Equipment installation auxiliary system, method and device and storage medium

Abstract

The embodiment of the invention provides an equipment installation auxiliary system, method and device and a storage medium, the system comprises a data acquisition module, an image display module and a processor, and the data acquisition module comprises a sensor and is configured to obtain sensing acquisition data of to-be-installed equipment; the image display module comprises a display screen and is configured to display installation guidance information to a user; the processor is configured to: acquire device image data; based on the sensing acquisition data and the equipment image data, generating installation guidance information; and displaying the installation guidance information to the user based on the image display module and / or the user terminal.

Description

Technical Field

[0001] This specification relates to the field of equipment installation, and in particular to an equipment installation auxiliary system, method, apparatus and storage medium. Background Technology

[0002] In different playback scenarios, factors such as the location and orientation of the audio device, as well as the spatial layout of its various components, can all affect the audio performance. To meet users' listening needs, accurate installation of the audio device is essential.

[0003] Currently, audio equipment manufacturers typically provide printed manuals or video tutorials to guide users in installing audio equipment. However, printed manuals and video tutorials lack user interaction, failing to provide real-time answers to user questions or corrective guidance.

[0004] Therefore, it is desirable to provide a device installation assistance system, method, apparatus, and storage medium that can provide real-time guidance to users during the installation process, identify installation errors of audio devices, and generate corresponding adjustment strategies, thereby improving installation efficiency and user experience. Summary of the Invention

[0005] This specification provides one or more embodiments of a device installation assistance system, which includes a data acquisition module, an image display module, and a processor. The data acquisition module includes sensors and is configured to acquire sensor data of the device to be installed. The image display module includes a display screen and is configured to display installation guidance information to a user. The processor is configured to: acquire device image data; generate installation guidance information based on the sensor data and the device image data; and display the installation guidance information to a user based on the image display module and / or a user terminal.

[0006] This specification provides one or more embodiments of a device installation assistance method, which includes: acquiring sensor data and device image data of the device to be installed; generating installation guidance information based on the sensor data and device image data; and displaying the installation guidance information to the user based on an image display module and / or a user terminal.

[0007] This specification provides one or more embodiments of a device installation assistance apparatus, the apparatus including at least one memory and at least one processor, the at least one memory for storing computer instructions, and the at least one processor for executing the computer instructions or portions thereof to implement any of the device installation assistance methods described herein.

[0008] This specification provides one or more embodiments of a computer-readable storage medium that stores computer instructions, which, when read by a computer, execute any of the device installation assistance methods described herein. Attached Figure Description

[0009] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0010] Figure 1 These are schematic diagrams illustrating application scenarios of the equipment installation assistance system according to some embodiments of this specification;

[0011] Figure 2 This is a system block diagram of the equipment installation auxiliary system shown in some embodiments of this specification;

[0012] Figure 3 This is an exemplary flowchart of a device installation assistance method according to some embodiments of this specification;

[0013] Figure 4 This is an exemplary flowchart illustrating the generation of installation error correction information according to some embodiments of this specification;

[0014] Figure 5 This is an exemplary flowchart illustrating the determination of installation correction information according to some embodiments of this specification;

[0015] Figure 6 This is an exemplary schematic diagram of an error message prediction model according to some embodiments of this specification;

[0016] Figure 7 This is an exemplary schematic diagram of a sound effect correction model shown in some embodiments of this specification. Detailed Implementation

[0017] The accompanying drawings used in the description of the embodiments will be briefly introduced below. The drawings do not represent all embodiments.

[0018] The terms “system,” “device,” “unit,” and / or “module” as used herein are one method of distinguishing different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0019] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0020] In the embodiments described in this specification, unless otherwise specified, the order of the steps is interchangeable, steps can be omitted, and other steps may be included in the operation process.

[0021] The installation process of audio equipment significantly impacts its audio quality. Typically, audio equipment manufacturers provide installation manuals or video tutorials to guide users through the installation process. However, these manuals and tutorials often lack interactivity, personalization, and specificity. Furthermore, error identification and correction during installation rely heavily on user judgment or require professional online or offline intervention, resulting in high installation costs and low efficiency.

[0022] This invention provides an equipment installation assistance system, method, apparatus, and storage medium that can answer user questions and provide real-time guidance during the installation process, offering intuitive visual guidance and automatically identifying and predicting installation errors and providing corrective guidance. This enables personalized user service and effectively improves installation efficiency and user experience.

[0023] Figure 1 This is a schematic diagram illustrating an application scenario of the equipment installation assistance system according to some embodiments of this specification.

[0024] Equipment installation assistance systems can be applied to various scenarios requiring audio equipment installation, such as auditoriums and studios. These scenarios demand more than just normal operation of the audio equipment; more importantly, the audio output must meet specific requirements. For example, in studios, especially for music recording or live broadcasts, audio equipment needs to faithfully reproduce the original timbre of various instruments, ensuring listeners experience the realism and nuance of the music.

[0025] Furthermore, due to differences in the environment, the audio effect of the same audio device may vary, and the spatial arrangement of the various sub-components of the audio device will affect its audio performance. For example, the position of the speakers will affect the sound field coverage of the audio device, and the distance between the speakers and the audience will affect the audience's perception of the volume of the audio device. The embodiments in this specification are illustrated using the installation of a sound system in a studio as an example.

[0026] In some embodiments, such as Figure 1 As shown, the application scenario 100 of the equipment installation assistance system may include a data acquisition device 110, a device to be installed 120, a processor 130, a storage device 140, a network 150, a user 160, and a user terminal 170.

[0027] Data acquisition device 110 refers to a device used to acquire data related to the device 120 to be installed. In some embodiments, data acquisition device 110 may be an integrated device including one or more sensors and one or more camera devices. The sensors may include a level sensor, a sound sensor, a temperature sensor, a humidity sensor, etc. The camera devices may be a digital camera, a depth camera, etc. For more information on level sensors, sound sensors, temperature sensors, and humidity sensors, please refer to [link to relevant documentation]. Figures 3-7 Related descriptions.

[0028] In some embodiments, the data acquisition device 110 can be deployed in the application scenario 100 of the device installation assistance system. For example, a level sensor can be deployed on the device 120 to be installed, a temperature sensor and a humidity sensor can be deployed in the installation scenario of the device 120 to be installed, and a camera device can be deployed around the device 120 to be installed and in the installation scenario.

[0029] The device to be installed 120 refers to a device that requires assisted installation via a device installation assistance system. In some embodiments, the device to be installed 120 may be an audio device, such as a sound system.

[0030] In some embodiments, the device to be installed 120 may include multiple sub-components. These sub-components may be devices that constitute the device to be installed. For example, the device to be installed 120 may be an audio system, and the sub-components may be various amplifiers, speakers, effects processors, etc., within that audio system.

[0031] In some embodiments, the processor 130 can process data and / or information acquired by the acquisition device 110, the device to be installed 120, the storage device 140, the network 150, the user 160, the user terminal 170, and / or other components of the application scenario 100 of the device installation assistance system. For example, the processor 130 can acquire sensor data acquired by the acquisition device 110 through the network 150. As another example, the processor 130 can acquire user input information uploaded by the user 160 through the user terminal 170 through the network 150.

[0032] In some embodiments, processor 130 may be a computer, a user console, a single processor 130, or a group of processors 130. The group of processors 130 may be centralized or distributed. In some embodiments, processor 130 may be implemented on a cloud platform. For example, the cloud platform may include one or any combination of private cloud, public cloud, hybrid cloud, etc.

[0033] In some embodiments, the processor 130 may be integrated into various components of the application scenario 100 of the device installation assistance system, or into various modules of the device installation assistance system.

[0034] In some embodiments, storage device 140 may store data, instructions, and / or any other information. For example, storage device 140 may store an installation diagram of the device 120 to be installed, sound acquisition data acquired by acquisition device 110, etc.

[0035] Storage device 140 may include one or more storage components, each of which may be a separate device or part of another device. In some embodiments, storage device 140 may include random access memory (RAM), read-only memory (ROM), removable memory (RMM), and any combination thereof. In some embodiments, storage device 140 may communicate with one or more components in application scenario 100 of the device installation assistance system via network 150.

[0036] In some embodiments, storage device 140 may include one or more databases. For example, a device type database, etc. More information about device type databases can be found in [link to relevant documentation]. Figure 3 Related explanations.

[0037] Network 150 includes any suitable network 150 capable of facilitating information and / or data exchange within the application scenario 100 of the device installation assistance system. In some embodiments, one or more components of the application scenario 100 of the device installation assistance system (e.g., acquisition device 110, device to be installed 120, processor 130, storage device 140, and user terminal 170, etc.) can exchange information and / or data with other components of the application scenario 100 of the device installation assistance system via network 150.

[0038] User 160 refers to the person who needs the installation of equipment 120. For example, User 160 could be the staff member responsible for the studio sound system, etc.

[0039] User terminal 170 refers to the device used by user 160 to interact with the device installation assistance system. For example, user terminal 170 may include desktop computer 170-1, tablet computer 170-2, smartphone 170-3, etc.

[0040] In some embodiments, user 160 can interact with other components of the device installation assistance system through user terminal 170. For example, user 160 can input and upload user input information to processor 130 and / or storage device 140 through user terminal 170. As another example, user 160 can view installation guidance information generated by processor 130 through user terminal 170.

[0041] It should be noted that the application scenarios are provided for illustrative purposes only and are not intended to limit the scope of this specification. Those skilled in the art will be able to make various modifications or variations based on the description in this specification. For example, the application scenario may also include a database. Furthermore, the application scenario may be implemented on other devices to achieve similar or different functions. However, these changes and modifications will not depart from the scope of this specification.

[0042] Figure 2 This is an exemplary block diagram of an equipment installation assistance system according to some embodiments of this specification.

[0043] In some embodiments, such as Figure 2 As shown, the equipment installation auxiliary system 200 may include a data acquisition module 210, an image display module 220, a processor 130, a user interaction module 230, and an electrical signal testing module 240.

[0044] The data acquisition module 210 refers to a module used for acquiring data. In some embodiments, the data acquisition module 210 can be configured to acquire sensor data from the device to be installed.

[0045] In some embodiments, the data acquisition module 210 can be configured as a separate device with acquisition function, or it can be integrated into the acquisition device 110.

[0046] In some embodiments, the data acquisition module 210 may include one or more sensors 211.

[0047] Sensor 211 refers to a device used to acquire various types of sensor data. For example, sensor 211 may include a level sensor, a sound sensor, a temperature sensor, a humidity sensor, etc. More information about sensors can be found at [link to relevant documentation]. Figure 1 Related descriptions.

[0048] In some embodiments, the data acquisition module 210 can be configured to acquire sensor data from the device to be installed.

[0049] In some embodiments, the data acquisition module 210 may be further configured to acquire sound acquisition data within the scene to be installed.

[0050] Image display module 220 refers to a module used to display images. In some embodiments, image display module 220 can be configured as a standalone device with display function, or it can be integrated into user terminal 170.

[0051] In some embodiments, the image display module 220 may include one or more displays 221.

[0052] Display screen 221 refers to a screen capable of displaying images and videos. Examples include mobile phone screens and computer monitors.

[0053] In some embodiments, the image display module 220 may be configured to display installation guidance information to the user 160.

[0054] For more information about the processor 130, please refer to [link / reference]. Figure 1 Related descriptions.

[0055] In some embodiments, the processor 130 may be configured to: acquire device image data; generate installation guidance information based on the sensor acquisition data and the device image data; and display the installation guidance information to the user 160 based on the image display module 220 and / or the user terminal 170.

[0056] In some embodiments, the processor 130 may be further configured to: acquire installation scenario data and installation process data; acquire component location information based on the installation process data; determine whether current error information exists based on the component location information; generate installation error correction information based on the current error information in response to the existence of current error information; determine predicted error information for future installation stages based on the installation scenario data, component location information, and device connection parameters in response to the absence of current error information; and generate installation error correction information based on the predicted error information.

[0057] In some embodiments, the processor 130 may be further configured to: determine environmental noise characteristics based on sound acquisition data; determine installation orientation information based on installation scenario data and installation process data; determine estimated audio data based on installation orientation information, installation scenario data, installation process data and environmental noise characteristics; and determine installation correction information based on the estimated audio data and correction conditions.

[0058] In some embodiments, the processor 130 may be further configured to: generate a sound test command and send it to the device to be installed in response to the current installation phase being a test installation phase; control the device to be installed to perform a sound test based on the sound test command; acquire sound test acquisition data based on the data acquisition module 210; determine test audio characteristics based on the sound test acquisition data; and determine estimated audio data based on the test audio characteristics.

[0059] In some embodiments, such as Figure 2 As shown, the equipment installation assistance system 200 may also include a user interaction module 230.

[0060] User interaction module 230 refers to a module used for interacting with a user. In some embodiments, user interaction module 230 can be configured as a standalone device with interactive functions, or it can be integrated into user terminal 170.

[0061] In some embodiments, the user interaction module 230 may be configured to acquire user voice commands.

[0062] In some embodiments, the user interaction module 230 may be further configured to receive user input information.

[0063] In some embodiments, such as Figure 2 As shown, the equipment installation auxiliary system 200 may also include an electrical signal testing module 240.

[0064] The electrical signal testing module 240 refers to a module used for performing electrical signal testing. In some embodiments, the electrical signal testing module 240 can be configured as a separate device with the function of generating electrical signals, or it can be integrated into the user terminal 170 and / or the processor 130.

[0065] In some embodiments, the electrical signal testing module 240 can be configured to generate test electrical signals and acquire test power-on data.

[0066] For more information on the data acquisition device 110, processor 130, and user terminal 170, please refer to [link / reference needed]. Figure 1 The relevant descriptions are available. For more information on the acquisition module 210, image display module 220, user interaction module 230, and electrical signal testing module 240, please refer to... Figures 3-7 Related descriptions.

[0067] It should be noted that the above description of the equipment installation auxiliary system 200 and its modules is for ease of description only and should not be construed as limiting this specification to the scope of the illustrated embodiments. It is understood that those skilled in the art, after understanding the principles of this system, may arbitrarily combine the various modules or construct subsystems connected to other modules without departing from these principles. In some embodiments, Figure 2 The data acquisition module 210, image display module 220, processor 130, user interaction module 230, and electrical signal testing module 240 disclosed herein can be different modules within a single system, or a single module can implement the functions of two or more of the aforementioned modules. For example, the modules can share a single storage module, or each module can have its own separate storage module. Such variations are all within the scope of protection of this specification.

[0068] Figure 3 This is an exemplary flowchart of a device installation assistance method according to some embodiments of this specification. Figure 3 As shown, process 300 may include steps 310-330 as described below. In some embodiments, process 300 may be executed by a processor.

[0069] Step 310: Obtain sensor data and device image data of the device to be installed.

[0070] For more information about the equipment to be installed, please refer to [link / reference needed]. Figure 1 Related explanations.

[0071] Sensor acquisition data refers to data acquired by sensors. In some embodiments, sensor acquisition data may include horizontal sensing data, etc.

[0072] Horizontal sensing data refers to data that characterizes the horizontal state of the equipment to be installed. For example, the angle between the equipment and its sub-components and the horizontal plane.

[0073] In some embodiments, the processor can acquire horizontal sensing data via a horizontal sensor. This horizontal sensor may include a capacitive horizontal sensor, a photoelectric horizontal sensor, etc. The horizontal sensor can be deployed on the device to be installed.

[0074] Device image data refers to image data associated with the device to be installed. In some embodiments, device image data may be image data of the device to be installed captured by a data acquisition device (such as a camera). For example, device image data may also be image data of the device to be installed captured and / or uploaded by a user through a user terminal. More information about data acquisition devices, camera devices, users, and user terminals can be found in [link to relevant documentation]. Figure 1 Related descriptions.

[0075] In some embodiments, device image data may include image data of the device to be installed from multiple angles.

[0076] In some embodiments, the acquisition device and / or user terminal can directly upload the acquired device image data to the processor via a network, or first upload it to a storage device and then have the processor read it from the storage device.

[0077] Step 320: Generate installation guidance information based on sensor data and device image data.

[0078] Installation guidance information refers to information used to guide users in correctly installing the device to be installed. In some embodiments, installation guidance information may include installation diagrams and installation illustrations.

[0079] Installation diagrams are schematic images used to guide users in the correct installation of the equipment to be installed. Examples include interactive 3D modeling images. 3D modeling images can be obtained by 3D scanning the equipment to be installed using a 3D scanner, while interactive 3D modeling images refer to 3D modeling images that users can interact with in specific ways (e.g., by clicking, rotating, or dragging with a mouse).

[0080] In some embodiments, the installation schematic image may include an overall schematic image and a partial schematic image of the device to be installed.

[0081] In this context, an overall schematic image refers to an image that illustrates the overall structure of the equipment to be installed. For example, an overall schematic image could be an image showing the spatial layout of the various sub-components of the equipment to be installed.

[0082] A partial schematic image is an image that illustrates the partial details of the device to be installed. For example, a partial schematic image can be an image that includes detailed structural features such as the interface design of each sub-component of the device to be installed (e.g., a USB (Universal Serial Bus) interface on sub-component X) and the connection methods between the sub-components (e.g., Bluetooth connection between sub-component X and sub-component Y).

[0083] In some embodiments, the processor can send an installation schematic image of the device to be installed to the image display module 220 and / or the user terminal 170, so that the user can install the device based on the installation schematic image.

[0084] Installation instructions are information used to guide users in correctly installing the equipment to be installed.

[0085] In some embodiments, the installation schematic information may include the names or numbers of the various sub-components of the device to be installed, installation tools, installation precautions, etc. Installation precautions may include avoiding direct contact with a hard wall, and ensuring the device is parallel to a horizontal plane. For example, when a user clicks on sub-component X of the device to be installed on the installation schematic image, the display screen and / or user terminal may display: Sub-component X, Installation tool is a screwdriver, and it needs to be kept parallel to a horizontal plane.

[0086] In some embodiments, the processor can generate installation guidance information in various ways based on sensor-acquired data and device image data. For example, the processor can determine the device type of the device to be installed using computer vision technology based on the device image data; determine the installation diagram and installation illustration information of the device to be installed by querying a device type database based on the device type of the device to be installed; and adjust and improve the installation diagram and installation illustration information of the device to be installed based on the sensor-acquired data.

[0087] The equipment type can include the product brand and product number of the equipment to be installed. Computer vision technology can include computer vision recognition models, image recognition algorithms, and feature comparison algorithms. Specifically, computer vision recognition models can include residual network models and VGG (Visual Geometry Group Network) models; image recognition algorithms can include Canny edge detection algorithms and LBP (Local Binary Patterns) texture feature extraction algorithms; and feature comparison algorithms can include support vector machine algorithms and decision tree algorithms.

[0088] The device type database may include various device types and their corresponding installation diagrams and installation information. In some embodiments, the device type database may be built by a processor and / or a technician based on historical data.

[0089] In some embodiments, the processor can improve the installation schematic image and installation information based on sensor data. For example, the processor can identify that sub-component X is not in a horizontal state through horizontal sensor data, and if the installation information determined by querying the device type database indicates that sub-component X needs to be kept parallel to the horizontal plane, then sub-component X can be highlighted in the installation schematic image (e.g., highlighted in red).

[0090] In some embodiments, the installation guidance information may further include installation error correction information. The processor may also determine whether current error information exists; in response to the existence of current error information, generate installation error correction information based on the current error information; in response to the absence of current error information, determine predicted error information for future installation stages based on installation scenario data, installation process data, component location information, and device connection parameters; and generate installation error correction information based on the predicted error information. For more information on this section, please refer to [link to relevant documentation]. Figure 4 Related descriptions.

[0091] In some embodiments, the installation guidance information may further include installation correction information. The processor may also determine ambient noise characteristics and installation orientation information; determine estimated audio data based on the installation orientation information, installation scenario data, installation process data, and ambient noise characteristics; and determine installation correction information based on the estimated audio data and correction conditions. More information on this section can be found at [link to relevant documentation]. Figure 5 Related descriptions.

[0092] Step 330: Display installation guidance information to the user based on the image display module and / or user terminal.

[0093] For more information on image display modules and user terminals, please refer to [link / reference]. Figure 1 and Figure 2 Related descriptions.

[0094] In some embodiments, the processor may send installation guidance information to the image display module 220 and / or the user terminal 170 to display the installation guidance information to the user. For example, the processor may send the 3D modeling image in the installation guidance information to the display screen 221 of the image display module 220 for display, and display and / or play the installation illustration information in the installation guidance information on the user terminal 170. The user can click, drag, zoom, and perform other operations on the 3D modeling image on the display screen 221 using a mouse and / or keyboard, and install each sub-component in conjunction with the corresponding installation illustration information.

[0095] In some embodiments, the processor may also generate feedback signals based on user voice commands.

[0096] User voice commands are commands generated based on user voice.

[0097] In some embodiments, the processor can acquire user voice commands through a user interaction module based on the sound acquisition data. For example, the processor can convert the sound acquisition data into text data using automatic speech recognition technology; and autonomously generate corresponding user voice commands by performing semantic understanding or intent recognition on the text data using natural language processing technology.

[0098] Automatic speech recognition technology may include, but is not limited to, acoustic feature extraction models. Natural language processing technology may include, but is not limited to, semantic analysis. More information about the user interaction module 230 can be found here. Figure 2 Related explanations.

[0099] Feedback signals refer to response signals that answer user voice commands. In some embodiments, feedback signals may include playing feedback audio to the scene to be installed or adjusting the current display content of the image display module 220.

[0100] The installation scenario refers to the spatial environment where the equipment to be installed is to be prepared. Examples include studios, cinemas, and conference rooms.

[0101] Feedback audio refers to audio that responds to a user's voice command. For example, if the user's voice command is "What are the installation tools for sub-component X?", the feedback audio could be: "The installation tools for sub-component X include a screwdriver and a wrench." In some embodiments, the processor can play feedback audio to the installation scene through the user interaction module.

[0102] The currently displayed content refers to the content currently displayed by the image display module. In some embodiments, the processor can adjust the currently displayed content of the image display module 220 based on user voice commands. For example, if the user voice command is "Please rotate the installation diagram image 20° clockwise," the processor can adjust the currently displayed content of the image display module 220 to the installation diagram image after rotating it 20° clockwise. As another example, if the user voice command is "What is the installation method for sub-component X?", the processor can adjust the currently displayed content of the image display module 220 to a partial diagram image and installation information corresponding to sub-component X.

[0103] In some embodiments of this specification, user voice commands are obtained through a user interaction module, and feedback signals are generated, making the interaction between the user and the system more convenient. Users can issue commands without manual operation and receive answers and guidance, which helps to improve the user's ease of operation and installation experience.

[0104] In some embodiments of this specification, installation guidance information is automatically generated based on sensor data and device image data. The installation diagram image allows users to more intuitively observe the installation structure of the device to be installed. The installation diagram information provides more detailed guidance information, thereby improving installation efficiency, enhancing the interactivity between the user and the device installation assistance system, and improving the user experience.

[0105] Figure 4 This is an exemplary flowchart illustrating the generation of installation error correction information according to some embodiments of this specification.

[0106] In some embodiments, the installation guidance information may include installation error correction information.

[0107] Installation error correction messages are messages that correct incorrect installation actions by the user. For example, if the installation diagram shows that sub-component X of the device to be installed is 3 meters to the right of sub-component Y, but in actual installation, sub-component X is installed to the left of sub-component Y, then the installation error correction message could be: "The installation positions of sub-component X and sub-component Y are incorrect. Please install sub-component X 3 meters to the right of sub-component Y."

[0108] Among them, sub-components can be the sub-devices that make up the equipment to be installed. For example, if the equipment to be installed is a sound system, the sub-components can be the various amplifiers, speakers, effects processors, etc. in the sound system.

[0109] In some embodiments, the processor can generate installation error correction information through process 400. For example... Figure 4 As shown, process 400 may include the following steps 410-460, and process 400 may be executed by a processor.

[0110] Step 410: Obtain installation scenario data and installation process data.

[0111] Installation scene data refers to data related to the scene to be installed. For example, installation scene data may include the spatial dimensions, shape, and object parameters of the scene to be installed.

[0112] The spatial dimensions can refer to the volume or area of ​​the space to be installed. For example, the spatial dimensions can be represented by the floor area and ceiling height of the space. The spatial shape can be a regular shape such as a cuboid or a hemisphere, or it can be other irregular shapes.

[0113] Object parameters within a space refer to the relevant parameters of objects in the scene to be installed. For example, the size and shape of objects within a space.

[0114] In some embodiments, the processor can acquire installation scene data input by the user based on a user interaction module. In some embodiments, the processor can also acquire relevant images of the installation scene through a camera device in the acquisition device, and analyze these images using computer vision technology to obtain installation scene data. More information about acquisition devices and computer vision technology can be found in [link to relevant documentation]. Figure 1 and Figure 2 Related descriptions.

[0115] Installation process data refers to the recorded data during the user's installation process. This includes, for example, video and image data from each step of the installation process.

[0116] In some embodiments, the processor can directly capture installation process data based on images taken by the user terminal. In other embodiments, the processor can also acquire relevant images of the user installation process through a camera in the acquisition device, and use computer vision technology to analyze these images to obtain installation scene data. More information about user terminals can be found at [link to relevant documentation]. Figure 1 Related descriptions.

[0117] Step 420: Obtain component location information based on installation process data.

[0118] Component location information refers to information that characterizes the installation position of each sub-component of the device to be installed. In some embodiments, component location information may include the individual installation position of each sub-component, the relative positional relationship between the sub-components, etc.

[0119] The mounting position of a sub-component can be represented by its own three-dimensional position coordinates. The relative positional relationship between sub-components can be represented by their relative distance and relative direction. For example, the vector distance between the three-dimensional position coordinates of two sub-components.

[0120] In some embodiments, the processor can acquire component location information based on installation process data in various ways. For example, the processor can directly extract component location information from installation process data acquired by a depth camera. Alternatively, the processor can use computer vision techniques (e.g., object detection algorithms) to analyze installation process data acquired by a conventional camera to obtain component location information.

[0121] In some embodiments, such as Figure 6 As shown, the processor can determine the component location information 611-3 based on the installation process data 611-1 and through the feature extraction layer 611 of the error information prediction model 610.

[0122] Error information prediction model 610 refers to a model used to determine predicted error information. In some embodiments, error information prediction model 610 can be a machine learning model, such as a convolutional neural network (CNN), a recurrent neural network (RNN), etc.

[0123] In some embodiments, the error information prediction model 610 may include a feature extraction layer 611 and an error prediction layer 612.

[0124] The feature extraction layer 611 refers to a model used to extract features from data. In some embodiments, the feature extraction layer 611 can be a machine learning model, such as a CNN.

[0125] In some embodiments, such as Figure 6 As shown, the input to the feature extraction layer 611 may include installation process data 611-1 and installation scene data 611-2, and the output may include component location information 611-3 and user habit information 611-4.

[0126] User habit information 611-4 refers to information related to the user's installation habits when installing the device to be installed. In some embodiments, user habit information 611-4 may include preferences for placing sub-components (e.g., preference for horizontal placement, preference for vertical placement), common installation errors (e.g., incorrect connection of sub-components), installation time for each sub-component (e.g., installation time for sub-component X is 2 minutes), etc.

[0127] For more information on installation process data 611-1 and installation scenario data 611-2, please refer to the relevant description in step 410 above.

[0128] In some embodiments, the feature extraction layer 611 and the error prediction layer 612 of the error information prediction model 610 can be trained and acquired separately.

[0129] In some embodiments, the processor may train the feature extraction layer 611 based on multiple sets of first training samples with first training labels.

[0130] In some embodiments, a first set of training samples may include sample installation process data and sample installation scenario data. The first training samples may be obtained based on historical data. For example, the sample installation process data and the sample installation scenario data may be historical installation process data and historical installation scenario data, respectively.

[0131] In some embodiments, the first training label may be historical actual component location information and actual user habit information corresponding to the first training sample. The first training label may be labeled by the processor and / or manually based on historical data. For example, the processor and / or technicians may statistically analyze a large amount of historical data to obtain actual user habit information, and label it with the historical actual component location information actually collected during the historical installation process as the first training label.

[0132] In some embodiments, the processor can input the first training sample into the initial feature extraction layer, construct a first loss function based on the component location information and user habit information output by the initial feature extraction layer and the first training label, update the initial feature extraction layer based on the first loss function, and complete the training of the initial feature extraction layer when a first preset condition is met, thus obtaining a trained initial feature extraction layer. The first preset condition may be that the first loss function converges, the number of iterations reaches a threshold, etc.

[0133] For an explanation of the error prediction layer 612, please refer to the relevant description in step 450 below.

[0134] Step 430: Based on the component location information, determine whether there is a current error message.

[0135] The current error message refers to the error message generated at the current moment when installing the device to be installed.

[0136] In some embodiments, error information may include component installation error type, component connection error type, and user operation error type.

[0137] Among them, component installation error type refers to the type of error in the installation position of sub-components. For example, the sub-component's own installation position is incorrect (including position deviating from the correct position, position close to heat source, position relatively enclosed, position unstable, etc.), the sub-component's orientation is incorrect, and the relative distance between sub-components is incorrect.

[0138] Component connection error type refers to the type of error in the connection method and / or interface design between sub-components. For example, one or more of the following: mismatched interface type, insufficient / excessive cable length, loose interface, or no connection.

[0139] User operation error types refer to the types of errors made during the user's installation process. Examples include incorrect installation order or improper installation procedures.

[0140] In some embodiments, the processor can use computer vision techniques (e.g., feature matching algorithms) to compare component location information and installation guidance information (including installation diagram images and installation illustrations) to determine the matching degree between the installation guidance information and the component location information. If the matching degree is greater than a matching degree threshold, it is determined that no current error information exists; otherwise, a current error information exists. The matching degree can be represented by a similarity coefficient. The matching degree threshold can be set by the processor by default or by technicians based on experience.

[0141] For more information on installation diagrams and illustrations, please refer to the relevant descriptions above.

[0142] In some embodiments, the processor may generate a test electrical signal and acquire test power-on data based on the electrical signal test module; and determine whether there is a current error message based on the test power-on data.

[0143] A test electrical signal is an electrical signal used to perform current error information testing on the device to be installed. In some embodiments, the test electrical signal may include a test voltage signal and a test current signal.

[0144] In some embodiments, the test electrical signal can be an analog electrical signal or a real electrical signal.

[0145] In some embodiments, the user and / or processor may generate an analog electrical signal based on a signal generator and inject it into the device to be installed as a test electrical signal via an injection device. The signal generator may include one or more of a function signal generator, a pulse signal generator, a synthesized signal generator, etc. The injection device may be a portable fault injection device, etc.

[0146] In some embodiments, the user and / or processor can also adjust the test electrical signal based on various debugging devices to meet testing requirements. For example, the amplitude of the test electrical signal can be adjusted using a variable gain amplifier or attenuator to match the range of the required test voltage signal.

[0147] In some embodiments, the user and / or processor may also generate test electrical signals by directly powering on the device to be installed.

[0148] Test power-on data refers to electrical data collected during power-on testing. Examples include voltage, current, and frequency response at multiple locations on the equipment to be installed.

[0149] In some embodiments, the processor can acquire test power-on data of the device to be installed through relevant devices. These relevant devices may include a volt-ammeter, a frequency response tester, etc.

[0150] For more information on the electrical signal testing module, please refer to [link / reference]. Figure 2 Related descriptions.

[0151] In some embodiments, the processor can determine whether the test power-on data is within a preset data range. If the test power-on data is within the preset data range, it is determined that there is no current error message; if the test power-on data exceeds the preset data range, it is determined that there is a current error message. The preset data range refers to a preset reasonable range of test power-on data.

[0152] In some embodiments, the preset power-on data range may be determined by the processor and / or a technician by querying a first preset relationship table based on the device type of the device to be installed and the current installation stage.

[0153] The first preset relationship table may include the correspondence between the device type, the current installation stage, and the preset data range of the device to be installed. In some embodiments, the first preset relationship table may be constructed by the processor and / or technicians based on historical data or experience. For example, the device type of the device to be installed is "home audio system", the current installation stage is "test installation stage", and the corresponding preset data range is "voltage 1-100 volts, current 0.1-1 ampere, frequency response 10Hz-30kHz".

[0154] In some embodiments, the installation process of the device to be installed may include multiple installation phases. The division of installation phases may be determined by processor default settings or by technicians based on experience. For example, installation phases may include a sub-component location determination phase, a sub-component installation phase, a sub-component connection phase, a testing installation phase, etc. The current installation phase refers to the installation phase at the current moment. In some embodiments, the processor may determine the current installation phase based on installation process data.

[0155] In some embodiments of this specification, test power-on data can be obtained through simple power-on testing, thereby quickly determining whether there is an installation error and improving installation efficiency. At the same time, testing based on real electrical signals generated by direct power-on helps to improve the accuracy of obtaining test power-on data, or testing based on simulated electrical signals helps to protect the equipment to be installed from electrical connections and physical damage, flexibly control simulated test electrical signals, and reduce testing costs.

[0156] Step 440: In response to the existence of current error information, generate installation error correction information based on the current error information.

[0157] In some embodiments, the processor can automatically generate corresponding installation error correction information based on the current error information. For example, the processor can determine the installation error correction information by looking up the current error information in a second preset relationship table. The second preset relationship table can include the correspondence between error information and installation error correction information. For example, the installation error correction information corresponding to the error information "Sub-component X's installation location is relatively enclosed" is "Sub-component X has a heat dissipation risk; please pay attention to the installation distance between the sub-component's installation location and surrounding objects." In some embodiments, the second preset relationship table can be constructed by the processor and / or technicians based on historical data or historical experience.

[0158] Step 450: In response to the absence of current error information, determine the predicted error information for future installation stages based on installation scenario data, component location information, and device connection parameters.

[0159] Device connection parameters refer to the connection parameters between the various sub-components of the device to be installed. In some embodiments, device connection parameters may include the connection type between the sub-components. The connection type may include, but is not limited to, one or more of USB, HDMI (High Definition Multimedia Interface), Bluetooth, etc.

[0160] In some embodiments, the processor can obtain device connection parameters input by the user based on the user interaction module, and can also retrieve the factory settings parameters of the device to be installed from the storage device, thereby obtaining the device connection parameters.

[0161] A future installation phase refers to an installation phase that will be performed in the future. In some embodiments, the processor can determine the installation phase following the current installation phase as a future installation phase. For example, if the installation phases include installation phases 1 through 5, and the current installation phase is installation phase 3, then the future installation phases could be installation phases 4 and 5.

[0162] Prediction error information refers to incorrect information that may occur in the predicted future. For more information on error information, please refer to the relevant description in step 430 above.

[0163] In some embodiments, the processor can determine predicted error information for future installation phases through various methods based on installation scenario data, component location information, and device connection parameters. For example, the processor can determine predicted error information by searching a database based on installation scenario data, component installation location information, and device connection parameters.

[0164] As an example only, the processor can construct a first vector database, which may include multiple first sample vectors and their corresponding multiple first data labels. The first sample vector may consist of sample installation scenario data, sample component installation location information, and sample device connection parameters. The first data label may be the prediction error information corresponding to the first sample vector. The first sample vector and its corresponding first data label may be determined based on historical data. For example, the first sample vector may consist of historical installation scenario data, historical component installation location information, and historical device connection parameters at a first historical moment. The first data label corresponding to the first sample vector may be the historical actual error information at a second historical moment. The first historical moment is prior to the second historical moment.

[0165] In some embodiments, the processor can construct a first feature vector based on installation scenario data, component installation location information, and device connection parameters, search a first vector database, calculate multiple first similarities between the first feature vector and multiple first sample vectors, determine the first sample vector with the highest first similarity, and use its corresponding first data label as prediction error information. The first similarity can be represented by cosine similarity, Euclidean distance, etc.

[0166] In some embodiments, such as Figure 6 As shown, the processor can determine the predicted error information 612-6 for the future installation stage based on the installation scenario data 611-2, component location information 611-3, and device connection parameters 612-1, through the error prediction layer 612 of the error information prediction model 610.

[0167] Error prediction layer 612 refers to a model used to determine prediction error information. In some embodiments, error prediction layer 612 can be a machine learning model, such as an RNN.

[0168] In some embodiments, such as Figure 6 As shown, the inputs to the error prediction layer 612 may include component location information 611-3, user habit information 611-4, device connection parameters 612-1, installation scenario data 611-2, installation schematic image 612-2, installation schematic information 612-3, and device operating parameters 612-4. The output may be predicted error information 612-6 for the future installation stage.

[0169] Equipment operating parameters 612-4 refer to parameters related to the operating status of the equipment to be installed. In some embodiments, equipment operating parameters 612-4 may include the maximum power, rated voltage, and operating temperature range of the equipment to be installed.

[0170] Among these, maximum power refers to the maximum output power that the equipment to be installed can achieve under normal operating conditions. Rated voltage refers to the voltage value required for the equipment to be installed under normal operating conditions. Operating temperature range refers to the temperature range of the equipment to be installed under normal operating conditions.

[0171] For more information on component location information 611-3, equipment connection parameters 612-1, installation scenario data 611-2, installation schematic image 612-2, and installation schematic information 612-3, please refer to [link / reference]. Figure 3 and Figure 5 Related explanations.

[0172] In some embodiments, the processor may train the error prediction layer based on multiple sets of second training samples with second training labels.

[0173] In some embodiments, a set of second training samples may include sample component location information, sample user habit information, sample device connection parameters, sample installation scenario data, sample installation schematic images, sample installation schematic information, and sample device operating parameters. The second training samples may be obtained based on historical data. For example, a set of second training samples may consist of historical component location information, historical user habit information, historical device connection parameters, historical installation scenario data, historical installation schematic images, historical installation schematic information, and historical device operating parameters from a historical installation process.

[0174] In some embodiments, the second training label can be historical actual error information corresponding to the second training sample. The second training label can be labeled by the processor and / or manually based on historical data. For example, if a set of second training samples is historical data of historical installation phase 1, the processor and / or technicians can statistically analyze a large amount of historical data to obtain historical error information of historical installation phase 2 actually collected during the historical installation process, and label it as the second training label. Here, historical installation phase 2 is after historical installation phase 1.

[0175] The process of training the error prediction layer is similar to that of training the feature extraction layer, and can be found in the relevant description of step 420, which will not be repeated here.

[0176] In some embodiments, the input to the error prediction layer 612 of the error information prediction model 610 may also include environmental data 612-5.

[0177] Environmental data 612-5 refers to data related to the environment in which the device to be installed is located. Examples include ambient temperature data and ambient humidity data. In some embodiments, ambient temperature data and ambient humidity data can be collected by temperature sensors and humidity sensors deployed at the installation site, respectively. More information about temperature sensors and humidity sensors can be found in [link to relevant documentation]. Figure 1 Related descriptions.

[0178] In some embodiments, the second training samples may further include sample environment data. The sample environment data may be obtained based on historical data. In some embodiments, the processor may train the error prediction layer based on the second training samples including the sample environment data. For details on the training method of the error prediction layer, please refer to the relevant description above.

[0179] In some embodiments of this specification, using the current environment of the device to be installed as input to the error prediction layer can improve the accuracy of the prediction results of the error prediction layer.

[0180] In some embodiments, the feature extraction layer and the error prediction layer can be jointly trained. The first joint training sample may include sample installation process data, sample installation scene data, sample device connection parameters, sample installation schematic image, sample installation schematic information, sample device operating parameters, and sample environment data. The label corresponding to the first joint training sample is the historical actual error information corresponding to the first joint training sample. The processor can input the sample installation process data and sample installation scene data into the feature extraction layer, and input the component location information and user habit information output by the feature extraction layer, along with the sample device connection parameters, sample installation schematic image, sample installation schematic information, sample device operating parameters, and sample environment data from the first joint training sample, into the error prediction layer. A first joint loss function is constructed based on the predicted error information output by the error prediction layer and the label corresponding to the first joint training sample. The feature extraction layer and the error prediction layer are updated based on the first joint loss function. When the first joint preset condition is met, the error information prediction model training is complete, and a trained error information prediction model is obtained. The first joint preset condition may be the convergence of the first joint loss function, the number of iterations reaching a threshold, etc.

[0181] In some embodiments of this specification, an error information prediction model is used to predict possible errors during the installation process based on data from multiple sources and user installation habits. This can help users correct errors more efficiently and thus improve installation efficiency.

[0182] Step 460: Generate installation error correction information based on the predicted error information.

[0183] In some embodiments, the processor can generate installation error correction information in various ways based on predicted error information. For example, the processor can determine the installation error correction information by looking up a second preset relationship table. More details about the second preset relationship table can be found in the description of step 440.

[0184] In some embodiments of this specification, the presence of current error information can be quickly determined based on the component location information. If current error information exists, installation error correction information can be generated in a timely manner. If current error information does not exist, error information in future installation stages can be accurately predicted. This helps to promptly remind users to correct current errors and effectively avoid future errors, thereby improving installation efficiency and ensuring installation quality.

[0185] Figure 5 This is an exemplary flowchart illustrating the determination of installation correction information according to some embodiments of this specification.

[0186] In some embodiments, the installation guidance information may also include installation correction information.

[0187] Installation correction information refers to information that provides guidance for correcting the installation process. In some embodiments, installation correction information may include a corrected installation diagram and information on the corrections made.

[0188] Correction information refers to changes made to the installation diagram. For example, if the original installation diagram shows sub-component X 3 meters to the right of sub-component Y, and the corrected installation diagram shows sub-component X 2.5 meters to the right of sub-component Y, then the correction information would be "The relative distance between sub-component X and sub-component Y has been corrected from 3 meters to 2.5 meters".

[0189] In some embodiments, the processor may determine installation correction information via process 500. For example... Figure 5 As shown, process 500 may include steps 510-550 as described below. In some embodiments, process 500 may be executed by a processor.

[0190] Step 510: Obtain sound acquisition data from the scene to be installed.

[0191] For more information on scenarios awaiting installation, please refer to [link / reference]. Figure 2 And its related descriptions.

[0192] Sound acquisition data refers to the sound data collected by the data acquisition module within the installation environment. For more information about the data acquisition module, please refer to [link to relevant documentation]. Figure 2 And its related descriptions.

[0193] Step 520: Determine the characteristics of environmental noise based on the sound acquisition data.

[0194] Environmental noise characteristics refer to the audio characteristics of environmental noise in the installation environment. Environmental noise can refer to other conventional environmental noise excluding man-made noise, such as wind noise and road noise.

[0195] In some embodiments, environmental noise characteristics may include the average volume of the environmental noise, frequency distribution, etc. Frequency distribution refers to the distribution of all frequencies. Frequency distribution can be represented by a spectrum or graph.

[0196] In some embodiments, the processor can determine the characteristics of ambient noise based on the sound acquisition data in various ways. For example, the processor can perform spectral analysis on the sound acquisition data using relevant equipment (e.g., a spectrum analyzer) to obtain frequency components; filter man-made noise using pattern recognition techniques based on the frequency components to extract ambient noise; and perform frequency domain analysis on the ambient noise to obtain noise frequency characteristics. The frequency domain analysis methods may include, but are not limited to, Fourier transform, wavelet transform, and fast Fourier transform. Pattern recognition techniques may include, but are not limited to, clustering analysis, k-nearest neighbor, and random forest.

[0197] Step 530: Determine the installation orientation information based on the installation scenario data and installation process data.

[0198] Installation orientation information refers to the orientation of a sub-component in the installation environment. For example, sub-component X faces the north wall.

[0199] In some embodiments, the processor can acquire the installation orientation information of the sub-component using computer vision technology. This computer vision technology may include, but is not limited to, one or more of object detection algorithms, instance segmentation algorithms, and pose estimation techniques.

[0200] For example, the processor can identify each sub-component through object detection algorithms, distinguish different sub-components and their boundaries through instance segmentation techniques, and determine the installation position and orientation information of the sub-component in the installation scene through pose estimation techniques. The object detection algorithms may include, but are not limited to, YOLO (You Only Look Once) and Faster Region-based Convolutional Neural Network (Faster R-CNN); the instance segmentation techniques may include, but are not limited to, Mask Region-based Convolutional Neural Network (Mask R-CNN); and the pose estimation techniques may include, but are not limited to, Perspective-n-Point (PnP) algorithms.

[0201] Step 540: Based on the installation orientation information, installation scenario data, installation process data, and environmental noise characteristics, determine the estimated audio data.

[0202] Predicted audio data refers to the data that is expected to be generated when the device to be installed plays audio after installation. In some embodiments, predicted audio data may include predicted audio features and predicted sound effect scores.

[0203] The estimated audio characteristics refer to the data characteristics of the audio played after installation. In some embodiments, the estimated audio characteristics may include estimated frequency response, soundstage width, timbre, clarity, equalization, distortion, etc.

[0204] Frequency response can characterize the volume of audio across all frequency ranges. For example, frequency response can be represented by a sequence of decibels (dB) of audio across all frequencies.

[0205] Sound field width can characterize the degree of lateral diffusion of audio. For example, sound field width can be represented by the central angle of the fan-shaped sound field formed by the audio diffusion.

[0206] Timbre can characterize the color or features of a sound. For example, timbre can include warmth, brightness, clarity, etc.

[0207] Clarity refers to the clarity of audio. In some embodiments, clarity can be represented by a value from 0 to 10, with a higher value indicating higher clarity. In some embodiments, clarity can be categorized based on the sound source, such as vocal clarity, instrument clarity, etc.

[0208] Equalization refers to the balance of audio across different frequencies. For example, equalization can be represented by the variance of the frequency response of the audio across all frequencies; the smaller the variance, the better the equalization.

[0209] Distortion refers to the degree of distortion in played audio. In some embodiments, distortion can be represented by a value from 0 to 10, with a higher value indicating higher distortion. In some embodiments, distortion can be classified according to the type of distortion, such as harmonic distortion and intermodulation distortion.

[0210] A sound effect rating refers to a score of the audio quality of a played audio file. In some embodiments, the sound effect rating can be represented by a value from 0 to 10, with a higher value indicating a higher sound effect rating and better audio quality.

[0211] In some embodiments, the processor can determine the estimated audio data in various ways based on installation orientation information, installation scene data, installation process data, and environmental noise characteristics. For example, the processor can determine the estimated audio characteristics by looking up a third preset relationship table; then, it can send the estimated audio characteristics to the user terminal, whereby the user determines the corresponding estimated sound effect score. The third preset relationship table may include the correspondence between installation orientation information, installation scene data, installation process data, environmental noise characteristics, and audio characteristics. The third preset relationship table may be constructed by the processor and / or technicians based on historical data or historical experience.

[0212] In some embodiments, such as Figure 7 As shown, the processor can determine the predicted audio data 711-4 based on the installation orientation information 711-1, installation scene data 611-2, installation process data 611-1, environmental noise characteristics 711-2, device type 711-3, and component location information 611-3 through the data prediction layer 711 of the sound effect correction model 710.

[0213] The sound effect correction model 710 refers to a model used to determine installation correction information. In some embodiments, the sound effect correction model 710 can be a machine learning model, such as a deep neural network (DNN), an RNN, etc.

[0214] In some embodiments, the sound effect correction model 710 may include a data prediction layer 711 and an information correction layer 712.

[0215] The data prediction layer 711 refers to the model used to determine the predicted audio data. In some embodiments, the data prediction layer 711 can be a machine learning model, such as an RNN.

[0216] In some embodiments, such as Figure 7 As shown, the inputs to the data prediction layer 711 may include installation orientation information 711-1, installation scene data 611-2, installation process data 611-1, environmental noise characteristics 711-2, equipment type 711-3, and component location information 611-3, and the output may be predicted audio data 711-4.

[0217] In some embodiments, the data prediction layer 711 and the information correction layer 712 of the sound effect correction model 710 can be trained and acquired separately.

[0218] In some embodiments, the processor may train a data prediction layer based on multiple sets of third training samples with third training labels.

[0219] In some embodiments, a third set of training samples may include sample installation orientation information, sample installation scene data, sample installation process data, sample environmental noise characteristics, sample device type, and sample component location information. The third training samples may be obtained based on historical data. For example, the sample installation orientation information, sample environmental noise characteristics, and sample device type may be historical installation orientation information, historical environmental noise characteristics, and historical device types from a historical installation process.

[0220] For more information on sample installation scenario data, sample installation process data, and sample component location information, please refer to [link / reference]. Figure 6 Related descriptions.

[0221] In some embodiments, the third training label can be the actual audio data corresponding to the third training sample. The third training label can be annotated by the processor and / or technicians based on historical data. For example, the processor and / or technicians can annotate the audio features of the actual audio data collected and played after the historical device was installed, along with their corresponding historical actual sound effect scores, as the third training label. The historical actual sound effect scores can be obtained by technicians based on their listening experience.

[0222] The process of training the data prediction layer is similar to the process of training the feature extraction layer; see [link to relevant documentation]. Figure 6 The relevant descriptions will not be repeated here.

[0223] For an explanation of the information correction layer 712, please refer to the relevant description in step 550 below.

[0224] In some embodiments, the input to the data prediction layer 711 of the sound effect correction model 710 may also include test power-on data 711-5 and environmental data 612-5.

[0225] For more information on test power-on data 711-5 and environmental data 612-5, please refer to [link / reference]. Figure 4 Related descriptions.

[0226] In some embodiments, the third training sample may further include sample test power-on data and sample environment data. The third training sample may be obtained based on historical data. In some embodiments, the third training label may be the actual audio data corresponding to the third training sample, which includes sample test power-on data and sample environment data.

[0227] In some embodiments, the processor may also train the data prediction layer 711 based on a third training sample, including sample test power-on data and sample environment data. The training method for the data prediction layer 711 can be found in the preceding description.

[0228] In some embodiments of this specification, training the data prediction layer by testing power-on data and environmental data can enhance the generalization ability of the sound effect correction model to different environments and different power-on states, thereby improving the prediction accuracy of the sound effect correction model.

[0229] In some embodiments, in response to the current installation phase being a test installation phase, the processor may determine the estimated audio data through steps 541-545 below.

[0230] For more information on the current installation phase, please refer to [link / reference]. Figure 4 Related descriptions.

[0231] The test installation phase refers to the phase in which the equipment to be installed is tested after installation.

[0232] In some embodiments, the processor may extract features from images captured by a camera device based on installation process data using computer vision technology (e.g., instance segmentation technology), and compare the extracted features with features corresponding to preset test installation stages to determine whether the current installation stage is a test installation stage.

[0233] In some embodiments, the processor can also determine whether the current installation stage is a test installation stage based on information input by the user through the user interaction module. For example, if the previous installation stage of the test installation stage was the sub-component connection stage, and the user confirms through the user interaction module that the sub-component connection stage has been completed, the processor can determine that it has now entered the test installation stage.

[0234] Step 541: Generate a sound test command and send it to the device to be installed.

[0235] A sound test instruction is an instruction to test the sound of the device to be installed. In some embodiments, the sound test instruction may include a sound test audio.

[0236] Audition audio refers to audio data used for auditions. Examples include a piece of music or a movie audio clip. Different audition commands can include different types of audition audio.

[0237] In some embodiments, in response to the current installation phase being a test installation phase, the processor can generate a test audio command in various ways. For example, the processor can obtain a test audio pre-set and input by the user based on the installation scenario and installation requirements, using a user interaction module.

[0238] In some embodiments, the audition instruction may also include audition parameters.

[0239] Test parameters refer to the parameters related to playing test audio. In some embodiments, test parameters may include test volume, test duration, etc.

[0240] In some embodiments, the processor can determine the sound test command in various ways based on the current installation stage, device type, installation scenario data, and test power-on data. For example, the processor can determine the sound test command by searching a database based on the current installation stage, device type, installation scenario data, and test power-on data.

[0241] As an example only, the processor can construct a second vector database, which may include multiple second sample vectors and their corresponding multiple second data tags. The second sample vector may consist of the current installation stage of the sample, the sample device type, the sample installation scenario data, and the sample test power-on data. The second data tag may be the sound test command corresponding to the second sample vector. The second sample vector and its corresponding second data tag may be determined based on historical data. For example, the second sample vector may consist of historical current installation stage, historical device type, historical installation scenario data, and historical test power-on data. The second data tag corresponding to the second sample vector may be the sound test command corresponding to the second sample vector. The sound test command corresponding to the second sample vector may be determined by the processor and / or the user based on historical data and / or prior experience.

[0242] In some embodiments, the processor can construct a second feature vector based on the current installation stage, device type, installation scenario data, and test power-on data. It can then search a second vector database, calculate multiple second similarities between the second feature vector and multiple second sample vectors, determine the second sample vector with the highest second similarity, and use its corresponding second data label as a sound test instruction. The second similarity can be represented by cosine similarity, Euclidean distance, etc.

[0243] In some embodiments of this specification, by comprehensively considering the current installation stage, device type, installation scenario data, and test power-on data, the appropriate sound test command for the current installation scenario can be accurately determined, reducing unnecessary changes to the sound test audio and adjustments to the sound test parameters, and improving sound test efficiency.

[0244] In some embodiments, the processor may send the sound test command to the device to be installed via a network. Further information regarding networks can be found in [link to relevant documentation]. Figure 1 Related descriptions.

[0245] Step 542: Based on the sound test command, control the device to be installed to perform a sound test.

[0246] In some embodiments, the processor may control the device to be installed to play test audio based on test parameters, according to a test instruction, in order to perform a test.

[0247] Step 543: Based on the data acquisition module, acquire the sound test acquisition data.

[0248] Audition data refers to the relevant data collected during an audition. In some embodiments, the processor can acquire audition data through a data acquisition module (e.g., a sound sensor in an acquisition device).

[0249] Step 544: Determine the characteristics of the test audio based on the audio acquisition data.

[0250] Test audio characteristics refer to the audio features of the test audio. In some embodiments, test audio characteristics may include the frequency response, soundstage width, timbre, clarity, equalization, distortion, etc. of the test audio. For more information on frequency response, soundstage width, timbre, clarity, equalization, and distortion, please refer to the relevant description in step 540 above.

[0251] In some embodiments, the processor can perform frequency domain analysis on the audio acquisition data to obtain test audio features. The frequency domain analysis methods may include, but are not limited to, Fourier transform, wavelet transform, and fast Fourier transform.

[0252] Step 545: Determine the estimated audio data based on the test audio features.

[0253] In some embodiments, the processor can determine the predicted audio data based on the test audio features and the current installation stage, through the data prediction layer of the audio effect correction model.

[0254] For more information on sound effect correction models and data prediction layers, please refer to the relevant descriptions above.

[0255] In some embodiments of this specification, test audio features can be quickly extracted from the audio sampling data, thereby determining the estimated audio data. This reduces the complexity of the data, removes redundant features, and accurately predicts the audio data for the future installation stage. This helps to determine in advance whether the subsequent installation effect will meet expectations, improves installation efficiency, and ensures installation quality.

[0256] Step 550: Based on the estimated audio data and correction conditions, determine the installation correction information.

[0257] Correction conditions refer to the conditions under which it is determined that correction information needs to be installed.

[0258] In some embodiments, the correction condition may be that the estimated sound effect score is lower than a preset score threshold, and / or the estimated audio features exceed a preset feature range. When the estimated sound effect score is lower than the preset score threshold, and / or the estimated audio features exceed the preset feature range, it is determined that installation correction information needs to be obtained; when the estimated sound effect score is not lower than the preset score threshold and the estimated audio features do not exceed the preset feature range, it is determined that installation correction information does not need to be obtained.

[0259] The preset scoring threshold and preset feature range can be set by the processor by default or determined by technicians through prior experience. For example, the estimated sound effect score range is 0-10, and the preset scoring threshold can be 6. The preset feature range corresponding to the sound field width in the estimated audio data can be 60-100 meters.

[0260] In some embodiments, in response to the user input information including a correction condition, the processor can directly invoke the correction condition. In response to the user input information not including a correction condition, the processor can determine the correction condition based on installation scenario data, environmental noise characteristics, and the device type of the device to be installed.

[0261] User input information refers to information that a user enters into the system. Examples include images, text, and commands that a user actively uploads. In some embodiments, the processor can acquire user input information based on a user interaction module.

[0262] In some embodiments, in response to the absence of correction conditions in the user input information, the processor can determine the correction conditions in various ways based on installation scenario data, environmental noise characteristics, and the device type of the device to be installed. For example, the processor can determine the correction conditions by searching a database based on installation scenario data, environmental noise characteristics, and the device type of the device to be installed.

[0263] As an example only, the processor can construct a third vector database, which may include multiple third sample vectors and their corresponding third data labels. The third sample vectors may consist of sample installation scenario data, sample environmental noise characteristics, and the device type of the device to be installed. The third data labels may be correction conditions corresponding to the third sample vectors. The third sample vectors and their corresponding third data labels can be determined based on historical data.

[0264] For example, the third sample vector can be composed of historical installation scenario data, historical environmental noise characteristics, and the equipment type of historical devices to be installed. The third data label corresponding to the third sample vector can be the correction condition corresponding to the third sample vector. The third data label can be composed of a preset scoring threshold and a preset feature range corresponding to the third sample vector.

[0265] In some embodiments, the processor can construct a third feature vector based on installation scenario data, environmental noise characteristics, and the device type of the device to be installed. It then searches a third vector database, calculates multiple third similarities between the third feature vector and multiple third sample vectors, determines the third sample vector with the highest third similarity, and uses its corresponding third data label as a correction condition. The third similarity can be represented by cosine similarity, Euclidean distance, etc. More information about the vector database can be found in the description of step 450.

[0266] In some embodiments of this specification, user requirements are given priority when determining correction conditions to improve user satisfaction; when the user has no specific requirements, correction conditions are determined autonomously based on parameters such as installation scenario data, equipment type, and environmental noise characteristics, making the installation guidance information more accurate and reliable.

[0267] In some embodiments, in response to the estimated audio data 711-4 and its confidence level meeting the correction conditions, the processor can determine the installation correction information 712-1 based on the estimated audio data 711-4, installation orientation information 711-1, installation schematic image 612-2, installation scene data 611-2, environmental noise characteristics 711-2, and device operating parameters 612-4, through the information correction layer 712 of the sound effect correction model 710.

[0268] The information correction layer 712 refers to the model used to determine the installation correction information 712-1. In some embodiments, the information correction layer 712 can be a machine learning model, such as a DNN.

[0269] In some embodiments, such as Figure 7 As shown, the inputs to the information correction layer 712 may include estimated audio data 711-4, installation orientation information 711-1, installation schematic image 612-2, installation scene data 611-2, environmental noise characteristics 711-2, and equipment operating parameters 612-4. The output may be installation correction information 712-1 (including correction information and the corrected installation schematic image).

[0270] In some embodiments, the processor may train the information correction layer 712 based on multiple sets of fourth training samples with fourth training labels.

[0271] In some embodiments, a set of fourth training samples may include sample predicted audio data, sample installation orientation information, sample installation schematic images, sample installation scene data, sample environmental noise characteristics, and sample device operating parameters, etc. The fourth training samples may be obtained based on historical data.

[0272] In some embodiments, the fourth training label can be the actual installation correction information corresponding to the fourth training sample. The fourth training label can be annotated by the processor and / or manually based on historical data. For example, the processor and / or technicians can annotate the historically corrected installation diagram and historical correction information corresponding to the fourth training sample as the fourth training label.

[0273] The process of training the information correction layer is similar to the process of training the error prediction layer; see [link to relevant documentation]. Figure 6 The relevant descriptions will not be repeated here.

[0274] In some embodiments, the data prediction layer 711 and the information correction layer 712 can be jointly trained. The second joint training sample can include sample installation orientation information, sample installation scene data, sample installation process data, sample environmental noise characteristics, sample device type, sample component location information, sample installation schematic image, sample environmental data, sample test power-on data, and sample device operating parameters. The label corresponding to the second joint training sample can be actual installation correction information. The processor can input sample environmental data, sample test power-on data, sample installation orientation information, sample installation scene data, sample installation process data, sample environmental noise characteristics, sample device type, and sample component location information into the data prediction layer 711, input the predicted audio data 711-4 output by the data prediction layer 711 into the information correction layer 712, construct a second joint loss function based on the installation correction information 712-1 output by the information correction layer 712 and the label corresponding to the second joint training sample, update the data prediction layer 711 and the information correction layer 712 based on the second joint loss function, and when the second joint preset condition is met, the error information prediction model training is complete, resulting in a trained sound effect correction model 710. The second joint precondition can be the convergence of the second joint loss function, the number of iterations reaching a threshold, etc.

[0275] In some embodiments of this specification, the data prediction layer extracts features from the input multi-dimensional data, which can accurately predict the sound performance of the audio device after installation. When the sound effect of the audio device is poor, the information correction layer can automatically adjust the correction strategy to ensure that the sound quality of the audio device after installation reaches a better state.

[0276] In some embodiments of this specification, estimated audio data can be determined based on installation orientation information, installation scenario data, and installation process data. Then, based on the estimated audio data and correction conditions, installation correction information can be determined. When it is determined that the estimated audio data does not meet the standard, installation correction information is generated in a timely manner. This helps to promptly remind users to adjust the equipment to be installed, effectively avoid future substandard results or errors, ensure installation quality, and improve installation effect.

[0277] The embodiments in this specification are merely illustrative and not intended to limit the scope of this specification. Various modifications and alterations that can be made by those skilled in the art under the guidance of this specification remain within its scope.

[0278] This specification provides one or more embodiments of a device installation assistance apparatus, the apparatus including at least one memory and at least one processor, the at least one memory for storing computer instructions, and the at least one processor for executing the computer instructions or parts thereof to implement a device installation assistance method.

[0279] This specification provides one or more embodiments of a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes a device installation assistance method.

[0280] Furthermore, certain features, structures, or characteristics in one or more embodiments of this specification may be appropriately combined.

[0281] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates 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 be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0282] If there is any inconsistency or conflict between the descriptions, definitions, and / or terms used in the materials referenced in this specification and the content described in this specification, the descriptions, definitions, and / or terms used in this specification shall prevail.

Claims

1. An equipment installation auxiliary system, characterized in that, The system includes a data acquisition module, an image display module, and a processor, wherein, The data acquisition module includes a sensor and is configured to acquire sensor data from the device to be installed. The image display module includes a display screen and is configured to show installation guidance information to the user; The processor is configured to: Acquire device image data; Based on the sensor data and the device image data, the installation guidance information is generated; and The installation guidance information is displayed to the user based on the image display module and / or the user terminal.

2. The system as described in claim 1, characterized in that, The installation guidance information includes installation error correction information; The processor is further configured to: Acquire installation scenario data and installation process data; Based on the installation process data, obtain the component location information; Based on the component location information, determine whether there is a current error message; In response to the existence of the current error information, the installation error correction information is generated based on the current error information; In response to the absence of the current error information, based on the installation scenario data, the component location information, and the device connection parameters, predictive error information for the future installation stage is determined; Based on the predicted error information, the installation error correction information is generated.

3. The system as described in claim 1, characterized in that, The installation guidance information also includes installation correction information, and the data acquisition module is further configured to acquire sound acquisition data in the scene to be installed. The processor is further configured to: Based on the sound acquisition data, the characteristics of the ambient noise are determined; Based on the installation scenario data and the installation process data, the installation orientation information is determined; Based on the installation orientation information, the installation scenario data, the installation process data, and the environmental noise characteristics, the estimated audio data is determined. Based on the estimated audio data and correction conditions, the installation correction information is determined.

4. The system as described in claim 3, characterized in that, The processor is further configured to: In response to the current installation phase being a test installation phase, a sound test command is generated and sent to the device to be installed; Based on the sound test command, control the device to be installed to perform a sound test; Based on the data acquisition module, acquire sound test data; Based on the collected audio data, the characteristics of the test audio are determined; Based on the test audio features, the estimated audio data is determined.

5. A method for assisting in equipment installation, characterized in that, The method includes: Acquire sensor data and device image data from the device to be installed; Based on the sensor data and the device image data, installation guidance information is generated; and The installation guidance information is displayed to the user based on the image display module and / or the user terminal.

6. The method as described in claim 5, characterized in that, The installation guidance information includes installation error correction information, and the method further includes: Acquire installation scenario data and installation process data; Based on the installation process data, obtain the component location information; Based on the component location information, determine whether there is a current error message; In response to the existence of the current error information, the installation error correction information is generated based on the current error information; In response to the absence of the current error information, based on the installation scenario data, the component location information, and the device connection parameters, predictive error information for the future installation stage is determined; Based on the predicted error information, the installation error correction information is generated.

7. The method as described in claim 5, characterized in that, The installation guidance information also includes installation correction information; The method further includes: Acquire sound data from the scene to be installed; Based on the sound acquisition data, the characteristics of the ambient noise are determined; Based on the installation scenario data and the installation process data, the installation orientation information is determined; Based on the installation orientation information, the installation scenario data, the installation process data, and the environmental noise characteristics, the estimated audio data is determined. Based on the estimated audio data and correction conditions, the installation correction information is determined.

8. The method as described in claim 7, characterized in that, The method further includes: In response to the current installation phase being a test installation phase, a sound test command is generated and sent to the device to be installed; Based on the sound test command, control the device to be installed to perform a sound test; Based on the data acquisition module, acquire sound test data; Based on the collected audio data, the characteristics of the test audio are determined; Based on the test audio features, the estimated audio data is determined.

9. An auxiliary device for equipment installation, characterized in that, The device includes at least one memory and at least one processor, the at least one memory being used to store computer instructions, and the at least one processor executing the computer instructions or parts thereof to implement the device installation assistance method according to any one of claims 5-8.

10. A computer-readable storage medium, characterized in that, The storage medium stores computer instructions, and when the computer reads the computer instructions, the computer executes the device installation assistance method as described in any one of claims 5-8.

Images