An intelligent audio system and method

Abstract

The present application provides an intelligent sound system and method. Multiple sound diffusivities are determined based on the sensing parameters of sensors in the sound device and all propagation distances, and a sound focusing point is determined according to all the sound diffusivities; the lag adjustment amount of the reflected sound in each direction is determined based on the sound focusing point and the dead zone range of the sound device, and the sound diffusion range is determined according to all the lag adjustment amounts; the sound pressure level distribution of the sound device in an enclosed space is determined based on the ambient noise and all the propagation distances; the compensation amount for the sensor hysteresis when the sound device plays sound in the enclosed space is determined based on the sound diffusion range and the sound pressure level distribution. When the sound device propagates sound in each direction, the sensor in the sound device is adaptively compensated for hysteresis by the compensation amount. The above solution can weaken the influence of the hysteresis of the sensor in the sound device on the intelligent control of the sound device, thereby improving the playback quality of the sound device in the enclosed space.

Description

Technical Field

[0001] This application relates to the technical field of smart speakers. More specifically, this application relates to a smart speaker system and method. Background Art

[0002] ‌Smart speakers are one of the smart home devices that have developed rapidly in recent years. They combine sound and artificial intelligence technologies. The internal circuit structure of smart speakers is complex, including multiple components such as power conversion circuits, wireless communication circuits, and sensor circuits. These technologies work together to make smart speakers highly intelligent and convenient.

[0003] The regulation of smart speakers mainly includes aspects such as adjusting volume, balance, bass, treble, channels, surround sound, sound source quality, audio equipment, and environmental factors to ensure the best audio effect. In the regulation process of existing smart speakers, a noise generator and an equalizer are used for debugging. The frequency points of the equalizer are adjusted to obtain a flat frequency response curve, and then the sound pressure level is measured to ensure that the sound pressure of the sound reinforcement at each test point meets the design requirements. Due to the energy absorption of the internal components of the sensor, there is a conflict between the absorbed energy and the transmitted energy, resulting in the sensor having hysteresis. When the environmental noise changes little, due to the hysteresis of the sensor, the sensor does not respond immediately, resulting in the speaker failing to adjust the volume in time, causing the dead zone effect in the sensor of the speaker. Therefore, how to weaken the influence of the hysteresis of the sensor in the speaker on the intelligent regulation of the speaker, so as to improve the playback quality of the speaker in a closed venue has become a problem faced by the industry. Summary of the Invention

[0004] ‌This application provides a smart speaker system and method, which can weaken the influence of the hysteresis of the sensor in the speaker on the intelligent regulation of the speaker, thereby improving the playback quality of the speaker in a closed venue.

[0005] In the first aspect, this application provides a smart speaker regulation method, including the following steps:

[0006] Start the delay regulation system of the smart speaker and obtain the propagation distances of the sound in the smart speaker in all directions in a closed venue;

[0007] Based on the sensing parameters of the sensors in the speaker and all the propagation distances, determine the sound diffusivity when the sound in the speaker propagates in all directions, and determine the sound focusing point of the speaker in the closed venue according to the differences between the sound diffusivities;

[0008] Determine the hysteresis adjustment amount of the sound reflected by the sensor in each direction in the sound device based on the sound focusing point and the dead zone range of the sensor in the sound device during playback. Analyze the diffusion of the sound emitted by the sound device according to all the hysteresis adjustment amounts to obtain the range of sound diffusion when the sensor in the sound device has hysteresis.

[0009] Collect the ambient noise of the sound device in an enclosed space, predict the received sound in each direction through the ambient noise and all the propagation distances, and then obtain the sound pressure level distribution of the sound device in the enclosed space.

[0010] Determine the compensation amount for the sensor hysteresis of the sound device when playing sound in the enclosed space based on the range of sound diffusion when the sensor in the sound device has hysteresis and the sound pressure level distribution. When the sound device propagates sound in each direction, perform adaptive hysteresis compensation on the sensor in the sound device through the compensation amount.

[0011] In some embodiments, determining the sound diffusivity of the sound in the sound device in each direction based on the sensing parameters of the sensor in the sound device and all the propagation distances specifically includes:

[0012] Obtain the sensitivity and linearity of the sensor in the sound device, and use the sensitivity and linearity of the sensor in the sound device as the sensing parameters of the sensor in the sound device.

[0013] Select a direction as the selected direction, and obtain the sound intensity of the sound emitted by the sound device.

[0014] Determine the sound propagation loss according to the sound intensity and the propagation distance corresponding to the selected direction among all the propagation distances.

[0015] Determine the sound diffusivity of the sound in the sound device when propagating in the selected direction according to the sound propagation loss and the sensing parameters.

[0016] Continue to determine the sound diffusivity of the sound in the sound device when propagating in the remaining directions.

[0017] In some embodiments, determining the sound focusing point of the sound device in the enclosed space according to the differences between the sound diffusivities specifically includes:

[0018] Determine the intensity difference amount between the sound diffusivities, and use each intensity difference amount as the difference between the corresponding sound diffusivities.

[0019] Obtain the size of the enclosed space of the enclosed space.

[0020] Determine the sound focusing point of the sound device in the enclosed space according to the size of the enclosed space and all the differences.

[0021] In some embodiments, determining the lag adjustment amount of the sound reflected by the sensor in each direction in the sound device based on the sound focusing point and the dead zone range of the sensor during playback of the sound device specifically includes:

[0022] Obtain the dead zone range of the sensor in the sound device during playback;

[0023] Determine the distances from the sound focusing point to each direction in the enclosed space;

[0024] Select a direction as the selected direction, and determine the sound lag amount in the selected direction according to the sound diffusivity corresponding to the selected direction and the distance corresponding to the selected direction:

[0025] Determine the lag adjustment amount of the sound reflected by the sensor in the sound device in the selected direction based on the sound lag amount and the dead zone range of the sensor;

[0026] Continue to determine the lag adjustment amount of the sound reflected by the sensor in the sound device in the remaining directions.

[0027] In some embodiments, performing a diffusion analysis on the sound emitted by the sound device based on all the lag adjustment amounts to obtain the range of sound diffusion when the sensor in the sound device has a lag specifically includes:

[0028] Obtain the sound intensity of the sound emitted by the sound device;

[0029] Determine the sound expansion intensity in each direction based on the sound intensity and all the lag adjustment amounts;

[0030] Determine the range of sound diffusion when the sensor in the sound device has a lag based on all the sound expansion intensities.

[0031] In some embodiments, predicting the received sound in each direction based on the ambient noise and all the propagation distances, and further obtaining the sound pressure level distribution of the sound device in the enclosed space specifically includes:

[0032] Obtain the received sound intensity of the received sound in each direction;

[0033] Determine the noise-removed sound intensity in each direction based on the ambient noise and each received sound intensity;

[0034] Determine the predicted sound intensity of the received sound in each direction based on all the noise-removed sound intensities and all the propagation distances;

[0035] Determine the sound pressure level distribution of the sound device in the enclosed space based on all the predicted sound intensities.

[0036] In some embodiments, determining the compensation amount for sensor hysteresis when the sound is played by the sound device in an enclosed space based on the range of sound diffusion and the sound pressure level distribution when there is hysteresis in the sensor of the sound device specifically includes:

[0037] Determining the sound dispersion amount of the enclosed space according to the sound pressure level distribution;

[0038] Obtaining the working time of the sensor in the sound device;

[0039] Determining the response extension amount of the sensor in the sound device according to the working time and the range of sound diffusion when there is hysteresis in the sensor of the sound device;

[0040] Determining the compensation amount for sensor hysteresis when the sound is played by the sound device in an enclosed space according to the sound dispersion amount and the response extension amount.

[0041] In a second aspect, the present application provides an intelligent sound device system, which includes a regulation unit, and the regulation unit includes:

[0042] An acquisition module, configured to obtain the propagation distances in all directions of the sound device in an enclosed space after starting the delay regulation system of the intelligent sound device;

[0043] A processing module, configured to determine the sound diffusion degree when the sound in the sound device propagates in all directions based on the sensing parameters of the sensor in the sound device and all the propagation distances, and determine the sound focusing point of the sound device in the enclosed space according to the difference between the sound diffusion degrees;

[0044] The processing module is further configured to determine the hysteresis adjustment amount of the sensor in the sound device for the reflected sound in all directions through the sound focusing point and the dead zone range of the sensor in the sound device during playback, and perform diffusion analysis on the sound transmitted by the sound device according to all the hysteresis adjustment amounts to obtain the range of sound diffusion when there is hysteresis in the sensor of the sound device;

[0045] The processing module is further configured to collect the ambient noise of the sound device in the enclosed space, predict the received sound in all directions through the ambient noise and all the propagation distances, and further obtain the sound pressure level distribution of the sound device in the enclosed space;

[0046] An execution module, configured to determine the compensation amount for sensor hysteresis when the sound is played by the sound device in an enclosed space through the range of sound diffusion and the sound pressure level distribution when there is hysteresis in the sensor of the sound device, and perform adaptive hysteresis compensation on the sensor in the sound device through the compensation amount when the sound device propagates sound in all directions.

[0047] In a third aspect, the present application provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the above-mentioned intelligent sound control method.

[0048] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, which when executed by a processor implements the above-mentioned intelligent sound control method.

[0049] The technical solutions provided by the embodiments disclosed in the present application have the following beneficial effects:

[0050] In the intelligent sound system and method provided by the present application, first, the delay control system of the intelligent sound is started to obtain the propagation distances of the sound in each direction in a closed space; based on the sensing parameters of the sensors in the sound and all the propagation distances, the sound diffusivity of the sound in the sound when propagating in each direction is determined, and the sound focusing point of the sound in the closed space is determined according to the differences between the sound diffusivities; the lag adjustment amount of the sensors in the sound for the reflected sound in each direction is determined through the sound focusing point and the dead zone range of the sensors when the sound is played, and the sound diffusion analysis is performed on the sound emitted by the sound according to all the lag adjustment amounts to obtain the sound diffusion range when the sensors in the sound have hysteresis; the ambient noise in the closed space where the sound is located is collected, and the received sound in each direction is predicted through the ambient noise and all the propagation distances, and then the sound pressure level distribution of the sound in the closed space is obtained; the compensation amount for the sensor hysteresis when the sound is played in the closed space is determined through the sound diffusion range when the sensors in the sound have hysteresis and the sound pressure level distribution, and when the sound propagates in each direction, the sensors in the sound are adaptively compensated for hysteresis through the compensation amount.

[0051] It can be seen that in the process of intelligent sound control of this application, first, the propagation effect of the sound in the enclosed space is analyzed by the dead zone range of the sensor during the playback of the sound and the propagation distance in each direction, and the adjustment degree of the lag situation of the sensor in the sound for the sound in each direction is determined, and then the lag adjustment amount is obtained. The lag adjustment amount is used to adjust the lag situation of the sensor in the sound, weaken the hysteresis during the playback of the sensor in the sound, and then reduce the dead zone effect of the sensor; secondly, the sound diffused from the sound is analyzed by all the lag adjustment amounts to determine the boundary of the expansion degree of the sound emitted from the sound, that is, the propagation range of the sound emitted from the sound, and then the range of sound diffusion when the sensor in the sound has hysteresis is obtained. The range of sound diffusion when the sensor in the sound has hysteresis is used to make corresponding adjustments to the hysteresis of the sensor in the sound, and then improve the propagation quality of the sound emitted from the sound in the enclosed space; furthermore, the ambient noise and all the propagation distances are used to predict the received sound in each direction, and the sound pressure distribution of the sound emitted from the sound in the enclosed space is determined, and then the sound pressure level distribution is obtained. The sound pressure level distribution is used to judge the sound in each direction of the sound in the enclosed space, which is convenient for predicting the hysteresis during the playback of the sound; thus, the compensation amount for the sensor hysteresis when the sound is played in the enclosed space is determined by the range of sound diffusion when the sensor in the sound has hysteresis and the sound pressure level distribution. The compensation amount is used to compensate for the hysteresis situation of the sensor in the sound; finally, when the sound propagates in each direction, the sensor in the sound is adaptively compensated for hysteresis by the compensation amount. The above solution can weaken the influence of the hysteresis of the sensor in the sound on the intelligent control of the sound, thereby improving the playback quality of the sound in the enclosed space. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 is an exemplary flowchart of an intelligent sound control method according to some embodiments of the present application;

[0053] Figure 2 is an exemplary flowchart of determining a sound focusing point according to some embodiments of the present application;

[0054] Figure 3 is an exemplary flowchart of determining the range of sound diffusion when the sensor in the sound has hysteresis according to some embodiments of the present application;

[0055] Figure 4 is a schematic structural diagram of a control unit according to some embodiments of the present application;

[0056] Figure 5 is a schematic structural diagram of a computer device for implementing the intelligent sound control method according to some embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] The core of this application is to start the delay control system of the smart speaker, obtain the propagation distances of the speaker in all directions in a closed venue; determine the sound diffusion degree of the sound in the speaker when propagating in all directions based on the sensing parameters of the sensors in the speaker and all the propagation distances, and determine the sound focusing point of the speaker in the closed venue according to the differences between the sound diffusion degrees in all directions; determine the lag adjustment amount of the sensors in the speaker for the reflected sound in all directions through the sound focusing point and the dead zone range of the sensors in the speaker during playback, and perform diffusion analysis on the sound transmitted by the speaker according to all the lag adjustment amounts to obtain the range of sound diffusion when the sensors in the speaker have hysteresis; collect the ambient noise of the speaker in the closed venue, predict the received sound in all directions through the ambient noise and all the propagation distances, and then obtain the sound pressure level distribution of the speaker in the closed venue; determine the compensation amount for the sensor hysteresis of the speaker when playing sound in the closed venue through the range of sound diffusion when the sensors in the speaker have hysteresis and the sound pressure level distribution, and when the speaker propagates sound in all directions, perform adaptive hysteresis compensation on the sensors in the speaker through the compensation amount. The above solution can weaken the influence of the hysteresis of the sensors in the speaker on the intelligent control of the speaker, thereby improving the playback quality of the speaker in a closed venue.

[0058] To better understand the above technical solution, the above technical solution will be described in detail below in combination with the accompanying drawings of the specification and specific implementation manners. Refer to Figure 1 , which is an exemplary flowchart of the smart speaker control method shown in some embodiments of this application. The smart speaker control method 100 mainly includes the following steps:

[0059] In step 101, start the delay control system of the smart speaker and obtain the propagation distances of the speaker in all directions in a closed venue.

[0060] Specifically, after starting the delay control system of the smart speaker, collect the propagation distances of the speaker in all directions in the closed venue through a distance acquisition device. Among them, the propagation distance is the distance from the speaker to the farthest end in the corresponding direction in the closed venue. The distance acquisition device is, for example, an ultrasonic sensor, a laser rangefinder, etc. In other embodiments, other methods can also be used for acquisition, which will not be elaborated here.

[0061] It should be noted that the closed venue in this application is an annular stadium. The seating area of the annular stadium is evenly divided into 20 areas, and the corresponding directions of each divided area are used as the directions in the closed venue; generally, there are multiple speakers working together in the closed venue. In this application, the playback effects of all speakers are the same. Therefore, this application analyzes one of the speakers.

[0062] In step 102, based on the sensing parameters of the sensors in the sound device and all the propagation distances, determine the sound diffusivity when the sound in the sound device propagates in each direction, and determine the sound focusing point of the sound device in the enclosed space according to the differences between the sound diffusivities.

[0063] In some embodiments, determining the sound diffusivity when the sound in the sound device propagates in each direction based on the sensing parameters of the sensors in the sound device and all the propagation distances can be implemented by the following steps:

[0064] Obtain the sensitivity and linearity of the sensors in the sound device, and use the sensitivity and linearity of the sensors in the sound device as the sensing parameters of the sensors in the sound device;

[0065] Select a direction as the selected direction, and obtain the sound intensity of the sound emitted by the sound device;

[0066] Determine the sound propagation loss according to the sound intensity and the propagation distance corresponding to the selected direction among all the propagation distances;

[0067] Determine the sound diffusivity when the sound in the sound device propagates in the selected direction according to the sound propagation loss and the sensing parameters;

[0068] Continue to determine the sound diffusivity when the sound in the sound device propagates in the remaining directions.

[0069] In specific implementation, obtain the sensitivity and linearity of the sensors in the sound device from the database of the sound device. Here, the sensitivity of the sensor represents the ratio of the output change amount to the input change amount in the sensor. High sensitivity means high signal-to-noise ratio, which is convenient for signal transmission, conditioning, and calculation. The linearity of the sensor represents the parameter value of the linear degree between the output and input of the sensor. The sound intensity of the sound emitted by the sound device can be obtained in the following manner: obtain the sound intensity of the sound emitted by the sound device through a sound intensity acquisition device in the prior art. Here, the sound intensity acquisition device can be a sound level meter, a sound intensity meter, etc. The sound propagation loss can be determined according to the sound intensity and the propagation distance corresponding to the selected direction among all propagation distances in the following manner: divide the sound intensity by the propagation distance corresponding to the selected direction among all propagation distances, perform a natural exponential operation on the obtained value, and use the reciprocal of the value obtained from the natural exponential operation as the sound propagation loss. Here, the sound propagation loss represents the parameter value of the loss degree when the sound emitted by the sound device propagates to the direction. The sound diffusivity of the sound in the sound device when propagating in the selected direction can be determined according to the sound propagation loss and the sensing parameters in the following manner: perform a logarithm operation with base 10 on the product of the sensitivity and linearity in the sensing parameters, subtract the value obtained from the logarithm operation from the sound propagation loss, divide the obtained difference value by the value obtained from the logarithm operation, and use the obtained quotient value as the sound diffusivity of the sound in the sound device when propagating in the selected direction. In other embodiments, it can also be determined in other ways, which are not limited here.

[0070] It should be noted that the sound diffusivity in this application is a parameter value reflecting the diffusion degree of the sound emitted by the sound device in the direction, used to judge the sound of the sound device in an enclosed space, which is convenient for adjusting the sound device.

[0071] In some embodiments, refer to Figure 2 As shown, this figure is a schematic flowchart of determining the sound focus point in some embodiments of this application. In this embodiment, the sound focus point of the sound device in the enclosed space can be determined according to the differences between the sound diffusivities in the following steps:

[0072] First, in step 1021, determine the intensity difference amount between the sound diffusivities, and use each intensity difference amount as the difference between the corresponding sound diffusivities.

[0073] Secondly, in step 1022, obtain the size of the enclosed space of the enclosed space.

[0074] Finally, in step 1023, determine the sound focus point of the sound device in the enclosed space according to the size of the enclosed space and all the differences.

[0075] In specific implementation, the intensity difference amount between each sound diffusivity can be determined in the following manner: select any two sound diffusivities as the selected two sound diffusivities, subtract the second sound diffusivity from the first sound diffusivity among the selected two sound diffusivities, and use the obtained subtracted value as the intensity difference amount of the selected two sound diffusivities. Then continue to determine the intensity difference amount of any remaining two sound diffusivities. Herein, the intensity difference amount is a parameter value representing the difference degree of sound attenuation between any two directions, and is used to analyze the sound reception situation in adjacent areas; obtaining the size of the enclosed venue can be achieved in the following manner: obtain the size of the enclosed venue from the database of the enclosed venue, where the size of the enclosed venue represents dimensions such as the length, width, and height of the enclosed venue; determining the sound focusing point of the sound device in the enclosed venue according to the size of the enclosed venue and the difference can be achieved in the following manner: determine the center position of the enclosed venue through an electronic theodolite in the prior art in combination with the size of the enclosed venue. Herein, the center position of the enclosed venue represents the coordinates of the center point of the enclosed venue. Place the enclosed venue in the first quadrant of the coordinate system. The abscissa of the outermost point on the due east side of the center point is 0, and the ordinate of the outermost point on the due south side of the center point is 0. For example, if the coordinates of the center point of the enclosed venue are (12, 13), subtract the maximum difference from the minimum difference among all the differences, perform a natural exponential operation on the obtained subtracted value, multiply the value obtained from the natural exponential operation by the abscissa in the center position of the enclosed venue, and use the obtained multiplied value as the abscissa of the sound focusing point. Multiply the value obtained from the natural exponential operation by the ordinate in the center position of the enclosed venue, and use the obtained multiplied value as the ordinate of the sound focusing point. The point corresponding to the coordinates composed of the abscissa and ordinate of the sound focusing point is used as the sound focusing point of the sound device in the enclosed venue. In other embodiments, other methods can also be used for determination, which are not limited herein.

[0076] It should be noted that the sound focusing point in this application represents the center point of the sound after reflection in the enclosed venue when the sound device emits sound, and is used to judge the reflected sound, and then make corresponding adjustments to the sound device according to the characteristics of the reflected sound.

[0077] In step 103, determine the hysteresis adjustment amount of the sensor in the sound device for the reflected sound in each direction according to the sound focusing point and the dead zone range of the sensor when the sound device is playing. Perform a diffusion analysis on the sound emitted by the sound device according to all the hysteresis adjustment amounts to obtain the range of sound diffusion when the sensor in the sound device has hysteresis.

[0078] In some embodiments, determining the hysteresis adjustment amount of the sensor in the sound device for the reflected sound in each direction according to the sound focusing point and the dead zone range of the sensor when the sound device is playing can be achieved by the following steps:

[0079] Obtain the dead zone range of the sensor when the audio is playing;

[0080] Determine the distances from the sound focus point to all directions in the enclosed venue;

[0081] Select a direction as the selected direction, and determine the sound lag amount of the selected direction according to the sound diffusivity corresponding to the selected direction and the distance corresponding to the selected direction:

[0082] Determine the lag adjustment amount of the sensor in the audio for the reflected sound in the selected direction according to the sound lag amount and the dead zone range of the sensor;

[0083] Continue to determine the lag adjustment amounts of the sensors in the audio for the reflected sounds in the remaining directions.

[0084] In specific implementation, obtaining the dead zone range of the sensor when the audio is playing can be achieved by the following method, that is: obtain all the historical dead zone ranges of the sensor during the historical playback of the audio from the database of the audio, and take the average range of all the historical dead zone ranges as the dead zone range of the sensor when the audio is playing. Among them, the dead zone range of the sensor when the audio is playing represents the specific range where the input signal in the audio changes while the output does not change, and is used to analyze the playback performance of the sensor; determining the distances from the sound focus point to all directions can be achieved by the following method, that is: collect the distances from the sound focus point to all directions in the enclosed venue through a distance acquisition device. Among them, the distance represents the distance from the sound focus point to the outermost edge of the direction; determining the sound lag amount of the selected direction according to the sound diffusivity corresponding to the selected direction and the distance corresponding to the selected direction can be achieved by the following method, that is: multiply the distance corresponding to the selected direction by the sound diffusivity, and take the obtained value as the sound lag amount of the selected direction. Among them, the sound lag amount represents the parameter value of the lag degree of the sound of the sensor in the audio in the direction; determining the lag adjustment amount of the sensor in the audio for the reflected sound in the selected direction according to the sound lag amount and the dead zone range of the sensor can be achieved by the following method, that is: initialize a lag adjustment amount model, take the sound lag amount as the initialization parameter of this lag adjustment amount model, take the dead zone range of the sensor as the constraint parameter of this lag adjustment amount model, and obtain the lag adjustment amount of the sensor in the audio for the reflected sound in the selected direction through this lag adjustment amount model. Among them, the lag adjustment amount model is an adjustment model for establishing the lag adjustment amount using machine learning algorithms (such as regression algorithms, neural networks, etc.). The adjustment model is, for example: lag adjustment amount = sound lag amount * C + dead zone range of the sensor * D, where C and D are weight coefficients, and C and D can be determined according to a large number of lag adjustment amounts. In other embodiments, other methods can also be used to determine them, which are not limited here.

[0085] It should be noted that the hysteresis adjustment amount in this application is a parameter value that reflects the degree of adjustment of the hysteresis situation of the sensor in the audio, and is used to adjust the sensor in the audio, reducing the hysteresis of the sensor in the audio and facilitating the reduction of the dead zone range of the sensor.

[0086] In some embodiments, referring to Figure 3 As shown, this figure is a schematic flowchart of determining the sound diffusion range when the sensor in the audio has hysteresis in some embodiments of this application. In this embodiment, the sound diffusion range when the sensor in the audio has hysteresis can be obtained by performing diffusion analysis on the sound transmitted by the audio according to all the hysteresis adjustment amounts, and the following steps can be adopted:

[0087] First, in step 1031, obtain the sound intensity of the sound transmitted by the audio;

[0088] Secondly, in step 1032, determine the sound expansion intensity in each direction according to the sound intensity and all the hysteresis adjustment amounts;

[0089] Finally, in step 1033, determine the sound diffusion range when the sensor in the audio has hysteresis according to all the sound expansion intensities.

[0090] When specifically implemented, determining the sound expansion intensity in each direction according to the sound intensity and all the hysteresis adjustment amounts can be achieved in the following way, that is: select a direction as the selected direction, collect the farthest distance and the nearest distance from the selected direction to the audio through the distance acquisition device, subtract the nearest distance from the farthest distance, divide the hysteresis adjustment amount corresponding to the selected direction by the obtained subtracted value, multiply the obtained divided value by the sound intensity, and use the obtained multiplied value as the sound expansion intensity of the selected direction, and continue to determine the sound expansion intensities of the remaining directions. Among them, the sound expansion intensity is a parameter value representing the expansion degree of the sound transmitted by the audio in the direction, and is used to analyze the sound intensity in the direction; determining the sound diffusion range when the sensor in the audio has hysteresis according to all the sound expansion intensities can be achieved in the following way, that is: divide the maximum sound expansion intensity among all the sound expansion intensities by the minimum sound expansion intensity, perform a logarithmic operation with the obtained divided value as the base of 2, multiply the obtained logarithmic operation value by the average value of all the sound expansion intensities, and use the obtained multiplied value as the sound diffusion range when the sensor in the audio has hysteresis. In other embodiments, other methods can also be used for determination, which are not limited here.

[0091] It should be noted that in this application, the sound emitted by the audio is diffusively analyzed according to all the hysteresis adjustment amounts, that is: the sound intensity of the sound emitted by the audio is obtained, and the sound expansion intensity in each direction is determined according to the sound intensity and all the hysteresis adjustment amounts; when there is hysteresis in the sensor in the audio, the range of sound diffusion is the boundary reflecting the expansion degree of the sound emitted by the audio, that is: the propagation range of the sound emitted by the audio, which is used to judge the sound emitted by the audio, facilitate corresponding adjustment of the sensor in the audio, and thus improve the propagation quality of the sound emitted by the audio in a closed venue.

[0092] In step 104, the ambient noise of the audio in the closed venue is collected, and the received sound in each direction is predicted through the ambient noise and all the propagation distances, so as to obtain the sound pressure level distribution of the audio in the closed venue.

[0093] It should be noted that the ambient noise in this application represents the noise in the closed venue where the audio is located, and is used to adjust the sound emitted by the audio. As a preferred embodiment, the ambient noise of the audio in the closed venue can be collected by a sound collection device. Among them, the sound collection device is, for example: an audio collector, a pickup, etc. In other embodiments, other methods can also be used to obtain it, which will not be elaborated here.

[0094] In some embodiments, predicting the received sound in each direction through the ambient noise and all the propagation distances, and then obtaining the sound pressure level distribution of the audio in the closed venue can be implemented by the following steps:

[0095] Obtain the received sound intensity of the received sound in each direction;

[0096] Determine the noise-removed sound intensity in each direction according to the ambient noise and each received sound intensity;

[0097] Determine the predicted sound intensity of the received sound in each direction according to all the noise-removed sound intensities and all the propagation distances;

[0098] Determine the sound pressure level distribution of the audio in the closed venue according to all the predicted sound intensities.

[0099] In specific implementation, a receiving sound intensity of received sounds in each direction is collected by a sound intensity collection device; determining a noise reduction sound intensity in each direction based on the environmental noise and each receiving sound intensity can be implemented in the following manner, that is: selecting one direction as a selected direction, and determining the noise reduction sound intensity of the selected direction by combining the receiving sound intensity and the environmental noise of the selected direction through a sound noise reduction software in the prior art (such as: Audacity, Fengyun Audio Processing Master, etc.), and then continuing to determine the noise reduction sound intensities of the remaining directions, where the noise reduction sound intensity represents the intensity of the sound transmitted from the receiving sound after noise reduction; determining the predicted sound intensity of the received sounds in each direction based on all the noise reduction sound intensities and all the propagation distances can be implemented in the following manner, that is: selecting one direction as a selected direction, performing a natural exponential operation on the propagation distance corresponding to the selected direction among all the propagation distances, multiplying the reciprocal of the value obtained from the natural exponential operation by the noise reduction sound intensity corresponding to the selected direction, and taking the value obtained from the multiplication as the predicted sound intensity of the received sound in the selected direction, and then continuing to determine the predicted sound intensities of the received sounds in the remaining directions, where the predicted sound intensity represents the sound intensity of the received sound after excluding noise and distance, and is used to predict the sound intensity in the direction; determining the sound pressure level distribution of the sound in the enclosed space based on all the predicted sound intensities can be implemented in the following manner, that is: arranging all the predicted sound intensities according to their positions in the enclosed space corresponding to the directions, and taking the arranged result as the sound pressure level distribution of the sound in the enclosed space. In other embodiments, other methods can also be used to determine it, which is not limited here.

[0100] It should be noted that the sound pressure level distribution in this application reflects the sound pressure distribution of the sound transmitted by the sound in the enclosed space, and is used to predict the sound pressure of the sound transmitted by the sound to each area, facilitating the judgment of the sound in each direction in the enclosed space, and further adjusting the sensors in the sound.

[0101] In step 105, the compensation amount for sensor hysteresis when the sound is played in the enclosed space by the sound is determined based on the range of sound diffusion when the sensor in the sound has hysteresis and the sound pressure level distribution. When the sound propagates in each direction by the sound, the sensor in the sound is adaptively compensated for hysteresis by the compensation amount.

[0102] In some embodiments, determining the compensation amount for sensor hysteresis when the sound is played in the enclosed space by the sound based on the range of sound diffusion when the sensor in the sound has hysteresis and the sound pressure level distribution can be implemented by the following steps:

[0103] Determining the sound discreteness of the enclosed space based on the sound pressure level distribution;

[0104] Obtaining the working time of the sensor in the sound;

[0105] Determine the response expansion amount of the sensor in the sound device according to the working time and the sound diffusion range when the sensor in the sound device has hysteresis.

[0106] Determine the compensation amount for the sensor hysteresis when the sound device plays sound in an enclosed space according to the sound dispersion amount and the response expansion amount.

[0107] In specific implementation, determining the sound dispersion amount of the enclosed space according to the sound pressure level distribution can be achieved in the following way: divide the average value of all predicted sound intensities in the sound pressure level distribution by the standard deviation of all predicted sound intensities in the sound pressure level distribution, and use the obtained value as the sound dispersion amount of the sensor in the sound device. Here, the sound dispersion amount is a parameter value representing the dispersion degree of the sound emitted by the sound device in the enclosed space; obtaining the working time of the sensor in the sound device can be achieved in the following way: obtain the working time of the sensor in the sound device from the database of the sound device. Here, the working time represents the time interval from the start of work to the end of work of the sensor in the sound device, and is used to adjust the sound propagation of the sensor in the sound device; determining the response expansion amount of the sensor in the sound device according to the working time and the sound diffusion range when the sensor in the sound device has hysteresis can be achieved in the following way: divide the sound diffusion range when the sensor in the sound device has hysteresis by the working time, subtract the obtained value from the sound diffusion range when the sensor in the sound device has hysteresis, and use the obtained value as the response expansion amount of the sensor in the sound device. Here, the response expansion amount is a parameter value representing the expansion degree of the sound emitted by the sound device in the enclosed space after excluding the influence of the working time, and is used to judge the sensor in the sound device; determining the compensation amount for the sensor hysteresis when the sound device plays sound in the enclosed space according to the sound dispersion amount and the response expansion amount can be achieved in the following way: initialize a hysteresis compensation amount model, use the sound dispersion amount as the initialization parameter of this hysteresis compensation amount model, use the response expansion amount as the constraint parameter of this hysteresis compensation amount model, and obtain the compensation amount for the sensor hysteresis when the sound device plays sound in the enclosed space through this hysteresis compensation amount model. Here, the hysteresis compensation amount model is an exponential model for establishing the hysteresis compensation amount using machine learning algorithms (such as regression algorithms, neural networks, etc.). The exponential model is, for example: hysteresis compensation amount = sound dispersion amount * A + response expansion amount * B. Here, A and B are weight coefficients, and A and B can be obtained through neural network training. In other embodiments, other methods can also be used to determine them, which are not limited here.

[0108] It should be noted that the compensation amount for the sensor hysteresis in this application is a parameter value reflecting the compensation degree of the hysteresis situation of the sensor in the sound device, and is used to compensate for the hysteresis situation of the sensor in the sound device, thereby weakening the hysteresis of the sensor in the sound device and improving the propagation quality of the sound device in the enclosed space.

[0109] In some embodiments, the adaptive hysteresis compensation for the sensors in the sound device by the compensation amount can be implemented by the following steps:

[0110] Obtain the response speed of the sensors in the sound device in a closed space;

[0111] Adjust the response speed of the sensors in the sound device by the compensation amount to obtain the adjusted response speed of the sound device in the closed space;

[0112] Update the response speed of the sensors in the sound device with the adjusted response speed.

[0113] Specifically, obtaining the response speed of the sound device in the closed space can be implemented in the following manner: obtain the response time of the sound device in the closed space from the database of the sound device, and characterize the response speed by the response time. Wherein, the response time represents the time required for the sensor to rise from zero to a stable output signal, and is used to reflect the dynamic response speed of the sensor. The shorter the response time, the faster the sensor is and the more capable it is of detecting changes in substances in a timely manner. Adjusting the response speed of the sensors in the sound device by the compensation amount to obtain the adjusted response speed of the sound device in the closed space can be implemented in the following manner: multiply the compensation amount by the response speed, and use the obtained value as the adjusted response speed of the sound device in the closed space; and use the adjusted response speed as the new response speed of the response speed of the sound device in the closed space. In other embodiments, it can also be determined by other methods, which are not limited herein.

[0114] In addition, on the other hand of the present application, in some embodiments, the present application provides an intelligent sound system, which includes a regulation unit. Refer to Figure 4 , this figure is a schematic structural diagram of the regulation unit shown according to some embodiments of the present application. The regulation unit 400 includes: an acquisition module 401, a processing module 402, and an execution module 403, which are described as follows:

[0115] The acquisition module 401. In the present application, the acquisition module 401 is mainly used to start the delay regulation system of the intelligent sound device and obtain the propagation distances of the sound device in various directions in the closed space;

[0116] The processing module 402. In the present application, the processing module 402 is used to determine the sound diffusion degree when the sound in the sound device propagates in various directions based on the sensing parameters of the sensors in the sound device and all the propagation distances, and determine the sound focusing point of the sound device in the closed space according to the differences between the sound diffusion degrees;

[0117] It should be noted that in the present application, the processing module 402 is further configured to determine the hysteresis adjustment amount of the sound reflected by the sensor in each direction in the sound device based on the sound focusing point and the dead zone range of the sensor in the sound device during playback, and perform diffusion analysis on the sound transmitted from the sound device according to all the hysteresis adjustment amounts to obtain the sound diffusion range when the sensor in the sound device has hysteresis;

[0118] In addition, it should be noted that in the present application, the processing module 402 is further configured to collect the ambient noise of the sound device in a closed space, predict the received sound in each direction based on the ambient noise and all the propagation distances, and further obtain the sound pressure level distribution of the sound device in the closed space;

[0119] The execution module 403. In the present application, the execution module 403 is mainly configured to determine the compensation amount for the sensor hysteresis when the sound device plays sound in a closed space based on the sound diffusion range when the sensor in the sound device has hysteresis and the sound pressure level distribution, and perform adaptive hysteresis compensation on the sensor in the sound device through the compensation amount when the sound device propagates sound in each direction.

[0120] In addition, the present application further provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the above-mentioned intelligent sound device control method.

[0121] In some embodiments, refer to Figure 5 , this figure is a schematic structural diagram of a computer device for implementing the intelligent sound device control method according to some embodiments of the present application. The intelligent sound device control method in the above embodiments can be implemented by Figure 5 the computer device shown. The computer device 500 includes at least one processor 501, a communication bus 502, a memory 503, and at least one communication interface 504.

[0122] The processor 501 can be a general-purpose central processing unit (CPU) or an application-specific integrated circuit (ASIC).

[0123] The communication bus 502 can be used to transmit information between the above components.

[0124] The memory 503 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or can also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 503 can exist independently and be connected to the processor 501 through the communication bus 502. The memory 503 can also be integrated with the processor 501.

[0125] Among them, the memory 503 is used to store the program code for executing the solution of this application and is controlled by the processor 501 to execute. The processor 501 is used to execute the program code stored in the memory 503. The program code can include one or more software modules. The methods used in the above embodiments can be implemented by one or more software modules in the program code in the processor 501 and the memory 503.

[0126] The communication interface 504 uses any device such as a transceiver to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0127] In a specific implementation, as an embodiment, the computer device can include multiple processors, and each of these processors can be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. Here, the processor can refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0128] The computer device described above can be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device can be a desktop computer, a laptop computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of the present application do not limit the type of the computer device.

[0129] In addition, the present application also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the intelligent sound box control method described above is implemented.

[0130] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present application.

[0131] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. An intelligent audio control method, characterized in that: The steps include: Start the delay control system of the smart speaker to obtain the propagation distance of the speaker in all directions in the closed venue; Determine the sound diffusion of the sound in the speaker when it propagates in various directions based on the sensing parameters of the sensor in the speaker and all the propagation distances, and determine the sound focal point of the speaker in the closed venue according to the differences between the various sound diffusions; Determine the hysteresis adjustment amount of the sensor in the speaker for the reflected sound in all directions according to the sound focal point and the dead zone range of the sensor when the speaker is playing, perform diffusion analysis on the sound transmitted by the speaker according to all the hysteresis adjustment amounts, and obtain the sound diffusion range when the sensor in the speaker has hysteresis; Collecting the ambient noise of the speaker in the closed space, predicting the received sound in each direction according to the ambient noise and all propagation distances, and then obtaining the sound pressure level distribution of the speaker in the closed space; The compensation amount of the sensor hysteresis when the speaker plays sound in a closed venue is determined by the range of sound diffusion when the sensor in the speaker has hysteresis and the sound pressure level distribution. When the speaker propagates sound in all directions, the sensor in the speaker is adaptively compensated for hysteresis by the compensation amount.

2. The method according to claim 1, characterized in that Determining the sound diffusion of the sound in the speaker when it propagates in all directions based on the sensing parameters of the sensor in the speaker and all propagation distances specifically includes: Acquire the sensitivity and linearity of the sensor in the speaker, and use the sensitivity and linearity of the sensor in the speaker as sensing parameters of the sensor in the speaker; Select a direction as the selected direction and obtain the sound intensity of the sound emitted by the speaker; Determine the sound propagation loss according to the sound intensity and the propagation distance corresponding to the selected direction among all the propagation distances; Determine the sound diffusion of the sound in the speaker when it propagates in a selected direction according to the sound propagation loss and the sensing parameter; The sound diffusion of the sound in the speaker when it propagates in the remaining directions is then determined.

3. The method according to claim 1, characterized in that Determining the sound focal point of the sound system in a closed venue according to the differences between the sound diffusion degrees specifically includes: Determine the intensity difference between each sound diffusion degree, and use each intensity difference as the difference between the corresponding sound diffusion degrees; Get the enclosure dimensions of the enclosure; The sound focus point of the sound system in the enclosed venue is determined according to the size of the enclosed venue and all differences.

4. The method according to claim 1, characterized in that Determining the hysteresis adjustment amount of the sensor in the speaker for the reflected sound in all directions by the sound focal point and the dead zone range of the sensor when the speaker is playing specifically includes: Obtaining the dead zone range of the sensor when the speaker is playing; Determine the distance from the sound focal point to all directions in the closed area; Select a direction as the selected direction, and determine the sound hysteresis in the selected direction according to the sound diffusion corresponding to the selected direction and the distance corresponding to the selected direction: Determining a hysteresis adjustment amount of the sensor in the speaker for the sound reflected in the selected direction according to the sound hysteresis amount and the dead zone range of the sensor; Continue to determine the hysteresis adjustment amount of the sensor in the speaker for the reflected sound in the remaining directions.

5. The method according to claim 1, characterized in that The diffusion analysis of the sound emitted by the speaker is performed according to all the hysteresis adjustment amounts, and the range of sound diffusion when the sensor in the speaker has hysteresis specifically includes: Obtaining the sound intensity of the sound emitted by the speaker; Determine the sound expansion intensity in all directions according to the sound intensity and all hysteresis adjustment amounts; The range of sound diffusion when the sensor in the speaker has hysteresis is determined according to all sound expansion intensities.

6. The method according to claim 1, characterized in that Predicting the received sound in each direction by using the ambient noise and all propagation distances, and then obtaining the sound pressure level distribution of the sound system in the closed venue specifically includes: Obtain the received sound intensity of received sound in each direction; Determine the noise-removed sound intensity in each direction according to the ambient noise and each received sound intensity; Determine the predicted sound intensity of the received sound in each direction according to all the de-noised sound intensities and all the propagation distances; The sound pressure level distribution of the sound system in the closed space is determined according to all the predicted sound intensities.

7. The method according to claim 1, characterized in that Determining the compensation amount of sensor hysteresis when the speaker plays sound in a closed venue by using the sound diffusion range and the sound pressure level distribution when the sensor in the speaker has hysteresis specifically includes: determining a sound dispersion amount of the enclosed venue according to the sound pressure level distribution; Get the working time of the sensor in the speaker; Determine the response expansion amount of the sensor in the speaker according to the working time and the range of sound diffusion when the sensor in the speaker has hysteresis; A compensation amount of sensor hysteresis when the speaker plays sound in a closed venue is determined according to the sound discrete amount and the response extension amount.

8. An intelligent sound system, comprising a control unit, characterized in that: The control unit comprises: An acquisition module, used to acquire the propagation distance of the speaker in each direction in the closed venue after starting the delay control system of the smart speaker; A processing module, configured to determine the sound diffusion of the sound in the speaker when it propagates in various directions based on the sensing parameters of the sensor in the speaker and all propagation distances, and determine the sound focal point of the speaker in the closed venue according to the differences between the various sound diffusions; The processing module is further used to determine the hysteresis adjustment amount of the sensor in the speaker for the reflected sound in all directions according to the sound focal point and the dead zone range of the sensor when the speaker is playing, and to perform diffusion analysis on the sound transmitted by the speaker according to all the hysteresis adjustment amounts to obtain the sound diffusion range when the sensor in the speaker has hysteresis; The processing module is further used to collect the environmental noise of the speaker in the closed place, predict the received sound in each direction according to the environmental noise and all propagation distances, and then obtain the sound pressure level distribution of the speaker in the closed place; The execution module is used to determine the compensation amount of the sensor hysteresis when the speaker plays sound in a closed place according to the sound diffusion range when the sensor in the speaker has hysteresis and the sound pressure level distribution, and when the speaker propagates sound in all directions, the sensor in the speaker is adaptively compensated for hysteresis according to the compensation amount.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a code, and the processor is configured to obtain the code and execute the intelligent audio control method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the intelligent audio control method according to any one of claims 1 to 7 is implemented.

Images