Sound insulation material performance analysis and improvement method and system

Abstract

The embodiment of the invention provides a sound insulation material performance analysis and improvement method and system, and the method comprises the steps: transmitting a first sound signal with a preset sound characteristic through a playing device, and enabling the playing device to be disposed at the outer side of a sound insulation material; a second sound signal is received through sound receiving equipment, the sound receiving equipment is arranged in the sound insulation material, and the second sound signal is a sound signal transmitted by the first sound signal through the sound insulation material; determining test data based on the first sound signal and the second sound signal; and determining a target improvement strategy based on the test data.

Description

Technical Field

[0001] The present invention relates to the field of audio and video, and in particular to a method and system for analyzing and improving the performance of sound insulation materials. Background Art

[0002] With the increasing requirements for sound insulation performance in the construction and industrial fields, the application of sound insulation materials is becoming more and more extensive. In the construction, automobile, aviation and other industries, the performance of sound insulation materials directly affects the comfort and safety of the environment.

[0003] Therefore, there is a need to provide a performance analysis and improvement method and system for sound insulation materials, which can comprehensively and accurately evaluate the performance of sound insulation materials, and can accurately and reasonably improve the performance of sound insulation materials, thereby improving the efficiency of improving the sound insulation effect of sound insulation materials. Summary of the invention

[0004] One or more embodiments of the present specification provide a method for analyzing and improving the performance of a sound insulation material. The method for analyzing and improving the performance of a sound insulation material comprises: emitting a first sound signal with a preset sound characteristic through a playback device, the playback device being arranged outside the sound insulation material; receiving a second sound signal through a sound receiving device, the sound receiving device being arranged inside the sound insulation material, the second sound signal being a sound signal transmitted by the first sound signal through the sound insulation material; determining test data based on the first sound signal and the second sound signal; and determining a target improvement strategy based on the test data.

[0005] One of the embodiments of the present specification provides a performance analysis and improvement system for sound insulation materials, the performance analysis and improvement system for sound insulation materials comprising: a sound emitting module, configured to emit a first sound signal with a preset sound characteristic through a playback device, the playback device being arranged outside the sound insulation material; a sound receiving module, configured to receive a second sound signal through a sound receiving device, the sound receiving device being arranged inside the sound insulation material, the second sound signal being a sound signal transmitted by the first sound signal through the sound insulation material; a first determination module, configured to determine test data based on the first sound signal and the second sound signal; and a second determination module, configured to determine a target improvement strategy based on the test data.

[0006] One or more embodiments of the present specification provide a device for analyzing and improving the performance of a sound insulation material, including a processor, wherein the processor is used to execute a method for analyzing and improving the performance of a sound insulation material.

[0007] One or more embodiments of the present specification provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a performance analysis and improvement method of a sound insulation material. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0009] Figure 1 It is a schematic diagram of application scenarios of the performance analysis and improvement system of the sound insulation material shown in some embodiments of this specification;

[0010] Figure 2 is an exemplary schematic diagram of a system for analyzing and improving the performance of sound insulation materials according to some embodiments of this specification;

[0011] Figure 3 is an exemplary flow chart of a method for analyzing and improving the performance of sound insulation materials according to some embodiments of this specification;

[0012] Figure 4 is an exemplary schematic diagram of a first improved strategy model according to some embodiments of this specification;

[0013] Figure 5 is an exemplary schematic diagram of a second improved strategy model according to some embodiments of this specification;

[0014] Figure 6 is an exemplary flow chart of determining a target improvement strategy according to some embodiments of this specification;

[0015] Figure 7 is an exemplary flow chart of another target improvement strategy according to some embodiments of this specification;

[0016] Figure 8 This is an exemplary top view of a sound insulation area surrounded by sound insulation material according to some embodiments of the present specification. DETAILED DESCRIPTION

[0017] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0018] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0019] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0020] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0021] Figure 1 It is a schematic diagram of the application scenario of the performance analysis and improvement system of the sound insulation material shown in some embodiments of this specification. With the development of society, sound insulation materials are used more and more in people's lives and work. For example, bedrooms, recording studios, vehicles, entertainment venues and other places mostly install sound insulation materials for sound insulation. Therefore, the performance analysis and improvement of sound insulation materials can effectively help users understand the performance of sound insulation materials and improve them according to the performance, which has important practical significance. In some embodiments, the application scenario 100 of the performance analysis and improvement system of sound insulation materials may include a playback device 110, a sound receiving device 120, sound insulation materials 130, a network 140 and a processor 150. In some embodiments, the application scenario 100 of the performance analysis and improvement system of sound insulation materials may also include a storage device and / or a user terminal (not shown in the figure).

[0022] The playback device 110 refers to a device that emits sound signals of different frequencies. For example, the playback device 110 may include but is not limited to a speaker, a sound system, and a loudspeaker. In some embodiments, the number of the playback device 110 may be one or more. In some embodiments, the playback device 110 may be arranged outside the sound insulation material. For example, the playback device 110 may be evenly arranged outside the sound insulation material. For another example, the playback device 110 may be arranged outside the sound insulation material according to a first preset rule. Among them, the first preset rule may be set manually. For example, the first preset rule may be to set the playback device 110 at each vertex angle outside the sound insulation material.

[0023] The sound receiving device 120 is a device for receiving sound signals transmitted through the sound insulation material. For example, the sound receiving device 120 may include but is not limited to a microphone, a radio, an audio processor, etc. In some embodiments, the number of the sound receiving devices 120 may be one or more. In some embodiments, the sound receiving device 120 may be arranged inside the sound insulation material. For example, the sound receiving device 120 may be evenly arranged inside the sound insulation material. For another example, the sound receiving device 120 may be arranged inside the sound insulation material according to a second preset rule. Among them, the second preset rule may be set manually. For example, the second preset rule may be to set the sound receiving device 120 at each vertex inside the sound insulation material.

[0024] The sound insulation material 130 is a material used to block or reduce the propagation of sound. For example, the sound insulation material 130 may include, but is not limited to, a sound insulation board, a sound insulation coating, and mineral wool. The sound insulation material 130 mainly reduces the sound intensity without changing the sound frequency. In some embodiments, the shape of the sound insulation material may be a cube, a cuboid, a cylinder, etc. For ease of description, the following description is based on the example of a cuboid sound insulation material.

[0025] The performance of the sound insulation material refers to the sound insulation material's ability to block sound. In some embodiments, the performance of the sound insulation material can be characterized by test data. In some embodiments, the performance of the sound insulation material is related to the thickness of the sound insulation material. For more information about test data, see Figure 3 For more information on thickness, see Figure 8 and related instructions.

[0026] In some embodiments, Figure 1 As shown, the sound insulation material 130 can surround and form a closed space. A plurality of playback devices 110 are arranged outside the closed space; a plurality of sound receiving devices 120 are arranged inside the closed space to test and evaluate the sound insulation performance.

[0027] The network 140 can connect the various components of the application scenario 100 of the performance analysis and improvement system of sound insulation materials and / or connect the application scenario 100 of the performance analysis and improvement system of sound insulation materials with external resources. The network 140 enables communication between the various components and with other parts outside the system to facilitate the exchange of data and / or information. For example, the first sound wave signal played by the playback device 110 and the second sound wave signal received by the sound receiving device 120 can be transmitted to the processor 150 through the network 140 for processing.

[0028] In some embodiments, the network 140 may be any one or more of a wired network or a wireless network. For example, the network 140 may include a cable network, an optical fiber network, a telecommunication network, or any combination thereof. The network connection between the various parts may be in one of the above-mentioned ways or in multiple ways.

[0029] The processor 150 can be used to manage data resources and process data and / or information from at least one component or external data source involved in the application scenario 100 of the performance analysis and improvement system of sound insulation materials. The processor 150 can execute program instructions based on these data, information and / or processing results to perform one or more functions described in this specification. For more information, please refer to Figure 2-Figure 7 In some embodiments, the processor 150 may be partially or completely integrated into the playback device 110, the sound receiving device 120, etc.

[0030] In some embodiments, processor 150 may include one or more sub-processing devices (e.g., a single-core processing device or a multi-core multi-core processing device). As an example only, processor 150 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), a microprocessor, etc., or any combination thereof.

[0031] In some embodiments, the processor 150 can obtain information and / or data from the playback device 110, the audio receiving device 120, etc. through the network 140, or can send the information and / or data to the storage device and / or the user terminal through the network 140.

[0032] In some embodiments, the application scenario 100 of the sound insulation material performance analysis and improvement system may also include one or more other devices, such as a storage device and / or a user terminal (not shown in the figure).

[0033] The storage device can be used to store data, instructions and / or any other information. For example, the storage device can be used to store instructions transmitted by a user terminal through a network. In some embodiments, the storage device can store data and / or instructions related to the performance analysis and improvement of sound insulation materials. For example, the storage device can store a first sound signal, a second sound signal, etc. As another example, the storage device can store instructions for processing a first sound signal and a second sound signal to determine test data. In some embodiments, data communication can be performed between the storage device and the processor 150 through the network 140, and the storage device can also be a part of the processor 150. In some embodiments, the storage device can also be partially or completely integrated into the playback device 110, the sound receiving device 120, etc.

[0034] The user terminal may include a mobile device, a tablet computer, a laptop computer, etc., or any combination thereof. In some embodiments, the user terminal may be part of a processing device.

[0035] In some embodiments, a user may send and / or receive information related to a performance test of a sound insulation material to a processing device via a user interface. In some embodiments, the user interface may be in the form of an application for a performance test of a sound insulation material implemented on a user terminal. The user interface may be configured to facilitate communication between a user terminal and a user associated with the user terminal.

[0036] It should be noted that the above description of the application scenario 100 of the performance analysis and improvement system of sound insulation materials is provided for illustrative purposes only and is not intended to limit the scope of the present application. For those of ordinary skill in the art, various variations and modifications can be made under the guidance of the present application. For example, the configuration and / or function of the application scenario 100 of the performance analysis and improvement system of sound insulation materials can be changed or modified according to the specific implementation scenario. However, these variations and modifications do not depart from the scope of the present application.

[0037] Figure 2 1 is an exemplary schematic diagram of a system for analyzing and improving the performance of sound insulation materials according to some embodiments of this specification. Figure 2 As shown, the sound insulation material performance analysis and improvement system 200 may include a sound emitting module 210 , a sound receiving module 220 , a first determining module 230 and a second determining module 240 .

[0038] In some embodiments, the sound emitting module 210 may be configured to emit a first sound signal with a preset sound characteristic through a playback device, and the playback device is disposed outside the sound insulation material.

[0039] In some embodiments, the sound receiving module 220 may be configured to receive a second sound signal through a sound receiving device, the sound receiving device being disposed inside the sound insulation material, and the second sound signal being a sound signal transmitted by the first sound signal through the sound insulation material.

[0040] The first determination module 230 may be configured to determine test data based on the first sound signal and the second sound signal.

[0041] The second determination module 240 may be configured to determine a target improvement strategy based on the test data.

[0042] In some embodiments, the second determination module may be further configured to: determine a target improvement strategy based on the test data and first distribution information, where the first distribution information refers to distribution information of the sound insulation material.

[0043] In some embodiments, the number of second sound signals is multiple, the test data includes first test data, and the first test data is related to the statistical value of the strength of the multiple second sound signals, the frequency of the multiple first sound signals, and the strength of the multiple first sound signals. The second determination module can be further configured to: determine one or more first improvement strategies based on the first test data and the first distribution information; and determine a target improvement strategy based on the first improvement strategy.

[0044] In some embodiments, the second determination module can be further configured to determine a second improvement strategy based on the first test data and the first distribution information; obtain the second test data based on the improved sound insulation material and the preset sound characteristics; the improved sound insulation material is obtained by improving the sound insulation material based on the second improvement strategy; the second test data is determined based on the first sound signal and the third sound signal, the third sound signal is the sound signal transmitted by the first sound signal through the improved sound insulation material; based on the first test data, the second test data, the first distribution information, the third distribution information and the qualified intensity sequence, the target improvement strategy is determined through the improved strategy model, the improved strategy model is a machine learning model, and the third distribution information refers to the distribution information of the improved sound insulation material.

[0045] In some embodiments, the sound emitting module 210 , the sound receiving module 220 , the first determining module 230 , and the second determining module 240 may be integrated into the processor 150 .

[0046] For more details about the sound emitting module 210, the sound receiving module 220, the first determining module 230 and the second determining module 240, see Figure 3-Figure 7 and its related description.

[0047] It should be understood that Figure 2 The system and its modules shown can be implemented in various ways. It should be noted that the above description of the performance analysis and improvement system of sound insulation materials and its modules is only for the convenience of description and cannot limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from this principle. In some embodiments, Figure 2 The sound emitting module 210, the sound receiving module 220, the first determining module 230 and the second determining module 240 disclosed in the specification can be different modules in a system, or one module can realize the functions of two or more modules. For example, each module can share a storage module, or each module can have its own storage module. Such variations are all within the protection scope of this specification.

[0048] Figure 3is an exemplary flow chart of the performance analysis and improvement method of the sound insulation material according to some embodiments of this specification. Figure 3 As shown, process 300 includes the following steps. In some embodiments, Figure 3 One or more operations of the process 300 shown may be performed in Figure 1 The performance analysis and improvement system of the sound insulation material shown is implemented in the application scenario 100. For example, Figure 3 The process 300 shown may be stored in a storage device in the form of instructions and called and / or executed by the processor 150 .

[0049] Step 310 , a first sound signal with a preset sound feature is emitted through a playback device. In some embodiments, step 310 may be performed by the sound emission module 210 .

[0050] A playback device refers to a device that plays audio, such as a stereo, a speaker, etc. In some embodiments, there may be one or more playback devices.

[0051] In some embodiments, the playback device is disposed outside the sound insulation material. For more information about the playback device, see Figure 1 and its related description.

[0052] The preset sound feature refers to a preset feature related to the sound. In some embodiments, the preset sound feature may include features such as sound frequency and sound intensity. For example, the preset sound feature may be expressed as (f i , B ij ), where f i is the sound frequency, B ij is the sound frequency f i The j-th sound intensity.

[0053] In some embodiments, there may be multiple preset sound features.

[0054] In some embodiments, the preset sound features may adopt the sound frequency and / or sound intensity commonly used in general sound insulation experiments. In some embodiments, the preset sound features may also be determined based on the application scenario of the sound insulation material to be tested. As an example only, if the application scenario of the sound insulation material to be tested is the sound insulation of the interior space of a car, a large amount of common noise in the environment where the car is located (such as urban roads, highways, etc.) can be collected in advance, and the sound frequency and sound intensity of the common noise can be extracted as the preset sound features.

[0055] The first sound signal refers to a sound wave signal emitted from a playback device. The number of the first sound signals is the same as the number of the playback devices.

[0056] In some embodiments, the sound emitting module 210 can generate corresponding audio data (such as audio data in mp3 format, etc.) based on preset sound features, and send the audio data corresponding to the preset sound features to the playback device; the playback device emits a first sound signal corresponding to the preset sound features according to the audio data.

[0057] In some embodiments, for audio data corresponding to multiple preset sound features, the sound emitting module 210 can send the audio data corresponding to the multiple preset sound features to multiple different playback devices, and different playback devices each play a first sound signal corresponding to a preset sound feature.

[0058] It can be understood that each playback device plays a set of sound frequencies and sound intensities, so that the first sound signals corresponding to multiple sound frequencies can be played simultaneously. The first sound signals with the same sound frequency and different sound intensities are played in different playback batches, so that the first sound signals with different sound intensities corresponding to the same sound frequency can be distinguished.

[0059] In some embodiments, for the first sound signals corresponding to multiple preset sound features with the same sound frequency and different sound intensities, since the sound frequencies are the same, it is difficult for the sound receiving module 220 to distinguish different sound intensities according to the sound frequencies when receiving when playing at the same time. The sound emitting module 210 can control the playback device to emit the first sound signal in different playback batches, so that the first sound signals corresponding to multiple preset audio features with the same sound frequency and different sound intensities are emitted in different playback batches. In some embodiments, each playback batch includes multiple first sound signals with different sound frequencies.

[0060] Step 320 , receiving a second sound signal through a sound receiving device. In some embodiments, step 320 may be performed by the sound receiving module 220 .

[0061] Sound receiving equipment refers to equipment used to receive sound signals, such as sound sensors and microphones.

[0062] In some embodiments, the sound receiving device is disposed inside the sound insulation material. In some embodiments, there may be multiple sound receiving devices. For more information about the sound receiving device, see Figure 1 and its related description.

[0063] The second sound signal is a sound signal transmitted by the first sound signal through the sound insulation material. The number of second sound signals is the same as the number of sound receiving devices. In some embodiments, when one or more playback devices play one or more first sound signals, the first sound signal passes through the sound insulation material and is weakened by the sound insulation material, thereby forming a second sound signal. It should be noted that when the sound insulation material weakens the first sound signal, it only weakens the sound intensity and does not change the sound frequency.

[0064] It is understandable that when there are multiple first sound signals in each playback batch, the second sound signal received by each sound receiving device is a mixed sound signal of multiple first sound signals after passing through sound insulation materials, which includes sound signals of multiple frequencies. Each sound receiving device can receive the mixed sound signal. Due to the different locations of different sound receiving devices, there may be certain differences in the received second sound signals. For example, the receiving strength corresponding to the same sound frequency in the second sound signals received by different sound receiving devices may be different.

[0065] In some embodiments, the sound receiving module 220 can receive the second sound signal through the sound receiving device in a variety of ways. For example, the sound insulation material tester can send a start instruction to the sound receiving module 220 through an interactive device (such as a keyboard, a mouse, a touch screen, etc.) while starting to play the first sound signal. After receiving the start instruction, the sound receiving module 220 starts to collect sound signals through the receiving sound receiving device and uses the collected sound signals as the second sound signal.

[0066] For another example, the sound emitting module 210 may send a start instruction to the sound receiving module 220 while sending audio data to the playback device. After receiving the instruction, the sound receiving module 220 starts to collect sound signals through the receiving device and uses the collected sound signals as the second sound signals.

[0067] In some embodiments, when there are multiple sound receiving devices, the sound signal collected by each sound receiving device is used as a second sound signal.

[0068] Step 330 , determining test data based on the first sound signal and the second sound signal. In some embodiments, step 330 may be performed by the first determination module 230 .

[0069] The test data refers to data related to the performance of the sound insulation material. In some embodiments, the test data may include the playback intensity corresponding to different sound frequencies, and the sound frequency and reception intensity of the second sound signal received by different sound receiving devices. The playback intensity refers to the sound intensity of the first sound signal played by the playback device.

[0070] In some embodiments, the playback intensity is equal to the sound intensity of the preset sound feature corresponding to the first sound signal. The receiving intensity refers to the sound intensity of the second sound signal received by the sound receiving device. It can be understood that when the playback device plays the first sound signal at the playback intensity, it is weakened by the sound insulation material when passing through the sound insulation material, and the sound intensity is weakened from the playback intensity to the receiving intensity, and the sound frequency does not change. By comparing the playback intensity of the first sound signal and the receiving intensity of the second sound signal corresponding to the preset sound features of different sound frequencies and different sound intensities, the performance of the sound insulation material can be analyzed.

[0071] In some embodiments, there are multiple second sound signals, and the test data includes first test data, which is related to statistical values ​​of the strengths of the multiple second sound signals, the frequencies of the multiple first sound signals, and the strengths of the multiple first sound signals.

[0072] The first test data refers to statistical data of the test data. In some embodiments, the first test data may include each sound frequency, each playback intensity, and the average value of the corresponding sound reception intensity received by each sound receiving device.

[0073] In some embodiments, the first test data can be expressed as [(f1, B 11 , C 11 ),…,(f1,B 1m , C 1m ),…,(f n , B n1 , C n1 ),…,(f n , B nm , C nm )], where f1,…,f n is the sound frequency of the first sound signal, B n1 …,B nm is the sound frequency f n The corresponding playing intensity of the first sound signals, C n1 ,…,C nm is the sound frequency f n The receiving strengths of the corresponding multiple second sound signals.

[0074] In some embodiments, the first determination module 230 may determine the first test data by following steps:

[0075] ① For the first sound signal of each playback batch emitted by the playback device, the first determination module 230 can perform spectral analysis on each second sound signal of the playback batch according to the frequency of the sound to obtain multiple second sound sub-signals, each of which corresponds to a sound frequency and sound intensity.

[0076] ② According to the frequency of the second sound sub-signal, a preset sound feature with the same sound frequency is matched among the multiple preset sound features corresponding to the first sound signal of the playback batch, and the sound intensity therein is used as the playback intensity of the sound frequency in the current playback batch. In some embodiments, since the sound frequencies of multiple first sound signals in the same playback batch are different, in the second sound signal received by each sound receiving device, each sound frequency has and only has one receiving intensity.

[0077] ③ Calculate the average value of the sound intensities of the second sound sub-signals with the same sound frequency in the second sound signals corresponding to the multiple sound receiving devices to obtain the receiving intensity of the second sound sub-signals with the same sound frequency;

[0078] ④ Determine the first test data based on the sound frequency, playback intensity, and reception intensity.

[0079] As an example only, the preset sound features corresponding to the three first sound signals of a certain playback batch are (f1, B 11 )、(f2,B 21 )、(f3,B 31 ), the two sound receiving devices receive the second sound signals V1 and V2 respectively. The first determination module 230 may:

[0080] ① Perform spectrum analysis on the second sound signal V1 to obtain three second sound sub-signals (f1, C 11-V1 )、(f2,C 21-V1 )、(f3,C 31-V1 ), where f1, f2, and f3 are the sound frequencies of the three second sound sub-signals, C 11-V1 , C 21-V1 , C 31-V1 are the sound intensities of the three second sound sub-signals corresponding to the second sound signal V1; similarly, the second sound signal V2 is subjected to spectrum analysis to obtain the three second sound sub-signals (f1, C 11-V2 ), (f2, C 21-V2 ), (f3, C 31-V2 ), where C 11-V2 , C 21-V2 , C 31-V2 are sound intensities of three second sound sub-signals corresponding to the second sound signal V2;

[0081] ② According to the sound frequency, a preset sound feature with the same sound frequency is matched among multiple preset sound features corresponding to the first sound signal of the playback batch, and the sound intensity thereof is used as the playback sound intensity. For example, the preset sound feature corresponding to the sound frequency f1 is (f1, B 11 ), then the playing intensity corresponding to the sound frequency f1 is B11 Similarly, we get the playback intensity B corresponding to f2 and f3 21 , B 31 ;

[0082] ③ Calculate the mean value of the sound intensity of the second sound sub-signal of the same frequency as the receiving intensity of the sound of that frequency. Taking the sound frequency f1 as an example, its receiving intensity The receiving intensity C of the sound frequency f2, f3 21 , C 31 The calculation method is similar;

[0083] ④ Determine the first test data of the playback batch [(f1, B 11 , C 11 ),(f2,B 21 , C 21 ),(f3,B 31 , C 31 )], and combine the first test data of multiple playback batches to obtain the complete first test data [(f1, B 11 , C 11 ),…,(f1,B 1m , C 1m ),…,(f n , B n1 , C n1 ),…,(f n , B nm , C nm )].

[0084] In some embodiments, the test data further includes second test data and third test data.

[0085] The second test data refers to the test data obtained by testing the improved sound insulation material. For more information about improved sound insulation materials, see Figure 7 and its related description.

[0086] The third test data refers to detailed performance data in the test data. For example, the third test data includes the sound frequency and playback intensity when the playback device plays the first sound signal and the receiving intensity corresponding to the sound frequency and playback intensity in the second sound signal received by each sound receiving device.

[0087] In some embodiments, the first determination module 230 may determine the third test data based on the first sound signal and the second sound signal. For more information on determining the third test data, see Figure 5 and related instructions.

[0088] Step 340 , determining a target improvement strategy based on the test data. In some embodiments, step 340 may be performed by the second determination module 240 .

[0089] The target improvement strategy refers to a strategy for improving the performance of the sound insulation material. For example, a strategy for enhancing the sound insulation performance of the sound insulation material. In some embodiments, the target improvement strategy may include one or more of changing the type of the sound insulation material, increasing the thickness of the sound insulation material, adding a damping material, and adding a cushion layer. For ease of description, the following description is based on the improvement of the thickness of the sound insulation material. Among them, the thickness improvement refers to increasing the thickness of the sound insulation material.

[0090] In some embodiments, the second determination module 240 can determine the qualified receiving intensity according to the frequency and playback intensity of the sound signals of different frequencies in the test data; and judge whether the performance of the sound insulation material is qualified according to the relationship between the receiving intensity and the qualified receiving intensity.

[0091] The qualified receiving intensity is the maximum receiving intensity of the sound signal when the performance of the sound insulation material is qualified. The qualified receiving intensity can be set by technicians based on experience; the performance of the sound insulation material includes the sound insulation effect. If the receiving intensity corresponding to at least one sound frequency is greater than the qualified receiving intensity, the performance of the sound insulation material may be unqualified.

[0092] In some embodiments, when the performance of the sound insulation material is unqualified, the second determination module 240 can determine the target improvement strategy through a variety of methods. For example, the second determination module can determine the target improvement strategy through the following steps:

[0093] S11. For each sound frequency in the test data and its corresponding playback intensity and receiving intensity, calculate the test intensity difference between the receiving intensity and the qualified receiving intensity, where the test intensity difference = receiving intensity - qualified receiving intensity.

[0094] S12. For each sound frequency, calculate a first weighted average value of the test intensity differences corresponding to the multiple playback intensities based on the first weight, and obtain a first intensity difference reflecting the sound insulation effect of the sound insulation material at the sound frequency.

[0095] For example, for the sound frequency f1, its playing intensity B 11 , B 12 , B 13 The corresponding test intensity differences are d 11 d 12 d 13 , then the first intensity difference corresponding to the sound frequency f1 Among them, w1, w2, and w3 are the playback intensity B 11 , B 12 , B 13 The corresponding first weight can be preset by a technician based on experience.

[0096] In some embodiments, the first weight may also be related to the sound insulation requirements for different playback intensities. For example, for a first sound signal with a higher playback intensity, the sound insulation requirement is higher, and the first weight of the first sound signal with a higher playback intensity is greater.

[0097] S13, according to the first intensity difference corresponding to each sound frequency, calculate the second weighted average value based on the second weight to obtain the second intensity difference reflecting the overall sound insulation effect of the sound insulation material. Among them, Di is the first intensity difference corresponding to the i-th sound frequency, ui is the second weight corresponding to the i-th sound frequency, and the second weight can be preset by the technician based on experience.

[0098] In some embodiments, the second weight may also be related to the sound insulation requirements of different sound frequencies. The higher the sound insulation requirement of the sound frequency, the greater the corresponding second weight.

[0099] S14. In response to the second strength difference value ≤ 0, it indicates that the overall sound insulation effect of the sound insulation material is basically qualified, and the sound insulation material is not improved here; in response to the second strength difference value > 0, it indicates that the overall sound insulation effect of the sound insulation material is unqualified, and the preset strategy table is queried based on the second strength difference value to determine the overall thickness improvement corresponding to the second strength difference value as the target improvement strategy.

[0100] The preset strategy table includes the overall thickness improvement of the sound insulation material corresponding to different second strength differences, wherein the overall thickness improvement refers to increasing the thickness of the sound insulation material as a whole. For example, if the overall thickness improvement is 1cm, it means that all sides are thickened by 1cm. For more information about thickness, see Figure 8 and related instructions.

[0101] In some embodiments, the larger the second strength difference in the preset strategy table, the larger the thickness improvement value. In some embodiments, the preset strategy table can be constructed based on experimental data, and the method for determining the thickness improvement of the sound insulation material corresponding to different second strength difference values ​​in the preset strategy table can refer to Figure 4 Description of the training data for the first improved strategy model.

[0102] In some embodiments, the second determination module 240 may determine a target improvement strategy based on the test data and the first distribution information.

[0103] The first distribution information refers to distribution information of the sound insulating material.

[0104] The distribution information of the sound insulation material may include the distribution of the sound insulation material in the space, for example, the area, length of each side, thickness and other information of the sound insulation area enclosed by the sound insulation material in the space.

[0105] In some embodiments, the first distribution information can be represented by a data sequence. For example, the first distribution information can be represented by {S, L1, h1, L2, h2, ..., Ls, hs}, where S is the area of ​​the sound insulation area enclosed by the sound insulation material in the space, L1, L2, ..., Ls are the lengths from the first side to the sth side of the area, and h1, h2, ..., hs are the thicknesses from the first side to the sth side of the area.

[0106] Figure 8 This is an exemplary top view of a sound insulation area surrounded by sound insulation materials shown in some embodiments of this specification. Figure 8 As shown, the sound insulation area in the figure is surrounded by sound insulation materials on four sides, wherein the length of the sound insulation material on the i-th side is Li and the thickness is hi. In some embodiments, the first side to the s-th side can be arranged from long to short according to the length of each side of the area, or can be arranged in a preset order of position, for example, in a preset order of clockwise or counterclockwise.

[0107] In some embodiments, the second determination module 240 may determine the target improvement strategy based on the test data and the first distribution information according to the following steps.

[0108] S21: Calculate the second strength difference based on the first test data. The process of calculating the second strength difference can refer to steps S11 to S13 and their related descriptions.

[0109] S22: In response to the second intensity difference ≤0, it indicates that the overall sound insulation effect of the sound insulation material is basically qualified, and the sound insulation material is not improved here; in response to the second intensity difference >0, it indicates that the overall sound insulation effect of the sound insulation material is unqualified, then a sound insulation test vector is constructed based on the first intensity difference corresponding to each sound frequency combined with the first distribution information.

[0110] For example, the sound insulation test vector can be expressed as (D1, D2, ..., Dn, S, L1, T1, L2, T2, ..., Ls, Ts), where D1, D2, ..., Dn are the sound frequencies from f1 to f n The corresponding first intensity difference.

[0111] S23: Retrieve the first reference sound insulation vector with the highest similarity in the first strategy vector database based on the sound insulation test vector, and use the reference improvement strategy corresponding to the first reference sound insulation vector as the target improvement strategy.

[0112] The first strategy vector database includes a plurality of first reference sound insulation vectors in the same format as the sound insulation test vector and their corresponding reference improvement strategies. The reference improvement strategy may include thickness improvements corresponding to each edge of the sound insulation area surrounded by the sound insulation material.

[0113] In some embodiments, the first strategy vector database can be constructed based on experimental data. The method for determining the reference improvement strategy corresponding to each first reference sound insulation vector can refer to Figure 4 A description of the method for obtaining labels for training data of the first improved strategy model.

[0114] In some embodiments, the second determination module 240 may also determine the target improvement strategy based on the test data and the first distribution information in other ways. For example, the second determination module 240 may also determine the target improvement strategy based on the second test data, the third test data and the first distribution information. For details, please refer to Figures 4 to 7 content and its related description.

[0115] In some embodiments of the present specification, a target improvement strategy is determined through test data and first distribution information to obtain an improvement in the thickness of each portion of the sound insulation material, so that the sound insulation material can be improved more accurately.

[0116] In some embodiments of the present specification, a first sound signal is emitted with preset sound characteristics, and a second sound signal is received to obtain test data, so that the performance of the sound insulation material can be comprehensively and accurately evaluated. By determining the target improvement strategy based on the test data, the performance of the sound insulation material can be accurately and reasonably improved, thereby improving the efficiency of improving the sound insulation effect of the sound insulation material.

[0117] It should be noted that the above description of process 300 is only for example and illustration, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to process 300 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0118] Figure 4 is an exemplary schematic diagram of a first improved strategy model according to some embodiments of the present specification.

[0119] In some embodiments, the number of second sound signals is multiple, and the test data may include first test data 410, and the first test data 410 is related to the statistical value of the strength of the multiple second sound signals, the frequency of the first sound signal, and the strength of the first sound signal. The second determination module 240 can determine the target improvement strategy 450 through the first improvement strategy model 420 based on the first test data 410, the first distribution information 441, and the qualified strength sequence 442, and the first improvement strategy model 420 is a machine learning model.

[0120] The first improvement strategy model 420 is a model for predicting the target improvement strategy 450 .

[0121] The first improved strategy model 420 may be a machine learning model, for example, at least one of a convolutional neural network (CNN) model, a deep neural network model (DNN), a neural network model (NN), and the like.

[0122] In some embodiments, the first improved strategy model 420 may include a first feature extraction layer 421 and a first prediction layer 422. In some embodiments, the first feature extraction layer 421 may be a machine learning model, such as CNN, etc. In some embodiments, the first prediction layer 422 may be a machine learning model, such as DNN, etc.

[0123] In some embodiments, the input of the first feature extraction layer 421 may be the first test data 410, and the output of the first feature extraction layer 421 may be the first performance characteristic 430; the input of the first prediction layer 422 may be the first performance characteristic 430, the first distribution information 441 and the qualified strength sequence 442, and the output of the first prediction layer 422 may be the target improvement strategy 450.

[0124] The first performance feature 430 refers to a feature related to the sound insulation performance in the first test data.

[0144] A qualified intensity sequence refers to a data sequence composed of multiple qualified reception intensities, for example, a data sequence composed of qualified reception intensities corresponding to different sound frequencies and playback intensities.

[0125] For more information about the first test data 410 and the first distribution information 441, see Figure 3 and its related description.

[0126] In some embodiments, the second determination module 240 may jointly train the initial first improved strategy model based on a plurality of first training samples with first labels to obtain a trained first improved strategy model 420. The training method may include but is not limited to the gradient descent method.

[0127] In some embodiments, the first training sample may include sample first test data of the sample sound insulation material, sample first distribution information, and sample qualified strength sequence. In some embodiments, the second determination module 240 may adjust the thickness of each edge of the sample sound insulation material multiple times based on a plurality of preset improvement strategies, and determine the sample sound insulation material whose final sound insulation effect meets the qualified receiving strength and whose total amount is increased the least as the target sound insulation material, and determine the preset improvement strategy corresponding to the target sound insulation material as the first label. Among them, the sound insulation effect meets the qualified receiving strength, which means that the receiving strength is less than the qualified receiving strength. The preset improvement strategy can be set manually. For more information about the increase in total amount, please refer to Figure 6 Related description.

[0128] In some embodiments, the output of the first feature extraction layer 421 can be the input of the first prediction layer 422, and the first feature extraction layer 421 and the first prediction layer 422 can be obtained by joint training of multiple first training samples with first labels. For example, the second determination module 240 can input the sample first test data into the initial first feature extraction layer to extract the sample first performance characteristics. After that, the second determination module 240 can input the extracted sample first performance characteristics together with the sample first distribution information and the sample qualified strength sequence into the initial first prediction layer to predict the sample target improvement strategy. The second determination module 240 can construct a loss function based on the sample target improvement strategy outputted by the initial first improvement strategy model and the first label, and iteratively update the parameters of the model in reverse based on the loss function; after multiple rounds of iterative training, the second determination module 240 continuously optimizes the model parameters, and when the loss function meets the preset conditions, the iteration is terminated, and the trained first improvement strategy model 420 is finally obtained. Among them, the preset conditions can be the convergence of the loss function, the number of iterations reaching a threshold, etc.

[0129] In some embodiments of the specification, by jointly training the first improvement strategy model 420, it is possible to optimize the first feature extraction layer 421 and the first prediction layer 422 to work together on the overall optimization goal, thereby significantly enhancing the prediction accuracy of the model. By jointly training the first feature extraction layer 421 and the first prediction layer 422, not only can the number of samples required be reduced, but also the problem of difficulty in obtaining the first performance characteristic of the label when training the first feature extraction layer 421 alone can be solved, thereby improving training efficiency. In actual applications, the second determination module 240 can quickly determine a target improvement strategy that is more in line with reality based on the trained first improvement strategy model 420 to meet the needs of improving sound insulation materials.

[0130] By combining multiple data sources, the first improvement strategy model 420 can analyze the performance of the sound insulation material more comprehensively and accurately, can more comprehensively reflect the performance of the sound insulation material in different locations, avoid the deviation caused by a single data source, and thus improve the reliability of the determined target improvement strategy.

[0131] Figure 5 is an exemplary schematic diagram of a second improved strategy model according to some embodiments of the present specification.

[0132] In some embodiments, the number of second sound signals is multiple, and the test data may include third test data 511, and the third test data 511 is related to the strength of the multiple second sound signals, the frequency of the multiple first sound signals, and the strength of the multiple first sound signals. The second determination module 240 can determine the target improvement strategy 450 through the second improvement strategy model 520 based on the third test data 511, the first distribution information 441, the second distribution information 512, and the qualified strength sequence 442, and the second improvement strategy model 520 is a machine learning model.

[0133] The second improvement strategy model 520 is another model for predicting the target improvement strategy 450. The second improvement strategy model 520 may be a machine learning model, for example, at least one of CNN, DNN, NN, and the like.

[0134] In some embodiments, the second improvement strategy model 520 may include a second feature extraction layer 521 and a second prediction layer 522; the input of the second feature extraction layer 521 may be third test data 511 and second distribution information 512, and the output of the second feature extraction layer 521 may be a second performance characteristic 530; the input of the second prediction layer 522 may be the second performance characteristic 530, the first distribution information 441 and the qualified strength sequence 442, and the output of the second prediction layer 522 may be a target improvement strategy 450.

[0135] The third test data refers to detailed performance data in the test data. In some embodiments, the third test data may be related to the strength of the plurality of second sound signals, the frequency of the plurality of first sound signals and the strength of the plurality of first sound signals.

[0136] For example only, the third test data can be expressed as [(f1, B 11 , C 11-V1 , C 11-V2 , …, C 11-Vh ),…,(f1,B 1m , C 1m-V1 , C 1m-V2 , …, C 1m-Vh ),…,(f n , B n1 , C n1-V1, C n1-V2 , …, C n1-Vh ),…,(f n , B nm , C nm-V1 , C nm-V2 , …, c nm-Vh )], where f1,…,f n is the sound frequency of the first sound signal, B 11 , …, B 1m is the playing intensity of the first sound signals corresponding to the sound frequency f1, C 11-V1 , C 11-V2 , …, C 11-Vh is the sound frequency f1 and the sound intensity B 11 The corresponding receiving strength of h radio devices, C 1m-V1 , C 1m-V2 , …, C 1m-Vh is the sound frequency f1 and the sound intensity B 1m The corresponding receiving strength of h radio devices, B n1 …,B nm is the sound frequency f n The corresponding playing intensity of the first sound signals, C n1-V1 , C n1-V2 , …, C n1-vh is the sound frequency f n Sound intensity B n1 The corresponding receiving strength of h radio devices, C nm-V2 , …, C nm-vh is the sound frequency f n Sound intensity B nm The corresponding reception strength of h radio devices.

[0137] The method for obtaining the third test data is similar to the method for obtaining the first test data. The only difference is that in step ③, the sound intensity of the second sound sub-signal of the same frequency in the second sound signals corresponding to multiple receiving devices is used as the receiving intensity of the second sound sub-signal of the frequency, without calculating the average value, thereby reflecting the receiving intensity of each receiving device.

[0138] The second distribution information 512 refers to information that can reflect the distribution of playback devices and / or sound receiving devices. In some embodiments, the second distribution information may include distribution information of playback devices and / or distribution information of sound receiving devices.

[0139] The distribution information of the playback device refers to information related to the specific position of the playback device outside the sound insulation material. For example, the distribution information of the playback device may include the position information of each playback device, and the position information of each playback device may be sorted according to the playback device serial number.

[0140] The distribution information of the sound receiving devices refers to information related to the specific positions of the sound receiving devices inside the sound insulation material. For example, the distribution information of the sound receiving devices may include the position information of each sound receiving device, and the position information of each sound receiving device may be sorted according to the sequence number of the sound receiving device.

[0141] In some embodiments, the position information can be represented by coordinates or relative position information. For example, the second determination module 240 can construct a unified coordinate system, and use the coordinate information of the center (e.g., geometric center, etc.) of the playback device and / or the sound receiving device on the coordinate system as the position information of the playback device and / or the sound receiving device. For another example, the second determination module 240 can set a certain position on the sound insulation material as a reference point, and use the direction and distance of the center (e.g., geometric center, etc.) of the playback device and / or the sound receiving device from the reference point as the position information of the playback device and / or the sound receiving device.

[0142] The second performance feature 530 refers to a feature related to the sound insulation performance in the third test data.

[0143] For more information about the third test data 410 and the first distribution information 441, see Figure 3 For more information about the qualified strength sequence 442, see Figure 4 and its related description.

[0144] In some embodiments, the second determination module 240 may jointly train the initial second improved strategy model 520 based on multiple second training samples with second labels to obtain a trained second improved strategy model 520. In some embodiments, the second training samples of the second improved strategy model 520 may include sample third test data of the sample sound insulation material, sample second distribution information, sample first distribution information, and sample qualified strength sequence. In some embodiments, the acquisition process of the second label is similar to the acquisition process of the first label. The training process of the second improved strategy model 520 can refer to the training process of the first improved strategy model 420, which will not be repeated here.

[0145] In some embodiments of the specification, by introducing the third test data 511 and the second distribution information 512, the second improved model 520 can more carefully reflect the sound insulation effect of the sound insulation material under different positions and conditions, so as to comprehensively evaluate the performance of the sound insulation material. By jointly training the second feature extraction layer 521 and the second prediction layer 522, not only can the number of second training samples required be reduced, but also the problem of difficulty in obtaining the second performance characteristics of the label when training the second feature extraction layer 521 alone can be solved, thereby improving the training efficiency. In practical applications, the second determination module 240 can further improve the accuracy of the target improvement strategy 450 based on the trained second improvement strategy model 520 to meet the needs of improving the sound insulation material.

[0146] A more comprehensive data basis is provided through the third test data 511, the first distribution information 441, the second distribution information 512 and the qualified intensity sequence 442, and the third test data 511 is related to the intensity of multiple second sound signals, and the data is more accurate, so that the second improvement strategy model 520 can determine a more reasonable target improvement strategy to improve the sound insulation effect.

[0147] Figure 6 is an exemplary flow chart of determining a target improvement strategy according to some embodiments of this specification. Figure 6 As shown, process 600 includes the following steps. In some embodiments, Figure 6 One or more operations of the process 600 shown may be performed in Figure 1 The performance analysis and improvement system of the sound insulation material shown is implemented in the application scenario 100. For example, Figure 6 The process 600 shown may be stored in a storage device in the form of instructions, and called and / or executed by the processor 150. In some embodiments, the process 600 may be executed by the second determination module 240.

[0148] In some embodiments, process 600 is to determine a target improvement strategy from the perspective of enhancing the sound insulation performance and cost of the sound insulation material. Figure 3 The process of determining target improvement strategies is similar.

[0149] Step 610: determine one or more first improvement strategies based on the first test data and the first distribution information.

[0150] The first improvement strategy refers to the sound insulation material improvement strategy that can make the performance of the sound insulation material qualified. Figure 3 The target improvement strategy in is similar and will not be repeated here.

[0151] In some embodiments, the second determination module 240 may determine the first improvement strategy by following the steps below:

[0152] S31: constructing a sound insulation test vector based on the first test data and the first distribution information. The process of constructing the sound insulation test vector can refer to step S21-step S22 and related descriptions.

[0153] S32: Retrieve the second reference sound insulation vector with the highest similarity from the second strategy vector database based on the sound insulation test vector, and use the multiple reference improvement strategies corresponding to the second reference sound insulation vector with the highest similarity as the first improvement strategy.

[0154] The second strategy vector database includes multiple second reference sound insulation vectors in the same format as the sound insulation test vector and multiple reference improvement strategies corresponding to them. In some embodiments, the second strategy vector database can be constructed based on experimental data. The method for determining the reference improvement strategy corresponding to each second reference sound insulation vector can refer to Figure 4 The difference is that here, the sample sound insulation materials whose final sound insulation effect meets the qualified receiving intensity and whose total increase is less than the total increase threshold are determined as multiple reference improvement strategies. Among them, the total increase threshold can be set manually.

[0155] Step 620: Determine a target improvement strategy based on the first improvement strategy.

[0156] In some embodiments, the second determination module 240 may determine the target improvement strategy based on the first improvement strategy by a variety of methods. For example, the second determination module 240 may determine the target improvement strategy by a preset strategy rule. The preset strategy rule refers to a preset rule for selecting the target improvement strategy from a plurality of first improvement strategies.

[0157] For example, the preset strategy rules may include selecting the first improvement strategy with the least amount of sound insulation material added as the target improvement strategy. For another example, the preset rules may include selecting the first improvement strategy with the most uniform thickness of each edge of the sound insulation area surrounded by the sound insulation material after improvement as the target improvement strategy. The most uniform thickness of each edge means that the difference between the thickness of each edge is the smallest. For example, the variance value of the thickness of each edge is the smallest.

[0158] In some embodiments, the second determination module 240 can also determine the predicted test data corresponding to the first improvement strategy based on the first improvement strategy, the first distribution information, the second distribution information and the preset sound characteristics through a performance prediction model, where the performance prediction model is a machine learning model; and determine the target improvement strategy based on the predicted test data.

[0159] The second distribution information refers to the distribution information of the playback devices and the sound receiving devices, for example, the placement position, placement direction and other information of one or more playback devices and the sound receiving devices.

[0160] For more information about the first distribution information and preset sound characteristics, please refer to Figure 3 and its related description.

[0161] The predicted test data refers to the test data corresponding to the sound insulation material improved by the first improvement strategy predicted by the performance prediction model. In some embodiments, the predicted test data may be the same as the first test data in form. For more information about test data, see Figure 3 and its related description.

[0162] The performance prediction model refers to a model used to determine the prediction test data. In some embodiments, the prediction test model can be a machine learning model. For example, Convolutional Neural Networks (CNN), Deep Neural Networks (DNN), etc.

[0163] In some embodiments, for a first improvement strategy among the one or more first improvement strategies, the second determination module 240 may input the first distribution information, the second distribution information, the preset sound feature data and the first improvement strategy into the performance prediction model, thereby obtaining the prediction test data corresponding to the first improvement strategy. Furthermore, the second determination module 240 may obtain one or more prediction test data corresponding to the one or more first improvement strategies.

[0164] In some embodiments, the input of the performance prediction model may include the first improvement strategy, the first distribution information, the second distribution information, and the preset sound characteristics, and the output may include the prediction test data. For more information about the first distribution information and the preset sound characteristics, see Figure 3 and its related description.

[0165] In some embodiments, the performance prediction model can be obtained by training multiple third training samples with third labels. Specifically, multiple third training samples with third labels can be input into the initial performance prediction model, and the loss function is constructed by the output result of the initial performance prediction model and the third label, and the parameters of the initial performance prediction model are iteratively updated by gradient descent or other methods based on the loss function. When the preset conditions are met, the model training is completed and a trained performance prediction model is obtained. Among them, the preset conditions can be that the loss function converges, the number of iterations reaches a threshold, etc.

[0166] In some embodiments, the second determination module 240 may use the improvement strategy, the first distribution information, the second distribution information and the preset sound characteristics in the historical test records of the sound insulation material as the third training sample. In some embodiments, the third label corresponding to the third training sample may be obtained through experiments.

[0167] For each third training sample, the sound insulation material that meets the first distribution information can be improved based on the improvement strategy therein, and the improved sound insulation material is tested based on preset sound characteristics through a playback device and a receiving device that meet the second distribution information. The first test data is determined according to the test results, and the first test data is used as the third label.

[0168] In some embodiments, the second determination module 240 may determine the target improvement strategy based on the predicted test data by the following steps:

[0169] ① For one or more first improvement strategies, determine the size relationship between each sound frequency, the receiving intensity corresponding to the playback intensity, and the qualified receiving intensity based on the predicted test data corresponding to each first improvement strategy, and screen out one or more improvement strategies whose receiving intensities corresponding to all sound frequencies are less than the corresponding qualified receiving intensity as the first candidate strategies.

[0170] As an example only, the prediction test data corresponding to the first improvement strategy 1 includes the sound frequency f1, the playback intensity B 11 The corresponding receiving strength is C 11 ; Sound frequency f2, playback intensity B 21 The corresponding receiving strength is C 21 ; The corresponding qualified receiving strengths are F 11 、F 21 , if C 11 <F 11 And C 21 <F 21 , then the first improved strategy is the first candidate strategy.

[0171] ② For each first candidate strategy, a receiving intensity sequence corresponding to each first candidate strategy is constructed based on the receiving intensity corresponding to each sound frequency and playback intensity in the corresponding predicted test data. For example, the receiving intensity sequence can be expressed as (C 11 , C 21 , …).

[0172] ③ For each first candidate strategy, based on the qualified receiving strength corresponding to each sound frequency and playback intensity in the corresponding predicted test data, a qualified strength sequence corresponding to each first candidate strategy is constructed in the order of the receiving strength. In some embodiments, the qualified receiving strength sequence can be expressed as (F 11 , F 21 , …).

[0173] ④ Calculate the similarity between the received strength sequence corresponding to each first candidate strategy and the qualified strength sequence, and use the first subsequent improved strategy whose similarity meets the similarity threshold as the second candidate strategy. The similarity threshold can be set by the technician based on prior experience.

[0174] ⑤ Calculate the total amount of sound insulation material required to improve the sound insulation material in each second candidate strategy, and use the second candidate strategy with the smallest amount of sound insulation material as the target improvement strategy. For example, calculate the total volume of sound insulation material required to improve the sound insulation material according to the second candidate strategy based on the height, length and improved thickness of the sound insulation material, and use the second candidate strategy with the smallest total volume required as the target improvement strategy. The height of the sound insulation material can be directly measured.

[0175] In some embodiments of the present specification, the predicted test data of the first improvement strategy is first determined through a performance prediction model, so as to accurately evaluate the sound insulation effect of the first improvement strategy; then, through the relationship between the receiving intensity and the qualified receiving intensity, the first candidate strategy with qualified sound insulation effect can be screened out; then, the similarity between the receiving intensity vector and the qualified receiving intensity vector is obtained through a screening, and the second candidate strategy with similarity satisfying the similarity is screened out, so as to filter out the improvement strategies whose sound insulation performance far exceeds the required sound insulation effect; finally, according to the total amount of sound insulation material increase required by the second candidate strategy, the target improvement strategy is determined, so that the target improvement strategy can have the lowest cost under the premise of qualified sound insulation effect.

[0176] In some embodiments of the present specification, a plurality of first improvement strategies are determined by using the first test data and the first distribution information, and a target improvement strategy is determined according to the first improvement strategies, so that the most reasonable target improvement strategy can be obtained.

[0177] Figure 7 FIG. 1 is an exemplary flow chart of another target improvement strategy according to some embodiments of this specification. Figure 7 As shown, process 700 includes the following steps. In some embodiments, Figure 7 One or more operations of the process 700 shown may be performed at Figure 1 The performance analysis and improvement system of the sound insulation material shown is implemented in the application scenario 100. For example, Figure 7 The process 700 shown may be stored in a storage device in the form of instructions, and called and / or executed by the processor 150. In some embodiments, the process 700 may be executed by the second determination module 240.

[0178] Step 710: Determine a second improvement strategy based on the first test data and the first distribution information.

[0179] The second improvement strategy refers to an improvement strategy when the sound insulation material is initially improved. The initial improvement refers to an experimental improvement operation on the sound insulation material. In some embodiments, the second determination module 240 can analyze the improvement effects of different improvement strategies based on the second test data after the initial improvement of the sound insulation material to further determine a target improvement strategy with better sound insulation effect.

[0180] The method for the second determination module 240 to determine the second improvement strategy based on the first test data and the first distribution information can be referred to as Figure 3 The method of determining the target improvement strategy in steps S21 to S23.

[0181] Step 720: Acquire second test data based on the improved sound insulation material and the preset sound characteristics.

[0182] Improved sound insulation material refers to sound insulation material obtained after improvement.

[0183] In some embodiments, the improved sound insulation material is obtained by improving the sound insulation material based on the second improvement strategy.

[0184] The second test data refers to data obtained by testing the performance of the improved sound insulation material. In some embodiments, the format of the second test data can be the same as the format of the first test data. For more information about the first test data, see Figure 3 and its related description.

[0185] In some embodiments, the second test data may be determined based on the first sound signal and the third sound signal.

[0186] The third sound signal refers to the sound signal received by the sound receiving device when the improved sound insulation material is tested. In some embodiments, the third sound signal is the sound signal transmitted by the first sound signal through the improved sound insulation material.

[0187] In some embodiments, the sound emitting module 210 may play the first sound signal through a playing device, and the sound receiving module 220 may receive the third sound signal transmitted through the improved sound insulation material through a sound receiving device.

[0188] In some embodiments, the first determination module 230 may determine the second test data based on the first sound signal and the third sound signal according to the method for determining the first test data. For details on the method for determining the first test data, see Figure 3 and its related description.

[0189] Step 730, based on the first test data, the second test data, the first distribution information, the third distribution information and the qualified strength sequence, determine the target improvement strategy by improving the strategy model.

[0190] The third distribution information refers to distribution information of improved sound insulation materials.

[0191] For more information on improving the distribution of soundproofing materials, refer to Figure 3 And related descriptions thereof, related descriptions on the distribution information of sound insulation materials.

[0192] The improvement strategy model refers to a model used to determine the target improvement strategy. In some embodiments, the improvement strategy model can be a machine learning model, such as CNN, DNN, etc.

[0193] In some embodiments, the improved strategy model may include a feature extraction layer and a prediction layer.

[0194] The feature extraction layer refers to a model layer structure for extracting the third performance feature. In some embodiments, the feature extraction layer can be a machine learning model, such as CNN.

[0195] In some embodiments, the input to the feature extraction layer may include the second test data and the output may include the third performance feature.

[0196] The third performance feature refers to a feature in the second test data related to the sound insulation performance. In some embodiments, the third performance feature can reflect the characteristics of the sound insulation effect of the improved sound insulation material on sounds of different sound frequencies.

[0197] The prediction layer refers to a model layer structure used to determine the target improvement strategy. In some embodiments, the prediction layer can be a machine learning model, such as DNN.

[0198] In some embodiments, the input of the prediction layer may include the first test data, the first distribution information, the third performance characteristic, the third distribution information, and the qualified strength sequence. In some embodiments, the output of the prediction layer may include the target improvement strategy. For more information about the first test data and the first distribution information, see Figure 3 For more information on qualified intensity sequences, see Figure 4 and its related description.

[0199] In some embodiments, the second determination module 240 can train the improved strategy model in a variety of ways. For example, the second determination module 240 can jointly train the feature extraction layer and the prediction layer to obtain a trained improved strategy model. Among them, the fourth training sample of the joint training includes the sample first test data, the sample second test data, the sample first distribution information, the sample third distribution information and the sample qualified strength sequence of the sample sound insulation material. In some embodiments, the acquisition process of the fourth label is similar to the acquisition process of the first label. The training process of the improved strategy model can refer to the training process of the first improved strategy model 420, which will not be repeated here.

[0200] In some embodiments of the present specification, a third performance feature reflecting the sound insulation effect corresponding to each sound frequency is extracted through the feature extraction layer; the target improvement strategy is determined through the prediction layer based on the first test data, the first distribution information, the third performance feature, the third distribution information and the qualified intensity sequence, and a more accurate target improvement strategy can be obtained by comparing the first test data, the first distribution information with the third performance feature and the third distribution information. By jointly training the feature extraction layer and the prediction layer, not only can the number of samples required be reduced, but also the problem of difficulty in obtaining label change features when training the change feature layer alone can be solved, thereby improving training efficiency. In practical applications, the second determination module 240 can quickly determine the target improvement strategy that can make the performance of the sound insulation material meet the requirements based on the trained performance prediction model, further improve the determination efficiency and accuracy of the target improvement strategy, and meet the business needs of the enterprise. In some embodiments of the present specification, a second improvement strategy is determined through first test data and first distribution information, the sound insulation material is improved based on the second improvement strategy, and the improved sound insulation material is tested to obtain third test data, which can further verify the improvement effect of the second improvement strategy. Based on the analysis of the third test data, the third distribution information and the first test data, the first distribution information, better target improvement effects can be obtained, thereby improving the performance analysis and improvement efficiency of the sound insulation material.

[0201] One or more embodiments of the present specification provide a device for analyzing and improving the performance of a sound insulation material, including a processing device, wherein the processing device is used to execute a method for analyzing and improving the performance of a sound insulation material.

[0202] One or more embodiments of the present specification provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a performance analysis and improvement method of a sound insulation material.

[0203] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0204] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0205] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0206] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0207] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0208] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0209] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A performance analysis and improvement method of a sound insulation material, characterized in that: include: A first sound signal with a preset sound characteristic is emitted through a playback device, wherein the playback device is arranged outside the sound insulation material; Receiving a second sound signal through a sound receiving device, wherein the sound receiving device is disposed inside the sound insulation material, and the second sound signal is a sound signal transmitted by the first sound signal through the sound insulation material; determining test data based on the first sound signal and the second sound signal; Based on the test data, a target improvement strategy is determined.

2. The method according to claim 1, characterized in that Determining a target improvement strategy based on the test data includes: The target improvement strategy is determined based on the test data and first distribution information, where the first distribution information refers to distribution information of the sound insulation material.

3. The method according to claim 2, characterized in that The number of the second sound signals is multiple, and the test data includes first test data, and the first test data is related to the statistical value of the strength of the multiple second sound signals, the frequency of the multiple first sound signals, and the strength of the multiple first sound signals; The determining the target improvement strategy based on the test data and the first distribution information includes: Determine one or more first improvement strategies based on the first test data and the first distribution information; Based on the first improvement strategy, a target improvement strategy is determined.

4. The method according to claim 2, characterized in that: The determining the target improvement strategy based on the test data and the first distribution information includes: Determine a second improvement strategy based on the first test data and the first distribution information; Based on the improved sound insulation material and the preset sound characteristics, second test data is obtained; the improved sound insulation material is obtained by improving the sound insulation material based on the second improvement strategy; the second test data is determined based on the first sound signal and a third sound signal, and the third sound signal is a sound signal transmitted by the first sound signal through the improved sound insulation material; Based on the first test data, the second test data, the first distribution information, the third distribution information and the qualified strength sequence, the target improvement strategy is determined through an improved strategy model, the improved strategy model is a machine learning model, and the third distribution information refers to the distribution information of the improved sound insulation material.

5. A system for analyzing and improving the performance of sound insulation materials, characterized in that: include: A sound emitting module is configured to emit a first sound signal with a preset sound characteristic through a playing device, wherein the playing device is arranged outside the sound insulation material; a sound receiving module, configured to receive a second sound signal through a sound receiving device, wherein the sound receiving device is disposed inside the sound insulation material, and the second sound signal is a sound signal transmitted by the first sound signal through the sound insulation material; A first determination module is configured to determine test data based on the first sound signal and the second sound signal; The second determination module is configured to determine a target improvement strategy based on the test data.

6. The system according to claim 1, characterized in that The second determining module is further configured to: The target improvement strategy is determined based on the test data and first distribution information, where the first distribution information refers to distribution information of the sound insulation material.

7. The system according to claim 6, characterized in that The number of the second sound signals is multiple, and the test data includes first test data, and the first test data is related to the statistical value of the strength of the multiple second sound signals, the frequency of the multiple first sound signals, and the strength of the multiple first sound signals; The second determining module is further configured to: Determine one or more first improvement strategies based on the first test data and the first distribution information; Based on the first improvement strategy, a target improvement strategy is determined.

8. The system according to claim 6, characterized in that The second determining module is further configured to: Determine a second improvement strategy based on the first test data and the first distribution information; Based on the improved sound insulation material and the preset sound characteristics, obtaining second test data; The improved sound insulation material is obtained by improving the sound insulation material based on the second improvement strategy; The second test data is determined based on the first sound signal and a third sound signal, wherein the third sound signal is a sound signal transmitted by the first sound signal through the improved sound insulation material; Based on the first test data, the second test data, the first distribution information, the third distribution information and the qualified strength sequence, the target improvement strategy is determined through an improved strategy model, the improved strategy model is a machine learning model, and the third distribution information refers to the distribution information of the improved sound insulation material.

9. A device for analyzing and improving the performance of sound insulation materials, comprising a processing device, characterized in that: The processing equipment is used to execute the performance analysis and improvement method of the sound insulation material as described in any one of claims 1 to 4.

10. A computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the performance analysis and improvement method of the sound insulation material according to any one of claims 1 to 4.

Images