Data analysis and control method based on cloud-edge-end sound intelligent membrane

Abstract

The present application provides a data analysis and control method based on cloud-edge-end sound intelligent membrane, which belongs to the field of data processing technology, and solves the echo problem in the air dome through dynamic control optimization. The method includes: the cloud server obtains the sound data collected by the edge pickup device, the edge pickup device is deployed at the sound field convergence point in the air dome, and the air dome is deployed with M edge audio devices, M is an integer greater than 3; the M edge audio devices are distributed and deployed in the edge area of ​​the air dome, and the sound wave beams of the M edge audio devices are all directed to the sound field convergence point; the cloud server determines whether the echo intensity of the sound field convergence point is greater than a preset threshold based on the sound data; if the echo intensity of the sound field convergence point is greater than the preset threshold, the cloud server reduces the intensity of the sound wave beams of N edge audio devices among the M edge audio devices, N is an integer greater than 1 and less than M, and the N edge audio devices are discretely distributed.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method for analyzing and controlling data based on cloud-edge-end audio intelligent membranes. Background Art

[0002] With the continuous advancement of science and technology and the continuous development of urban construction, air-domed stadiums are gradually gaining attention as a new architectural form. Air-domed stadiums utilize bubble membrane to construct the venue structure, which is characterized by its lightness, high strength, and strong plasticity. In venues such as stadiums and concert halls, the polymer properties of the membrane material give it high sound wave reflectivity, which is of great significance for optimizing acoustic performance.

[0003] Air dome technology primarily utilizes polymer materials, using specialized processes to create membranes with defined structures and functions. These materials typically possess excellent mechanical and acoustic properties. In applications such as stadiums and concert halls, membranes effectively reflect sound waves, achieving excellent acoustic effects. Furthermore, the membrane's lightweight nature reduces foundation loads during construction.

[0004] Research on the acoustic performance of air domes primarily focuses on aspects such as the reflectivity, absorption, and diffusion rate of sound waves. The reflectivity of sound waves is crucial to the clarity of sound within the dome. The high reflectivity of the membrane material can effectively improve sound clarity within the dome, but it can also lead to echoes. Therefore, effectively suppressing and controlling echoes is a key aspect of research into the acoustic performance of air domes. To address the echo problem in air domes, researchers have proposed a variety of technical approaches. For example, they can adjust the acoustic properties of the membrane material by changing its structural design; use sound-absorbing materials or structures to reduce the reflectivity of sound waves; and use acoustic simulation software to analyze the sound field and optimize the design parameters of the air dome. Furthermore, the acoustic effect can be further improved by adjusting the internal structural layout of the dome or using acoustic partition materials.

[0005] Therefore, how to further optimize and solve the echo problem in air-inflated pavilions is also an issue currently under research. Summary of the Invention

[0006] An embodiment of the present application provides a cloud-edge-end sound intelligent membrane data analysis and control method to solve the echo problem in the air-inflated dome through dynamic control optimization.

[0007] To achieve the above objectives, this application adopts the following technical solutions:

[0008] In a first aspect, a cloud-edge-end sound intelligent membrane data analysis and control method is provided, which is applied to a cloud server deployed in the cloud, the method including: the cloud server obtains sound data collected by an edge sound pickup device, the edge sound pickup device is deployed at a sound field convergence point in an air dome, and the air dome is deployed with M edge sound devices, where M is an integer greater than 3; the M edge sound devices are distributedly deployed in the edge area of ​​the air dome, and the sound wave beams of the M edge sound devices are all directed to the sound field convergence point; the cloud server determines, based on the sound data, whether the echo intensity of the sound field convergence point is greater than a preset threshold; if the echo intensity of the sound field convergence point is greater than the preset threshold, the cloud server reduces the intensity of the sound wave beams of N edge sound devices among the M edge sound devices, where N is an integer greater than 1 and less than M, and the N edge sound devices are discretely distributed edge sound devices among the M edge sound devices.

[0009] Optionally, the sound data is data collected by the edge pickup device over a period of time. The cloud server determines whether the echo intensity of the sound field convergence point is greater than a preset threshold based on the sound data, including: the cloud server analyzes the sound data to determine whether there are multiple sound ripples in the sound data with a similarity higher than a similarity threshold; if there are multiple sound ripples with a similarity higher than the similarity threshold, the cloud server determines whether the echo intensity of the sound field convergence point is greater than the preset threshold through multiple sound ripples.

[0010] Optionally, the cloud server determines whether the echo intensity of the sound field convergence point is greater than a preset threshold through multiple sound ripples, including: the cloud server determines whether the sound wave intensity of at least two sound ripples among the multiple sound ripples is greater than the preset sound wave intensity threshold; if the sound wave intensity of at least two sound ripples is greater than the preset sound wave intensity threshold, the cloud server determines whether the shortest sound wave interval duration between the at least two sound ripples is greater than the preset sound wave interval time threshold; wherein, if the sound wave intensity of at least two sound ripples is greater than the preset sound wave intensity threshold, and the shortest sound wave interval duration between at least two sound ripples is greater than the preset sound wave interval time threshold, it indicates that the echo intensity of the sound field convergence point is greater than the preset threshold, otherwise, the echo intensity of the sound field convergence point is not greater than the preset threshold.

[0011] Optionally, in the circular area covered by the air-inflated pavilion, M edge audio devices are evenly deployed at the edge of the circular area, the sound field convergence point is located in the central area of ​​the circular area, and the cloud server reduces the intensity of the sound wave beams of N edge audio devices among the M edge audio devices, including: the cloud server selects N edge audio devices with odd serial numbers, or N edge audio devices with even serial numbers from the M edge audio devices, and each two adjacent edge audio devices among the N edge audio devices are separated by an edge audio device that does not belong to the N edge audio devices; the cloud server reduces the intensity of the sound wave beams of the N edge audio devices.

[0012] Optionally, the cloud server selects N edge audio devices with odd serial numbers, or N edge audio devices with even serial numbers from M edge audio devices, including: for the cloud server determining that the echo intensity of the sound field convergence point is greater than a preset threshold for the first time: the cloud server selects N edge audio devices with odd serial numbers from the M edge audio devices; for the cloud server determining that the echo intensity of the sound field convergence point is greater than the preset threshold for the second time: the cloud server selects N edge audio devices with even serial numbers from the M edge audio devices, and at this time, MN edge audio devices with odd serial numbers among the M edge audio devices need to be called back to adjust the intensity of the sound wave beam; for the cloud server determining that the echo intensity of the sound field convergence point is greater than the preset threshold for the third time: the cloud server selects N edge audio devices with odd serial numbers from the M edge audio devices, and at this time, MN edge audio devices with even serial numbers among the M edge audio devices need to be called back to adjust the intensity of the sound wave beam; and then, and so on.

[0013] Optionally, the cloud server reduces the intensity of the sound wave beams of each of the N edge audio devices, including: the cloud server sends audio data with reduced gain to the N edge audio devices, and the audio duration of the audio data with reduced gain is greater than or equal to the duration of the sound data; at this time, in the case that the intensity of the sound wave beams of MN edge audio devices needs to be called back, the method also includes: the cloud server sends audio data with normal gain to the MN edge audio devices, and the audio duration of the audio data with normal gain is greater than or equal to the duration of the sound data.

[0014] Optionally, the area covered by the air dome is an elliptical area, with two ends of the elliptical area being a first end and a second end, respectively. The sound field convergence point is located near the first end in the elliptical area. M edge audio devices are evenly deployed at the edge of the elliptical area and near the second end. The cloud server reduces the intensity of the sound wave beams of N edge audio devices among the M edge audio devices, including: the cloud server selects two edge audio devices from the M edge audio devices, N=2, the sum of the serial numbers of the two edge audio devices is K, the positions of the two edge audio devices are symmetrical about a first axis, which is a line connecting the two centers of the elliptical area. If the M edge audio devices are traversed in a clockwise direction according to their respective positions, the serial numbers of the M edge audio devices change from 1 to M. The cloud server reduces the intensity of the sound wave beams of the two edge audio devices.

[0015] Optionally, M is an even number, and the cloud server selects two edge audio devices from the M edge audio devices, including: for the cloud server determining that the echo intensity of the sound field convergence point is greater than a preset threshold for the first time: the cloud server selects the 1st edge audio device and the Mth edge audio device from the M edge audio devices; for the cloud server determining that the echo intensity of the sound field convergence point is greater than the preset threshold for the second time: the cloud server selects the 2nd edge audio device and the M-1th edge audio device from the M edge audio devices. At this time, the 1st edge audio device and the Mth edge audio device need to be called back to the intensity of the sound wave beam; and so on; for the cloud server determining that the echo intensity of the sound field convergence point is greater than the preset threshold for the M / 2th time: the cloud server selects the M / 2th edge audio device and the M / 2+1th edge audio device from the M edge audio devices. At this time, the M / 2-1th edge audio device and the M / 2+2th edge audio device need to be called back with the intensity of the sound wave beam; for the cloud server's M / 2+1th determination that the echo intensity of the sound field convergence point is greater than the preset threshold: the cloud server selects the M / 2-1th edge audio device and the M / 2+2th edge audio device from the M edge audio devices. At this time, the M / 2th edge audio device and the M / 2+1th edge audio device need to be called back with the intensity of the sound wave beam; and so on; for the cloud server's M-1th determination that the echo intensity of the sound field convergence point is greater than the preset threshold: the cloud server selects the 1st edge audio device and the Mth edge audio device from the M edge audio devices. At this time, the 2nd edge audio device and the M-1th edge audio device need to be called back with the intensity of the sound wave beam; then, polling is performed again.

[0016] Optionally, the cloud server reduces the intensity of the sound wave beams of each of the two edge audio devices, including: the cloud server sends audio data with reduced gain to the two edge audio devices, and the audio duration of the audio data with reduced gain is greater than or equal to the duration of the sound data; at this time, in the case that the two edge audio devices need to be called back to adjust the intensity of the sound wave beams, the method also includes: the cloud server sends audio data with normal gain to the two edge audio devices, and the audio duration of the audio data with normal gain is greater than or equal to the duration of the sound data.

[0017] According to a second aspect, a cloud server is provided, which is deployed in the cloud and configured as follows: the cloud server obtains sound data collected by an edge sound pickup device, the edge sound pickup device is deployed at a sound field convergence point in an air dome, and the air dome is deployed with M edge sound devices, where M is an integer greater than 3; the M edge sound devices are distributedly deployed in an edge area of ​​the air dome, and the sound wave beams of the M edge sound devices are all directed to the sound field convergence point; the cloud server determines, based on the sound data, whether the echo intensity of the sound field convergence point is greater than a preset threshold; if the echo intensity of the sound field convergence point is greater than the preset threshold, the cloud server reduces the intensity of the sound wave beams of N edge sound devices among the M edge sound devices, where N is an integer greater than 1 and less than M, and the N edge sound devices are discretely distributed edge sound devices among the M edge sound devices.

[0018] Optionally, the sound data is data collected by the edge pickup device over a period of time. The cloud server determines whether the echo intensity of the sound field convergence point is greater than a preset threshold based on the sound data, including: the cloud server analyzes the sound data to determine whether there are multiple sound ripples in the sound data with a similarity higher than a similarity threshold; if there are multiple sound ripples with a similarity higher than the similarity threshold, the cloud server determines whether the echo intensity of the sound field convergence point is greater than the preset threshold through multiple sound ripples.

[0019] Optionally, the cloud server determines whether the echo intensity of the sound field convergence point is greater than a preset threshold through multiple sound ripples, including: the cloud server determines whether the sound wave intensity of at least two sound ripples among the multiple sound ripples is greater than the preset sound wave intensity threshold; if the sound wave intensity of at least two sound ripples is greater than the preset sound wave intensity threshold, the cloud server determines whether the shortest sound wave interval duration between the at least two sound ripples is greater than the preset sound wave interval time threshold; wherein, if the sound wave intensity of at least two sound ripples is greater than the preset sound wave intensity threshold, and the shortest sound wave interval duration between at least two sound ripples is greater than the preset sound wave interval time threshold, it indicates that the echo intensity of the sound field convergence point is greater than the preset threshold, otherwise, the echo intensity of the sound field convergence point is not greater than the preset threshold.

[0020] Optionally, in the circular area covered by the air-inflated pavilion, M edge audio devices are evenly deployed at the edge of the circular area, the sound field convergence point is located in the central area of ​​the circular area, and the cloud server reduces the intensity of the sound wave beams of N edge audio devices among the M edge audio devices, including: the cloud server selects N edge audio devices with odd serial numbers, or N edge audio devices with even serial numbers from the M edge audio devices, and each two adjacent edge audio devices among the N edge audio devices are separated by an edge audio device that does not belong to the N edge audio devices; the cloud server reduces the intensity of the sound wave beams of the N edge audio devices.

[0021] Optionally, the cloud server selects N edge audio devices with odd serial numbers, or N edge audio devices with even serial numbers from M edge audio devices, including: for the cloud server determining that the echo intensity of the sound field convergence point is greater than a preset threshold for the first time: the cloud server selects N edge audio devices with odd serial numbers from the M edge audio devices; for the cloud server determining that the echo intensity of the sound field convergence point is greater than the preset threshold for the second time: the cloud server selects N edge audio devices with even serial numbers from the M edge audio devices, and at this time, MN edge audio devices with odd serial numbers among the M edge audio devices need to be called back to adjust the intensity of the sound wave beam; for the cloud server determining that the echo intensity of the sound field convergence point is greater than the preset threshold for the third time: the cloud server selects N edge audio devices with odd serial numbers from the M edge audio devices, and at this time, MN edge audio devices with even serial numbers among the M edge audio devices need to be called back to adjust the intensity of the sound wave beam; and then, and so on.

[0022] Optionally, the cloud server reduces the intensity of the sound wave beams of each of the N edge audio devices, including: the cloud server sends audio data with reduced gain to the N edge audio devices, and the audio duration of the audio data with reduced gain is greater than or equal to the duration of the sound data; at this time, in the case that the intensity of the sound wave beams of MN edge audio devices needs to be called back, the method also includes: the cloud server sends audio data with normal gain to the MN edge audio devices, and the audio duration of the audio data with normal gain is greater than or equal to the duration of the sound data.

[0023] Optionally, the area covered by the air dome is an elliptical area, with two ends of the elliptical area being a first end and a second end, respectively. The sound field convergence point is located near the first end in the elliptical area. M edge audio devices are evenly deployed at the edge of the elliptical area and near the second end. The cloud server reduces the intensity of the sound wave beams of N edge audio devices among the M edge audio devices, including: the cloud server selects two edge audio devices from the M edge audio devices, N=2, the sum of the serial numbers of the two edge audio devices is K, the positions of the two edge audio devices are symmetrical about a first axis, which is a line connecting the two centers of the elliptical area. If the M edge audio devices are traversed in a clockwise direction according to their respective positions, the serial numbers of the M edge audio devices change from 1 to M. The cloud server reduces the intensity of the sound wave beams of the two edge audio devices.

[0024] Optionally, M is an even number, and the cloud server selects two edge audio devices from the M edge audio devices, including: for the cloud server determining that the echo intensity of the sound field convergence point is greater than a preset threshold for the first time: the cloud server selects the 1st edge audio device and the Mth edge audio device from the M edge audio devices; for the cloud server determining that the echo intensity of the sound field convergence point is greater than the preset threshold for the second time: the cloud server selects the 2nd edge audio device and the M-1th edge audio device from the M edge audio devices. At this time, the 1st edge audio device and the Mth edge audio device need to be called back to the intensity of the sound wave beam; and so on; for the cloud server determining that the echo intensity of the sound field convergence point is greater than the preset threshold for the M / 2th time: the cloud server selects the M / 2th edge audio device and the M / 2+1th edge audio device from the M edge audio devices. At this time, the M / 2-1th edge audio device and the M / 2+2th edge audio device need to be called back with the intensity of the sound wave beam; for the cloud server's M / 2+1th determination that the echo intensity of the sound field convergence point is greater than the preset threshold: the cloud server selects the M / 2-1th edge audio device and the M / 2+2th edge audio device from the M edge audio devices. At this time, the M / 2th edge audio device and the M / 2+1th edge audio device need to be called back with the intensity of the sound wave beam; and so on; for the cloud server's M-1th determination that the echo intensity of the sound field convergence point is greater than the preset threshold: the cloud server selects the 1st edge audio device and the Mth edge audio device from the M edge audio devices. At this time, the 2nd edge audio device and the M-1th edge audio device need to be called back with the intensity of the sound wave beam; then, polling is performed again.

[0025] Optionally, the cloud server reduces the intensity of the sound wave beams of each of the two edge audio devices, including: the cloud server sends audio data with reduced gain to the two edge audio devices, and the audio duration of the audio data with reduced gain is greater than or equal to the duration of the sound data; at this time, in the case that the two edge audio devices need to be called back to adjust the intensity of the sound wave beams, the method also includes: the cloud server sends audio data with normal gain to the two edge audio devices, and the audio duration of the audio data with normal gain is greater than or equal to the duration of the sound data.

[0026] In a third aspect, a computer-readable storage medium is provided, comprising: a computer program or instructions; when the computer program or instructions are run on a computer, the computer is caused to execute the method described in the first aspect.

[0027] In a fourth aspect, a computer program product is provided, comprising: a computer program or instructions, which, when executed on a computer, causes the computer to execute the method described in the first aspect.

[0028] In summary, based on the edge sound pickup device deployed at the sound field convergence point in the air dome, and the air dome is deployed with M edge sound devices, and the M edge sound devices are distributed and deployed in the edge area of ​​the air dome, the cloud server located in the cloud can determine whether the echo intensity of the sound field convergence point is greater than the preset threshold by obtaining the sound data collected by the edge sound pickup device; if the echo intensity of the sound field convergence point is greater than the preset threshold, the cloud server reduces the intensity of the sound wave beam of each of the N edge sound devices among the M edge sound devices. At this time, since the N edge sound devices are discretely distributed edge sound devices among the M edge sound devices, reducing the intensity of the sound wave beam can achieve echo suppression, that is, solving the echo problem in the air dome through dynamic control optimization. In addition, since the above solution is implemented through the cloud, the edge sound devices in the air dome only need to be networked to the cloud, which can reduce the complexity of its actual deployment. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 A schematic diagram of the cloud system framework provided in an embodiment of the present application;

[0030] Figure 2 Schematic diagram of the application scenario of the air dome provided in this application embodiment Figure 1 ;

[0031] Figure 3 Schematic diagram of the application scenario of the air dome provided in this application embodiment Figure 2 .

[0032] Figure 4 A flow chart of the cloud-edge-end audio intelligent film data analysis and control method provided in an embodiment of the present application; DETAILED DESCRIPTION

[0033] The technical solution in this application will be described below with reference to the accompanying drawings.

[0034] In the embodiment of the present application, "indication" may include direct indication and indirect indication, and may also include explicit indication and implicit indication. The information indicated by a certain information (such as the first indication information, the second indication information, or the third indication information below) is called information to be indicated. In the specific implementation process, there are many ways to indicate the information to be indicated, such as but not limited to, the information to be indicated can be directly indicated, such as the information to be indicated itself or the index of the information to be indicated. The information to be indicated can also be indirectly indicated by indicating other information, wherein the other information and the information to be indicated have an association relationship. It is also possible to indicate only a part of the information to be indicated, while the other parts of the information to be indicated are known or agreed in advance. For example, the indication of specific information can be achieved by means of the arrangement order of each information agreed in advance (such as specified in the protocol), thereby reducing the indication overhead to a certain extent. At the same time, the common parts of each information can be identified and indicated uniformly to reduce the indication overhead caused by indicating the same information separately.

[0035] In addition, the specific indication method can also be various existing indication methods, such as but not limited to the above-mentioned indication methods and various combinations thereof. The specific details of the various indication methods can be referred to the prior art and will not be repeated herein. As can be seen from the above, for example, when it is necessary to indicate multiple information of the same type, there may be a situation where the indication methods for different information are different. In the specific implementation process, the required indication method can be selected according to specific needs. The embodiment of the present application does not limit the selected indication method. In this way, the indication method involved in the embodiment of the present application should be understood to cover various methods that can enable the party to be indicated to obtain the information to be indicated.

[0036] It should be understood that the information to be indicated can be sent as a whole or divided into multiple sub-information and sent separately, and the sending period and / or sending time of these sub-information can be the same or different. The specific sending method is not limited in the embodiments of this application. The sending period and / or sending time of these sub-information can be predefined, for example, predefined according to a protocol, or can be configured by the transmitting device by sending configuration information to the receiving device.

[0037] "Pre-definition" or "pre-configuration" can be implemented by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in the device, and the embodiments of the present application do not limit the specific implementation method. Among them, "saving" can mean saving in one or more memories. The one or more memories can be set separately or integrated in an encoder or decoder, a processor, or a communication device. The one or more memories can also be partially set separately and partially integrated in a decoder, a processor, or a communication device. The type of memory can be any form of storage medium, and the embodiments of the present application do not limit this.

[0038] The "protocol" involved in the embodiments of the present application may refer to a protocol family in the communication field, a standard protocol with a similar protocol family frame structure, or a related protocol used in future communication systems. The embodiments of the present application do not make specific limitations on this.

[0039] In the embodiments of the present application, descriptions such as "when...", "in the case of...", "if" and "if" all mean that the device will perform corresponding processing under certain objective circumstances. It does not limit the time, nor does it require the device to perform judgment actions when implemented, nor does it mean that there are other limitations.

[0040] In the description of the embodiments of this application, unless otherwise specified, " / " indicates that the associated objects are in an "or" relationship. For example, A / B can mean A or B. "And / or" in the embodiments of this application is merely a description of the associated relationship between the associated objects, indicating that three relationships can exist. For example, "A and / or B" can mean: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, in the description of the embodiments of this application, unless otherwise specified, "multiple" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural. Furthermore, to facilitate the clear description of the technical solutions of the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish between identical or similar items with substantially the same function or effect. Those skilled in the art will understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit differences. At the same time, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or design. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way for easy understanding.

[0041] To facilitate understanding of the embodiments of the present application, first Figure 1 The cloud system shown in FIG is used as an example to describe in detail the system applicable to the embodiment of the present application. Figure 1 A schematic diagram of the architecture of a cloud system applicable to the method provided in an embodiment of the present application.

[0042] like Figure 1 As shown, the cloud system includes: edge sound pickup equipment, edge audio equipment and cloud server.

[0043] Edge audio devices generally refer to audio devices used in edge service scenarios. For example, an audio device can be a microphone, such as an array microphone. In one possible implementation, the device could be a Shure MXA902 linear array microphone, which can include a built-in Dante AVIO network module (supporting 128-channel audio transmission) and support pushing noise-reduced voice streams to the cloud via the Shure IntellimixCloud API. Edge audio devices generally refer to audio devices used in edge service scenarios. For example, they could be speakers that support beamforming, meaning they can send sound beams. For example, by controlling the direction of sound wave propagation through a speaker array, they focus sound energy on a specific area, rapidly attenuating the sound pressure level beyond that area. In one possible implementation, the audio device could be a Yamaha VXL1B-16P steerable array speaker, which supports remote platform control and can receive beam angle configuration files (JSON format) sent from the cloud. Cloud servers can be deployed in the cloud, such as cloud servers or server clusters, Azure Stack HCI hyperconverged clusters, or any other possible form factor, without specific limitations.

[0044] The sound pickup device can connect to the edge gateway via the MQTT / RTSP protocol, the audio device can connect to the edge gateway via the Dante / AES67 protocol, and the edge gateway can connect to the cloud server via the TLS1.3 protocol. This allows for a bandwidth of 2-8 Mbps / channel between the sound pickup device and the cloud service, and a bandwidth of 15 Mbps / channel between the audio device and the cloud service, ensuring an end-to-end delay of ≤200ms (from sound pickup to cancellation sound output), meeting the ISO 3382-3 acoustic response standard.

[0045] For the air-inflated pavilion, the edge sound pickup device is deployed at the sound field convergence point in the air-inflated pavilion, that is, the core audio-visual area. The air-inflated pavilion is deployed with M edge sound devices, where M is an integer greater than 3; the M edge sound devices are distributedly deployed in the edge area of ​​the air-inflated pavilion.

[0046] For example, Figure 2 As shown, in one application scenario of an air dome, the circular area covered by the air dome (i.e., the area projected onto the ground) is a circular area. M edge speakers are evenly deployed at the edges of the circular area, with the sound field convergence point located in the center of the circular area. For example, if M = 6, six edge speakers are evenly deployed at the edges of the circular area, connected to form a hexagon. The sound beam of each edge speaker is directed toward the edge pickup device at the sound field convergence point, but the sound beam of each edge speaker does not reach the edge pickup device at the sound field convergence point to prevent strong reverberation caused by overlapping multiple sound beams.

[0047] For example, in another application scenario of the air dome, Figure 3 As shown, the elliptical area of ​​the area covered by the air dome, that is, the area projected onto the ground is an elliptical area. The two ends of the elliptical area are the first end and the second end respectively. The sound field convergence point is located in the elliptical area close to the first end. M edge audio devices are evenly deployed at the edge of the elliptical area and close to the second end. If M=6, the 6 edge audio devices are evenly deployed near the edge of the second end. The sound beam of each edge audio device is directed to the edge pickup device at the sound field convergence point, but the sound beam of each edge audio device does not cover the edge pickup device at the sound field convergence point to avoid the overlap of multiple sound beams and the generation of strong reverberation.

[0048] See also Figure 4 The present application embodiment provides a method for analyzing and controlling data based on cloud-edge-end audio intelligence. The method can be executed by a cloud server. The process of the method includes:

[0049] S401: The cloud server obtains the sound data collected by the edge sound pickup device.

[0050] As mentioned above, the edge sound pickup device is deployed at the sound field convergence point in the air dome. The air dome is deployed with M edge sound devices, where M is an integer greater than 3. The M edge sound devices are distributedly deployed in the edge area of ​​the air dome, and the sound wave beams of each of the M edge sound devices are directed to the sound field convergence point.

[0051] The sound data is collected by the edge pickup device over a continuous period of time. This continuous period can be 10 seconds, 5 seconds, etc. The edge pickup device can execute periodically, and the length of the period is the same as the continuous period. In other words, the edge pickup device can report the sound data collected during each period to the cloud server. For ease of understanding, the embodiments of this application are described using any period as an example.

[0052] S402: The cloud server determines whether the echo intensity at the sound field convergence point is greater than a preset threshold based on the sound data.

[0053] The cloud server analyzes the sound data to determine whether there are multiple sound ripples with a similarity higher than the similarity threshold in the sound data, that is, whether there are multiple echoes. If there are multiple sound ripples with a similarity higher than the similarity threshold, the cloud server determines whether the echo intensity at the sound field convergence point is greater than a preset threshold through the multiple sound ripples. For example, the cloud server determines whether the sound wave intensity of at least two sound ripples among the multiple sound ripples is greater than the preset sound wave intensity threshold; if the sound wave intensity of at least two sound ripples is less than or equal to the preset sound wave intensity threshold, it means that the echo is relatively small and does not affect the actual audio-visual experience, and no processing is required. It should be understood that the sound wave intensity threshold can be dynamically set according to actual conditions, and the embodiments of the present application do not impose specific restrictions. If the sound wave intensity of at least two sound ripples is greater than the preset sound wave intensity threshold, the cloud server determines whether the shortest sound wave interval between the at least two sound ripples is greater than the preset sound wave interval time threshold.

[0054] Among them, if the sound wave intensity of at least two sound ripples is greater than the preset sound wave intensity threshold, and the shortest sound wave interval between at least two sound ripples is greater than the preset sound wave interval time threshold, then it means that the echo intensity at the sound field convergence point is greater than the preset threshold. In other words, the shortest sound wave interval is greater than the preset sound wave interval time threshold, which means that the time interval between the two large echoes is relatively large. This situation will make the user clearly hear the echo, thus affecting the audio-visual experience and requiring dynamic adjustment. Otherwise, the echo intensity at the sound field convergence point is not greater than the preset threshold. It should be understood that the sound wave interval time threshold can be 1.2 seconds to 1.5 seconds, and can be dynamically set according to actual conditions without specific restrictions.

[0055] S403: If the echo intensity at the sound field convergence point is greater than a preset threshold, the cloud server reduces the intensity of the sound wave beams of N edge audio devices among the M edge audio devices.

[0056] N is an integer greater than 1 and less than M.

[0057] The N edge speaker devices are discretely distributed edge speaker devices among the M edge speaker devices.

[0058] Regarding the above Figure 2 In the scenario shown, one possible implementation is:

[0059] If the M edge audio devices are traversed in a clockwise direction according to their respective positions, the sequence numbers of the M edge audio devices will increase by 1 starting from 1 until they reach M. The sequence number of each edge audio device can indicate the number of the edge audio device it is.

[0060] On this basis, the cloud server selects N edge audio devices with odd serial numbers, or N edge audio devices with even serial numbers from the M edge audio devices, and each two adjacent edge audio devices among the N edge audio devices are separated by an edge audio device that does not belong to the N edge audio devices, that is, sparse selection is achieved, thereby achieving echo suppression or attenuation.

[0061] For example, for the cloud server to determine that the echo intensity of the sound field convergence point is greater than the preset threshold for the first time: the cloud server selects N edge audio devices with odd serial numbers from M edge audio devices; for the cloud server to determine that the echo intensity of the sound field convergence point is greater than the preset threshold for the second time: the cloud server selects N edge audio devices with even serial numbers from M edge audio devices. At this time, MN edge audio devices with odd serial numbers among the M edge audio devices need to be called back to adjust the intensity of the sound wave beam; for the cloud server to determine that the echo intensity of the sound field convergence point is greater than the preset threshold for the third time: the cloud server selects N edge audio devices with odd serial numbers from M edge audio devices. At this time, MN edge audio devices with even serial numbers among the M edge audio devices need to be called back to adjust the intensity of the sound wave beam; and then, and so on.

[0062] For easy understanding, such as Figure 2 As shown, for the cloud server to determine that the echo intensity of the sound field convergence point is greater than the preset threshold for the first time: the cloud server selects the 1st, 3rd, and 5th edge sound devices from the 6 edge sound devices; for the cloud server to determine that the echo intensity of the sound field convergence point is greater than the preset threshold for the second time: the cloud server selects the 2nd, 4th, and 6th edge sound devices from the 6 edge sound devices. At this time, the 1st, 3rd, and 5th edge sound devices among the 6 edge sound devices need to be called back with the intensity of the sound wave beam; for the cloud server to determine that the echo intensity of the sound field convergence point is greater than the preset threshold for the third time: the cloud server again selects the 1st, 3rd, and 5th edge sound devices from the 6 edge sound devices. At this time, the 2nd, 4th, and 6th edge sound devices among the 6 edge sound devices need to be called back with the intensity of the sound wave beam; and then, and so on.

[0063] As a result, the cloud server reduces the intensity of the sound beams of each of the N edge audio devices. For example, the cloud server sends audio data with reduced gain to the N edge audio devices (e.g., the gain can be reduced by 5-15% under normal gain), and the audio duration of the audio data with reduced gain is greater than or equal to the duration of the sound data, to ensure that the audio data has not yet finished playing when the edge pickup is reported next time. At this time, if the intensity of the sound beams of the MN edge audio devices needs to be called back, the method also includes: the cloud server sends audio data with normal gain to the MN edge audio devices, and the audio duration of the audio data with normal gain is greater than or equal to the duration of the sound data.

[0064] It should be understood that since the intensity of the sound wave beam of some edge audio equipment is not reduced in each adjustment, the overall audio-visual effect of the system will not be greatly affected, and the impact of the echo is also suppressed or weakened.

[0065] Regarding the above Figure 3 In the scenario shown, another possible implementation is:

[0066] If the M edge audio devices are traversed in a clockwise direction according to their respective positions, the sequence numbers of the M edge audio devices will increase by 1 starting from 1 until they reach M. The sequence number of each edge audio device can indicate the number of the edge audio device it is.

[0067] On this basis, the cloud server selects two edge audio devices from M edge audio devices, N=2, the sum of the serial numbers of the two edge audio devices is K, and the positions of the two edge audio devices are symmetrical about the first axis, which is the line connecting the two centers of the elliptical area.

[0068] Specifically, M is an even number. For the cloud server to determine that the echo intensity of the sound field convergence point is greater than the preset threshold for the first time, the cloud server selects the 1st edge sound device and the Mth edge sound device from the M edge sound devices; for the cloud server to determine that the echo intensity of the sound field convergence point is greater than the preset threshold for the second time, the cloud server selects the 2nd edge sound device and the M-1th edge sound device from the M edge sound devices. At this time, the 1st edge sound device and the Mth edge sound device need to be called back to the intensity of the sound wave beam; and so on; for the cloud server to determine that the echo intensity of the sound field convergence point is greater than the preset threshold for the M / 2th time, the cloud server selects the M / 2th edge sound device and the M / 2+1th edge sound device from the M edge sound devices. At this time, the M / 2-1th edge sound device The audio device and the M / 2+2th edge audio device need to be called back for the intensity of the sound wave beam; for the cloud server's M / 2+1th determination that the echo intensity of the sound field convergence point is greater than the preset threshold: the cloud server selects the M / 2-1th edge audio device and the M / 2+2th edge audio device from the M edge audio devices. At this time, the M / 2th edge audio device and the M / 2+1th edge audio device need to be called back for the intensity of the sound wave beam; and so on; for the cloud server's M-1th determination that the echo intensity of the sound field convergence point is greater than the preset threshold: the cloud server selects the 1st edge audio device and the Mth edge audio device from the M edge audio devices. At this time, the 2nd edge audio device and the M-1th edge audio device need to be called back for the intensity of the sound wave beam; then, poll again.

[0069] For easy understanding, such as Figure 2As shown, when the cloud server determines that the echo intensity of the sound field convergence point is greater than the preset threshold for the first time, the cloud server selects the first and sixth edge sound devices from the six edge sound devices. When the cloud server determines that the echo intensity of the sound field convergence point is greater than the preset threshold for the second time, the cloud server selects the second and fifth edge sound devices from the six edge sound devices. At this time, the first and sixth edge sound devices among the six edge sound devices need to be called back with the intensity of the sound wave beam. When the cloud server determines that the echo intensity of the sound field convergence point is greater than the preset threshold for the third time, the cloud server selects the third and fourth edge sound devices from the six edge sound devices. At this time, the second and fifth edge sound devices among the six edge sound devices need to be called back with the intensity of the sound wave beam. When the cloud server determines that the echo intensity of the sound field convergence point is greater than the preset threshold for the fourth time, the cloud server selects the second and fifth edge sound devices from the six edge sound devices. At this time, the third and fourth edge sound devices among the six edge sound devices need to be called back with the intensity of the sound wave beam. If the cloud server determines the echo intensity of the sound field convergence point is greater than the preset threshold for the fifth time, the cloud server selects the first and sixth edge speakers from the six edge speakers. At this time, the second and fifth edge speakers among the six edge speakers need to be called back for the intensity of the sound wave beam. Then, polling is repeated.

[0070] It should be understood that, since the intensity of the sound beam of some edge audio equipment is not reduced during each adjustment, the overall audio-visual effect of the system will not be greatly affected. Figure 3 In the scenario shown, the sound field convergence point is located in the elliptical area near the first end. The pan-energy of the sound wave beam of the edge sound device may be reflected by the membrane wall of the first end. Therefore, two edge sound devices symmetrically located along the first axis can be selected to reduce the gain of the sound wave beam, thereby reducing reflections and achieving the effect of suppressing or weakening echoes.

[0071] On this basis, the cloud server reduces the intensity of the sound beams of the two edge audio devices. For example, the cloud server sends audio data with reduced gain to the two edge audio devices, where the duration of the audio of the audio data with reduced gain is greater than or equal to the duration of the sound data. At this time, if the intensity of the sound beams of the two edge audio devices needs to be adjusted back, the method also includes: the cloud server sends audio data with normal gain to the two edge audio devices, where the duration of the audio of the audio data with normal gain is greater than or equal to the duration of the sound data.

[0072] In summary, based on the edge sound pickup device deployed at the sound field convergence point in the air dome, and the air dome is deployed with M edge sound devices, and the M edge sound devices are distributed and deployed in the edge area of ​​the air dome, the cloud server located in the cloud can determine whether the echo intensity of the sound field convergence point is greater than the preset threshold by obtaining the sound data collected by the edge sound pickup device; if the echo intensity of the sound field convergence point is greater than the preset threshold, the cloud server reduces the intensity of the sound wave beam of each of the N edge sound devices among the M edge sound devices. At this time, since the N edge sound devices are discretely distributed edge sound devices among the M edge sound devices, reducing the intensity of the sound wave beam can achieve echo suppression, that is, solving the echo problem in the air dome through dynamic control optimization. In addition, since the above solution is implemented through the cloud, the edge sound devices in the air dome only need to be networked to the cloud, which can reduce the complexity of its actual deployment.

[0073] In this embodiment, a cloud server is also provided, which is deployed in the cloud and is configured as follows: the cloud server obtains sound data collected by the edge sound pickup device, the edge sound pickup device is deployed at the sound field convergence point in the air-inflated dome, and the air-inflated dome is deployed with M edge sound devices, where M is an integer greater than 3; the M edge sound devices are distributedly deployed in the edge area of ​​the air-inflated dome, and the sound wave beams of the M edge sound devices are all directed to the sound field convergence point; the cloud server determines whether the echo intensity of the sound field convergence point is greater than a preset threshold based on the sound data; if the echo intensity of the sound field convergence point is greater than the preset threshold, the cloud server reduces the intensity of the sound wave beams of N edge sound devices among the M edge sound devices, where N is an integer greater than 1 and less than M, and the N edge sound devices are discretely distributed edge sound devices among the M edge sound devices.

[0074] Optionally, the sound data is data collected by the edge pickup device over a period of time. The cloud server determines whether the echo intensity of the sound field convergence point is greater than a preset threshold based on the sound data, including: the cloud server analyzes the sound data to determine whether there are multiple sound ripples in the sound data with a similarity higher than a similarity threshold; if there are multiple sound ripples with a similarity higher than the similarity threshold, the cloud server determines whether the echo intensity of the sound field convergence point is greater than the preset threshold through multiple sound ripples.

[0075] Optionally, the cloud server determines whether the echo intensity of the sound field convergence point is greater than a preset threshold through multiple sound ripples, including: the cloud server determines whether the sound wave intensity of at least two sound ripples among the multiple sound ripples is greater than the preset sound wave intensity threshold; if the sound wave intensity of at least two sound ripples is greater than the preset sound wave intensity threshold, the cloud server determines whether the shortest sound wave interval duration between the at least two sound ripples is greater than the preset sound wave interval time threshold; wherein, if the sound wave intensity of at least two sound ripples is greater than the preset sound wave intensity threshold, and the shortest sound wave interval duration between at least two sound ripples is greater than the preset sound wave interval time threshold, it indicates that the echo intensity of the sound field convergence point is greater than the preset threshold, otherwise, the echo intensity of the sound field convergence point is not greater than the preset threshold.

[0076] Optionally, in the circular area covered by the air-inflated pavilion, M edge audio devices are evenly deployed at the edge of the circular area, the sound field convergence point is located in the central area of ​​the circular area, and the cloud server reduces the intensity of the sound wave beams of N edge audio devices among the M edge audio devices, including: the cloud server selects N edge audio devices with odd serial numbers, or N edge audio devices with even serial numbers from the M edge audio devices, and each two adjacent edge audio devices among the N edge audio devices are separated by an edge audio device that does not belong to the N edge audio devices; the cloud server reduces the intensity of the sound wave beams of the N edge audio devices.

[0077] Optionally, the cloud server selects N edge audio devices with odd serial numbers, or N edge audio devices with even serial numbers from M edge audio devices, including: for the cloud server determining that the echo intensity of the sound field convergence point is greater than a preset threshold for the first time: the cloud server selects N edge audio devices with odd serial numbers from the M edge audio devices; for the cloud server determining that the echo intensity of the sound field convergence point is greater than the preset threshold for the second time: the cloud server selects N edge audio devices with even serial numbers from the M edge audio devices, and at this time, MN edge audio devices with odd serial numbers among the M edge audio devices need to be called back to adjust the intensity of the sound wave beam; for the cloud server determining that the echo intensity of the sound field convergence point is greater than the preset threshold for the third time: the cloud server selects N edge audio devices with odd serial numbers from the M edge audio devices, and at this time, MN edge audio devices with even serial numbers among the M edge audio devices need to be called back to adjust the intensity of the sound wave beam; and then, and so on.

[0078] Optionally, the cloud server reduces the intensity of the sound wave beams of each of the N edge audio devices, including: the cloud server sends audio data with reduced gain to the N edge audio devices, and the audio duration of the audio data with reduced gain is greater than or equal to the duration of the sound data; at this time, in the case that the intensity of the sound wave beams of MN edge audio devices needs to be called back, the method also includes: the cloud server sends audio data with normal gain to the MN edge audio devices, and the audio duration of the audio data with normal gain is greater than or equal to the duration of the sound data.

[0079] Optionally, the area covered by the air dome is an elliptical area, with two ends of the elliptical area being a first end and a second end, respectively. The sound field convergence point is located near the first end in the elliptical area. M edge audio devices are evenly deployed at the edge of the elliptical area and near the second end. The cloud server reduces the intensity of the sound wave beams of N edge audio devices among the M edge audio devices, including: the cloud server selects two edge audio devices from the M edge audio devices, N=2, the sum of the serial numbers of the two edge audio devices is K, the positions of the two edge audio devices are symmetrical about a first axis, which is a line connecting the two centers of the elliptical area. If the M edge audio devices are traversed in a clockwise direction according to their respective positions, the serial numbers of the M edge audio devices change from 1 to M. The cloud server reduces the intensity of the sound wave beams of the two edge audio devices.

[0080] Optionally, M is an even number, and the cloud server selects two edge audio devices from the M edge audio devices, including: for the cloud server determining that the echo intensity of the sound field convergence point is greater than a preset threshold for the first time: the cloud server selects the 1st edge audio device and the Mth edge audio device from the M edge audio devices; for the cloud server determining that the echo intensity of the sound field convergence point is greater than the preset threshold for the second time: the cloud server selects the 2nd edge audio device and the M-1th edge audio device from the M edge audio devices. At this time, the 1st edge audio device and the Mth edge audio device need to be called back to the intensity of the sound wave beam; and so on; for the cloud server determining that the echo intensity of the sound field convergence point is greater than the preset threshold for the M / 2th time: the cloud server selects the M / 2th edge audio device and the M / 2+1th edge audio device from the M edge audio devices. At this time, the M / 2-1th edge audio device and the M / 2+2th edge audio device need to be called back with the intensity of the sound wave beam; for the cloud server's M / 2+1th determination that the echo intensity of the sound field convergence point is greater than the preset threshold: the cloud server selects the M / 2-1th edge audio device and the M / 2+2th edge audio device from the M edge audio devices. At this time, the M / 2th edge audio device and the M / 2+1th edge audio device need to be called back with the intensity of the sound wave beam; and so on; for the cloud server's M-1th determination that the echo intensity of the sound field convergence point is greater than the preset threshold: the cloud server selects the 1st edge audio device and the Mth edge audio device from the M edge audio devices. At this time, the 2nd edge audio device and the M-1th edge audio device need to be called back with the intensity of the sound wave beam; then, polling is performed again.

[0081] Optionally, the cloud server reduces the intensity of the sound wave beams of each of the two edge audio devices, including: the cloud server sends audio data with reduced gain to the two edge audio devices, and the audio duration of the audio data with reduced gain is greater than or equal to the duration of the sound data; at this time, in the case that the two edge audio devices need to be called back to adjust the intensity of the sound wave beams, the method also includes: the cloud server sends audio data with normal gain to the two edge audio devices, and the audio duration of the audio data with normal gain is greater than or equal to the duration of the sound data.

[0082] The above embodiments can be implemented in whole or in part via software, hardware (e.g., circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When loaded or executed on a computer, the processes or functions described in the embodiments of this application are fully or partially performed. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired means (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0083] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0084] In this application, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0085] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0086] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0087] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0088] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0089] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0090] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0091] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0092] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for analyzing and controlling data based on cloud-edge-end audio intelligent membrane, characterized in that: Applied to a cloud server deployed in the cloud, the method includes: The cloud server obtains sound data collected by the edge sound pickup device, where the edge sound pickup device is deployed at a sound field convergence point in the air dome. The air dome is deployed with M edge sound devices, where M is an integer greater than 3. The M edge sound devices are distributedly deployed in an edge area of ​​the air dome, and the sound wave beams of each of the M edge sound devices are directed toward the sound field convergence point. The cloud server determines, based on the sound data, whether the echo intensity of the sound field convergence point is greater than a preset threshold; If the echo intensity of the sound field convergence point is greater than the preset threshold, the cloud server reduces the intensity of the sound wave beam of each of N edge sound devices among the M edge sound devices, where N is an integer greater than 1 and less than M, and the N edge sound devices are discretely distributed edge sound devices among the M edge sound devices.

2. The method according to claim 1, characterized in that The sound data is data collected by the edge sound pickup device over a period of time. The cloud server determines whether the echo intensity of the sound field convergence point is greater than a preset threshold based on the sound data, including: The cloud server determines, by analyzing the sound data, whether there are multiple sound ripples in the sound data whose similarity is higher than a similarity threshold; If there are multiple sound ripples with similarity higher than the similarity threshold, the cloud server determines whether the echo intensity of the sound field convergence point is greater than the preset threshold through the multiple sound ripples.

3. The method according to claim 2, characterized in that The cloud server determines, by using the multiple sound ripples, whether the echo intensity of the sound field convergence point is greater than the preset threshold, including: The cloud server determines whether the sound wave intensities of at least two sound waves among the plurality of sound waves are greater than a preset sound wave intensity threshold; If the sound wave intensities of the at least two sound ripples are greater than the preset sound wave intensity threshold, the cloud server determines whether the shortest sound wave interval between the at least two sound ripples is greater than the preset sound wave interval time threshold; Among them, if the sound wave intensity of at least two sound ripples is greater than the preset sound wave intensity threshold, and the shortest sound wave interval between the at least two sound ripples is greater than the preset sound wave interval time threshold, it means that the echo intensity of the sound field convergence point is greater than the preset threshold; otherwise, the echo intensity of the sound field convergence point is not greater than the preset threshold.

4. The method according to any one of claims 1 to 3, characterized in that The air dome is covered by a circular area, the M edge audio devices are evenly deployed at the edge of the circular area, the sound field convergence point is located in the center of the circular area, and the cloud server reduces the intensity of the sound wave beam of each of N edge audio devices among the M edge audio devices, including: The cloud server selects the N edge audio devices with odd serial numbers, or the N edge audio devices with even serial numbers, from the M edge audio devices, where every two adjacent edge audio devices among the N edge audio devices are separated by an edge audio device that is not one of the N edge audio devices. The cloud server reduces the intensity of the sound wave beams of each of the N edge audio devices.

5. The method according to claim 4, characterized in that The cloud server selects the N edge audio devices with odd serial numbers, or the N edge audio devices with even serial numbers, from the M edge audio devices, including: When the cloud server determines for the first time that the echo intensity of the sound field convergence point is greater than the preset threshold: The cloud server selects the N edge audio devices with odd serial numbers from the M edge audio devices; When the cloud server determines for the second time that the echo intensity of the sound field convergence point is greater than the preset threshold: The cloud server selects the N edge sound devices with even serial numbers from the M edge sound devices. At this time, the MN edge sound devices with odd serial numbers among the M edge sound devices need to be called back for the intensity of the sound wave beam; When the cloud server determines for the third time that the echo intensity of the sound field convergence point is greater than the preset threshold: The cloud server selects the N edge sound devices with odd serial numbers from the M edge sound devices. At this time, the MN edge sound devices with even serial numbers among the M edge sound devices need to be called back for the intensity of the sound wave beam; And so on.

6. The method according to claim 5, characterized in that The cloud server reduces the intensity of the sound wave beams of each of the N edge audio devices, including: The cloud server sends the audio data with reduced gain to the N edge audio devices, where the duration of the audio data with reduced gain is greater than or equal to the duration of the sound data; At this time, when the intensity of the sound wave beams of the MN edge audio devices needs to be adjusted back, the method further includes: The cloud server sends audio data with normal gain to the MN edge audio devices, where a duration of the audio data with normal gain is greater than or equal to a duration of the sound data.

7. The method according to any one of claims 1 to 3, characterized in that The air dome is covered by an elliptical area, the two ends of the elliptical area are respectively a first end and a second end, the sound field convergence point is located in the elliptical area close to the first end, the M edge audio devices are evenly deployed at the edge of the elliptical area and close to the second end, and the cloud server reduces the intensity of the sound wave beam of each of N edge audio devices among the M edge audio devices, including: The cloud server selects two edge audio devices from the M edge audio devices, N=2, the sum of the serial numbers of the two edge audio devices is K, the positions of the two edge audio devices are symmetrical about a first axis, the first axis is a line connecting the two centers of the elliptical area, and if the M edge audio devices are traversed in a clockwise direction according to their respective positions, the serial numbers of the M edge audio devices are changed to increase by 1 starting from 1 until they increase to M; The cloud server reduces the intensity of the sound wave beams of each of the two edge audio devices.

8. The method according to claim 7, characterized in that M is an even number, and the cloud server selects two edge audio devices from the M edge audio devices, including: When the cloud server determines for the first time that the echo intensity of the sound field convergence point is greater than the preset threshold: The cloud server selects a first edge audio device and an Mth edge audio device from the M edge audio devices; When the cloud server determines for the second time that the echo intensity of the sound field convergence point is greater than the preset threshold: The cloud server selects a second edge sound device and an M-1th edge sound device from the M edge sound devices. At this time, the first edge sound device and the Mth edge sound device need to be called back on the intensity of the sound wave beam; And so on; When the cloud server determines for the M / 2th time that the echo intensity of the sound field convergence point is greater than the preset threshold: The cloud server selects the M / 2th edge sound device and the M / 2+1th edge sound device from the M edge sound devices. At this time, the M / 2-1th edge sound device and the M / 2+2th edge sound device need to be called back on the intensity of the sound wave beam; When the cloud server determines for the M / 2+1th time that the echo intensity of the sound field convergence point is greater than the preset threshold: The cloud server selects the M / 2-1th edge sound device and the M / 2+2th edge sound device from the M edge sound devices. At this time, the intensity of the sound wave beam needs to be called back for the M / 2th edge sound device and the M / 2+1th edge sound device. And so on; When the cloud server determines for the M-1th time that the echo intensity of the sound field convergence point is greater than the preset threshold: The cloud server selects the first edge sound device and the Mth edge sound device from the M edge sound devices. At this time, the second edge sound device and the M-1th edge sound device need to be called back on the intensity of the sound wave beam; Then, poll again.

9. The method according to claim 8, characterized in that The cloud server reduces the intensity of the sound wave beams of the two edge audio devices, including: The cloud server sends the audio data with reduced gain to the two edge audio devices, where the duration of the audio data with reduced gain is greater than or equal to the duration of the sound data; At this time, in the case where the intensity of the sound wave beam of the two edge audio devices needs to be adjusted back, the method further includes: The cloud server sends audio data with normal gain to the two edge audio devices, where a duration of audio of the audio data with normal gain is greater than or equal to a duration of the sound data.

10. A cloud server, characterized in that: The cloud server is deployed in the cloud and is configured as follows: The cloud server obtains sound data collected by the edge sound pickup device, where the edge sound pickup device is deployed at a sound field convergence point in the air dome. The air dome is deployed with M edge sound devices, where M is an integer greater than 3. The M edge sound devices are distributedly deployed in an edge area of ​​the air dome, and the sound wave beams of each of the M edge sound devices are directed toward the sound field convergence point. The cloud server determines, based on the sound data, whether the echo intensity of the sound field convergence point is greater than a preset threshold; If the echo intensity of the sound field convergence point is greater than the preset threshold, the cloud server reduces the intensity of the sound wave beam of each of N edge sound devices among the M edge sound devices, where N is an integer greater than 1 and less than M, and the N edge sound devices are discretely distributed edge sound devices among the M edge sound devices.

Images