Sound effect prediction and sound box combination recommendation method and system

By collecting and analyzing data samples in the target area, building a digital model, predicting the sound effects under the speaker settings, and recommending the speaker combination based on the user's expectations, it solves the problem that users find it difficult to choose when purchasing speakers, and improves the accuracy of sound effects prediction Sex and user experience.

CN119052710APending Publication Date: 2024-11-29HANSONG NANJING TECH LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411139461.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

It is difficult for users to make appropriate choices when purchasing speakers, which affects the sound effect, especially in environments where different speaker types and installation locations have a significant impact on the sound experience.

Method used

By collecting data samples from the target area, determining the acoustic environment and area models, building a digital model, predicting the sound effects under the speaker setting parameters, and recommending suitable speaker combinations based on the user's expected acoustic parameters.

Benefits of technology

Provide users with personalized speaker combination recommendations, improve the prediction accuracy and user experience of sound effects, simplify the speaker selection process, and reduce costs and time overhead.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119052710A_ABST
    Figure CN119052710A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides a sound effect prediction and sound box combination recommendation method and system. The method comprises the steps that data samples in a target area are collected; determining an acoustic environment and a region model of the target region based on the data sample; constructing a digital model of the target area based on the area model and the acoustic environment; and according to the digital model and the sound box setting parameters, predicting a predicted sound effect in the target area under the sound box setting parameters. The method further comprises the steps of determining a candidate loudspeaker box combination based on expected acoustic parameters of a user; determining a predicted acoustic effect corresponding to the candidate sound box combination through the sound effect prediction method; determining a recommended loudspeaker box combination from the candidate loudspeaker box combinations based on the predicted acoustic effect; and displaying the recommended sound box combination and the corresponding predicted acoustic effect.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of sound effect prediction, and in particular to a method and system for sound effect prediction and speaker combination recommendation. Background Art

[0002] In different usage environments, the configuration and installation location of different speaker types will directly affect the sound effects experienced by users. In professional or entertainment occasions such as conference rooms, concert halls, theaters and home theaters, users generally pursue high-quality acoustic experience; while in more private rooms or study environments, users tend to create an acoustic atmosphere that is coordinated with the space. However, faced with a wide range of speaker products on the market, users often find it difficult to make appropriate choices when purchasing speakers and planning their placement.

[0003] Therefore, it is hoped to provide a method and system for sound effect prediction and speaker combination recommendation, so as to achieve the purpose of personalized recommendation of applicable scenarios of different speakers for users. Summary of the invention

[0004] One or more embodiments of the present specification provide a sound effect prediction method, including: collecting data samples in a target area; determining the acoustic environment and regional model of the target area based on the data samples; constructing a digital model of the target area based on the regional model and the acoustic environment; and predicting the predicted sound effects in the target area under the speaker setting parameters based on the digital model and speaker setting parameters.

[0005] One or more embodiments of the present specification provide a method for recommending a speaker combination, comprising: determining a candidate speaker combination based on the user's expected acoustic parameters; determining the predicted acoustic effect corresponding to the candidate speaker combination through the aforementioned sound effect prediction method; determining a recommended speaker combination from the candidate speaker combinations based on the predicted acoustic effect; and displaying the recommended speaker combination and its corresponding predicted acoustic effect.

[0006] One of the embodiments of the present specification provides a sound effect prediction system, including an acquisition module, a determination module, a construction module and a prediction module; the acquisition module is configured to acquire data samples in a target area; the determination module is configured to determine the acoustic environment and the regional model of the target area based on the data samples; the construction module is configured to construct a digital model of the target area based on the regional model and the acoustic environment; the prediction module is configured to predict the predicted sound effect in the target area under the speaker setting parameters based on the digital model and the speaker setting parameters.

[0007] One or more embodiments of the present specification provide a sound effect prediction device, including a processor, and the processor is used to execute the above-mentioned sound effect prediction method.

[0008] 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 the aforementioned sound effect prediction method. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] 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:

[0010] Figure 1 is an application scenario diagram of the sound effect prediction system according to some embodiments of this specification;

[0011] Figure 2 is a module diagram of a sound effect prediction system according to some embodiments of this specification;

[0012] Figure 3 is an exemplary flow chart of a sound effect prediction method according to some embodiments of this specification;

[0013] Figure 4 is a schematic diagram of a method for determining an acoustic environment according to some embodiments of this specification;

[0014] Figure 5 is a schematic diagram of sound sample collection according to some embodiments of this specification;

[0015] Figure 6 It is an exemplary flow chart of the speaker combination recommendation method shown in some embodiments of this specification. DETAILED DESCRIPTION

[0016] 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.

[0017] 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.

[0018] 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.

[0019] 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.

[0020] Figure 1 It is an application scenario diagram of the sound effect prediction system shown in some embodiments of this specification. The application scenario 100 of the sound effect prediction system involved in the embodiments of this specification will be described in detail below. It should be noted that the following embodiments are only used to explain this application and do not constitute a limitation on this application.

[0021] like Figure 1 As shown, the application scenario 100 of the sound effect prediction system may include a target area 110 , a processor 120 , a user terminal 130 , and a speaker combination 140 .

[0022] The target area 110 may be an area where sound effect prediction and / or speaker combination recommendation is required, such as a concert hall, theater, conference room, home theater, etc.

[0023] A speaker assembly 140 may be provided in the target area 110. In some embodiments, the speaker assembly may include at least one speaker. As an example, the speaker assembly 140 may be placed at a preset position in the target area 110.

[0024] The processor 120 can process data and / or information in the sound effect prediction system 200. In some embodiments, the processor 120 can be a computer, a user console, a single processor or a processor group, etc. The processor group can be centralized or distributed. In some embodiments, the processor 120 can be implemented on a cloud platform.

[0025] In some embodiments, the processor 120 may include a memory. The memory is used to store data during the operation of the sound effect prediction system 200. For example, the stored data may include but is not limited to data samples, candidate speaker combinations, etc.

[0026] The user terminal 130 may refer to one or more terminal devices or software used by the user. In some embodiments, the user terminal 130 may be a mobile device such as a mobile phone, a tablet computer, a laptop computer, or any combination thereof. In some embodiments, the user terminal 130 may interact with other components in the sound effect prediction system through a network. For example, the user terminal 130 may present the data generated by the processor 120 to the user.

[0027] In some embodiments, the user terminal may include a device for data collection. As an example only, the data collection device may include an image collection device and a sound collection device, which may be independent devices or integrated in the aforementioned mobile devices such as mobile phones, tablet computers, and laptop computers.

[0028] In addition to the above application scenarios, the sound effect prediction system involved in some embodiments of this specification can also be applied to other scenarios where sound effect prediction is required.

[0029] Figure 2 It is a module diagram of a sound effect prediction system according to some embodiments of this specification.

[0030] In some embodiments, the sound effect prediction system 200 may include a collection module 210 , a determination module 220 , a construction module 230 , and a prediction module 240 .

[0031] The acquisition module 210 is configured to acquire data samples in the target area, wherein the data samples may include sound samples and image samples.

[0032] In some embodiments, the acquisition module 210 is further configured to determine sound acquisition parameters based on the sound source type, the area model, the spatial structure type, and the acquisition device type; and acquire sound samples based on the sound acquisition parameters.

[0033] The determination module 220 is configured to determine the acoustic environment and the area model of the target area based on the data samples.

[0034] In some embodiments, the determination module 220 is further configured to determine the acoustic propagation characteristics of the target area based on the sound sample; and determine the acoustic environment of the target area based on the area model and the acoustic propagation characteristics.

[0035] In some embodiments, the determination module 220 is further configured to determine the spatial structure type of the target area based on the image samples; and determine the acoustic environment of the target area based on the spatial structure type, the area model and the acoustic propagation characteristics.

[0036] In some embodiments, the determination module 220 is further configured to determine image feature points based on the image samples; construct a three-dimensional point cloud model of the target area based on the image feature points; and determine the area model based on the three-dimensional point cloud model.

[0037] The construction module 230 is configured to construct a digital model of the target area based on the area model and the acoustic environment.

[0038] The prediction module 240 is configured to predict the predicted sound effect in the target area under the speaker setting parameters according to the digital model and the speaker setting parameters.

[0039] In some embodiments, the sound effect prediction system 200 may also include a recommendation module, which is configured to determine a candidate speaker combination based on the user's expected acoustic parameters; determine the predicted acoustic effects corresponding to the candidate speaker combination; determine a recommended speaker combination from the candidate speaker combinations based on the predicted acoustic effects; and display the recommended speaker combination and its corresponding predicted acoustic effects.

[0040] In some embodiments, the recommendation module is further configured to adjust the recommended speaker combination based on user feedback. For more information about the recommendation module, please refer to this manual. Figure 6 Description in .

[0041] In some embodiments, the recommendation module can be integrated into the sound effect prediction system, or can be used as a separate recommendation system for recommending speaker combinations.

[0042] In some embodiments, the sound effect prediction system 200 and its various modules may be integrated into the processor 120. For detailed description of the functions performed by the sound effect prediction system 200 and its various modules, please refer to the specification. Figure 3-Figure 6 Related content.

[0043] It should be understood that Figure 2 The system and its modules shown can be implemented in various ways. For example, by hardware, software, or a combination of software and hardware. The system and its modules of this specification can be implemented not only by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, but also by software implemented by, for example, various types of processors, and can also be implemented by a combination of the above hardware circuits and software (e.g., firmware).

[0044] It should be noted that the above description of the sound data acquisition system and its modules is only for 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 modules disclosed in the specification may be different modules in a system, or one module may realize the functions of two or more modules. For example, the modules may share a storage module, or each module may have its own storage module. Such variations are within the scope of protection of this specification.

[0045] Figure 3 is an exemplary flow chart of a sound effect prediction method according to some embodiments of this specification. Figure 3 As shown, the process 300 includes the following steps. In some embodiments, the process 300 may be executed by a processor.

[0046] Step 310: Collect data samples within the target area.

[0047] The target area refers to an area where data samples need to be collected. In some embodiments, the target area can be determined based on the actual needs of data sample collection. For example, the target area can be an area where sound effect prediction and / or speaker combination recommendation is required, such as a concert hall, theater, conference room, home theater, etc.

[0048] The data sample refers to a data set obtained by actual measurement or observation in the target area, wherein the data sample may include at least one of an image sample and a sound sample.

[0049] The image sample is a picture of the target area obtained based on image acquisition. For example, the image sample can be at least one picture covering the entire target area, or multiple pictures that jointly show comprehensive features of the target area.

[0050] In some embodiments, the image sample may include a two-dimensional photo of the target area taken by a common camera, and / or a point cloud photo of the target area taken by a 3D camera.

[0051] In some embodiments, the user uses an ordinary camera to take pictures of various parts of the room, and the processor collects image samples based on the photos taken by the user, including walls, floors, ceilings, and furniture; wherein the collected image samples need to ensure that the pictures cover every corner of the room and all objects in order to perform detailed three-dimensional reconstruction.

[0052] The sound sample is an audio file in the target area obtained based on acoustic acquisition.

[0053] In some embodiments, the processor can control the speaker to play the test signal at a specific location in the room according to different test parameter settings, and control the sound collection device to record the sound signal at multiple other locations in the room to comprehensively collect sound samples.

[0054] In some embodiments, the sound sample may include multiple sound components such as direct sound, reflected sound after being reflected by different interfaces, and reverberation formed by superposition of multiple reflections.

[0055] In some embodiments, test parameter setting is a comprehensive process, which may include multiple dimensions such as volume, frequency, and test signal type (such as pulse wave, sine wave, etc.). In order to improve the convenience of user operation, some experience-based parameter values ​​may be preset and directly recommended to the user so that the user can quickly and accurately set the test conditions.

[0056] In some embodiments, the processor may obtain more sound samples by setting a plurality of playback positions and collection positions of the test signals, so that the collection positions and playback positions cover the entire room as evenly as possible.

[0057] The playback position refers to the specific location in the room where the speaker is used to play the test signal. For example, the playback position may include the center of the room, near a wall, and in a corner of the room.

[0058] The acquisition location refers to the specific position in the room where the processor is used to record the sound signal. It is usually distributed in multiple key areas of the room to achieve comprehensive coverage of the entire room acoustic environment.

[0059] In some embodiments, the processor may determine the sound collection parameters based on the sound source type, the regional model, the spatial structure type, and the collection device type, and acquire the sound samples based on the sound collection parameters.

[0060] For more information on how to collect sound samples, please refer to this manual. Figure 5 See the relevant instructions in .

[0061] Step 320: Determine the acoustic environment and regional model of the target area based on the data samples.

[0062] The acoustic environment refers to the environment formed by the acoustic characteristics of sound propagation, reflection, absorption, etc. in a closed or semi-closed space. The acoustic environment can affect the comfort and effect of the user's listening in the aforementioned space. For example, the acoustic environment may include but is not limited to the characteristics of sound absorption and reflection.

[0063] In some embodiments, the processor can determine the noise level, echo effect, sound field uniformity, and size, shape, and layout of the target area based on the data samples, and determine the acoustic environment of the target area by analyzing the aforementioned data.

[0064] In some embodiments, the processor may determine the acoustic propagation characteristics of the target area based on the sound samples; and determine the acoustic environment of the target area based on the area model and the acoustic propagation characteristics.

[0065] For more information on how to determine the acoustic environment of the target area, see this manual. Figure 4 See the relevant instructions in .

[0066] In some embodiments, the processor may determine the size, shape, and arrangement of the target area based on the data samples, and input the aforementioned data into the modeling software to obtain a regional model of the target area.

[0067] In some embodiments, the processor may determine image feature points based on image samples; construct a three-dimensional point cloud model of the target area through the image feature points; and determine the area model based on the three-dimensional point cloud model.

[0068] Image feature points refer to points with some local special properties, such as image edge points (contour points).

[0069] In some embodiments, the processor pre-processes the acquired image based on an existing algorithm, wherein the pre-processing includes but is not limited to at least one of correction, elimination of illumination change, and distortion.

[0070] In some embodiments, the processor may implement correction of the image samples in a variety of ways, such as histogram equalization, gamma correction, image denoising, or other ways capable of completing the correction.

[0071] In some embodiments, the processor may extract image feature points from the preprocessed image based on a computer vision algorithm, wherein the computer vision algorithm adopts an existing algorithm, such as a SIFT (Scale-Invariant Feature Transform) algorithm, an ORB (Oriented FAST and Rotated BRIEF) algorithm, and the like.

[0072] A 3D point cloud model refers to a collection of discrete points in space, which usually have attribute information. In some embodiments, the attribute information may include location information and other information, such as color, reflectivity, etc., which may be selected according to actual needs.

[0073] In some embodiments, the processor may reconstruct a three-dimensional point cloud model of the room based on feature point matching and camera position estimation based on photogrammetry and structure from motion (SFM) techniques.

[0074] Feature point matching is a process of finding corresponding feature points in two images and establishing a corresponding relationship between them.

[0075] In some embodiments, the camera position estimate can be determined using existing algorithms, such as direct visual odometry, visual odometry, pose estimation methods, etc.

[0076] The regional model is a way to divide and represent three-dimensional space. It divides the entire scene or specific space into several regions with specific attributes or functions.

[0077] In some embodiments, these areas may include direct mappings of physical spaces (such as rooms, corridors, balconies, etc.), and / or abstract divisions based on functions (such as quiet zones, reverberation zones, etc.). For example, the processor may obtain user input through a user terminal, and determine abstract divisions based on functions based on the user input. The user input may include manually determined division results.

[0078] In some embodiments, the processor may filter, denoise, align, and reconstruct the point cloud data based on point cloud processing software to obtain an initial region model.

[0079] In some embodiments, the processor may determine the initial region model as the region model of the target region.

[0080] In some embodiments, the processor may further process the initial region model to obtain a region model of the target region. For example, the processor may map the image texture in the image sample to the initial region model to improve the realism and aesthetics of the initial region model.

[0081] Image texture refers to the visual properties of the spatial distribution of gray levels in an image, which reflects the structural regularity and repetitive patterns of the image surface. It can include information such as grayscale changes, roughness, directionality, and periodicity in local areas of the image.

[0082] In some embodiments, the processor may obtain the image texture in the image sample through gray level co-occurrence matrix, local binary pattern, etc.

[0083] Step 330: construct a digital model of the target area based on the area model and the acoustic environment.

[0084] The digital model is a virtual model that corresponds to the real environment of the target area. As a reduced replica of the target area, the virtual model retains the physical structure layout and acoustic characteristics of the real environment in the target area. Therefore, it can simulate the sound field distribution generated by the speakers when playing audio in the virtual space.

[0085] In some embodiments, the processor can input the data of the three-dimensional model and the acoustic environment into simulation modeling software, such as AutoCAD, Ansys Twin Builder or other software capable of implementing corresponding functions, and the software can automatically generate a corresponding digital model.

[0086] Step 340 , predicting the predicted sound effect in the target area under the speaker setting parameters according to the digital model and the speaker setting parameters.

[0087] Speaker setup parameters are numerical values ​​that define the configuration and performance of a speaker in a specific environment.

[0088] In some embodiments, the speaker setting parameters include at least one of the speaker type, the number of speakers, and the placement position. The speaker type refers to the speaker model circulated on the market; the placement position refers to the placement position, placement direction, placement height, etc. of the speaker in the room, and may also include other parameters that can reflect the speaker position.

[0089] In some embodiments, the speaker setting parameters may be determined by the processor by obtaining user input. For example, the processor obtains the speaker type, speaker quantity, and placement position, etc. input by the user through the user terminal.

[0090] In some embodiments, the speaker setting parameters may also be determined based on at least one recommended speaker combination generated by the system. For example, the processor may determine a candidate speaker combination based on the user's desired acoustic parameters, and determine at least one recommended speaker combination from the candidate speaker combinations; determine the placement of the recommended speaker combination by obtaining user input, or randomly generate the placement of the speaker combination based on preset rules, and then determine the speaker setting parameters. The preset rules may include preset speaker placements based on prior experience and / or actual needs.

[0091] Detailed instructions for desired acoustic parameters and determining recommended speaker combinations can be found in this manual. Figure 6 Related description in .

[0092] The sound effect refers to the sound characteristics when the audio is played in the target area. For example, the sound effect may include at least one of the sound field distribution and the sound quality, and may also include other parameters that can reflect the sound characteristics.

[0093] Among them, sound field distribution refers to the changes in sound pressure, sound intensity, timbre and other acoustic characteristics of sound at different positions in space; sound quality is a parameter that can comprehensively reflect the clarity, fidelity, balance, etc. of sound.

[0094] In some embodiments, the processor can simulate the sound field distribution corresponding to different speaker setting parameters in the digital model. For example, the performance data of each speaker in the current speaker setting parameters is obtained based on the speaker database, and based on the performance data of the speaker, the sound field distribution in the target area is simulated in the aforementioned digital model through acoustic simulation software. The acoustic simulation software can be at least one of EASE, ODEON or COMSOL, or other software that can simulate the sound field distribution.

[0095] The speaker database is a database containing performance data of various speakers, including but not limited to at least one of frequency response, power output, and directivity. Among them, frequency response refers to the sound frequency range that the sound system can reproduce; power output refers to the audio power that the speaker can output; directivity refers to the ability of the speaker to output sound in all directions. In some embodiments, the speaker database may also include other data characterizing the performance of the speaker, which can be determined according to actual needs.

[0096] In some embodiments, the processor can determine the sound quality in the target area under the above-mentioned speaker setting parameters through an effect prediction model based on the sound field distribution. In some embodiments, the effect prediction model can be a machine learning model, such as a convolutional neural network model (CNN).

[0097] In some embodiments, the input of the effect prediction model may include the sound field distribution, and the output may include the sound quality in the target area.

[0098] In some embodiments, the processor may train the initial effect prediction model by gradient descent method or other possible training methods to obtain a trained effect prediction model. The training sample may be determined based on historical data, including at least one historical speaker setting parameter; the training label may be determined based on the historical sound quality actually corresponding to the historical speaker setting parameter.

[0099] In some embodiments, the trained label can be determined by obtaining user input. For example, the processor can obtain the user's detection result of the historical speaker setting parameters through the user terminal, and determine the trained label based on the detection result. The detection result can include but is not limited to at least one of historical sound clarity, historical fidelity, and historical balance.

[0100] In some embodiments of the present specification, by constructing a digital model of the target area and simulating the sound field distribution of different speaker setting parameters in the digital model, the sound effect can be determined. The sound effect can be determined without actually installing the speakers for experiments, and the sound effect of any speaker combination can be simulated more conveniently, quickly and at a low cost.

[0101] 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.

[0102] Figure 4 FIG. 1 is a schematic diagram of a method for determining an acoustic environment according to some embodiments of the present specification. Figure 4 As shown, the method 400 for determining an acoustic environment includes the following contents: In some embodiments, the method 400 for determining an acoustic environment may be executed by a processor.

[0103] In some embodiments, the processor may determine an acoustic propagation characteristic 420 of the target area based on the sound sample 410 ; and determine an acoustic environment 440 of the target area based on the area model 430 and the acoustic propagation characteristic 420 .

[0104] For more information about sound samples, acoustic environments, and regional models, see Figure 3 and its related description.

[0105] The acoustic propagation characteristics refer to the characteristics of the sound sample propagating in the target area. For example, the acoustic propagation characteristics may include but are not limited to at least one of the echo, reverberation time and frequency response of the sound sample in the target area.

[0106] In some embodiments, the processor may determine the acoustic propagation characteristics based on the sound sample through a digital signal processing (DSP) algorithm. For example, the DSP algorithm may include but is not limited to a Fourier transform algorithm, an adaptive filtering algorithm, etc. The type of the DSP algorithm may also be other algorithms that can complete the relevant processing.

[0107] In some embodiments, the processor may determine the acoustic environment of the target area in a variety of ways based on the area model and the acoustic propagation characteristics. For example, the processor may determine the acoustic environment through an acoustic environment determination model based on the area model and the acoustic propagation characteristics.

[0108] The acoustic environment determination model refers to a model used to determine the acoustic environment of the target area. In some embodiments, the acoustic environment determination model can be a machine learning model, such as a convolutional neural network model (CNN).

[0109] In some embodiments, the input of the acoustic environment determination model may include a regional model of the target area and acoustic propagation characteristics of the target area, and the output may be the acoustic environment of the target area.

[0110] In some embodiments, the acoustic environment determination model can be obtained by training based on a large number of first training samples with first labels. The processor can input multiple first training samples with first labels into the initial acoustic environment determination model, construct a loss function through the first label and the result of the initial acoustic environment determination model, and iteratively update the initial acoustic environment determination model based on the loss function. When the preset conditions are met, the model training is completed and a trained acoustic environment determination model is obtained. Among them, the preset conditions can be that the loss function converges, the number of iterations reaches a threshold, etc.

[0111] In some embodiments, the first training sample may be a sample region model and a sample acoustic propagation characteristic corresponding to a sample target region in historical data.

[0112] In some embodiments, the first label may be a sample acoustic environment corresponding to the sample target area. In some embodiments, the processor may obtain the sample acoustic environment through an existing algorithm based on the aforementioned regional model and acoustic propagation characteristics. For example, the existing algorithm may be a recursive neural network, a support vector machine, etc. The type of the existing algorithm may also be other algorithms that can complete related processing.

[0113] In some embodiments, the processor may determine a spatial structure type 460 of the target area based on the image sample 450 ; and determine an acoustic environment 440 of the target area based on the spatial structure type 460 , the area model 430 , and the acoustic propagation characteristics 420 .

[0114] The spatial structure type refers to the material type of each structure in the target area. For example, the material type of the ceiling is gypsum board, the material of the floor is tile, and so on.

[0115] The material type refers to the material corresponding to the structure in the target area. For example, the material type may include but is not limited to glass, cement, wood, etc.

[0116] Structure refers to architectural elements or objects in the target area. For example, structure can include but is not limited to walls, ceilings, windows, etc. in the target area.

[0117] In some embodiments, the processor may determine the spatial structure type of the target area through a classifier based on the image sample. For example, the classifier may include but is not limited to a support vector machine, a random forest, etc. The type of the classifier may also be other algorithms that can complete the relevant processing.

[0118] In some cases, the classifier can only distinguish the general type of the spatial structure from the image sample, and the recognition rate of other materials such as imitation materials is limited. In this case, the processor can collect additional sound samples to further determine the material of the spatial structure.

[0119] In some embodiments, the processor may determine supplementary acquisition parameters based on spatial material parameters, sound source type, and regional model of the target area; obtain supplementary sound samples based on the supplementary acquisition parameters; and determine the spatial structure type based on the supplementary sound samples and spatial material parameters.

[0120] Spatial material parameters refer to data used to characterize the type and distribution of materials in the space where the target area is located. For example, spatial material parameters may include the location of the same material in the space where the target area is located. For another example, spatial material parameters may also include spatial material types. For example, if there is building B in target area A, the spatial material parameters of target area A are the location of building B, and possible materials 1, material 2, ..., material n of building B.

[0121] The spatial material type refers to one or more possible materials of the buildings in the target area. For example, as in the above example, the spatial material type is material 1, material 2, ..., material n.

[0122] The sound source type refers to the directional type of the sound source. For example, the sound source type can be a 12-sided directional sound source. The sound source type can also be a directional sound source of other surfaces.

[0123] The supplementary acquisition parameters refer to data used to guide the user to obtain supplementary sound samples through the sound source device and the acquisition device. For example, the supplementary acquisition parameters may include but are not limited to supplementary sound source parameters and supplementary distribution data of the acquisition device.

[0124] The supplementary sound source parameters refer to the sound parameters of the sound source when the supplementary sound samples are obtained. For example, the supplementary sound source parameters may at least include the sound source position distribution of the supplementary sound samples.

[0125] The supplementary distribution data of the collection devices refers to the data related to the location distribution of the collection devices.

[0126] In some embodiments, the processor may determine the supplementary acquisition parameters based on a variety of methods. For example, the processor may construct a vector to be matched based on the spatial material parameters of the target area, the type of sound source, and the regional model. The supplementary acquisition parameters are determined by matching the vector to be matched in the parameter vector database.

[0127] The parameter vector database refers to a database used to determine the supplementary acquisition parameters. The database includes at least one reference vector and its corresponding reference acquisition parameter.

[0128] In some embodiments, the processor may determine the spatial structure type based on the supplementary sound samples in the historical data, and compare the aforementioned determined spatial structure type with the design parameters during the spatial design, and determine the historical data corresponding to the smallest error as the historical sample data.

[0129] In some embodiments, the reference vector in the parameter vector database can be determined based on the historical sample data. For example, the processor can construct a historical vector based on the historical spatial material parameters, historical sound source types, historical regional models, and subsequent historical supplementary acquisition parameters of the target area in the historical sample data, cluster the historical vectors to form a preset number of cluster centers, construct the historical spatial material parameters, historical sound source types, and historical regional models corresponding to the cluster centers into a reference vector, and determine the reference acquisition parameters corresponding to the reference vector based on the historical supplementary acquisition parameters.

[0130] In some embodiments, the processor may calculate the similarity between the vector to be matched and at least one reference vector, and use the reference acquisition parameters corresponding to the standard vector with the highest vector similarity as the supplementary acquisition parameters. The similarity may be negatively correlated to the vector distance between the vector to be matched and the standard vector, and the vector distance may be determined based on the cosine distance, etc.

[0131] In some embodiments, the processor may construct a spatial material atlas based on acquisition difficulty, sound source type, regional model, and spatial material parameters; and based on the spatial material atlas, determine supplementary acquisition parameters through a parameter determination model.

[0132] The spatial material graph refers to a knowledge graph used to represent the material distribution and properties of a target area. In some embodiments, the spatial material graph may be composed of at least one node and at least one edge, where the edge connects the nodes, and the nodes and edges may have properties.

[0133] In some embodiments, the nodes of the spatial material atlas may include a first type of node and a second type of node.

[0134] In some embodiments, a class of nodes can represent an object or a part of an object, and the object or part of an object corresponding to each class of nodes has the same material. For example, if an object is composed of only one material, then the object can be used as a class of nodes; for another example, if another object is composed of multiple materials, then the object can be divided into multiple parts based on the aforementioned multiple materials, and each part corresponds to a class of nodes. In some embodiments, the attributes of a class of nodes can reflect the material-related characteristics of the class of nodes. For example, the attributes of a class of nodes can include but are not limited to at least one of the size parameters of the class of nodes, the type of spatial material, the difficulty of acquisition, and the location of the class of nodes.

[0135] The size parameters of a type of node may include but are not limited to the volume, surface area, shape, etc. of the type of node.

[0136] The position of a type of node refers to the position of the type of node in the target area. In some embodiments, the processor can determine the position of the type of node by pre-setting a coordinate system in the target area.

[0137] The acquisition difficulty refers to the difficulty of a type of node to collect sound. In some embodiments, the acquisition difficulty can be represented by a numerical value, and the higher the numerical value, the greater the acquisition difficulty of the type of node.

[0138] In some embodiments, the processor may determine the acquisition difficulty based on multiple groups of methods. For example, the processor may use the average of the historical acquisition difficulties of a type of nodes as the acquisition difficulty.

[0139] In some embodiments, the processor may also determine the acquisition difficulty based on the material type of a class of nodes. Exemplarily, the processor may determine the acquisition difficulty based on the fact that the acquisition difficulty is negatively correlated to the number of material types of adjacent nodes of a class of nodes by the following formula (1).

[0140] Wherein, s is the difficulty of acquisition, n is the number of material types of adjacent nodes of a type of node, and α is a preset constant. In some embodiments, α is a positive number less than 1 and can be obtained by preset.

[0141] In some embodiments of the present specification, by determining the acquisition difficulty based on the material type of the node, the effect of the number of material types on sound wave propagation can be more accurately reflected, which helps to establish a more accurate spatial material map and thus improve the accuracy of acoustic environment simulation.

[0142] In some embodiments, the second type of node may correspond to a sound source in the target area. In some embodiments, the attributes of the second type of node may reflect the characteristics of the second type of node related to the sound source. For example, the second type of node may include but is not limited to the sound source type of the second type of node and the location of the second type of node.

[0143] The position of the second type of node refers to the position of the second type of node in the target area. In some embodiments, the position of the second type of node is obtained in a similar manner to the position of the first type of node, which will not be described in detail here.

[0144] In some embodiments, when objects or parts of objects corresponding to two nodes are in contact, the nodes are connected by edges, and the attributes of the edges include at least one of contact type and contact area.

[0145] The contact type refers to the manner or type of contact between an object or a part of an object. For example, the contact type may include but is not limited to direct contact (such as two materials are closely connected) or indirect contact (such as two materials are separated by other materials, but the distance between the two is within a preset range, which can be determined based on actual needs).

[0146] The contact area refers to the area of ​​direct contact between materials. If the contact type is indirect contact, the contact area is 0.

[0147] In some embodiments, the parameter determination model may be a machine learning model. For example, the parameter determination model may be a graph neural network (GNN) model.

[0148] The input of the parameter determination model can be a spatial material atlas, and the output of a type of node can be a supplementary acquisition parameter of the target area.

[0149] In some embodiments, the parameter determination model can be obtained by training based on multiple second training samples with second labels through gradient descent method or other feasible training methods. The training process is similar to the training process of the acoustic environment determination model mentioned above, and the details can be found in the relevant description above.

[0150] In some embodiments, the second training sample may be a historical sample spatial material atlas, which is constructed based on the historical material distribution in the second training sample and the historical correlation between them. The second signature may be a supplementary acquisition parameter actually used in the history corresponding to the second training sample.

[0151] In some embodiments of the present specification, by constructing a spatial material atlas and a parameter determination model, the spatial structure type can be determined more accurately, thereby facilitating the subsequent accurate determination of the acoustic environment, thereby simulating a sound field distribution that is close to reality.

[0152] Supplementary sound samples refer to sample data used to further determine the spatial structure type or spatial material parameters. For more information about sound samples, see Figure 3 , Figure 5 and its related description.

[0153] The acquisition device refers to a device used to acquire sound samples and / or supplement sound samples. For example, the acquisition device may be a microphone.

[0154] In some embodiments, the processor may obtain a supplementary sound sample based on the supplementary acquisition parameter. For example, the processor may perform acoustic acquisition in the target area through an acquisition device based on the supplementary acquisition parameter to obtain the supplementary sound sample.

[0155] In some embodiments, the processor may determine the spatial structure type based on the supplementary sound samples and spatial material parameters in the following manner. For example, the processor may extract the supplementary sound samples corresponding to the structure with questionable material, and compare them with the standard sound data of the candidate material, and use the candidate material with the highest similarity as the material corresponding to the structure with questionable material, and then combine all the above questionable materials into a sequence as the spatial structure type. Among them, the supplementary sound samples corresponding to the structure with questionable material refer to the sound samples collected within the preset distance range of the aforementioned structure with questionable material; the standard sound data of the candidate material refers to the reference sound samples collected within the preset distance range of the aforementioned candidate material. The preset distance range can be pre-set based on prior experience and / or actual needs.

[0156] A questionable material refers to a material whose material type has not been accurately identified in the target area. For example, a questionable material may be a replica material, a synthetic material, etc.

[0157] The candidate material refers to the possible material type of the questionable material. For example, in response to the questionable material A being a composite board imitating marble, the candidate materials corresponding to the questionable material A may include but are not limited to polyester resin, limestone powder, glass fiber, etc.

[0158] Standard sound data refers to the sound wave data obtained by acoustically collecting known materials.

[0159] In some embodiments, the processor may test the candidate material under target conditions and use the acquired sound data as standard sound data. The target environment may be the same space as the target area where the structure with questionable material is located, using the same testing equipment and acquisition equipment, and using the same equipment parameters.

[0160] In some embodiments of the present specification, supplementary acquisition parameters are determined by combining spatial material parameters, sound source types, and regional models to provide accurate data support for subsequent acoustic environment simulation. By obtaining supplementary sound samples based on supplementary acquisition parameters, the accuracy of acoustic characteristic analysis can be improved and simulation errors can be reduced. By determining the spatial structure type based on supplementary sound samples and spatial material parameters, the propagation and interaction of sound wave data in space can be more accurately analyzed, thereby further improving the accuracy of acoustic environment analysis.

[0161] In some embodiments, the processor may also input the spatial structure type into the acoustic environment determination model to determine the acoustic environment of the target space.

[0162] In some embodiments, when the input of the acoustic environment determination model includes a spatial structure type, the first training sample may also include a sample spatial structure type of a sample target area in historical data.

[0163] For more information on the acoustic environment determination model, see Figure 4 and its related description.

[0164] In some embodiments of the present specification, the processor can more accurately analyze the propagation behavior of the sound wave data in the target area by combining the image samples to determine the spatial structure type. In addition, the acoustic environment determination model further introduces the spatial structure type as the input of the model, which not only enriches the amount of information of the acoustic environment determination model, enhances the applicability and extensiveness of the acoustic environment determination model in environments of different types and complexity, but also makes the evaluation of the acoustic environment more comprehensive and accurate, and improves the prediction accuracy and reliability.

[0165] In some embodiments of the present specification, the processor can determine the acoustic propagation characteristics of the target area by analyzing the sound samples, which helps to more accurately predict the propagation behavior of the sound wave data in the target area, thereby improving the prediction accuracy of the acoustic environment. In addition, the processor can automatically and accurately analyze the acoustic environment of the target area based on the acoustic environment determination model, thereby reducing manual intervention and improving the efficiency, accuracy and reliability of the prediction.

[0166] Figure 5 FIG. 1 is a schematic diagram of sound sample collection according to some embodiments of this specification. Figure 5 As shown, the sound sample collection 500 includes the following contents: In some embodiments, the sound sample collection 500 may be executed by a processor.

[0167] In some embodiments, the processor may determine the sound collection parameters 530 based on the sound source type 510 , the area model 430 , the space structure type 460 , and the collection device type 520 ; and acquire the sound sample 540 based on the sound collection parameters 530 .

[0168] For more information about sound source types and spatial structure types, see Figure 4 and its related description.

[0169] For more information on regional models, see Figure 3-Figure 4 and its related description.

[0170] The acquisition device type refers to the type of device used to acquire sound samples. For example, the acquisition device type can be a microphone, a sound analyzer, etc.

[0171] Sound samples refer to sound wave signals collected by the acquisition device. In some embodiments, sound samples can be used to determine acoustic space parameters. For example, the processor can determine acoustic space parameters based on sound samples and their characteristics according to the specification document "Indoor Reverberation Time Measurement Specification [Attached Articles]" GB / T50076-2013 or existing methods. In some embodiments, the processor can also determine acoustic space parameters based on sound samples through other algorithms that can complete related processing. For more information about sound samples, please refer to Figure 3 and its related description.

[0172] Acoustic space parameters refer to the indicators and parameters used to describe the acoustic characteristics of the target area, which are used to evaluate and understand the propagation of sound in the target area. For example, acoustic space parameters at least include spatial reverberation time.

[0173] In some embodiments, the processor may also determine acoustic propagation characteristics of the target area based on the acoustic space parameters.

[0174] For more information on acoustic propagation properties, see Figure 4 and its related description.

[0175] In some embodiments, the processor may acquire sound samples through a collection device based on the sound collection parameters.

[0176] The sound collection parameters are parameters used to guide the user to obtain sound samples. For example, the sound collection parameters may include but are not limited to sound source parameters, collection device distribution data, preset standard positions of sound sources, etc.

[0177] The sound source device refers to a device used to emit sound samples, such as a speaker, a sound source ball, etc.

[0178] The sound source parameters refer to the sound parameters of the sound source in the target area, such as volume.

[0179] In some embodiments, the processor may perform a background noise test on the target area to obtain the range of the background noise, and then randomly select a volume parameter that meets the national standard as the sound source parameter of the target area according to the national standard. For example, when the processor uses the impulse response integration method to perform an acoustic test, the peak sound pressure level generated by the impulse sound source at the location of the acquisition device should be at least 45 decibels higher than the background noise in the corresponding frequency band, that is, the sound source parameter is at least 45 decibels higher; and when measuring the reverberation time, it should be at least 35 decibels higher than the background noise, that is, the sound source parameter is at least 35 decibels higher.

[0180] In some embodiments, the processor places the sound source in the target area according to a preset standard position. Wherein, the preset standard position refers to a position for placing the sound source. In some embodiments, the preset standard position can be set by a professional technician or by system default.

[0181] The acquisition device distribution data refers to the data of the position distribution of the acquisition device. For example, the acquisition device distribution data can be represented by a vector. Exemplarily, the acquisition device distribution data can be represented by (x, y, z). Among them, x, y, z are the coordinate values ​​of the acquisition device in the three-dimensional space rectangular coordinate system x-axis, y-axis, and z-axis respectively.

[0182] In some embodiments, the processor can use any point in the space where the target area is located as the origin of the coordinate system and construct a three-dimensional rectangular coordinate system with the origin. The origin can be set by professional technicians or by system default. For example, the origin can include but is not limited to the center point of the space where the target area is located.

[0183] In some embodiments, the processor can determine the sound collection parameters based on a variety of methods. For example, the processor can construct a vector to be matched based on the sound source type, area model, spatial structure type, and collection device type of the target area. The sound collection parameters are determined by matching the vector to be matched in the sound parameter vector database.

[0184] The sound parameter vector database refers to a database used to determine sound acquisition parameters, and includes at least one reference vector.

[0185] In some embodiments, the reference vector in the parameter vector database can compare the spatial structure type determined based on the sound sample in the historical data with the design parameters during the spatial design, and determine the historical data corresponding to the minimum error as the historical sample data. For example, the processor can construct a historical vector based on the historical sound source type, historical regional model, historical spatial structure type, historical acquisition device type of the target area in the historical sample data, and subsequent historical sound acquisition parameters, cluster the historical vectors to form a preset number of cluster centers, construct the historical sound source type, historical regional model, historical spatial structure type, and historical acquisition device type corresponding to the cluster center into a reference vector, and mark the reference vector based on the historical sound acquisition parameters.

[0186] In some embodiments, the processor may calculate the similarity between the vector to be matched and at least one reference vector, and use the mark corresponding to the standard vector with the highest vector similarity as the sound collection parameter. The similarity may be negatively correlated to the vector distance between the vector to be matched and the standard vector, and the vector distance may be determined based on the cosine distance, etc.

[0187] In some embodiments, the processor can determine the sound source parameters, grid the regional model to obtain a gridded regional model; based on the sound source parameters, sound source type, and gridded regional model, estimate the signal-to-noise ratio of the candidate device distribution data through a signal-to-noise ratio estimation model; and determine the collection device distribution data based on the qualified candidate device distribution data.

[0188] The gridded regional model refers to the sub-model after the regional model is gridded.

[0189] In some embodiments, the processor may grid the model based on a unit grid size to obtain a plurality of gridded region models.

[0190] The unit grid size refers to a division unit used to grid the regional model. In some embodiments, the processor may determine the unit grid size according to the space size required by the measuring device.

[0191] In some embodiments, the unit grid size needs to be larger than the volume required by the measuring device and smaller than n times the volume of the measuring device. Wherein n is a constant. In some embodiments, the constant n may be negatively correlated with the computing power of the computing device. Exemplarily, the greater the computing power of the computing device, the smaller the constant n.

[0192] The measuring device refers to a device used to emit and collect sound samples. For example, the measuring device may include a sound source device and a collection device.

[0193] The volume required for the measuring device refers to the minimum space required to ensure that the measuring device works properly and accurately emits and collects sound samples.

[0194] The candidate device distribution data is data used to determine the collection device distribution data.

[0195] The signal-to-noise ratio is a value used to measure the quality of data collected by the collection device when collecting data based on the candidate device distribution data. For example, the larger the signal-to-noise ratio, the smaller the impact of noise, and the better the quality of data obtained when collecting data based on the candidate device distribution data.

[0196] The signal-to-noise ratio prediction model refers to a model used to determine the signal-to-noise ratio. In some embodiments, the signal-to-noise ratio prediction model may be a machine learning model, such as a convolutional neural network model (CNN).

[0197] In some embodiments, the input of the signal-to-noise ratio estimation model may include sound source parameters, sound source type, gridded area model, spatial structure type, acquisition device type and candidate device distribution data of the target area, and the output may be the signal-to-noise ratio of the candidate device distribution data.

[0198] In some embodiments, the signal-to-noise ratio estimation model can be obtained by training through gradient descent or other training methods based on a large number of third training samples with third labels. The training process is similar to the training process of the acoustic environment determination model mentioned above, and the details can be found in the relevant description above.

[0199] In some embodiments, the third training sample may include sample sound source parameters, sample sound source types, sample gridded area models, sample spatial structure types, sample acquisition device types, and sample candidate device distribution data corresponding to the sample target areas in the historical data.

[0200] In some embodiments, the third label is the average of multiple actual historical signal-to-noise ratios of the sample candidate device distribution data corresponding to the third sample. For example, the processor may obtain multiple actual historical signal-to-noise ratios of the sample candidate device distribution data actually detected in the historical data, and determine the average of the multiple actual historical signal-to-noise ratios as the third label.

[0201] In some embodiments, the processor may determine the candidate device distribution data corresponding to the highest signal-to-noise ratio as the collection device distribution data.

[0202] In some embodiments of the present specification, the processor can analyze the acoustic characteristics of the target area more carefully by gridding the regional model, thereby improving the accuracy of the sound collection parameters. Based on the sound source type, sound source parameters and gridded regional model, the signal-to-noise ratio of the candidate device distribution data is determined by the signal-to-noise ratio estimation model, and the signal-to-noise ratio of multiple candidate device distribution data can be predicted more accurately, thereby improving the reliability and accuracy of the model estimation. By determining the candidate device distribution data with the highest signal-to-noise ratio as the collection device distribution data, the rationality of the location and configuration of the collection device can be improved, and the quality of the collected sound samples can be improved.

[0203] In some embodiments of the present specification, the processor determines sound collection parameters based on the sound source type, regional model, spatial structure type and collection device type, and obtains sound samples based on the sound collection parameters, so as to more accurately reflect the actual acoustic environment of the target area, thereby obtaining complete sound sample data, facilitating the subsequent accurate evaluation of the acoustic environment of the room and accurately predicting the sound field distribution and acoustic quality of different speaker playback combinations.

[0204] Figure 6 is an exemplary flow chart of a method for recommending a speaker combination according to some embodiments of this specification. Figure 6 As shown, the speaker combination recommendation method 600 includes the following contents. In some embodiments, the speaker combination recommendation method 600 can be executed by a processor.

[0205] Step 610: Determine a candidate sound combination based on the user's desired acoustic parameters.

[0206] The expected acoustic parameter refers to the corresponding audio playback setting value when the sound effect desired by the user can be obtained. In some embodiments, the expected acoustic parameter may include multiple parameters that can reflect the sound effect, including but not limited to at least one of sound clarity, stereo effect, and mixing effect.

[0207] In some embodiments, the processor may determine the expected acoustic parameters based on a variety of methods, such as obtaining based on user input, obtaining based on historical audio playback data of the user, or obtaining through other methods.

[0208] In some embodiments, the processor may determine the style characteristics and setting characteristics of the user's audio playback based on the user's historical audio playback data.

[0209] Style features refer to the audio style preferred by the user.

[0210] In some embodiments, audio styles can be divided based on a variety of different criteria. For example, based on the content of the audio, the audio style can be divided into multiple types including but not limited to music, movies, and vocals; for another example, based on the sound features in the audio, the features corresponding to different audio contents can be further divided, such as music can be further divided into multiple types including but not limited to classical music, pop music, jazz, electronic music, folk music, etc.

[0211] The above classification criteria are only examples. In some embodiments, the audio styles may be classified based on a variety of other different criteria, which may be set according to actual needs.

[0212] In some embodiments, the style feature acquired by the processor may include at least one of the aforementioned features. For example, the processor may acquire only one feature under one standard, such as music; for another example, the processor may acquire multiple features under one standard, such as music, movies, etc.; for another example, the processor may acquire multiple features under multiple standards, such as music-jazz, music-pop, etc.

[0213] In some embodiments, the processor may obtain the duration of a user playing audios of different audio styles, and determine a style preference score corresponding to an audio style based on the proportion of the playback duration of audios of a certain audio style to the total playback duration of the user.

[0214] In some embodiments, the processor may count the style preference scores of the user under different audio styles, and determine the style characteristics of the user based on the style preference scores. For example, the audio style with the highest style preference score is determined as the style characteristic of the user; for another example, a preset number of audio styles with the highest style preference scores are determined as the style characteristics of the user, where the preset number can be set according to actual needs.

[0215] The setting feature refers to the audio playback setting preferred by the user, including but not limited to at least one of volume setting and mixing setting.

[0216] In some embodiments, the processor may obtain the playback duration of the user under different audio playback settings, and determine a setting preference score corresponding to the audio playback setting based on the proportion of the playback duration under one audio playback setting to the total playback duration of the user.

[0217] In some embodiments, the processor may count the setting preference scores of the user under different audio playback settings, and determine the setting characteristics of the user based on the setting preference scores. For example, the audio playback setting with the highest setting preference score is determined as the setting characteristic of the user.

[0218] In some embodiments, the processor may also obtain multiple setting features of the user in a manner similar to determining the user style.

[0219] In some embodiments, the processor may determine recommended acoustic parameters based on the user's style characteristics, wherein the recommended acoustic parameters refer to recommended values ​​of audio playback settings.

[0220] In some embodiments, the processor may determine the recommended acoustic parameters based on the style characteristics of the user by querying a preset reference acoustic parameter table. The reference acoustic parameter table may include at least one reference style characteristic and its corresponding reference acoustic parameter. The reference acoustic parameter table may be determined based on the historical audio playback settings of at least one user under different audio styles. For example, the processor may use the audio playback settings with the highest usage as the reference acoustic parameters corresponding to the audio style.

[0221] In some embodiments, the processor may adjust the recommended acoustic parameters in a variety of ways to obtain the user's desired acoustic parameters.

[0222] In some embodiments, the processor may adjust the recommended acoustic parameters based on the user's setting characteristics to obtain the user's desired acoustic parameters. For example, the processor may fine-tune the recommended acoustic parameters based on the user's setting characteristics to obtain the desired acoustic parameters. Taking the volume setting as an example, if the user's setting characteristic is 60% volume, the processor may adjust the volume in the recommended acoustic parameters to 60% based on the volume value in the setting characteristic, and use the adjusted recommended acoustic parameters as the desired acoustic parameters.

[0223] In some embodiments of the present specification, by obtaining the user's historical audio playback data, determining the style characteristics and setting characteristics, and then determining the user's expected acoustic parameters, a more friendly and low-threshold approach can be provided to the user, and the sound effects the user expects to obtain can be determined more conveniently and quickly, thereby making reasonable recommendations for speaker playback combinations efficiently and accurately.

[0224] In some embodiments, the desired acoustic parameters are also related to the spatial structure type and the acoustic spatial parameters.

[0225] For detailed information on spatial structure types, please refer to this manual Figure 4 For detailed description of acoustic space parameters, please refer to this manual. Figure 5 Related description in .

[0226] In some embodiments, the processor can determine the items to be adjusted and their corresponding adjustment amounts by querying the acoustic parameter adjustment table based on the spatial structure type and acoustic space parameters of the target area; and make preliminary adjustments to the recommended acoustic parameters according to the items to be adjusted and their corresponding adjustment amounts.

[0227] In some embodiments of the present specification, the acoustic parameter adjustment table may include a reference space structure type corresponding to a reference area, a reference acoustic space parameter, and its corresponding reference adjustment item and reference adjustment amount.

[0228] In some embodiments, the processor may determine the acoustic parameter adjustment table based on historical adjustment data that meets the requirements. The historical adjustment data that meets the requirements may include historical data in which the user has not made further adjustments to the acoustic parameters after adjusting the historical data. The processor may determine the historical adjustment items and historical adjustment amounts based on the aforementioned data and use them as reference data in the acoustic parameter adjustment table. The historical adjustment data that meets the requirements may also include data with the best test results when different adjustment amounts are tested under different spatial structure types and acoustic space parameters.

[0229] In some embodiments, the acoustic parameter adjustment table may further include an adjusted reference value corresponding to the reference adjustment item. The processor may determine the reference value corresponding to the item to be adjusted based on the current value of the item to be adjusted and the adjusted reference value.

[0230] In some embodiments, the processor may further adjust the preliminarily adjusted acoustic parameters based on the user's setting characteristics to determine the user's desired acoustic parameters. The adjustment method is similar to the adjustment of the recommended acoustic parameters based on the setting characteristics, and can refer to the relevant description above.

[0231] In some embodiments, a set of desired acoustic parameters may correspond to at least one set of candidate speaker combinations.

[0232] The candidate speaker combination refers to at least one group of selectable speaker configuration solutions used to determine the recommended speaker combination. In some embodiments, the candidate speaker combination includes but is not limited to at least one of the number of speakers, speaker positions, and speaker types.

[0233] In some embodiments, the processor may determine the candidate speaker type and the number of candidate speakers in a preset reference speaker combination table based on the user's expected acoustic parameters; and place the candidate speakers in the regional model according to preset rules based on the candidate speaker type and the number of candidate speakers, thereby obtaining a candidate speaker combination. The preset rules may include random placement, priority placement in a preset position, etc., wherein the preset position may include but is not limited to at least one of a corner and next to a TV, which may be determined based on actual needs.

[0234] In some embodiments, the reference speaker combination table may include at least one set of reference data, each set of reference data may include reference expected acoustic parameters and their corresponding reference speaker types and reference speaker quantities. In some embodiments, the reference speaker combination table may be determined based on historical data. For example, the processor may determine the reference speaker combination table based on historical expected acoustic parameters of at least one user in historical data, and the historical speaker types and historical speaker quantities used by the user.

[0235] Step 620, determining the predicted sound effect corresponding to the candidate speaker combination.

[0236] In some embodiments, the processor may obtain a regional model of the target area, and determine a predicted sound effect corresponding to the candidate speaker group based on the candidate speaker combination and its corresponding speaker data.

[0237] For detailed information on predicting sound effects and their determination, please refer to this manual. Figure 3-Figure 5 Related description in .

[0238] Step 630: Determine a recommended speaker combination from the candidate speaker combinations based on the predicted sound effects.

[0239] In some embodiments, the processor may determine a candidate speaker combination whose predicted sound effects meet preset conditions as a recommended speaker combination.

[0240] In some embodiments, the preset condition may include at least one of the following: the sound quality is the best, and the predicted sound effect best meets the acoustic parameters expected by the user. In some embodiments, the preset condition may also include other conditions, which may be determined according to actual needs.

[0241] Step 640, display the recommended speaker combination and its corresponding predicted sound effect.

[0242] In some embodiments, the processor may display the recommended speaker combination and its corresponding predicted sound effect to the user. For example, the processor may display the recommended speaker combination in the aforementioned digital model and display the sound field distribution therein in the form of sound waves. Displaying the recommended speaker combination includes displaying the model, quantity, and location of different speakers therein, and may also display text descriptions and other information that can reflect the speaker type and placement location.

[0243] In some embodiments, the processor may also display a recommended speaker combination and its corresponding sound effects in a two-dimensional top view of the aforementioned digital model, which may be specifically determined based on the user's selection.

[0244] In some embodiments, the processor may adjust the recommended speaker combination based on user feedback to determine an adjusted recommended speaker combination, wherein the user feedback refers to the user's adjustment data on the recommended speaker combination, which may be determined by the processor by obtaining user input from a user terminal.

[0245] In some embodiments, the user feedback may include at least one of an adjustment to the recommended speaker combination and an adjustment to the desired acoustic parameters.

[0246] In some embodiments, the processor may obtain the user's adjustment to the recommended speaker combination in a variety of ways. For example, the processor may obtain the user's direct input instruction to adjust the recommended speaker combination on the interface of the aforementioned visualization result, including but not limited to at least one of moving the speaker position, deleting the speaker, and adding the speaker. For another example, the processor may obtain the user's selected preset adjustment instruction to adjust the recommended speaker combination, input the adjustment instruction through voice, etc. In some embodiments, the processor may also obtain the user's adjustment to the recommended speaker combination in other ways.

[0247] In some embodiments, the processor may obtain the user's adjustment to the desired acoustic parameters in a variety of ways. For example, the processor may obtain the user's adjustment to the desired acoustic parameters directly input on the interface of the aforementioned visualization results, including but not limited to at least one of the adjustments to the sound clarity, the stereo effect, and the mixing effect. For another example, the processor may obtain a preset adjustment instruction selected by the user to adjust at least one of the desired acoustic parameters. In some embodiments, the processor may also obtain the user's adjustment to the desired acoustic parameters in other ways.

[0248] In some embodiments, the processor may determine the sound effects corresponding to the adjusted recommended speaker combination, and then determine a new recommended speaker combination.

[0249] For example, in response to user feedback including adjustments to the expected acoustic parameters, the processor can determine the updated expected acoustic parameters based on the user feedback, determine the updated candidate speaker playback combination based on the updated expected acoustic parameters, and determine the sound effects corresponding to the updated candidate speaker playback combination, and then determine a new recommended speaker combination from the updated candidate speaker combination playback combination based on the sound effects, and display the new recommended speaker combination and its corresponding sound effects to the user. For detailed instructions on determining sound effects and their determination, please refer to this manual Figure 3-Figure 5 Related description in .

[0250] For another example, in response to user feedback including adjustments to the recommended speaker combination, the processor may determine an updated recommended speaker combination based on the user feedback, determine the sound effects of the updated recommended speaker combination, and display the updated recommended speaker combination and its corresponding sound effects to the user.

[0251] In some embodiments of the present specification, the recommended speaker combination is adjusted by obtaining user feedback, and then a new recommended speaker combination is determined, so that the determined speaker combination data can better meet user expectations and improve user experience.

[0252] 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.

[0253] 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.

[0254] 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.

[0255] 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.

[0256] 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.

[0257] 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.

[0258] 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 sound effect prediction method, characterized in that: include: Collect data samples in the target area; Based on the data samples, determining the acoustic environment and the regional model of the target area; Based on the regional model and the acoustic environment, construct a digital model of the target area; According to the digital model and the speaker setting parameters, the predicted sound effect in the target area under the speaker setting parameters is predicted.

2. The method according to claim 1, characterized in that The data samples include sound samples; The step of determining the acoustic environment and the regional model of the target area based on the data sample includes: Based on the sound sample, determining the acoustic propagation characteristics of the target area; The acoustic environment of the target area is determined based on the area model and the acoustic propagation characteristics.

3. The method according to claim 2, characterized in that The data samples also include image samples; The determining the acoustic environment of the target area based on the area model and the acoustic propagation characteristics further includes: Based on the image samples, determining the spatial structure type of the target area; The acoustic environment of the target area is determined based on the spatial structure type, the area model and the acoustic propagation characteristics.

4. The method according to claim 2, characterized in that The data samples collected in the target area include: Determining sound collection parameters based on the sound source type, the regional model, the spatial structure type, and the collection device type; The sound sample is acquired based on the sound acquisition parameter.

5. The method according to claim 1, characterized in that The data samples include image samples; and determining the acoustic environment and the regional model of the target area based on the data samples includes: Based on the image sample, determining image feature points; Based on the image feature points, construct a three-dimensional point cloud model of the target area; The region model is determined based on the three-dimensional point cloud model.

6. A method for recommending a speaker combination, characterized in that: include: Determine a candidate speaker combination based on the user's desired acoustic parameters; Determining the predicted acoustic effect corresponding to the candidate speaker combination by the sound effect prediction method according to any one of claims 1 to 5; Based on the predicted acoustic effect, determining a recommended speaker combination from the candidate speaker combinations; The recommended speaker combination and its corresponding predicted acoustic effect are displayed.

7. The method according to claim 6, characterized in that The method further comprises: The recommended speaker combination is adjusted based on user feedback.

8. A sound effect prediction system, characterized in that: It includes acquisition module, determination module, construction module and prediction module; The acquisition module is configured to collect data samples within the target area; The determination module is configured to determine the acoustic environment and the regional model of the target area based on the data sample; The construction module is configured to construct a digital model of the target area based on the area model and the acoustic environment; The prediction module is configured to predict, based on the digital model and the speaker setting parameters, the predicted sound effect in the target area under the speaker setting parameters.

9. A sound effect prediction device, comprising a processor, wherein the processor is used to execute the sound effect prediction method according to any one of claims 1 to 6.

10. A computer-readable storage medium storing computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the sound effect prediction method according to any one of claims 1 to 6.

Citation Information

Cited By

  • Sound field adaptive cloud control method and system based on deep learning

    CN120455895A