whether the environmental audio contains a preset type of noise according to the second preset recognition model, and obtains a second confidence level. When the second confidence level is greater than or equal to the second preset confidence level threshold, a first preset result is fed back, wherein the second preset confidence level threshold is greater than the first preset confidence level threshold; and Upon receiving the first preset result from the server, it is determined that the ambient audio contains noise of the preset type.

2. The sound detection method as described in claim 1, characterized in that, After obtaining the first level of confidence, the process also includes: When the second confidence level is less than the second preset confidence level threshold and the difference between the second confidence level and the second preset confidence level threshold is less than the preset difference threshold, the second preset result is fed back. Upon receiving the second preset result from the server, a prompt message is displayed to the user; and Upon receiving a confirmation instruction input by the user based on the prompt information, it is determined that the ambient audio contains noise of the preset type, and the second preset confidence threshold is updated according to the second confidence level.

3. The sound detection method as described in claim 2, characterized in that, After updating the second preset confidence threshold based on the second confidence level, the method further includes: A first target value is determined based on the second confidence level and the preset confidence level reduction value; and The first preset confidence threshold is updated based on the first target value.

4. The sound detection method as described in claim 1, characterized in that, After updating the first preset confidence threshold based on the first confidence level, the method further includes: A second target value is determined based on the first confidence level and the preset confidence level increment value; and The second preset confidence threshold is updated based on the second target value.

5. The sound detection method according to any one of claims 1 to 4, characterized in that, The method further includes: When the ambient audio contains noise of the preset type, an electronic control command is generated according to a preset control strategy; and The operating status of the air conditioner is adjusted according to the electronic control command.

6. A sound detection device, characterized in that, The sound detection device performs the sound detection method as described in any one of claims 1 to 5, and the sound detection device comprises: The information acquisition module is used to acquire ambient audio within the current environment; The noise recognition module is used to determine whether the ambient audio contains a preset type of noise based on a first preset recognition model, and to obtain a first confidence level. The first preset recognition model is used to determine whether the ambient audio contains a preset type of noise by judging whether there is a regular relationship between frequency and loudness in the ambient audio. The preset type of noise includes the noise of the range hood. The information prompt module is used to display a prompt message to the user when the first credibility is less than a first preset credibility threshold and the difference between the first credibility and the first preset credibility threshold is less than a preset difference threshold; and The threshold update module is used to determine that the ambient audio contains the preset type of noise when it receives a confirmation instruction input by the user based on the prompt information, and update the first preset confidence threshold according to the first confidence level. After obtaining the first level of confidence, the process also includes: When the first confidence level is greater than or equal to the first preset confidence level threshold, the environmental audio is uploaded to the server, so that the server determines whether the environmental audio contains a preset type of noise according to the second preset recognition model, and obtains a second confidence level. When the second confidence level is greater than or equal to the second preset confidence level threshold, a first preset result is fed back, wherein the second preset confidence level threshold is greater than the first preset confidence level threshold; and Upon receiving the first preset result from the server, it is determined that the ambient audio contains noise of the preset type.

7. A voice system, characterized in that, The voice system includes: a memory, a processor, and a sound detection program stored in the memory and executable on the processor, wherein the sound detection program, when executed by the processor, implements the sound detection method as described in any one of claims 1 to 5.

8. An air conditioner, characterized in that, The air conditioner includes the voice system as described in claim 7.

9. A storage medium, characterized in that, The storage medium stores a sound detection program, which, when executed by a processor, implements the sound detection method as described in any one of claims 1 to 5.

Images