Audio data processing method and apparatus, and home appliance

Abstract

The application discloses an audio data processing method and device and household electrical appliances. The method comprises the following steps: obtaining a first reference energy value, wherein the first reference energy value is an energy value determined by a reference device when the reference device listens to test audio in a test environment; listening to the test audio in the test environment, and determining an energy value when the test audio is listened to as an original energy value; and calculating a first compensation value for the to-be-compensated device based on the first reference energy value and the original energy value, wherein the first compensation value is used for correcting an original energy value determined by the to-be-compensated device when the to-be-compensated device listens to wake-up audio. The technical scheme provided by the application can improve the accuracy of responding to wake-up audio when a device listens to the wake-up audio.

Description

Technical Field

[0001] This application belongs to the field of audio data processing technology, and in particular relates to an audio data processing method, apparatus and household appliance. Background Technology

[0002] With the maturity of voice recognition technology, home appliances with intelligent voice functions are beginning to enter users' homes. When users use intelligent voice functions, they must first wake up the device using a wake-up word. Whether the wake-up is successful depends on the wake-up energy value input by the user's voice. However, due to differences in the installation of the hardware (such as microphones) for listening to wake-up voices within the devices, or due to differences in the hardware itself (such as differences in the microphone's placement or structure), there may be a problem where devices that are far away are woken up by the user's wake-up command. Summary of the Invention

[0003] The embodiments of this application provide an audio data processing method, apparatus, and home appliance, which can at least to some extent improve the accuracy of responding to wake-up audio when the device is listening to wake-up audio.

[0004] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0005] According to a first aspect of the embodiments of this application, an audio data processing method is provided, the method being executed on any device to be compensated, the method comprising: obtaining a first reference energy value, the first reference energy value being an energy value determined by a reference device when listening to test audio in a test environment; listening to the test audio in the test environment and determining the energy value when listening to the test audio as an original energy value; and calculating a first compensation value for the device to be compensated based on the first reference energy value and the original energy value, the first compensation value being used to correct the original energy value determined by the device to be compensated when listening to wake-up audio.

[0006] In some embodiments of this application, based on the foregoing scheme, after calculating the first compensation value for the device to be compensated, the method further includes: listening to a first wake-up audio and determining the original energy value when listening to the first wake-up audio as the target original energy value; and correcting the target original energy value using the first compensation value to obtain a first theoretical energy value.

[0007] In some embodiments of this application, based on the foregoing scheme, after obtaining the first theoretical energy value, the method further includes: obtaining the first theoretical energy value determined by other devices to be compensated in the same area when listening to the first wake-up audio; selecting the device to be compensated with the largest first theoretical energy value among the various devices to be compensated as the target response device in response to the first wake-up audio.

[0008] In some embodiments of this application, based on the foregoing scheme, after obtaining the first theoretical energy value, the method further includes: uploading the first theoretical energy value to the server so that the server smooths the first theoretical energy values ​​uploaded by each device to be compensated of the same model to obtain a second reference energy value, and calculates a second compensation value for each device to be compensated based on the second reference energy value and the first theoretical energy value; obtaining the second compensation value issued by the server, wherein the second compensation value is used to correct the first theoretical energy value determined by the device to be compensated when listening to the wake-up audio.

[0009] In some embodiments of this application, based on the foregoing scheme, after obtaining the second compensation value issued by the server, the method further includes: listening to the second wake-up audio and determining the first theoretical energy value when listening to the second wake-up audio as the target first theoretical energy value; and correcting the target first theoretical energy value through the second compensation value to obtain the second theoretical energy value.

[0010] In some embodiments of this application, based on the foregoing scheme, after obtaining the second theoretical energy value, the method further includes: obtaining the second theoretical energy value determined by other devices to be compensated in the same area when listening to the second wake-up audio; selecting the device to be compensated with the largest second theoretical energy value among the various devices to be compensated as the target response device in response to the second wake-up audio.

[0011] According to a second aspect of the embodiments of this application, an audio data processing method is also provided. The method is executed on a server and includes: acquiring a first theoretical energy uploaded by various devices of the same model to be compensated; smoothing each of the first theoretical energy values ​​to obtain a second reference energy value; calculating a second compensation value for each device to be compensated based on the second reference energy value and the first theoretical energy uploaded by each device to be compensated; and sending each of the second compensation values ​​to each device to be compensated, wherein the second compensation value is used to correct the first theoretical energy value determined by the device to be compensated when listening to wake-up audio.

[0012] According to a third aspect of the embodiments of this application, an audio data processing apparatus is provided. The apparatus is disposed in any device to be compensated. The apparatus includes: a first acquisition unit, configured to acquire a first reference energy value, wherein the first reference energy value is an energy value determined by a reference device when listening to test audio in a test environment; a monitoring unit, configured to monitor the test audio in the test environment and determine the energy value when monitoring the test audio as an original energy value; and a first calculation unit, configured to calculate a first compensation value for the device to be compensated based on the first reference energy value and the original energy value, wherein the first compensation value is used to correct the original energy value determined by the device to be compensated when listening to wake-up audio.

[0013] According to a fourth aspect of the embodiments of this application, an audio data processing apparatus is provided. The apparatus is disposed on a server and includes: a second acquisition unit, configured to acquire first theoretical energy uploaded by various devices of the same model to be compensated; a smoothing processing unit, configured to smooth each of the first theoretical energy values ​​to obtain a second reference energy value; a second calculation unit, configured to calculate a second compensation value for each device to be compensated based on the second reference energy value and the first theoretical energy uploaded by each device to be compensated; and a distribution unit, configured to distribute each of the second compensation values ​​to each device to be compensated, wherein the second compensation value is used to correct the first theoretical energy value determined by the device to be compensated when listening to wake-up audio.

[0014] According to a fifth aspect of the embodiments of this application, a home appliance is provided, the home appliance including one or more processors and one or more memories, the one or more memories storing at least one piece of program code, the at least one piece of program code being loaded and executed by the one or more processors to implement the method described in any of the embodiments of the first aspect above.

[0015] In this application, the original energy value of the device to be compensated is determined by listening to test audio in a test environment. Then, based on the obtained first reference energy value and the original energy value, a first compensation value is calculated for the device to be compensated to correct the original energy value determined when listening to wake-up audio. After the device is officially put into use, the determined original energy value is corrected by the first compensation value, which avoids the problem of inaccurate energy value determination caused by differences in the installation of listening devices between different devices, thereby improving the accuracy of the device's response to wake-up audio when listening to wake-up audio.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0018] Figure 1 A schematic diagram of an exemplary system architecture to which the technical solutions of the embodiments of this application can be applied is shown;

[0019] Figure 2 A flowchart of an audio data processing method according to an embodiment of this application is shown;

[0020] Figure 3 Another flowchart of the audio data processing method in an embodiment of this application is shown;

[0021] Figure 4 An overall flowchart of the audio data processing method in an embodiment of this application is shown;

[0022] Figure 5 A block diagram of an audio data processing apparatus according to an embodiment of this application is shown;

[0023] Figure 6 A block diagram of an audio data processing apparatus according to an embodiment of this application is shown;

[0024] Figure 7 A schematic diagram of the structure of a household appliance in an embodiment of this application is shown. Detailed Implementation

[0025] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0026] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0027] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0028] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0029] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "multiple" means two or more.

[0030] Figure 1 A schematic diagram of an exemplary system architecture to which the technical solutions of the embodiments of this application can be applied is shown.

[0031] like Figure 1 As shown, the system architecture may include home appliance 101, network 102, and server (e.g., cloud 103). Network 102 serves as the medium for providing a communication link between home appliance 101 and cloud 103. Network 102 may include various connection types, such as wired communication links, wireless communication links, etc.

[0032] In one embodiment of this application, the proposed audio data processing scheme can be applied to any device to be compensated (e.g., it can be such as...). Figure 1 The home appliance 1 shown can also be home appliance 2). Specifically, home appliance 1 can obtain a first reference energy value before leaving the factory. The first reference energy value can be an energy value determined by a reference device when listening to test audio in a test environment. Further, home appliance 1 can listen to the test audio in the test environment and determine the energy value when listening to the test audio as the original energy value. Finally, home appliance 1 calculates a first compensation value for the home appliance to correct the original energy value determined when listening to the wake-up audio, based on the first reference energy value and the original energy value.

[0033] Furthermore, in one embodiment of this application, during actual use, each home appliance can upload the first theoretical energy value obtained after correction by the first compensation value to the server (e.g., the cloud). The server then smooths the first theoretical energy values ​​uploaded by each home appliance of the same model to obtain a second reference energy value. Based on the second reference energy value and the first theoretical energy value, the server calculates the second compensation value for each home appliance. The second compensation value can be used to correct the first theoretical energy value determined by the home appliance when listening to the wake-up audio, thus obtaining the second theoretical energy value.

[0034] In this application, it should be noted that the wake-up audio can refer to the audio used by the user to wake up the smart voice function of the device. For example, in a scenario where each home appliance (e.g., multiple air conditioners) is equipped with voice recognition, if a user wants to turn on the nearest appliance via voice command, they need to wake it up with a voice message (i.e., the wake-up audio, such as "Hello, hello"). Each appliance can then determine whether it should be woken up based on a first theoretical energy value or a second theoretical energy value. After the appliance is woken up, the user can continue to issue voice commands to it.

[0035] In this application, the original energy value of the device to be compensated is determined by listening to test audio in a test environment. Then, based on the obtained first reference energy value and the original energy value, a first compensation value is calculated for the device to be compensated to correct the original energy value determined when listening to wake-up audio. After the device is officially put into use, the determined original energy value is corrected by the first compensation value, which avoids the problem of inaccurate energy value determination caused by differences in the installation of listening devices between different devices, thereby improving the accuracy of the device's response to wake-up audio when listening to wake-up audio.

[0036] It should be noted that the audio data processing method provided in this application embodiment can be executed by the home appliance 101. Accordingly, the audio data processing device is generally installed in the home appliance 101.

[0037] It should also be noted that, Figure 1 The number of home appliances, networks, and cloud devices mentioned is merely illustrative. The cloud primarily provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0038] It's important to explain that cloud computing, as described above, is a computing model that distributes computing tasks across a resource pool comprised of numerous computers, enabling various application systems to access computing power, storage space, and information services as needed. The network providing these resources is called the "cloud." From the user's perspective, the resources in the "cloud" appear infinitely scalable and can be accessed, used on demand, and expanded at any time. By establishing a cloud computing resource pool (referred to as a cloud platform, generally called an IaaS (Infrastructure as a Service) platform), various types of virtual resources are deployed within the resource pool for external customers to choose from. The cloud computing resource pool mainly includes: computing devices (virtualized machines containing operating systems), storage devices, and network devices.

[0039] It should also be noted in this application that the home appliances mentioned in this application may be air conditioners, washing machines, refrigerators, robot vacuum cleaners, etc.

[0040] The implementation details of the technical solutions in the embodiments of this application will be described in detail from multiple perspectives below:

[0041] This explanation is from the perspective of the device to be compensated.

[0042] Reference Figure 2 The diagram illustrates a flowchart of an audio data processing method according to an embodiment of this application. This audio data processing method can be executed by a device with computational processing capabilities, such as any device to be compensated (e.g., Figure 1 The household appliance shown in Figure 1) is used to perform this action. (Refer to...) Figure 2 As shown, the audio data processing method includes at least steps 210 to 230, which are described in detail below:

[0043] Step 210: Obtain the first reference energy value, which is the energy value determined by the reference device when listening to test audio in the test environment.

[0044] Step 220: Listen to the test audio in the test environment and determine the energy value when listening to the test audio as the original energy value.

[0045] Step 230: Based on the first reference energy value and the original energy value, calculate a first compensation value for the device to be compensated. The first compensation value is used to correct the original energy value determined by the device to be compensated when listening to the wake-up audio.

[0046] In this application, because the monitoring devices (such as microphones) used to listen for wake-up voices are installed in different locations or with different numbers of microphones in different devices, the energy values ​​determined by each device when a sound source at the same distance from the device emits a sound to each device may differ. This can lead to the problem that when a user tries to wake up a device, a device that is farther away may be woken up instead. For example, at home, a user in the living room might try to wake up the living room air conditioner, but the air conditioner in the bedroom might be woken up instead.

[0047] Based on this, the energy value of the reference device when listening to the test audio can be determined first under a standard test environment, and this energy value can be used as the first reference energy value. Before leaving the factory, the device (i.e., the device to be compensated) can first obtain the first reference energy value, and then determine the energy value when listening to the test audio under the same standard test environment, as the original energy value. Finally, based on the first reference energy value and the original energy value, the first compensation value is calculated and recorded in the device to be compensated.

[0048] After leaving the factory, the device to be compensated can correct the original energy value determined when monitoring the wake-up audio using a first compensation value during actual use, thereby obtaining a first theoretical energy value. This allows the device to compare its own determined first theoretical energy value with the first theoretical energy values ​​determined by other devices, ultimately determining whether it should be woken up. In this way, the problem of inaccurate wake-up audio responses caused by differences in the installation of monitoring devices in various devices can be largely solved.

[0049] It should be noted that the test audio mentioned above can be a standard audio preset according to the set audio and EQ parameters.

[0050] In such Figure 2 In one embodiment of step 210, the first reference energy value may be multiple energy values ​​determined by the reference device during multiple listening tests in a standard test environment, and the average of these multiple energy values ​​is calculated to obtain the first reference energy value. Alternatively, the test audio may be sampled, the energy value of each sampling point is determined, and the energy values ​​of each sampling point are then averaged to obtain the first reference energy value.

[0051] In this embodiment, the test audio is sampled either at equal time intervals or randomly; this application does not limit the sampling method. Each sampling point yields an energy value. Finally, the first reference energy value is obtained by averaging the energy values ​​from all sampling points.

[0052] It should be noted that the test audio can be sampled using a continuous peak sampling (i.e., taking the peak value of each frame of audio) algorithm.

[0053] In this application, by sampling the test audio and taking the average value of the energy values ​​at each sampling point as the first reference energy value, the advantage is that the accuracy of determining the first reference energy value can be improved.

[0054] In such Figure 2 In one embodiment of step 220 shown, the test audio is monitored in a test environment. The energy value of the test audio being monitored can be determined after the energy value of the test audio monitored by the compensation device reaches a set threshold.

[0055] Furthermore, the device to be compensated may sample the test audio and determine the energy value of each sampling point, and then average the energy values ​​of each sampling point to obtain the original energy value.

[0056] In such Figure 2 In one embodiment of step 230 shown, a first compensation value is calculated for the device to be compensated based on the first reference energy value and the original energy value. This can be achieved by using the difference between the first reference energy value and the original energy value as the first compensation value.

[0057] For example, with Figure 1 Taking the system architecture shown as an example, firstly, the energy value of the baseline device when listening to the test audio is tested, for example, 580,000. Then, the energy values ​​of appliance 1 and appliance 2 when listening to the test audio are tested separately, for example, appliance 1 is 600,000 and appliance 2 is 560,000. Then, the first compensation value of appliance 1 can be calculated as 580,000 - 600,000 = -20,000, and the first compensation value of appliance 2 is 580,000 - 560,000 = 20,000. This solution can largely eliminate the impact caused by differences in the installation of the monitoring devices in each device.

[0058] In such Figure 2 After step 230, i.e. after calculating the first compensation value for the device to be compensated, steps 241 to 242 can also be performed:

[0059] Step 241: Listen to the first wake-up audio and determine the original energy value when listening to the first wake-up audio as the target original energy value.

[0060] Step 242: Correct the original target energy value using the first compensation value to obtain the first theoretical energy value.

[0061] In this application, continue to use Figure 1 Taking the system architecture shown as an example, after determining the first compensation value corresponding to home appliance 1, home appliance 1 can be shipped from the factory and put into formal use. When the first wake-up audio issued by the user is heard (such as hearing the wake-up voice of "hello hello"), the original energy value when listening to the first wake-up audio can be determined. For example, if the original energy value is 600,000, and the first compensation value is -40,000, then the first theoretical energy value is calculated to be 600,000 - 40,000 = 560,000.

[0062] In this application, after obtaining the first theoretical energy value, steps 243 to 244 may also be performed:

[0063] Step 243: Obtain the first theoretical energy value determined by other devices to be compensated in the same area when listening to the first wake-up audio.

[0064] Step 244: Select the device with the largest first theoretical energy value from among the various devices to be compensated, and use it as the target response device to respond to the first wake-up audio.

[0065] In this application, continue to use Figure 1 Taking the system architecture shown as an example, home appliance 1 and home appliance 2 belong to the same area (for example, both are installed in the same home). When the user issues the first wake-up audio, the first theoretical energy value determined by home appliance 1 is 560,000, and the first theoretical energy value determined by home appliance 2 is 520,000. Since the first theoretical energy value determined by home appliance 1 is the largest, it means that home appliance 1 is closest to the user. Therefore, home appliance 1 is determined as the target response device to respond to the first wake-up audio.

[0066] In this application, by correcting the determined original energy value through the first compensation value of each household appliance, the influence caused by the difference in the installation of the listening device in each household appliance can be largely eliminated, thereby improving the accuracy of the response to the wake-up audio when the household appliances listen to the wake-up audio.

[0067] Furthermore, in this application, after obtaining the first theoretical energy value, the following steps 251 to 252 may also be performed:

[0068] Step 251: Upload the first theoretical energy value to the server so that the server can smooth the first theoretical energy values ​​uploaded by each device to be compensated of the same model to obtain a second reference energy value, and calculate the second compensation value for each device to be compensated based on the second reference energy value and the first theoretical energy value.

[0069] Step 252: Obtain the second compensation value issued by the server. The second compensation value is used to correct the first theoretical energy value determined by the device to be compensated when listening to the wake-up audio.

[0070] Once the device is manufactured and put into use, it can upload the first theoretical energy value to the server, and the server can obtain the first theoretical energy value determined when each device listens to the wake-up audio through the interface established with the device.

[0071] In this application, the server can smooth the first theoretical energy values ​​uploaded by various devices of the same model to obtain a second reference energy value. For example, it can smooth the first theoretical energy values ​​uploaded by air conditioners of the same model to obtain the second reference energy value corresponding to that model of air conditioner. Furthermore, the server can also calculate a second compensation value for each device to be compensated to correct the first theoretical energy value based on the second reference energy value and the first theoretical energy values ​​uploaded by various devices of the same model, and send the corresponding second compensation values ​​to each device to be compensated.

[0072] It should be noted that the server performs smoothing processing on the first theoretical energy values ​​uploaded by each device of the same model to be compensated. This can be done by averaging the first theoretical energy values ​​uploaded by each device to be compensated and using the average value as the second baseline energy value.

[0073] For example, if the server obtains the first theoretical energy value of 520,000 uploaded by air conditioner device A in household 1, the first theoretical energy value of 550,000 uploaded by air conditioner device A in household 2, and the first theoretical energy value of 520,000 uploaded by air conditioner device A in household 3, then the second reference energy value corresponding to air conditioner device A is calculated to be 530,000.

[0074] In this application, if the server detects that the obtained first theoretical energy value is abnormal (such as too high or too low), it can be discarded.

[0075] In this application, based on the second reference energy value and the first theoretical energy value, the second compensation value of each device to be compensated is calculated accordingly. This can be achieved by using the difference between the second reference energy value and the first theoretical energy value as the second compensation value.

[0076] For example, if the second baseline energy value corresponding to air conditioner model A is 530,000, and the first theoretical energy value uploaded by air conditioner model A in household 1 is 520,000, then the second compensation value corresponding to air conditioner model A in household 1 is 530,000 - 520,000 = 10,000. If the first theoretical energy value uploaded by air conditioner model A in household 2 is 550,000, then the second compensation value corresponding to air conditioner model A in household 2 is 530,000 - 550,000 = -20,000.

[0077] In one embodiment of this application, after the device to be compensated obtains the second compensation value sent by the server, the following steps 253 to 254 may also be performed:

[0078] Step 253: Listen to the second wake-up audio and determine the first theoretical energy value when listening to the second wake-up audio, as the target first theoretical energy value.

[0079] Step 254: Correct the target first theoretical energy value using the second compensation value to obtain the second theoretical energy value.

[0080] In this application, continue to use Figure 1 Taking the system architecture shown as an example, if home appliance 1 obtains the second compensation value sent by the server, after listening to the second wake-up audio sent by the user, it can determine the first theoretical energy value based on the aforementioned scheme. For example, if the first theoretical energy value is 540,000, and the second compensation value is -20,000, then the second theoretical energy value is calculated to be 540,000 - 20,000 = 520,000.

[0081] Furthermore, after obtaining the second theoretical energy value, steps 255 to 256 can be performed as follows:

[0082] Step 255: Obtain the second theoretical energy value determined by other devices to be compensated in the same area while listening to the second wake-up audio.

[0083] Step 256: Select the device with the largest second theoretical energy value among the various devices to be compensated, and use it as the target response device to respond to the second wake-up audio.

[0084] In this application, continue to use Figure 1Taking the system architecture shown as an example, home appliance 1 and home appliance 2 belong to the same area (for example, both are installed in the same home). When the user issues the second wake-up audio, the second theoretical energy value determined by home appliance 1 is 520,000, and the second theoretical energy value determined by home appliance 2 is 530,000. Since the second theoretical energy value determined by home appliance 2 is the largest, it means that home appliance 2 is closest to the user. Therefore, home appliance 2 is determined as the target response device to respond to the second wake-up audio.

[0085] It should be noted that the first wake-up audio and the second wake-up audio mentioned above may refer to the same wake-up audio or different wake-up audio.

[0086] In this application, because the monitoring devices (such as microphones) installed in devices of the same model may have differences in individual components and sensitivity due to different production batches, a first theoretical energy value is obtained by correcting and compensating the original energy value determined when the device monitors the wake-up audio using a first reference energy value. This is further corrected and compensated using a second reference energy value to obtain a second theoretical energy value. This approach can largely overcome the impact of differences in the installation location and number of monitoring devices, as well as differences in individual components and sensitivity. Therefore, when the device performs the proximity wake-up function, it can ensure that the final energy value determined when monitoring the wake-up audio is optimal, improving the accuracy of the device's response to the wake-up audio.

[0087] This will be explained from the perspective of the server side.

[0088] Reference Figure 3 This diagram illustrates another flowchart of an audio data processing method according to an embodiment of this application. This audio data processing method can be executed by a device with computing capabilities, such as a server (e.g.,...). Figure 1 The cloud instance 103 shown is used for execution. (Refer to...) Figure 3 As shown, the audio data processing method includes at least steps 260 to 290, which are described in detail below:

[0089] Step 260: Obtain the first theoretical energy uploaded by each of the same model of devices to be compensated.

[0090] Step 270: Smooth each of the first theoretical energy values ​​to obtain the second reference energy value.

[0091] Step 280: Based on the second reference energy value and the first theoretical energy uploaded by each device to be compensated, calculate the second compensation value for each device to be compensated.

[0092] Step 290: The second compensation values ​​are sent to each device to be compensated. The second compensation values ​​are used to correct the first theoretical energy value determined by the device to be compensated when listening to the wake-up audio.

[0093] To enable those skilled in the art to better understand this application, the following will be combined with Figure 4 The audio data processing scheme proposed in this application will be briefly described in general with reference to a specific embodiment.

[0094] Reference Figure 4 This document illustrates the overall flowchart of the audio data processing method in an embodiment of this application. Specifically, it includes steps S1 to S6:

[0095] Step S1: Play test audio to the reference device and determine the energy value of the reference device when listening to the test audio, as the first reference energy value.

[0096] Step S2: Play test audio to the device to be compensated and determine the energy value of the device listening to the test audio as the first original energy value.

[0097] Step S3: The device to be compensated calculates a first compensation value based on the first reference energy value and the original energy value.

[0098] Step S4: The device to be compensated determines the original energy value when listening to the wake-up audio, corrects the original energy value based on the first compensation value to obtain the first theoretical energy value, and uploads the first theoretical energy value to the cloud.

[0099] Step S5: The cloud performs smoothing processing on the first theoretical energy values ​​uploaded by each device to be compensated of the same model to obtain a second reference energy value. Based on the second reference energy value and the first theoretical energy value, the cloud calculates the second compensation value for each device to be compensated and sends the second compensation value to each device to be compensated.

[0100] Step S6: The device to be compensated determines the first theoretical energy value when listening to the wake-up audio again, and corrects the first theoretical energy value based on the second compensation value to obtain the second theoretical energy value. The second theoretical energy value is used to select the target response device for responding to the wake-up audio from multiple devices to be compensated in the same area.

[0101] The following describes an apparatus embodiment of this application, which can be used to execute the audio data processing method in the above embodiments of this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the audio data processing method described above.

[0102] See Figure 5The diagram shows a block diagram of an audio data processing apparatus according to an embodiment of this application. This apparatus can be installed in any device to be compensated.

[0103] like Figure 5 As shown, the audio data processing apparatus 500 according to an embodiment of this application includes: a first acquisition unit 501, a monitoring unit 502, and a first calculation unit 503.

[0104] The first acquisition unit 501 is used to acquire a first reference energy value, which is the energy value determined by the reference device when listening to test audio in a test environment; the listening unit 502 is used to listen to the test audio in the test environment and determine the energy value when listening to the test audio as the original energy value; the first calculation unit 503 is used to calculate a first compensation value for the device to be compensated based on the first reference energy value and the original energy value, which is used to correct the original energy value determined by the device to be compensated when listening to wake-up audio.

[0105] In some embodiments of this application, based on the foregoing scheme, the device further includes: a first correction unit, configured to, after calculating a first compensation value for the device to be compensated, listen to a first wake-up audio and determine the original energy value when listening to the first wake-up audio as a target original energy value; and correct the target original energy value using the first compensation value to obtain a first theoretical energy value.

[0106] In some embodiments of this application, based on the foregoing scheme, the device further includes: a first selection unit, configured to, after obtaining the first theoretical energy value, acquire the first theoretical energy value determined by other devices to be compensated in the same area while listening to the first wake-up audio; and select the device to be compensated with the largest first theoretical energy value among the various devices to be compensated as the target response device in response to the first wake-up audio.

[0107] In some embodiments of this application, based on the foregoing scheme, the device further includes: an uploading unit, configured to upload the first theoretical energy value to a server after obtaining the first theoretical energy value, so that the server smooths the first theoretical energy values ​​uploaded by each device to be compensated of the same model to obtain a second reference energy value, and calculates a second compensation value for each device to be compensated based on the second reference energy value and the first theoretical energy value; and obtains the second compensation value issued by the server, wherein the second compensation value is used to correct the first theoretical energy value determined by the device to be compensated when listening to the wake-up audio.

[0108] In some embodiments of this application, based on the foregoing scheme, the device further includes: a second correction unit, configured to, after obtaining the second compensation value sent by the server, listen to the second wake-up audio and determine a first theoretical energy value when listening to the second wake-up audio as a target first theoretical energy value; and correct the target first theoretical energy value using the second compensation value to obtain a second theoretical energy value.

[0109] In some embodiments of this application, based on the foregoing scheme, the device further includes: a second selection unit, used to obtain, after obtaining the second theoretical energy value, the second theoretical energy value determined by other devices to be compensated in the same area while listening to the second wake-up audio; and to select the device to be compensated with the largest second theoretical energy value among the various devices to be compensated, as the target response device in response to the second wake-up audio.

[0110] See Figure 6 The diagram shows a block diagram of an audio data processing apparatus according to an embodiment of this application, which may be located on a server.

[0111] like Figure 6 As shown, the audio data processing apparatus 600 according to an embodiment of this application includes: a second acquisition unit 601, a smoothing processing unit 602, a second calculation unit 603, and a sending unit 604.

[0112] The second acquisition unit 601 is used to acquire the first theoretical energy uploaded by each device to be compensated of the same model; the smoothing processing unit 602 is used to smooth each of the first theoretical energy values ​​to obtain a second reference energy value; the second calculation unit 603 is used to calculate the second compensation value of each device to be compensated based on the second reference energy value and the first theoretical energy uploaded by each device to be compensated; and the sending unit 604 is used to send each of the second compensation values ​​to each device to be compensated, wherein the second compensation value is used to correct the first theoretical energy value determined by the device to be compensated when listening to the wake-up audio.

[0113] Based on the same inventive concept, this application also provides a household appliance, see reference. Figure 7 The diagram shows a structural schematic of a home appliance according to an embodiment of this application. The home appliance includes one or more memories 704, one or more processors 702, and at least one computer program (program code) stored in the memory 704 and executable on the processor 702. When the processor 702 executes the computer program, it implements the audio data processing method as described above.

[0114] Among them, Figure 7In this document, a bus architecture (represented by bus 700) is used. Bus 700 may include any number of interconnected buses and bridges, linking various circuits including one or more processors represented by processor 702 and memory represented by memory 704. Bus 700 may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 705 provides an interface between bus 700 and receiver 701 and transmitter 703. Receiver 701 and transmitter 703 may be the same element, i.e., a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 702 is responsible for managing bus 700 and general processing, while memory 704 can be used to store data used by processor 702 during operation.

[0115] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and embodiments are within the scope and spirit of this application and the appended claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hardwired, or any combination thereof. Furthermore, the functional units may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit.

[0116] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0117] The units described as separate components may or may not be physically separate. Similarly, the components of the control device may or may not be physical units; they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0118] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0119] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. An audio data processing method, characterized in that, The method is executed on any device to be compensated, and the method includes: Obtain a first reference energy value, wherein the first reference energy value is the energy value determined by the reference device when listening to test audio in the test environment; Listen to the test audio in the test environment and determine the energy value when listening to the test audio as the original energy value; Based on the first reference energy value and the original energy value, a first compensation value is calculated for the device to be compensated, and the first compensation value is used to correct the original energy value determined by the device to be compensated when listening to the wake-up audio; After calculating the first compensation value for the device to be compensated, the first wake-up audio is listened to, and the original energy value when listening to the first wake-up audio is determined as the target original energy value; the target original energy value is corrected using the first compensation value to obtain the first theoretical energy value. After obtaining the first theoretical energy value, the first theoretical energy value is uploaded to the server so that the server can smooth the first theoretical energy values ​​uploaded by each device of the same model to be compensated to obtain a second reference energy value. Based on the second reference energy value and the first theoretical energy value, the server calculates the second compensation value for each device to be compensated. The server then obtains the second compensation value, which is used to correct the first theoretical energy value determined by the device to be compensated when listening to the wake-up audio.

2. The method according to claim 1, characterized in that, After obtaining the first theoretical energy value, the method further includes: Obtain the first theoretical energy value determined by other devices to be compensated within the same area while listening to the first wake-up audio; Among all the devices to be compensated, the device with the largest first theoretical energy value is selected as the target response device in response to the first wake-up audio.

3. The method according to claim 1, characterized in that, After obtaining the second compensation value issued by the server, the method further includes: Listen to the second wake-up audio and determine the first theoretical energy value when listening to the second wake-up audio, as the target first theoretical energy value; The second compensation value is used to correct the first theoretical energy value of the target, thereby obtaining the second theoretical energy value.

4. The method according to claim 1, characterized in that, After obtaining the second theoretical energy value, the method further includes: Obtain the second theoretical energy value determined by other devices to be compensated within the same area while listening to the second wake-up audio; Among all the devices to be compensated, the device with the largest second theoretical energy value is selected as the target response device in response to the second wake-up audio.

5. An audio data processing method, characterized in that, The method is executed on the server side, and the method includes: Obtain the first theoretical energy value uploaded by each device to be compensated of the same model; The first theoretical energy values ​​are smoothed to obtain the second reference energy values; Based on the second reference energy value and the first theoretical energy value uploaded by each device to be compensated, the second compensation value of each device to be compensated is calculated accordingly. Each of the second compensation values ​​is sent to each device to be compensated, and the second compensation value is used to correct the first theoretical energy value determined by the device to be compensated when listening to the wake-up audio. The first theoretical energy value is determined by the device to be compensated through the following steps: obtaining a first reference energy value determined by a reference device when listening to test audio in a test environment; determining the original energy value when listening to the test audio in the test environment; calculating a first compensation value for the device to be compensated based on the first reference energy value and the original energy value; listening to a first wake-up audio and determining the target original energy value when listening to the first wake-up audio; correcting the target original energy value using the first compensation value to obtain the first theoretical energy value.

6. An audio data processing device, characterized in that, The device is installed in any of the devices to be compensated, and the device includes: The first acquisition unit is used to acquire a first reference energy value, which is an energy value determined by a reference device when listening to test audio in a test environment. The monitoring unit is used to monitor the test audio in a test environment and determine the energy value when monitoring the test audio as the raw energy value; The first calculation unit is used to calculate a first compensation value for the device to be compensated based on the first reference energy value and the original energy value. The first compensation value is used to correct the original energy value determined by the device to be compensated when listening to the wake-up audio. After calculating the first compensation value for the device to be compensated, the first wake-up audio is listened to, and the original energy value at the time of listening to the first wake-up audio is determined as the target original energy value; the target original energy value is corrected using the first compensation value to obtain the first theoretical energy value; After obtaining the first theoretical energy value, the first theoretical energy value is uploaded to the server so that the server can smooth the first theoretical energy values ​​uploaded by each device of the same model to be compensated to obtain a second reference energy value. Based on the second reference energy value and the first theoretical energy value, the server calculates the second compensation value for each device to be compensated. The server then obtains the second compensation value, which is used to correct the first theoretical energy value determined by the device to be compensated when listening to the wake-up audio.

7. An audio data processing device, characterized in that, The device is located on the server side, and the setup includes: The second acquisition unit is used to acquire the first theoretical energy value uploaded by each compensation device of the same model. A smoothing unit is used to smooth each of the first theoretical energy values ​​to obtain a second reference energy value; The second calculation unit is used to calculate the second compensation value for each device to be compensated based on the second reference energy value and the first theoretical energy value uploaded by each device to be compensated. The sending unit is used to send each of the second compensation values ​​to each device to be compensated, and the second compensation value is used to correct the first theoretical energy value determined by the device to be compensated when listening to the wake-up audio. The first theoretical energy value is determined by the device to be compensated through the following steps: obtaining a first reference energy value determined by a reference device when listening to test audio in a test environment; determining the original energy value when listening to the test audio in the test environment; calculating a first compensation value for the device to be compensated based on the first reference energy value and the original energy value; listening to a first wake-up audio and determining the target original energy value when listening to the first wake-up audio; correcting the target original energy value using the first compensation value to obtain the first theoretical energy value.

8. A household appliance, characterized in that, The method includes one or more processors and one or more memories, wherein at least one piece of program code is stored in the one or more memories, and the at least one piece of program code is loaded and executed by the one or more processors to implement the method as claimed in any one of claims 1-4.

Images