Multifunctional intelligent mattress and manufacturing method

Abstract

The invention is suitable for the technical field of intelligent mattress manufacturing control, and provides a multifunctional intelligent mattress and a manufacturing method, and the method is applied to a multifunctional intelligent mattress manufacturing control system. The system comprises an information acquisition module, a model construction module, a model training module, a model evaluation module, a parameter determination module, a production application module, a wireless communication module, a memory, an alarm, a processing center and an intelligent mobile terminal. The information acquisition module, the model construction module, the model training module, the model evaluation module, the parameter determination module, the production application module, the wireless communication module, the memory and the alarm are respectively connected with the processing center; the intelligent mobile terminal is in wireless network connection with the wireless communication module in the range of a wireless network or the Internet. The invention further provides a multifunctional intelligent mattress. The process parameters can be preset, the quality problem is prevented in advance, automatic production is achieved, and the production efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent mattress manufacturing control, and specifically relates to a multifunctional intelligent mattress and a manufacturing method in the field of artificial intelligence. Background Art

[0002] Existing intelligent mattresses can already monitor users' sleep data in real time, including the number of body movements, sleep posture modeling, heart rate monitoring, etc., and provide users with a personalized sleep experience by intelligently adjusting the mattress hardness. However, with the continuous development of technologies such as the Internet of Things, big data, and artificial intelligence, the intelligent level of intelligent mattresses will be further improved. Intelligent mattresses can not only more accurately identify users' sleep states and needs and provide more personalized sleep solutions, but in addition to the basic sleep monitoring and adjustment functions, intelligent mattresses must also incorporate more personalized elements such as intelligent wake-up and health abnormality reminders, strictly control the production process, and ensure the production quality to meet users' pursuit of high-quality sleep. Summary of the Invention

[0003] In order to solve the deficiencies in the prior art, the purpose of the present invention is to provide a multifunctional intelligent mattress and a manufacturing method. By setting up various functional modules such as an information acquisition module, a model construction module, a model training module, a model evaluation module, a parameter determination module, and a production application module, collect information on abnormal phenomena in the production quality of daily intelligent mattresses in the industry for early prevention starting from the design, preset production process parameters, and perform automated production and automated detection, reducing human interference and avoiding abnormal problems such as "excessive radiation, inaccurate sleep detection, malfunction or inaccuracy of adjustment functions, poor support / breathability and environmental protection, limited massage function effect, and immature snoring intervention technology" in intelligent mattresses, improving production efficiency and reducing production costs.

[0004] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0005] A manufacturing method for a multifunctional intelligent mattress is applied to a manufacturing control system for a multifunctional intelligent mattress. The system includes an information acquisition module, a model construction module, a model training module, a model evaluation module, a parameter determination module, a production application module, a wireless communication module, a memory, an alarm, a processing center, and an intelligent mobile terminal; the information acquisition module, the model construction module, the model training module, the model evaluation module, the parameter determination module, the production application module, the wireless communication module, the memory, and the alarm are respectively connected to the processing center; the intelligent mobile terminal includes a smart phone, a tablet computer, and a smart remote control, and is wirelessly connected to the wireless communication module within the range of a wireless network or the Internet.

[0006] The manufacturing method for a multifunctional intelligent mattress provided by the present invention includes the following steps:

[0007] S10. Before production, the information acquisition module acquires historical image data of normal and abnormal production quality of the intelligent mattress and performs preprocessing for subsequent model construction, and transfers it to the model construction module;

[0008] S20. The model construction module determines the model architecture, designs the network hierarchical structure, adds auxiliary layers, and defines model parameters to construct the model for subsequent model training and verification, and transfers it to the model training module;

[0009] S30. The model training module trains the model based on the collected data and adjusts the model parameters to optimize the model performance to the predetermined intelligent mattress production process parameters, ensuring the quality stability of the intelligent mattress, and transfers it to the model evaluation module;

[0010] S40. The model evaluation module performs model verification and evaluation based on the trained model, and adjusts and optimizes the model according to the verification results to improve the performance and accuracy of the model, and transfers it to the parameter determination module;

[0011] S50. The parameter determination module conducts production tests based on the production process parameters predicted by the trained model to obtain the optimal intelligent mattress production process parameters to ensure the subsequent production quality, and transfers it to the production application module;

[0012] S60. The production application module performs production and various detections on the intelligent mattress for the intelligent mattress production detection equipment according to the set production process parameters in accordance with the program instructions to ensure that the intelligent mattress meets the quality requirements.

[0013] The present invention also provides a multifunctional intelligent mattress, which is implemented by using the above-mentioned method for manufacturing a multifunctional intelligent mattress.

[0014] Advantages of the present invention compared with the prior art:

[0015] By setting up each functional module, information on abnormal phenomena in the daily production quality of intelligent mattresses in the industry is collected and preset production process parameters are set to prevent problems from occurring layer by layer from design to production; through an automatic feeding robot, the bed net, top / bottom surface fabrics, sponge and other filling layers are sent to the designated positions by an AGV (Automated Guided Vehicle), and the system automatically completes disassembly and feeding; the positioning and measurement of the incoming materials are completed by a vision system without manual intervention to ensure the accurate positioning of each component; the raw materials can be adapted by the vision system to produce products of different sizes to meet the diverse market demands; within the allowable cutting error range, the system calculates through vision AI and automatically corrects the deviation to accurately compound the fabric, filling layer, etc., ensuring the quality and precision of the products; it can automatically read QR codes and automatically read information, collect on-site production data in real time, transmit it back to the background, and perform AI analysis and processing, timely control the production system, and feedback to the office system to realize the digital management of the production process; through the automatic mattress production line, an integrated APS advanced production scheduling, MES manufacturing execution system, SCADA data acquisition and monitoring system, etc. are used to build a digital factory, which is seamlessly connected with cloud platform technology to realize functions such as remote fault diagnosis and offline programming, providing strong technical support for the product service process; by using the principle of ergonomics, joint points are set and motors are configured to realize multi-angle transformation of the bed body, etc., and it has an AI sleep monitoring function. Through monitoring the sleep state, it realizes linkage with other smart home devices, thus realizing automated production and automated detection, reducing human interference, and avoiding abnormal problems such as "excessive radiation, inaccurate sleep detection, malfunction or inaccuracy of adjustment functions, poor support / breathability and environmental protection, limited massage function effect, and immature snoring intervention technology" of intelligent mattresses, improving production efficiency and reducing production costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or exemplary technical descriptions. The following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0017] Figure 1 It is a schematic diagram of the system module of the present invention;

[0018] Figure 2 It is a schematic diagram of the information acquisition module of the present invention;

[0019] Figure 3 It is a schematic diagram of the model construction module of the present invention;

[0020] Figure 4 It is a schematic diagram of the model training module of the present invention;

[0021] Figure 5Schematic diagram of the model evaluation module of the present invention;

[0022] Figure 6 Schematic diagram of the parameter determination module of the present invention;

[0023] Figure 7 Schematic diagram of the production application module of the present invention;

[0024] Figure 8 Schematic diagram of the method process control program of the present invention;

[0025] Figure 9 Schematic diagram of the program of step S10 in the method process of the present invention;

[0026] Figure 10 Schematic diagram of the program of step S20 in the method process of the present invention;

[0027] Figure 11 Schematic diagram of the program of step S30 in the method process of the present invention;

[0028] Figure 12 Schematic diagram of the program of step S40 in the method process of the present invention;

[0029] Figure 13 Schematic diagram of the program of step S50 in the method process of the present invention;

[0030] Figure 14 Schematic diagram of the program of step S60 in the method process of the present invention. Detailed implementation manners

[0031] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0032] The following describes the specific implementation of the present invention in detail with reference to specific embodiments:

[0033] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application. It should be noted that when a module is referred to as being "disposed on" another module, it can be directly on the other module or indirectly on the other module. When a module is referred to as being "connected to" another module, it can be directly connected to the other module or indirectly connected to the other module.

[0034] In the description of this application, "a plurality of" means two or more, unless otherwise specifically defined. "Several" means one or more, unless otherwise specifically defined.

[0035] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "connected" and "coupled" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components or the interaction relationship between two components. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific situations. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0036] Please refer to Figure 1 As shown, the present invention provides a method for manufacturing a multi-functional intelligent mattress, which is applied to a control system for manufacturing a multi-functional intelligent mattress. The system includes an information acquisition module, a model construction module, a model training module, a model evaluation module, a parameter determination module, a production application module, a wireless communication module, a memory, an alarm, a processing center, and an intelligent mobile terminal; the information acquisition module, the model construction module, the model training module, the model evaluation module, the parameter determination module, the production application module, the wireless communication module, the memory, and the alarm are respectively connected to the processing center; the intelligent mobile terminal includes a smart phone, a tablet computer, and a smart remote control, and is wirelessly connected to the wireless communication module within the range of a wireless network or the Internet.

[0037] The wireless communication module is provided with a wireless network unit, which is responsible for the transceiver of wireless signals and automatically forms a network connection with the intelligent mobile terminal within an effective network range. The wireless signals include various Internet of Things signals such as MQTT, CoAP, HTTP, REST API, Zigbee, LoRaWAN, NB-IoT, and Bluetooth.

[0038] The alarm compares the actual evaluation score of the model with the model evaluation score standard stored in the memory. If it does not meet the standard, it will automatically emit an audible alarm and notify to continue training; and compares the quality information of the intelligent mattress with the intelligent mattress production quality standard stored in the memory. If it does not meet the standard, it will automatically emit an audible alarm and notify to adjust the parameters and rework; and compares the quality information of the intelligent mattress with the intelligent mattress production quality standard stored in the memory. If it does not meet the standard, it will automatically emit an audible alarm and notify to rework again.

[0039] The memory is responsible for storing information of the information acquisition module, model construction module, model training module, model evaluation module, parameter determination module, production application module, wireless communication module, and alarm, as well as storing the model evaluation sub-criteria and the intelligent mattress production quality standard.

[0040] The processing center is responsible for information transfer among the information acquisition module, model construction module, model training module, model evaluation module, parameter determination module, production application module, wireless communication module, alarm, and memory. It is the hub center of the system and compares the actual model evaluation score with the model evaluation sub-criteria stored in the memory: if it meets the standard, it is the predetermined intelligent mattress production process parameter; if it does not meet the standard, it is passed to the alarm and notifies to continue training. It also compares the quality information of the intelligent mattress with the intelligent mattress production quality standard stored in the memory: if it meets the standard, it is set as the formal production process parameter; if it does not meet the standard, it is passed to the alarm and notifies to adjust the parameters and rework. It further compares the quality information of the intelligent mattress with the intelligent mattress production quality standard stored in the memory: if it meets the standard, it notifies that it can be packaged; if it does not meet the standard, it is passed to the alarm and notifies to rework again.

[0041] Please refer to Figure 2 As shown, the information acquisition module includes a data acquisition unit, a data cleaning unit, a data augmentation unit, an integration data unit, a conversion data unit, a filtering and denoising unit, a grayscale conversion unit, and a feature extraction unit. It is responsible for acquiring the normal and abnormal historical image data of the intelligent mattress production quality and performing preprocessing, and then passing it to the model construction module.

[0042] Furthermore, the data acquisition unit obtains the historical data of various quality data, user data, and its production process parameters of similar intelligent mattresses by connecting to the industry database and passes it to the data cleaning unit; the data cleaning unit cleans the acquired historical data to remove outliers, duplicate values, or missing values in the data and passes it to the data augmentation unit; the data augmentation unit increases the quantity and diversity of the intelligent mattress training data through data augmentation methods such as rotation, scaling, flipping, cropping, and color transformation and passes it to the integration data unit; the integration data unit obtains the standardized intelligent mattress data according to the data standardization processing formula "z=(x - μ) / σ" and passes it to the conversion data unit; the conversion data unit obtains the normalized intelligent mattress data according to the normalization calculation formula "x'=(x - min(x)) / (max(x) - min(x))" and passes it to the filtering and denoising unit; the filtering and denoising unit is based on the Gaussian filtering method calculation formula Obtain the denoised intelligent mattress image and transfer it to the grayscale conversion unit; the grayscale conversion unit obtains the grayscale intelligent mattress image according to the grayscale calculation formula "f(i,j) = max(R(I,j), G(I,j), B(i,j))" and transfers it to the feature extraction unit; the feature extraction unit converts the labeled data into feature vectors useful for model training and extracts key features such as shape features, color features, and intelligent element identifiers to improve the training speed and performance of the model.

[0043] Please refer to Figure 3 As shown, the model construction module includes a network layer unit, a network parameter unit, a hierarchical optimization unit, and a data partitioning unit, which are responsible for constructing the model by determining the model architecture, designing the network layer structure, adding auxiliary layers, and defining model parameters according to the extracted feature information, and transferring it to the model training module.

[0044] Furthermore, the network layer unit customizes and optimizes the network layer structure according to the selected convolutional neural network as the model architecture and based on specific application scenarios and requirements, and transfers it to the network parameter unit; the network parameter unit adjusts the number of network layers, the size of the convolutional kernel, the stride, the padding method, and selects the loss function and optimization algorithm according to the network layer structure, and transfers it to the hierarchical optimization unit; the hierarchical optimization unit adjusts the size of the input data and performs normalization processing by adding zero-padding layers and normalization layers before and after the convolutional layer respectively, and transfers it to the data partitioning unit; the data partitioning unit divides the dataset with key feature vectors after extraction into a training set, a validation set, and a test set and establishes a convolutional neural network structure for subsequent model training.

[0045] Please refer to Figure 4 As shown, the model training module includes an input padding unit, a convolutional input unit, a pooling conversion unit, a fully connected layer unit, a normalized output unit, an output conversion unit, and a backpropagation unit, which are responsible for training the model according to the collected data, adjusting the model parameters, optimizing the model performance to the predetermined intelligent mattress production process parameters, and transferring it to the model evaluation module.

[0046] Furthermore, the input padding unit obtains padding data according to the data padding size calculation formula "Ph = [(Ho - 1) * Sh + Kh - Hi] / 2, Pw = [(Wo - 1) * Sw + Kw - Wi] / 2", inputs it, and passes it to the convolution input unit; the convolution input unit obtains the convolution input value according to the convolution input calculation formula "z(t) = ∫x(m)y(t - m)dm", activates the function input, and passes it to the pooling conversion unit; the pooling conversion unit obtains the maximum pixel value after pooling according to the max pooling calculation formula "Z(I,j) = max(X[i*Ps(i + 1)*Ps,j*Ps(j + 1)*Ps])" and enters the fully connected layer, and passes it to the fully connected layer unit; the fully connected layer unit obtains the output data of the connection layer according to the fully connected layer calculation formula "y = f(∑(Wn*Xn) + b)", enters the output layer, and passes it to the normalization output unit; the normalization output unit obtains the output of Batch Norm according to the Batch Norm layer calculation formula "h = φ(Bn(Wx + b))", and passes it to the output conversion unit; the output conversion unit obtains the size of the output value after convolution according to the output layer conversion calculation formula "N = (P - F + 2C) / S + 1", and passes it to the backpropagation unit; the backpropagation unit obtains the loss function value according to the loss function calculation formula "L = max(0, m + y*(f(x) - b))" and performs backpropagation to optimize the performance of the network model.

[0047] Please refer to Figure 5 As shown, the S model evaluation module includes a classification marking unit, a learning and training unit, and a model evaluation unit, which are responsible for validating and evaluating the model according to the trained model, adjusting and optimizing the model according to the verification results, and passing it to the parameter determination module.

[0048] Furthermore, the classification marking unit divides the quality anomaly categories of the intelligent mattress into corresponding data sample categories for marking, and passes it to the learning and training unit; the learning and training unit determines the training model according to the gradient descent data, inputs the data in the training set into the model for simulation training under different environmental conditions, and passes it to the model evaluation unit; the model evaluation unit obtains the comprehensive F evaluation score according to the model evaluation score calculation formula "F = 2(Ac*Re) / (Ac + Re)", and passes it to the processing center.

[0049] Please refer to Figure 6 As shown, the parameter determination module includes a hardness adjustment unit, a temperature adjustment unit, a comfort index unit, a breathability index unit, a trial debugging unit, and an anomaly recognition unit, which are responsible for obtaining the optimal production process parameters of the intelligent mattress through production tests according to the production process parameters predicted by the trained model, and passing them to the production application module.

[0050] Further, the hardness adjustment unit obtains the hardness to be adjusted for the smart mattress according to the mattress hardness adjustment calculation formula "Ho = Hi + K * (H max - H min )" and transmits it to the temperature adjustment unit; the temperature adjustment unit obtains the temperature to be adjusted for the smart mattress according to the mattress temperature adjustment calculation formula "To = Ti + K * (T max - T min )" and transmits it to the comfort index unit; the comfort index unit obtains the comfort index of the mattress according to the mattress comfort index calculation formula "Di = We * Se + Wh * Sh + Ws * Sp" and transmits it to the air permeability index unit; the air permeability index unit obtains the air permeability rate of the mattress according to the mattress air permeability rate calculation formula "K = Q / (ΔP * A)" and transmits it to the trial debugging unit; the trial debugging unit conducts trial production and inspection of the smart mattress through the mattress production inspection equipment according to the operation command and the predetermined smart mattress production process parameters to obtain quality information and transmits it to the processing center; the anomaly recognition unit matches the real-time obtained smart mattress production inspection image with the corresponding image in the trained convolutional neural network model and confirms its anomaly category for subsequent production improvement and parameter adjustment.

[0051] Please refer to Figure 7 As shown, the production application module includes a function design unit, a structure manufacturing unit, a system configuration unit, an appearance inspection unit, a function testing unit, a safety testing unit, and a durability testing unit, which are responsible for producing and conducting various inspections on the smart mattress according to the set production process parameters through the mattress production inspection equipment according to the program instructions to ensure that the smart mattress meets the quality requirements.

[0052] Furthermore, the functional design unit designs by obtaining various user data through sensors according to user order information and matching process parameters with the model, and transmits them to the structure manufacturing unit; the structure manufacturing unit manufactures the basic structure of the mattress through the mattress automatic production line according to the control command and the predetermined production process parameters, including quilting layer, bottoming, buttoning cloth and filling, and transmits it to the system configuration unit; the system configuration unit configures the control system with complete functions for the mattress according to the user information and the matched intelligent function parameters, and transmits it to the appearance detection unit; the appearance detection unit obtains the quality information of the appearance and dimensional deviation of the intelligent mattress through a high-definition camera and a coordinate measuring machine respectively according to the control command and the predetermined operation parameters, and transmits it to the function testing unit; the function testing unit obtains various functional test data such as temperature control, massage function, sleep monitoring, softness and hardness, air permeability, compressive strength, edge support force, etc. of the mattress through function testing equipment, and transmits it to the safety testing unit; the safety testing unit obtains various safety test data such as electrical safety, material safety, fire safety, harmful substance content, flame retardancy, etc. of the intelligent mattress through the mattress safety testing equipment, and transmits it to the durability testing unit; the durability testing unit obtains various aging test data such as durability test, temperature test, humidity test, etc. of the intelligent mattress through the aging test equipment according to the operation command and the predetermined operation parameters, and transmits it to the processing center.

[0053] System operation principle:

[0054] Before production, the information acquisition module acquires the historical image data of normal and abnormal production quality of the intelligent mattress and performs preprocessing for subsequent model construction, and transmits it to the model construction module; the model construction module constructs the model by determining the model architecture, designing the network hierarchical structure, adding auxiliary layers, and defining model parameters according to the extracted feature information for subsequent model training and verification, and transmits it to the model training module; then the model training module trains the model according to the collected data and adjusts the model parameters to optimize the model performance with the predetermined production process parameters of the intelligent mattress to ensure the quality stability of the intelligent mattress, and transmits it to the model evaluation module; then the model evaluation module verifies and evaluates the model according to the trained model, and adjusts and optimizes the model according to the verification results to improve the performance and accuracy of the model, and transmits it to the parameter determination module; the parameter determination module obtains the optimal production process parameters of the intelligent mattress through production tests in different situations according to the production process parameters predicted by the trained model to ensure the subsequent production quality, and transmits it to the production application module; then the production application module produces and conducts various detections on the intelligent mattress according to the set production process parameters for the intelligent mattress production detection equipment respectively according to the program instructions to ensure that the intelligent mattress meets the quality requirements.

[0055] When the operator or manager is outdoors or in a different location, they can use a smart mobile terminal to automatically form a network connection with the wireless communication module within a wireless network or the Internet, integrating with smart mobile terminals, the Internet, and Internet of Things technologies. Through the APP software on the smart mobile terminal or remote control software on a computer, they can perform close-range or remote control to produce smart mattresses under normal conditions to meet user quality requirements. Managers can remotely control and monitor the production and inspection of smart mattresses, view daily operating conditions, data changes, equipment activity logs, etc. By using the pre-deployed code or adding a deployment code, they can achieve remote connection and control of smart mattress production. They can view the remote production and inspection of smart mattresses in real time through both the smart mobile terminal and the computer, improving production efficiency and reducing production costs.

[0056] Please refer to Figure 8 As shown, a method for manufacturing a multifunctional smart mattress provided by the present invention includes the following steps:

[0057] S10. Before production, the information acquisition module acquires historical image data of normal and abnormal production quality of the smart mattress and performs preprocessing for subsequent model construction, and transmits it to the model construction module;

[0058] Please refer to Figure 9 As shown, the step S10 includes the following steps:

[0059] S11. The data acquisition unit obtains historical data of various quality data, user data, and production process parameters of similar smart mattresses by connecting to an industry database for subsequent data cleaning, and transmits it to the data cleaning unit;

[0060] Furthermore, various production process parameters of smart mattresses are collected from domestic and foreign smart mattress databases through a data collector, as well as the quality information of corresponding smart mattress images or videos and data on the usage effects of different users, and classified and aggregated; the smart mattress quality data includes, but is not limited to, historical data on the usage effect evaluations of different users for different such smart mattresses, and also includes normal and abnormal quality information of similar smart mattresses obtained from third-party shared data platforms such as the Internet, social media, professional testing institutions, various trade platforms, and public databases through legal means such as web crawling, sensor collection, manual annotation, dataset purchase, and crowdsourcing, as well as historical data on the usage habits, needs, and usage effects of different users, in order to obtain high-quality, diverse, and rich historical data of similar smart mattresses, specifically including historical data on quality information such as raw materials, performance parameters, process parameters, and test data of smart mattresses.

[0061] S12. The data cleaning unit cleans the collected historical data to remove outliers, duplicate values or missing values in the data, so as to improve the quality and accuracy of the data, and transmits it to the enhanced data unit;

[0062] Further explanation, due to sensor failures, recording errors or system anomalies in the production and detection of smart mattresses, outliers appear, which affect the accuracy of subsequent analysis; missing value processing is performed on the data with missing parts; each feature in the dataset is detected by writing code to determine missing values, and the missing value patterns are identified. According to the number and impact of missing values, code is written to select to fill or delete samples or variables containing missing values. For time series data, forward filling or backward filling is used to fill in the missing values; the processing effect is verified by comparing indicators such as data quality, model accuracy and reliability before and after processing. If the processing effect is not good, reselect the processing method or re-clean the data until the best effect is achieved, so as to remove duplicate, incorrect and invalid data to effectively process missing values for subsequent model construction and analysis; the mattress detection data includes comfort, material and quality, noise level, durability and maintenance, user evaluation, smart functions (smart adjustment, health monitoring, massage, etc.), and various performance data such as the thickness, air permeability and moisture discharge performance, and anti-mite and antibacterial properties of the mattress.

[0063] S13. The enhanced data unit increases the quantity and diversity of smart mattress training data through data augmentation methods such as rotation, scaling, flipping, cropping, and color transformation, so as to improve the generalization ability of the model, and transmits it to the integrated data unit;

[0064] Further explanation, when the cleaned smart mattress image data is rotated by a certain angle through the rotation of smart mattress image data, multiple pixels will correspond to the same pixel after rotation, resulting in the loss of pixels in the rotated smart mattress image data. Therefore, a mapping is constructed using reverse thinking to map the pixel coordinates after rotation to the pixel coordinates of the original smart mattress image data, so as to ensure that each pixel after rotation has a pixel value; the neighborhood interpolation algorithm is used to copy each original pixel in the rotated smart mattress data unchanged to the corresponding four pixels after expansion, retaining all the information of the original smart mattress image data; the smart mattress image data with abnormal orientation after scaling is flipped 180 degrees around the central axis or symmetry axis of the original image to ensure the orientation consistency of the smart mattress data; the flipped smart mattress image data is cropped to ensure the integrity and clarity of the image.

[0065] S14. The integrated data unit obtains the standardized smart mattress data according to the data standardization processing formula "z=(x - μ) / σ, where z is the standardized data, x is the original data, μ is the mean of the data, and σ is the standard deviation of the data", so as to improve the stability of the model, and transmits it to the conversion data unit;

[0066] Further explanation, the original data of the intelligent mattress collected is calibrated, including time synchronization, unit conversion, range adjustment, etc. For example, ensure that all timestamps are in a unified format and synchronized with the system clock; convert the data collected by different sensors, detection devices, etc. to the same unit to ensure the accuracy of the data; use the above data standardization processing formula "z=(x - μ) / σ" through the written code to convert data from different sources such as dates, values, texts, etc. into a standard normal distribution with a mean of 0 and a standard deviation of 1, subtract the mean and divide by the standard deviation to make it in a unified standard format to ensure the consistency and comparability of the data for subsequent processing; encode unstructured data to convert it into structured data, or convert text data into numerical representations for easy model processing and analysis, so as to process the original data into a form that meets specific standards for subsequent model training and analysis.

[0067] S15. The data conversion unit obtains the normalized intelligent mattress data according to the normalization calculation formula "x'=(x - min(x)) / (max(x)-min(x)), where x' is the normalized data, x is the original data, and min(x) and max(x) are the minimum and maximum values of the data respectively" to improve the model performance and transfer it to the filtering and denoising unit;

[0068] Further explanation, through the written code, the above normalization calculation formula "x'=(x - min(x)) / (max(x)-min(x))" is used to scale and map the cleaned data to the specified range of [0,1] in proportion, convert the data into a unified format or range for data normalization, and perform data discretization such as converting continuous features into discrete features to transform the data, so as to eliminate the total difference between different samples or features and the dimensionality impact between data, make the distribution of the data consistent, and confirm whether the data has been normalized to the specified range or distribution as expected, and verify the normalization effect through statistical descriptions such as maximum and minimum values; the data includes various types such as texts, pictures, audios, videos, etc. to eliminate the dimensionality differences between different data, thereby improving the accuracy and efficiency of data analysis to better adapt to subsequent analysis and processing.

[0069] S16. The filtering and denoising unit obtains the denoised intelligent mattress image according to the Gaussian filtering method calculation formula where G(x,y) is the pixel of the two-dimensional Gaussian function, (x,y) is the pixel coordinate, and σ is the standard deviation" for grayscale image conversion and transfer it to the grayscale conversion unit;

[0070] Further explanation: The Gaussian filter output pixel value obtained according to the Gaussian filter calculation formula is the weighted average of the input pixel values within its neighborhood, and the weights are given by the Gaussian function. Among them, the standard deviation σ determines the width of the Gaussian function, and the Gaussian function is discretized, that is, the weights are calculated within a certain window size, and then these weights are applied to the corresponding neighborhood pixel values of the input image to obtain the output pixel value. The pixels are arranged in ascending order according to the gray value, and the median value is taken as the new gray value; check the sampling values in the input signal to determine whether they represent the signal itself. By using an observation window composed of an odd number of samplings, the values within the window are sorted, the median value is taken as the output, the earliest value is discarded, a new sampling is obtained, and the above calculation process is repeated to reduce the random noise in the image and make the image smoother.

[0071] S17. The grayscale conversion unit obtains the grayscale intelligent mattress image according to the grayscale calculation formula "f(I,j) = max(R(I,j), G(I,j), B(I,j)), where f(I,j) is the image after grayscale, and R(I,j), G(I,j), and B(I,j) are the original images of the three colors" for subsequent feature extraction and transmits it to the feature extraction unit;

[0072] Further explanation: The grayscale intelligent mattress image is obtained through the grayscale calculation formula. Check the sampling values in the input signal to determine whether they represent the signal itself. By using an observation window composed of an odd number of samplings, the values within the window are sorted, the median value is taken as the output, the earliest value is discarded, a new sampling is obtained, and the above calculation process is repeated to remove the noise in the intelligent mattress image or other signals for subsequent extraction of the key features of the intelligent mattress image, including information such as shape features, color features, and intelligent element identifiers, as well as appearance quality information such as packaging appearance, anti-counterfeiting marks, fonts, and patterns; then the standardized data is classified through the written code, and the classified data is automatically labeled to add accurate labels or annotations to the data, which are used as the target variables or features during subsequent model training, and used as the training set and validation set to ensure that the model has accurate data reference during the training process, enabling it to learn how to generate corresponding labels according to the data features to improve the labeling efficiency and accuracy; for some data, the user needs to remotely add new labels or modify the existing labels through the mobile phone to enter the system to ensure that they accurately reflect the essential features of the data. The labeled data is deployed to the corresponding system platform for subsequent application or analysis to improve the accuracy and reliability of the labels, facilitate the extraction of key features in the subsequent data, and be more conducive to model training, testing, and verification.

[0073] S18. The feature extraction unit converts the labeled data into feature vectors useful for model training and extracts the key features of shape features, color features, and intelligent element identifiers to improve the training speed and performance of the model.

[0074] It is further explained that the most representative features and the most useful features for the model that can reflect the essential content of the data and have the degree of distinction and description are selected from the pre-processed smart mattress data to reduce the dimension of the features, reduce the computational complexity, and at the same time improve the performance and generalization ability of the model; after feature extraction, principal component analysis is used to perform feature dimensionality reduction to obtain a large amount of feature information in order to reduce the dimension of the features and reduce the computational complexity; after feature dimensionality reduction, the features are binary encoded to improve the interpretability of the features and the performance of the model; since some information of the original data may be lost after feature extraction and dimensionality reduction, feature reconstruction such as principal component reconstruction or least squares reconstruction is performed to restore the data information as much as possible; evaluation is performed through cross-validation, and the feature extraction method and parameters are adjusted according to the evaluation results to evaluate the quality and effect of the extracted features, improve the training speed and performance of the model, and improve the efficiency of data analysis by reducing the amount or complexity of the data while keeping the original appearance of the data as much as possible.

[0075] S20, the model building module determines the model architecture, designs the network hierarchy, adds auxiliary layers, and defines model parameters according to the extracted feature information to build the model for subsequent model training and verification, and passes it to the model training module;

[0076] See also Figure 10 As shown, the step S20 includes the following steps:

[0077] S21, the network level unit uses the selected convolutional neural network as the model architecture and customizes and optimizes the network level structure according to the specific application scenarios and requirements for subsequent defect detection and quality identification, and passes it to the network parameter unit;

[0078] Further explanation: Since the convolutional neural network (CNN) is a type of deep neural network, which is particularly suitable for processing data with a grid topology structure, it can automatically learn and extract useful features such as edges, lines, corners, and more complex combined features from images in the production of intelligent mattresses for subsequent defect detection, quality classification, etc. Since the basic structure of the CNN consists of an input layer, a convolutional layer, an activation function layer, a pooling layer, a fully connected layer, and an output layer, these layers can work together in the CNN model for intelligent mattress production to extract and process image features, including: the input layer can receive image data of the intelligent mattress as input; the convolutional layer sets multiple convolutional layers, each containing multiple convolutional kernels, which can extract local features in the image. As the network structure deepens, it gradually becomes more abstract from the appearance; adding a ReLU activation function layer after the convolutional layer can introduce non-linear factors and enhance the expressive ability of the model; adding a pooling layer after the convolutional layer can reduce the dimension of the feature map, reduce the amount of computation, and at the same time maintain the spatial invariance of important features; adding a fully connected layer at the end of the network is used to convert the feature maps output by the convolutional layer and the pooling layer into classification results, that is, the category or quality level of the intelligent mattress.

[0079] S22. The network parameter unit adjusts the number of network layers, the size of the convolutional kernel, the stride, the padding method, and selects the loss function and optimization algorithm according to the network hierarchy structure to ensure the performance and accuracy of the model, and transfers them to the hierarchical optimization unit;

[0080] Further explanation: Defining model parameters according to the network hierarchy design, including the size of the convolutional kernel, the stride, the padding method, the activation function, etc., as well as the pooling method of the pooling layer, the size of the pooling window, etc., and the number of neurons in the fully connected layer and other hierarchical parameters directly affect the performance and accuracy of the model; then set hyperparameters related to model training such as the size of the input image, the number of label types, the total number of training cycles, the batch size, etc., and adjust them according to the specific dataset and task requirements; select optimization algorithms such as SGD, Adam, etc., and set corresponding parameters such as the learning rate and momentum, which directly affect the training effect and convergence speed of the model to ensure that the model can accurately extract features from images and perform effective classification or prediction.

[0081] S23. The hierarchical optimization unit adjusts the size of the input data and performs normalization processing by adding a zero-padding layer and a normalization layer before and after the convolutional layer respectively to improve the training speed and stability of the model, and transfers them to the data partitioning unit;

[0082] Furthermore, by setting a zero-padding layer to perform zero-padding on the edges of the input image before the convolution operation, the size of the input data is adjusted to facilitate the convolution operation, maintain the image edge information, ensure that the convolution kernel can be correctly applied to the image boundary, and at the same time help to maintain the image edge information and avoid information loss during the convolution process; zero-padding can more effectively process input images of different sizes without complex preprocessing, help control the size of the feature map output by the convolution layer, make the network design more flexible and controllable, ensure that the network can adapt to the changes of intelligent mattresses of different sizes and resolutions, and accurately extract and process image features; normalize the distribution of the input data to improve the training speed and stability of the model, accelerate the training process of the neural network and improve the convergence speed, and at the same time enhance the stability of the model. Normalize the input of the activation function before the activation function of each layer of the network. Calculate the mean and variance of this batch for each small batch of data, and then perform batch normalization on the linear calculation result, that is, subtract the mean and divide by the standard deviation to ensure that the calculation result conforms to the standard normal distribution with a mean of 0 and a variance of 1. Then perform translation and scaling operations to adapt to different data distribution requirements, keep the input of the middle layer of the network relatively stable, help solve the problem of gradient disappearance or gradient explosion during the training process, thereby accelerating the training and enhancing the stability of the model, and can improve the robustness of the model to the weight initialization method, reduce the trouble brought by the weight initialization selection, and improve the generalization ability and training efficiency of the model.

[0083] S24. The data partitioning unit partitions the dataset with key feature vectors after extraction into a training set, a validation set, and a test set and constructs a convolutional neural network structure for subsequent model training.

[0084] Furthermore, according to the preselected segmentation strategy, determine the proportions of the training set, validation set, and test set, and ensure that the data distributions among the subsets are as consistent as possible to avoid introducing biases. In some application scenarios, due to the time-series characteristics of the data, write code to divide the dataset into a training set for training the model, a validation set for adjusting model parameters and selecting the best model, and a test set for evaluating the final performance of the model according to the time series to ensure the temporal consistency between the training and test sets. Establish a training set and a test set required for training the prediction model for abnormal quality recognition of intelligent mattresses in different environments in a 9:1 relationship through a convolutional neural network deep learning approach for the dataset, thereby establishing a deep convolutional neural network structure: 3 convolutional layers, 3 max-pooling layers, 2 fully connected layers, 1 softmax layer, and 1 output layer. Add zero-padding layers and normalization layers when necessary. Since the convolutional kernels in the convolutional layers contain weight coefficients while the pooling layers do not, the pooling layers are not independent layers. The convolutional layers are used to extract local features of the image, the pooling layers are used to reduce the dimension of the feature maps, and the fully connected layers are used to integrate features and perform classification.

[0085] S30. The model training module trains the model based on the collected data, adjusts the model parameters to optimize the model performance for the predetermined intelligent mattress production process parameters, ensures the quality stability of the intelligent mattress, and transfers it to the model evaluation module;

[0086] Please refer to Figure 11 As shown, the step S30 includes the following steps:

[0087] S31. The input padding unit obtains padding data according to the mattress data padding size calculation formula "Ph = [(Ho - 1) * Sh + Kh - Hi] / 2, Pw = [(Wo - 1) * Sw + Kw - Wi] / 2, where Ph and Pw are the padding sizes in the height / width directions respectively, Hi and Wi are the heights / widths of the input feature maps respectively, Kh and Kw are the heights / widths of the convolutional kernels respectively, Sh and Sw are the values of the strides in the height / width directions respectively, and Ho and Wo are the heights and widths of the output feature maps respectively", inputs the data, and transfers it to the convolutional input unit;

[0088] Further explanation: After normalizing the image, the intelligent mattress data first enters the input layer. The padding data is obtained through the above-mentioned padding size calculation formula and enters the zero-padding layer, which pads zeros to the edges of the input data of the convolutional layer to adjust the size of the input data for convolution operations, so as to maintain the same spatial dimension of the input and output, thereby preventing the loss of image edge information and enabling the spatial dimension of the input data to remain unchanged during subsequent convolution operations, so as to preserve the image edge information and the processing of subsequent layers; the number of padding is jointly determined by the size of the convolutional kernel, the stride, and the padding size. In order to keep the height and width of the input and output images the same, or to reduce the rapid reduction of the size during consecutive convolution operations, the number is usually set to the convolutional kernel size minus; the height Hi / width Wi of the input feature map, the height Kh / width Kw of the convolutional kernel, the stride values Sh / Sw in the height / width direction, and the height Ho / width Wo of the output feature map are all obtained through the model design parameters.

[0089] S32. The convolution input unit obtains the convolution input value according to the convolution input calculation formula "z(t) = ∫x(m)y(t - m)dm, where z(t) is the output function, x(t) is the input function, y(t) is the convolution kernel function, and dm is the integral microelement of the variable m", activates the function input, and transmits it to the pooling conversion unit;

[0090] Further explanation: The "width" or "increment" of the integral microelement dm when integrating each infinitesimal interval of the variable m is used to obtain the cumulative effect z(t) over the entire domain by accumulating the function values (i.e., x(m)y(t - m)) on these infinitesimal intervals. dm is the integral microelement of the variable m, that is, the infinitesimal quantity in the integration process; and the convolution value is obtained through convolution calculation and enters the convolutional layer, and the activation function value is obtained through the ReLU function calculation formula "f(x) = max(0, x + Y)" and enters the activation function layer. In the formula, f(x) is the activated function, x is the eigenvalue output by the convolutional layer or the fully connected layer, and Y is a random variable. When the input x is greater than 0, x is output; when the input x is less than or equal to 0, 0 is output; when x = 0, it is non-differentiable, that is, when the input is positive, the original value is maintained, and when the input is negative, 0 is output; however, the ReLU activation function is used after the convolutional layer to increase the non-linearity of the network and promote the model to learn complex patterns.

[0091] S33. The pooling conversion unit obtains the maximum pixel value after pooling according to the maximum pooling calculation formula "Z(I,j) = max(X[i*Ps(i+1)*Ps,j*Ps(j+1)*Ps]), where Z(I,j) is a pixel value in the output feature map after pooling, i and j are the positions in the output feature map respectively, max is to obtain the maximum value among all pixel values in the input window, X is the input feature map, and Ps is the window size of the pooling operation", and enters the fully connected layer to retain important feature information and transmit it to the fully connected layer unit;

[0092] Further explanation, by calculating the average value of all values in each region according to the maximum pooling calculation formula as the output, more information in the feature map can be retained, which helps to improve the accuracy of the model, retains more detailed information, and is used in the deeper layers of the network to ensure the integrity of information; before the maximum pooling, the maximum pixel value after average pooling is obtained according to the average pooling calculation formula "Z(I,j) = mean(X[i*Ps(i+1)*Ps,j*Ps(j+1)*Ps])", where Z(i,j) is a pixel value in the output feature map after pooling, mean is to obtain the average value among all pixel values in the input window, and according to this formula, the maximum value is selected from each region of the input feature map as the output, retaining the most significant features in the feature map, reducing the size of the feature map, and losing some useful information. Since the maximum value of each region is concerned, the grain size feature is retained, and features with better classification recognition are selected.

[0093] S34. The fully connected layer unit obtains the output data of the connection layer according to the fully connected layer calculation formula "y = f(∑(Wn*Xn)+b)", where y is the output result, f is the activation function, Wn is the weight of the nth input feature, Xn is the n input features, n is the dimension of the input features, and b is the bias, and enters the output layer for subsequent output calculation and transmits it to the normalized output unit;

[0094] Further explanation, the data after pooling is calculated by the fully connected layer according to the fully connected layer calculation formula "y = f(∑(Wn*Xn)+b)" to obtain the output value after convolution. In the formula, y is the output result, f is the activation function, Wn is the weight of the nth input feature, Xn is the n input features, n is the dimension of the input features, and b is the bias; the "y = f(∑(Wn*Xn)+b)" is deduced from "y = f(W*X+b)" to "y = f(W1*X1+W2*X2+…+Wn*Xn+b)" and transformed. In the formula, W is the weight and Xn is the input feature; through the fully connected layer, the features extracted by the convolutional layer and the pooling layer are integrated and classified, so that each neuron is connected to all neurons in the previous layer, and the output is generated through weighted summation and non-linear activation function.

[0095] S35. The normalization output unit obtains the output of Batch Norm according to the Batch Norm layer calculation formula "h = φ(Bn(Wx + b)), where h is the output of the fully connected layer, φ is the activation function, Bn is the operator for batch normalization, W is the weight parameter, X is the input of the fully connected layer, and b is the bias parameter", and passes it to the output conversion unit;

[0096] Further explanation: The formula "h = φ(Bn(Wx + b))" is derived from "Bn(x) = γ⊙[(X - μb) / σb] + β", where μb is the mean, σb is the standard deviation, γ is the stretching parameter, β is the offset parameter, and (X - μb) / σb is the standardized normal distribution. The Batch Norm layer (abbreviated as "BN layer") is placed between the affine transformation and the activation function in the fully connected layer, normalizes the output values of each layer in the network, making them more compliant with the normal distribution, which can accelerate the training speed of the neural network, help prevent gradient vanishing and gradient explosion. The BN layer reduces the correlation between input data by normalizing the data of each mini-batch, making the mean of each sample 0 and the variance 1, thereby reducing the problem of internal covariate shift, helping to accelerate the training process, improve the stability and generalization ability of the model, and avoid the problem of reducing the representation ability of the neural network.

[0097] S36. The output conversion unit obtains the size of the output value after convolution according to the output layer conversion calculation formula "N = (P - F + 2C) / S + 1, where N is the size of the output after convolution, P is the size of the input before convolution, F is the size of the convolution kernel, C is the number of layers of adding 0 around the image, and S is the stride size", for subsequent model analysis and training, and passes it to the backpropagation unit;

[0098] Further explanation: The output size N is the size of the feature map after the convolution operation. The input size P is the width or height of the input image or feature map. The padding size PH in the height direction and the padding size PW in the width direction are respectively obtained through the above step S21. The size of the convolution kernel F is obtained through the above step S22. The number of layers C of adding 0 around the image is the number of layers of adding 0 around the input image or feature map to control the size of the output feature map, and is also obtained from the above network construction. The stride size S is the distance at which the convolution kernel slides on the input image or feature map and is obtained from the above calculation.

[0099] S37. The backpropagation unit obtains the value of the loss function according to the loss function calculation formula "L = max(0, m + y*(f(x) - b)), where L is the value of the loss function, m is the hyperparameter, y is the sample label (0 or 1), f(x) is the predicted value of the model, and b is the classification boundary", and performs backpropagation to optimize the performance of the network model.

[0100] Further explanation: In the loss function calculation formula "L = max(0, m + y * (f(x) - b))", when f(x) ≤ b, then L = m + y(f(x) - b); when f(x) > b, then L = 0. In machine learning or optimization problems, f(x) is an optimization objective, b is a threshold, and m and y are parameters. When the target value f(x) is less than or equal to the threshold b, the value of L is equal to m + y(f(x) - b); when the target value f(x) is greater than the threshold b, the value of L is 0. Use the training set data to train the model, adjust the model parameters to minimize the loss function, so that the predicted value of the positive sample is greater than a certain threshold, and the predicted value of the negative sample is less than a certain threshold. Then, obtain the convolutional output values dw[l] = dz[l] * a[l - 1], db[l] = dz[l], and da[l - 1] = W[l]T * dz[l] through the backpropagation calculation formula "dz[l] = da[l] * g[l]′(z[l])". Here, da[l] is the input data, da[1] is the output data, and g[l]′ is the derivative of the sigmoid activation function. The backpropagation of the convolutional layer transfers the error term da[l] through the convolutional operation to the previous layer, flips the convolutional kernel and applies it to the error map, calculates the local gradient through the derivative of the activation function, and is implemented through matrix operations. Deform the input and the convolutional kernel into matrices and perform matrix multiplication, that is, pull the numbers in the convolutional window into a row to form a column vector and perform matrix multiplication. The backpropagation of the fully connected layer calculates the gradient of the weight and the gradient of the bias through the chain rule. For each node, the error term is passed to the node of the previous layer through the weight matrix, and the local gradient is calculated through the derivative of the activation function, and is implemented through matrix operations. Multiply the error term by the output of the current layer and multiply by the input of the previous layer to update it in the direction of minimizing the loss function.

[0101] S40. The model evaluation module performs model verification and evaluation based on the trained model, adjusts and optimizes the model according to the verification results to improve the performance and accuracy of the model, and transmits it to the parameter determination module;

[0102] Please refer to Figure 12 As shown, the step S40 includes the following steps:

[0103] S41. The classification and marking unit classifies and marks the corresponding data sample categories according to the quality anomaly categories of the intelligent mattress for subsequent machine learning of the model, and transmits it to the learning and training unit;

[0104] Further explanation: classify according to various quality anomalies of the intelligent mattress: "excessive radiation" is category 1, "inaccurate sleep detection" is category 2, "malfunction or inaccuracy of the adjustment function" is category 3, "poor support, breathability and environmental protection" is category 4, "limited massage function effect" is category 5, "immature snoring intervention technology" is category 6; when category 1 is the positive sample, the remaining categories are negative samples, that is, the labeled data is (1, 0, 0, 0, 0, 0), when category 2 is the positive sample, the remaining categories are negative samples, that is, the labeled data is (0, 1, 0, 0, 0, 0), when category 3 is the positive sample, the remaining categories are negative samples, that is, the labeled data is (0, 0, 1, 0, 0, 0), when category 4 is the positive sample, the remaining categories are negative samples, that is, the labeled data is (0, 0, 0, 1, 0, 0), when category 5 is the positive sample, the remaining categories are negative samples, that is, the labeled data is (0, 0, 0, 0, 1, 0), when category 6 is the positive sample, the remaining categories are negative samples, that is, the labeled data is (0, 0, 0, 0, 0, 1); the above six anomaly categories are relatively typical anomaly classifications of the intelligent mattress, including but not limited to the above six categories, and one or more of the categories can also be reclassified into more categories, and more refined and in-depth classifications can be made according to the actual production and detection results. The above classifications are not fixed, and the model is retrained each time the category changes to meet the needs of subsequent production practice.

[0105] S42. The learning and training unit determines the training model according to the gradient descent data, and inputs various mattress quality data in the training set into the model for simulation training to ensure the accuracy of model recognition and transmits it to the model evaluation unit;

[0106] Further explanation: By continuously adjusting the model parameters to minimize the loss function, the prediction accuracy of the model is improved to ensure that the model can accurately identify the adaptability of the intelligent mattress in different environments; the data analysis rules are fitted by training the model with the data set in the training set, that is, various learning parameters such as the weights and biases of the model are determined; and the model parameters and hyperparameters are adjusted during the model training process by using the data set in the validation set to optimize the model performance, avoid overfitting, and select the model. However, it does not participate in the determination of the learning parameters, but selects the model parameters and hyperparameters with smaller model errors; then, after the model training is completed, the generalization ability of the model on unknown data is evaluated by using the data set in the test set, and it is used once after training to evaluate the effect of the final model. It does not participate in the learning parameter process nor the hyperparameter selection process; the mattress quality data includes raw material data, performance parameters, process parameters, inspection data, etc.; the raw material data includes the shape diagrams and processing diagrams and data of the electronic components of various intelligent mattresses, as well as user information such as the physiological data, body shape data, and sleep preference data of the user; the performance parameters include comfort, material, intelligent adjustment, zoning design, sleep monitoring, noise level, breathability, other special functions, etc.

[0107] S43. The model evaluation unit obtains the comprehensive evaluation score F according to the model evaluation score calculation formula "F = 2(Ac * Re) / (Ac + Re), where F is the evaluation score of the trained model, Ac is the precision rate, and Re is the recall rate", and transmits it to the processing center;

[0108] Further explanation: Ac and Re are respectively calculated by "Ac = (Tp + Tn) / (Tp + Fp + Fn + Tn), Re = Tp / (Tp + Fn)", where Tp is the number of true positive samples, Fp is the number of actually false positive samples, Fn is the number of false negative samples, and Tn is the number of true negative samples; after the model training is completed, tests are carried out to verify the accuracy and reliability of the model, and problems that may be found in the model during the test process are optimized and adjusted; the evaluation score of the trained model, that is, the F value, is the harmonic mean of the precision rate and the recall rate, which can evaluate the performance of the classification model. The value range is from 0 to 1, where 1 is the best performance and 0 is the worst performance. If the F value is higher, the prediction effect of the model is better, and vice versa. Therefore, if the F value is close to 1, it indicates that the model performs well when maintaining the balance between the precision rate and the recall rate; the hyperparameters are adjusted according to the performance of the model such as the learning rate and regularization coefficient to optimize the model performance.

[0109] S44. The processing center compares the actual evaluation score of the model with the model evaluation score standard stored in the memory: if it meets the standard, it is the production process parameters of the predetermined intelligent mattress; if it does not meet the standard, it is transmitted to the alarm and notifies to continue training until it meets the standard.

[0110] For further explanation, the test evaluation criteria for the intelligent mattress quality anomaly category recognition training model are best when greater than 0.8, and are specifically determined according to factors such as the educational level, technical level, work attitude, quality awareness, and physical condition of the operators, as well as the technical performance, working precision, usage efficiency, and maintenance status of the production process equipment, the performance, specifications, composition, and shape of raw materials and auxiliary materials, the rationality of process regulations, operating procedures, and working methods, and the temperature, humidity, lighting, noise, and cleanliness of the working environment; the intelligent mattress production process parameters include production inspection equipment operation parameters, intelligent mattress operation parameters, production inspection processes, etc. Among them, the production inspection equipment operation parameters: equipment control parameters such as the start and stop of the mattress automatic production line, encoder parameters, PLC control parameters, touch screen operation parameters, sensor parameters, actuator parameters, vision recognition and data acquisition, material processing parameters such as conveying speed, material size recognition and deviation correction, material compounding and positioning, unstacking type, running speed and precision, maximum load, applicable bed net range, and stability of feeding for unstacking and feeding parameters, automatic centering alignment parameters such as alignment precision, alignment speed, alignment system stability, automatic sensing of mattress width, rolling center design, and strong applicability to product diversity and combination, automatic spraying parameters such as spraying amount, spraying speed, spraying precision, intelligent recognition system, servo control system, spraying device, spraying trajectory, and spraying system stability, automatic pressing parameters such as pressing force, pressing time, pressing speed, pressing method, pressing uniformity, and pressing system stability, automatic edging parameters such as edging material size, edging speed and precision, applicable thickness range, cutting width, head working angle, table lifting form, sewing speed, drive form, stitch type, and edging system stability, automatic packaging parameters such as packaging material type, packaging speed, packaging precision, packaging efficiency, packaging size adaptability, power supply, air pressure requirements, and packaging system stability; parameters such as the sensor type and distribution, data acquisition frequency, analysis algorithm, automatic adjustment parameter range, and warning mechanism of the mattress automatic detection equipment. These process parameters are automatically matched and applied in production through the trained model to avoid the occurrence of various quality anomalies.

[0111] S50. The parameter determination module conducts production tests based on the production process parameters predicted by the trained model to obtain the optimal intelligent mattress production process parameters to ensure subsequent production quality and transmits them to the production application module;

[0112] Please refer to Figure 13 As shown, step S50 includes the following steps:

[0113] S51. The hardness adjustment unit adjusts the mattress hardness according to the mattress hardness adjustment calculation formula "Ho = Hi + K * (H max -H min ), where Ho is the mattress output hardness (kg / m 3), Hi is the input hardness of the mattress (kg / m 3 ), K is the mattress hardness adjustment coefficient, H max is the maximum hardness of the mattress (kg / m 3 ), H min is the minimum hardness of the mattress (kg / m 3 )” to obtain the hardness to be adjusted for the smart mattress for subsequent smart mattress testing and transmit it to the temperature adjustment unit;

[0114] Further explanation: The input hardness Hi of the mattress, the maximum hardness Hmax of the mattress, and the minimum hardness Hmin of the mattress are all obtained by detecting through the set hardness sensors; the mattress hardness adjustment coefficient K is the ability to adjust the mattress hardness according to personal needs, which is obtained through the accumulation of historical experience data. Specifically, it is determined by factors such as hard materials, whether there is filling, whether there is a mattress hardener, the bed board structure, and adjustable performance. The hardness of the mattress is adjusted indirectly by the following several methods, including: adding a layer of extra-hard coir, hard sponge and other hard materials on the mattress to increase the hardness of the mattress; replacing the original sponge filling with high-density foam or springs, etc., by self-replacing or adding fillers to increase the hardness of the mattress; placing a mattress hardener under the mattress to increase the overall hardness of the mattress by increasing the support points; changing the mattress base with an elastic and slatted structure to a non-elastic solid board structure to improve the hardness feeling of the mattress; setting a function with adjustable hardness to achieve personalized setting of hardness by freely combining different "magic blocks" or layers, etc., and adjusting the mattress hardness according to personal sleep habits and physical conditions.

[0115] S52. The temperature adjustment unit obtains the temperature to be adjusted for the smart mattress according to the mattress temperature adjustment calculation formula "To = Ti + K * (T max - T min ), where To is the output temperature of the mattress (°C), Ti is the input temperature of the mattress (°C), K is the mattress temperature adjustment coefficient, T max is the maximum temperature of the mattress (°C), T min is the minimum temperature of the mattress (°C)" for subsequent smart mattress testing and transmit it to the comfort index unit;

[0116] Further explanation: The input temperature Ti of the mattress, the maximum temperature T max of the mattress, and the minimum temperature T minObtained by detecting through the set temperature sensor; the mattress temperature adjustment coefficient K is a parameter of the mattress temperature adjustment function, obtained through the accumulation of historical experience data, describing the sensitivity and range of mattress temperature adjustment, determined by parameters such as the temperature range, adjustment accuracy, heating / cooling speed of the built-in temperature control system, and the intelligent adjustment of the mattress temperature is achieved through the following methods: using a mobile phone APP or other intelligent devices to control the temperature of the mattress by connecting with the built-in temperature adjustment system; correctly setting and using the temperature adjustment function; designing a customized temperature adjustment plan according to the user's temperature needs, where the temperature adjustment system is determined by various factors such as the user's temperature setting, environmental temperature, and mattress material.

[0117] S53. The comfort index unit obtains the mattress comfort index according to the mattress comfort index calculation formula "Di = We * Se + Wh * Sh + Ws * Sp, where Di is the mattress comfort index, We is the weight of the mattress environmental factor, Se is the score of the mattress environmental factor, Wh is the weight of human perception, Sh is the score of human perception, Ws is the weight of mattress preference, and Sp is the score of mattress preference" for subsequent intelligent mattress testing and transmits it to the breathability index unit; the

[0118] Furthermore, the mattress comfort index calculation formula is determined by factors such as the material, structure, softness and hardness of the mattress, personal sleep habits, physical characteristics, as well as environmental conditions, human perception, and personal preferences; the mattress comfort index Di is a quantitative index comprehensively considering the mattress comfort; the weight of the mattress environmental factor We is the degree of importance of the environmental factor in the evaluation of mattress comfort; the score of the mattress environmental factor Se is scored according to environmental conditions such as the temperature and humidity of the mattress; the weight of human perception Wh is the importance of the subjective feeling of human beings on mattress comfort in the evaluation; the score of human perception Sh is scored based on the actual experience of human beings on the softness and hardness, supportiveness, etc. of the mattress; the weight of mattress preference Ws is the degree of preference of an individual or a specific group for specific attributes of the mattress; the score of mattress preference Sp is to convert the specific preference attributes of the mattress into a quantifiable score; the weights of the mattress environmental factor We, the weight of human perception Wh, and the weight of mattress preference Ws are all determined by design parameters and historical experience data; the scores of the mattress environmental factor Se, the score of human perception Sh, and the score of mattress preference Sp are all obtained through historical experience data of user ratings.

[0119] S54. The breathability index unit calculates the breathability rate of the intelligent mattress according to the formula "K = Q / (ΔP * A), where K is the breathability rate of the mattress (m 3 / m 2 ·KPa·h), Q is the gas flow rate of the mattress (m 3 / h), ΔP is the gas permeability of the mattress through the porous material (KPa), and A is the test area area of the mattress sample (m2 )”Obtain the air permeability rate of the mattress for subsequent intelligent mattress testing and transmit it to the trial debugging unit;

[0120] Further explanation: The calculation formula of the mattress air permeability rate evaluates the air permeability performance of the intelligent mattress, provides a better sleep experience for users, represents the ease with which the solid bulk layer (i.e., the material layer) of the mattress allows gas to pass through, is an important indicator to measure the porosity of the mattress material, and is related to the comfort, health, and service life of the mattress; the mattress gas flow rate Q, the gas pressure drop of the mattress through the porous material ΔP, and the test area area A of the mattress specimen are obtained through design parameters or tests; then the total music playing time T of the mattress is calculated according to the formula "T = t * N", where T is the total music playing time of the mattress, t is the music playing time per time of the mattress, and N is the number of music playing times; and the noise level of the mattress is calculated according to the formula "Lp = 20log10(P / P0)", where Lp is the sound pressure level of the noise, P is the sound pressure, and P0 is the reference sound pressure.

[0121] S55. The trial debugging unit conducts trial production and detection of the intelligent mattress through the mattress production detection equipment according to the operation command and the predetermined intelligent mattress production process parameters to obtain quality information, ensure the accuracy of the intelligent mattress quality, and transmit it to the processing center;

[0122] Further explanation: Design and sample according to different user information to match the corresponding mattress functions and parameters, and sew various materials such as fabric, sponge, memory foam, latex, non-woven fabric, etc. together through the mattress automatic production line according to the predetermined process parameters to form the quilting layer structure of the mattress surface, bottom, and side. Then, the selected small wire springs are wrapped with materials such as non-woven fabric and cool cloth to form independent pocketed springs, or the springs are fixed with serpentine wires to form a whole network spring to form the mattress bottom layer as the mattress support; then, the selected sponge, latex, palm, cotton felt and other filling materials are sewn together and filled into the mattress to increase the comfort and support of the mattress; then install sensors and intelligent control systems, configure the development environment, write code, conduct system testing and debugging, and compare with the calculation results of the above steps S51 - S54 according to the test results and match with the model for various debugging to ensure that the performance of the intelligent mattress meets the design requirements for subsequent normal production; after the system debugging is qualified, use materials such as PE film, kraft paper, carton, tape, etc. for packaging to protect the mattress, including automatic operations such as labeling, printing product information, and encapsulation, to ensure safety during transportation.

[0123] S56. The processing center compares the quality information of the intelligent mattress with the intelligent mattress production quality standards stored in the memory: if it meets the standard, it is set as the formal production process parameters; if it does not meet the standard, it is transmitted to the alarm and the parameter adjustment and rework are notified.

[0124] Further explanation: The production quality standards for the intelligent mattress include: 1) Electrical safety: requirements in aspects such as insulation resistance, insulation strength, leakage current, and short-circuit protection. The insulation resistance between the electrical components and the shell should be greater than 1 MΩ. The equipment should be able to withstand an insulation strength test voltage of 1500 V AC without breakdown, the leakage current should be lower than 0.5 mA, and at the same time, the equipment should have a short-circuit protection function; 2) Mechanical safety: It should be able to withstand the mechanical shock and vibration specified by the industry, without causing structural damage. The design of the corners and gaps should meet the ergonomic and safety standards to avoid harm to users; 3) Comfort and support: The softness and hardness, breathability, support performance, etc. should meet the industry standards to ensure that the mattress can provide a comfortable sleep experience; 4) Material quality: The fabrics, filling materials, support layer materials, etc. used should meet the relevant safety standards and environmental protection requirements, be non-toxic, harmless, odorless, and have strict limits on the content of harmful substances such as formaldehyde and heavy metals; 5) Intelligent functions: The accuracy and reliability of intelligent control functions such as temperature adjustment, sleep monitoring, and massage functions are high. It can automatically identify the user's sleeping posture and sleep state, and actively adjust the mattress according to different sleeping postures and states to provide a personalized sleep experience; 6) Durability and stability: The service life, stability, and performance under long-term use of the mattress meet the requirements of the durability test to ensure that there is no deformation or performance degradation during long-term use; The process parameters include data such as the production process flow, production equipment control parameters, detection equipment control parameters, and intelligent mattress operation parameters.

[0125] S57. The anomaly recognition unit matches the real-time obtained intelligent mattress production detection image with the corresponding image in the trained convolutional neural network model and confirms its anomaly category for subsequent production improvement and parameter adjustment.

[0126] Furthermore, the image is input into the model, and the trained model is used to predict the new monitoring image. According to the output result, the abnormal type of the intelligent mattress is judged. If the judgment of the intelligent mattress abnormality by the model reaches a certain threshold, the warning system is triggered, and corresponding solutions are taken in a timely manner; the abnormal types of the intelligent mattress quality include: 1) Excessive radiation: The electromagnetic radiation exceeds the specified limit due to the use of sensors and electronic devices with strong radiation and improper installation, or improper use and installation of the power cord, and improper energy supply, resulting in leakage current exceeding the limit and generating radiation, which affects the human circulatory system, immunity, and metabolic functions, and even induces cancer and accelerates the proliferation of human cancer cells. Therefore, measures such as selecting low-radiation devices and using radiation-proof materials are taken for prevention; 2) Inaccurate sleep detection: Due to various factors such as environmental noise and electromagnetic interference affecting the sensor, or the low accuracy and sensitivity of the sensor, or the built-in algorithm being inaccurate or imperfect and unable to accurately identify the user's sleep stage or judge the user's sleep quality, or differences in the user's sleep habits and physiological characteristics, as well as physical conditions, age, gender, etc., or the device is not correctly installed, calibrated, or used, or the sensor is contaminated or damaged, resulting in inaccurate data collection and unable to fully reflect the user's true sleep situation. Therefore, sensors with high accuracy and sensitivity must be selected, and detection should be carried out in an environment without noise and electromagnetic interference. The built-in algorithm must be accurate and perfect to accurately obtain personal information such as the user's sleep habits and physiological characteristics. Devices such as sensors should be correctly installed, calibrated, or used, and sensors without pollution or damage should be selected; 3) Malfunction or inaccuracy of the adjustment function: Due to abnormalities in the Internet of Things system or network, the intelligent mattress cannot be normally linked with other intelligent devices in the home through Internet of Things technology, or the parameter settings for automatically adjusting the hardness, temperature, etc. during the user's sleep stage are unreasonable, resulting in frequent system failures. Therefore, the system network must be stable before testing, and the automatically adjusted parameters must be verified to be qualified before use; 4) Poor support, breathability, and environmental protection: Due to the selection of materials such as memory foam, latex, and 3D materials not meeting the standards, corresponding materials meeting support, breathability, and environmental protection must be selected; 5) Limited massage function effect: Since the massage function is achieved by the vibration of the bed board, when vibrating at a high gear, the head of the bed makes a buzzing sound, and when vibrating at a low gear, there is almost no feeling, resulting in a limited actual effect. Therefore, measures such as selecting a suitable massage mode and intensity, using airbag and vibration massage technologies, and combining intelligent temperature control and angle adjustment functions are taken to improve; 6) Immature snoring intervention technology: Due to insensitive induction monitoring, easy mis-triggering, and limited recognition and processing effects of snoring, measures such as adopting dual snoring monitoring technologies, achieving accurate monitoring and active intervention, and dynamically adjusting according to individual differences are taken to improve.

[0127] S60. The production application module produces and conducts various inspections on the smart mattress according to the set production process parameters and program instructions of the smart mattress production and inspection equipment to ensure that the smart mattress meets the quality requirements.

[0128] Please refer to Figure 14 As shown, step S60 includes the following steps:

[0129] S61. The function design unit obtains various user data through sensors according to the user order information, matches the process parameters with the model, and conducts function design to meet the user's order requirements and transmits them to the structure production unit;

[0130] Further explanation, the user data includes physiological data, body shape data, sleep preference data, and personal basic information. Among them, the physiological data includes the user's heart rate, breathing frequency and depth, body movement (such as turning over and moving during sleep), user body temperature, ambient temperature and humidity data, sleep quality (such as whether falling asleep on time, sleep depth, sleep duration, deep sleep duration, light sleep duration, etc.) and other physiological data; the body shape data includes the user's weight, body shape, spinal curve and other body shape data, which helps the intelligent mattress adjustment system according to the user's body shape characteristics; the sleep preference data includes the mattress softness and hardness, sleeping position and other sleep preferences that the user prefers. Through long-term data accumulation and analysis of the user, the mattress can gradually learn and adapt to the user's sleep habits; the personal basic information includes special information such as the user's name, gender, age, mobile phone number, physical condition, etc., to ensure the authenticity of the user's identity, for personalized recommendation or service, as well as account creation, subsequent customer service, etc., and comply with relevant laws and regulations to ensure the security and compliance of user privacy. By accurately obtaining the relevant information of the user in detail and preventing various quality anomalies that occur in daily production in advance, the corresponding intelligent mattress design is carried out, including: 1) Determining the design goal: clarifying the functions of the intelligent mattress required by the user, such as real-time monitoring of sleep status (heart rate, breathing, body movement, etc.), providing comfortable sleep support and automatic adjustment functions, having sleep data analysis and reporting functions, etc., as well as the intelligent mattress system composition of the mattress body, sensor array, control unit, communication module, actuator and power module; 2) Selecting appropriate mattress materials and structural design: The mattress body is made of high-quality memory foam, latex or springs and other materials to provide comfortable sleep support, and is covered with breathable, mite-proof and radiation-proof fabrics. In the structural design, a zoning design is adopted to adapt to the pressure requirements of different parts of the human body and improve sleep comfort; 3) Sleep monitoring and health management function design: Through the built-in sensors, the user's sleep status such as heart rate, breathing frequency, number of turnovers, number of body movements and sleeping position is monitored in real time. Through the intelligent algorithm analysis and processing of the system, a detailed sleep report is provided for the user to help the user understand their sleep quality and may provide improvement suggestions; 4) Integrating intelligent elements such as sensor array and control unit for network design: The sensor array includes pressure sensors, heart rate and breathing sensors, temperature sensors, etc., for real-time monitoring of the user's sleep status. The processing control unit is responsible for processing sensor data and automatically adjusting the softness and hardness of the mattress or triggering other intelligent functions according to the preset algorithm. The wireless communication module is used to upload sleep data to the cloud or smart home system to realize remote monitoring and data analysis; 5) Personalized adjustment and support function design: According to the user's body shape, sleeping position and body pressure distribution, data is analyzed through ergonomic modeling and AI algorithm to provide a personalized sleep support solution for the user, and the softness and hardness of the mattress are automatically adjusted to adapt to the needs and preferences of different users to ensure that the user obtains the best sleep experience;5) Comfort and entertainment function design: Automatically adjust the mattress angle according to the preset wake-up time to gently wake up the user, or raise the head of the mattress to relieve snoring problems. The mattress is flexibly designed by imitating actions such as TV viewing, yoga, and zero gravity, so that it can be adjusted into different action postures arbitrarily, enabling it to have various entertainment modes, enhancing the user's sleep and leisure experience, and at the same time protecting the user's cervical and spinal health; and so on. In this way, similar quality problems can be prevented from recurring during subsequent production and manufacturing at the design source, so as to fully meet the actual needs of target users.;

[0131] S62. The structure manufacturing unit manufactures the quilting layer, the base layer, the button cloth, and the filling through the mattress automatic production line according to the control command and the predetermined production process parameters to manufacture the basic structure of the mattress, and transfers it to the system configuration unit;

[0132] Further explanation: According to the user's requirements, the vision system completes the positioning and measurement of the incoming materials without manual intervention to ensure the precise positioning of each component; memory foam, latex, 3D materials, etc. that meet the requirements of support, breathability, and environmental protection are selected to ensure that the mattress meets the requirements of support, breathability, and environmental protection; sensors and electronic devices with low radiation and low noise, as well as various radiation-proof materials, are used to avoid excessive radiation and excessive noise, which may be harmful to the human body and affect the user's sleep; sensors with high precision and high sensitivity are used to ensure the accuracy of sleep detection, enabling the raw materials to be adaptively produced into products of different sizes by the vision system to meet the diverse market demands; then, according to the production process parameters matched by the target users, various materials such as fabric, sponge, memory foam, latex, and non-woven fabric are sewn together through the mattress automatic production line to form the quilting layer structures of the mattress surface, bottom, and side; then, the selected small wire springs are wrapped with materials such as non-woven fabric and cool cloth to form independent pocketed springs, or the springs are fixed with serpentine wires to form a continuous spring network to form the mattress bottom layer as the mattress support; then, through the automatic loading robot, various filling core materials such as sponge, latex, palm, and cotton felt purchased are sent to the designated position by the AGV (Automated Guided Vehicle) to automatically complete splitting, loading, sewing together, and filling into the mattress interior to increase the comfort and support of the mattress, and within the allowable cutting error range, the system calculates through visual AI to automatically correct the deviation and precisely composite the fabric, filling layer, etc. to ensure the quality and precision of the product; the intelligent chip and various sensor devices are installed in the central position of the core and wrapped and sealed to form the core part of the intelligent mattress, and the filling is arranged according to the designed flexible area to ensure the softness and comfort of the mattress, and components such as sound-emitting devices and wake-up devices are added, and dual snoring monitoring technology is adopted to ensure the standard installation of sensors, electronic devices, and their power cords to avoid electromagnetic radiation exceeding the specified limit and causing radiation, affecting the human circulatory system, immunity, and metabolic functions, and even inducing cancer and accelerating the proliferation of human cancer cells; at the same time, ensure that the sensors are pollution-free and undamaged to avoid inaccurate subsequent data collection and inability to fully reflect the user's true sleep situation, and select a massage device with an appropriate gear, using airbag and vibration massage technology combined with intelligent temperature control and angle adjustment functions to ensure the effectiveness of the massage function; and so on, so as to prevent various quality anomalies that occur in daily production in the production processes such as material procurement, loading alignment, glue spraying and pressing, edge wrapping and packaging, and equipment installation to avoid similar quality problems when users use it in the future.

[0133] S63. The system configuration unit configures the control system with complete functions for the mattress according to the user information and the matched intelligent function parameters to fully meet the personalized needs of the user and transmits it to the appearance detection unit;

[0134] Further explanation: After various sensors are installed, install the intelligent control system, configure the development environment, write code, conduct preliminary system tests, and compare with the calculation results of the above steps S51 - S54 and match with the model to conduct various debugging operations, including: whether the function of adjusting the mattress hardness can be achieved through the mobile phone APP or remote control to meet the needs of different people; whether it has a sleep monitoring function, can record sleep data, help improve sleep quality and monitor physiological data such as heart rate and respiration; whether the noise generated during the intelligent adjustment process affects sleep; whether the breathability is good to keep the mattress dry, reduce the sense of stuffiness and dampness, and enhance sleep comfort; whether it has other special functions such as providing accurate sleep reports, sleep - assisting wake - up functions, and linkage with smart home to further enhance the user experience; whether the electronic radiation is too strong to determine whether the radiation of sensors and electronic devices meets the requirements and whether the installation is standardized, so as not to cause electromagnetic radiation to exceed the specified limit value, whether the use and installation of the power cord are correct, and it has no impact on the human circulatory system, immunity, and metabolic functions, avoiding inducing cancer and preventing the proliferation of human cancer cells; whether the sleep detection is accurate, whether the accuracy and sensitivity of the sensors are high, and whether the built - in algorithm can accurately identify the user's sleep stage or judge the user's sleep quality; whether the linkage between the Internet of Things system or network and other smart devices is normal, and whether the sleep stage can accurately adjust parameters such as hardness and temperature; whether the snoring intervention technology is mature, whether the induction monitoring is sensitive, whether it can accurately monitor and actively intervene, and whether it can be dynamically adjusted according to individual differences, etc., to ensure that the performance of the smart mattress meets the design requirements; finally, select a fabric with good breathability, comfortable feel, and radiation protection according to the inner core size to make the cover material, sew the outside of the mattress, ensure that the cover material is tightly combined with the inner core, and at the same time maintain the appearance beautiful and tidy; in this way, the system can automatically read the QR code and automatically read information, collect on - site production data in real - time, transmit it back to the background, and conduct AI analysis and processing, timely control the production system, and feedback to the office system to achieve digital management of the production process; and use the mattress automatic production line to build a digital factory by integrating APS advanced production scheduling, MES manufacturing execution system, SCADA data acquisition and monitoring system, etc., seamlessly connect with cloud platform technology, and realize functions such as remote fault diagnosis and offline programming, providing strong technical support for the product service process; at the same time, use the ergonomic principle to set the joint points of various sensors, configure motors to achieve multi - angle transformation of the bed body, etc., and have an AI sleep monitoring function, realize linkage with other smart home devices by monitoring the sleep state, so as to timely discover and adjust and improve various system abnormal problems that occur in daily production during system debugging, and avoid repeated occurrence of similar system problems when users use it in the future.

[0135] S64. The appearance detection unit obtains the quality information of the appearance and dimensional deviation of the smart mattress through a high-definition camera and a coordinate measuring machine respectively according to the control command and predetermined operation parameters, so as to obtain user preferences and transmit them to the function test unit;

[0136] Further explanation, through the set high-definition camera, 360-degree angle shooting is carried out to shoot images of different position points of the smart mattress from multiple different angles, so as to identify different position points of the smart mattress from different angles, and then it is possible to more accurately and comprehensively identify and obtain each position point and its shape of the smart mattress, or based on the images of multiple smart mattresses taken from different angles, the smart mattress is identified by multi-angle matching, and then the appearance quality information of the smart mattress is determined, including: whether the fabric is without damage, stains, obvious color difference, whether the surface is without prickly touch, whether the hardness is uniform, whether the fabric seam tightness is consistent, whether there is no broken thread or skipped stitch, whether the length of a single floating thread and the cumulative floating thread length are within the specified range, whether the whole is flat, whether the thickness is uniform, whether the mattress surface is plump, whether there is no unevenness or collapse, whether the certificate is complete, whether the product name, registered trademark, manufacturing company name, factory address, contact phone number and warranty card and other information are marked, whether the sewing and hemming process is fine and meets the standard, whether the filling inside the zipper is flat and without sundries, whether the spring or other support structures are intact; and the length, width and height dimensions of the smart mattress are obtained through the set coordinate measuring machine to ensure that the dimensional deviation is within the specified range to ensure the applicability and aesthetics of the mattress; the appearance quality inspection of the smart mattress includes: 1) Image monitoring of the raw materials input in production to ensure that the quality of the raw materials meets the production requirements and avoid production problems caused by raw material problems; 2) Real-time image monitoring during the production process, which can monitor the operation status of the production line and promptly discover and handle abnormal situations; 3) Image monitoring of the finished smart mattress to detect whether there are defects, whether the colors are consistent and other abnormalities in the appearance of the smart mattress; According to specific production requirements and algorithm requirements, other types of image data such as images under different lighting conditions and images at different angles also need to be collected to improve the accuracy and robustness of the algorithm.

[0137] S65. The function test unit obtains various functional test data such as temperature control, massage function, sleep monitoring, softness and hardness, air permeability, compressive strength, edge support force, etc. of the mattress through function test equipment and transmits them to the safety test unit;

[0138] Further explanation: According to the operation command and predetermined operation parameters, temperature control detection of the mattress is carried out through devices such as the set temperature sensor or thermal imager, measuring the actual temperature change of the mattress at different set temperatures to ensure that the mattress can accurately and quickly respond and adjust to the appropriate temperature; massage function detection of the mattress is carried out using tools such as pressure sensors or vibration testers, simulating different massage needs of users to detect whether the massage function of the mattress can accurately respond and evaluate the diversity and comfort of massage strength, frequency and mode; detection of the sleep monitoring of the mattress is carried out using devices such as sleep monitors, heart rate monitors or respiratory monitors, real-time monitoring of the user's sleep state, sleep quality and physical states such as breathing and heart rate during sleep to verify the accuracy and reliability of the mattress sleep monitoring function; soft hardness detection of the mattress is carried out through devices such as pressure distribution testers or mattress hardness testers, simulating the weights and sleeping postures of different users, measuring the pressure distribution and deformation conditions of the mattress in different areas to evaluate the soft hardness adjustment function and adaptability of the mattress; air permeability detection of the mattress is carried out using devices such as air permeability testers or humidity sensors, simulating the air circulation and humidity changes inside the mattress under different sleep environments and humidity conditions to ensure that the mattress has good air permeability performance; compressive strength detection of the mattress is carried out using devices such as pressure testing machines or universal material testing machines, applying different levels of pressure to the mattress to detect its deformation conditions and recovery ability to evaluate the compressive strength and durability of the mattress; edge support force detection of the mattress is carried out using devices such as edge support force testers or simulating user sitting and lying test equipment to detect whether the mattress edge collapses or deforms when bearing pressure to ensure that the mattress edge has good support performance, so as to ensure that all functions of the mattress are normal.

[0139] S66. The safety test unit obtains various safety test data of the intelligent mattress, such as electrical safety, material safety, fire safety, harmful substance content, flame retardancy, etc., through the mattress safety test equipment, and transmits them to the durability test unit;

[0140] Further explanation: According to the operation command and predetermined operation parameters, conduct electrical safety tests on the mattress through an insulation resistance tester or an insulation strength tester, measure the insulation resistance between the electrical components and the shell, ensure that the resistance value is greater than the specified standard, prevent electrical leakage and short circuits, and verify the insulation performance of the equipment when withstanding high voltages; use a material composition analyzer to conduct material safety tests on the mattress, detect the chemical components of the materials used in the mattress, ensure that the materials meet safety standards, are non-toxic, harmless, and allergen-free, analyze the composition of the materials, and identify potential harmful substances; use a fire simulation test device or a temperature rise test equipment to conduct fire safety tests on the mattress, evaluate the safety performance of the mattress under fire conditions, simulate a fire environment, test indicators such as the burning speed and smoke generation amount of the mattress, ensure that the mattress will not intensify the fire or produce toxic smoke when a fire occurs, monitor the temperature rise of the mattress under normal working conditions, and prevent fires caused by overheating; use a harmful substance detector to conduct harmful substance tests on the mattress, detect harmful substances such as formaldehyde, heavy metals, and volatile organic compounds that may exist in the mattress, ensure that the mattress meets environmental protection and safety standards; use a combustion tester to conduct flame retardancy tests on the mattress, simulate the contact of the mattress material with a flame, test its burning speed, burning time, and the situation of the residue after burning, to judge the flame retardancy level and safety of the mattress, so as to ensure that all safety performances of the mattress are normal.

[0141] S67. The durability test unit obtains various aging test data such as the durability test, temperature test, and humidity test of the intelligent mattress through the aging test equipment according to the operation command and predetermined operation parameters, and transmits them to the processing center.

[0142] Further explanation: Conduct durability tests on the mattress through a mattress durability testing machine (also known as a mattress durability tester, mattress comprehensive testing machine). By simulating the continuous rolling movements during human sleep, use a cylindrical or hexagonal loading roller to repeatedly load the mattress. After a specific number of rollings, observe whether the change state of the mattress meets the qualified requirements, and test the ability of the mattress to withstand long-term repetitive loads, so as to evaluate its durability performance and reliability; use equipment such as temperature sensors or thermal imagers to conduct temperature tests on the mattress, measure the actual temperature changes of the mattress at different set temperatures, ensure that the mattress can accurately and quickly respond and adjust to the appropriate temperature, which helps to evaluate the temperature adjustment performance and comfort of the mattress; use a mattress humidity tester to conduct humidity tests on the mattress, measure the performance changes of the intelligent mattress under different humidity conditions, and by simulating different humidity environments, the adaptability of the mattress to humidity changes, as well as its breathability and comfort in a humid environment can be evaluated, so as to ensure the normal durability of the mattress.

[0143] S68. The processing center compares the quality information of the smart mattress with the production quality standards of the smart mattress stored in the memory. If it meets the standards, it notifies that it can be packaged. If it does not meet the standards, it transmits the information to the alarm and notifies rework.

[0144] Further explanation: In addition to the production quality standards of the smart mattress described in step S55 above, the production quality standards of the smart mattress also include: 1) Appearance: The mattress fabric has no damage, no stains, no obvious color difference, no prickly touch on the surface, and is evenly soft and hard; the fabric seams are of consistent tightness, without thread breaks or skipped stitches, and the length of a single floating thread and the cumulative length of floating threads are within the specified range; the overall mattress is flat, with uniform thickness, a plump surface, and no problems such as unevenness or collapse. The mattress comes with a complete certificate indicating product name, registered trademark, manufacturing company name, factory address, contact phone number, warranty card, and other information; the sewing and edging processes are fine and meet the standards. The filling inside the zipper is flat and free of debris, and the springs or other support structures are intact; the dimensional deviations of the length, width, and height of the mattress are within the specified range to ensure the applicability and aesthetics of the mattress. 2) Other functions: It can provide uniform support according to the curve of the human body, reduce the pressure points on the body, and feel comfortable when trying to sleep and fit the body, especially in areas such as the shoulders, waist, and hips; materials such as memory foam, latex, and springs can well adapt to the body shape, have natural antibacterial and anti-mite properties and good breathability, and provide good support; it can be randomly and intelligently controlled through a mobile phone APP or a remote control, and has low operating noise; the fabric and internal structure design of the mattress have good breathability to keep the mattress dry, reduce the sense of stuffiness and the growth of bacteria caused by a humid environment. 3) Compliance with national standards: The test methods for the durability, height loss, and hardness of the mattress specified in the "Test Methods for Functional Characteristics of Furniture Mattresses"; the terms and definitions, instrumentation, test conditions, test procedures, and test reports for the mattress hardness grade test specified in the "Test and Evaluation Method for Mattress Hardness Grade Distribution"; the production technical requirements for spring soft mattresses specified in the "Soft Furniture Spring Soft Mattress", including regulations on fabric, auxiliary materials, cushion layer, durability, hardness grade, test device, and anti-mite function, etc. If the inspection is qualified, it notifies packaging, and uses materials such as PE film, kraft paper, cartons, and adhesive tapes for packaging to protect the mattress, including automated operations such as labeling, printing mattress information, and encapsulation, to ensure safety during transportation.

[0145] Further explanation: The above steps are displayed in sequence according to the arrows, but these steps do not necessarily have to be executed in the order indicated by the arrows. Unless clearly stated in this document, there is no strict order restriction for the execution of these steps. These steps can also be executed according to other orders, and some steps may include multiple sub-steps or multiple stages. These sub-steps or stages do not necessarily have to be completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages does not necessarily have to be sequential, but can be executed alternately or in rotation with at least a part of other steps or sub-steps or stages of other steps.

[0146] Further explanation: The present invention is described in accordance with the content implemented by the software program of a multifunctional intelligent mattress manufacturing control system as described above. For each multifunctional intelligent mattress manufacturing method, it is divided into several modules or units to implement the software program instructions generated by each step. The software program instructions include the above-mentioned multifunctional intelligent mattress manufacturing method.

[0147] The system of the present invention further includes a computer-readable storage medium containing a memory; the memory stores a computer program, and when each functional module executes the computer program, it realizes the steps of the multifunctional intelligent mattress manufacturing method described in any one of the above; the computer-readable storage medium stores a computer program, and when the computer program is executed by each functional module, it realizes the steps of the multifunctional intelligent mattress manufacturing method described in any one of the above; it further includes a multifunctional intelligent mattress manufacturing control device implemented by the above-mentioned multifunctional intelligent mattress manufacturing method.

[0148] Further explanation: The computer-readable storage medium includes a memory, which can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the programs and instructions corresponding to the multifunctional intelligent mattress manufacturing method in the present invention, including the information transfer instructions of each module; the memory executes various functional applications and data processing of each module by running the stored non-volatile software programs and instructions, that is, realizes the multifunctional intelligent mattress manufacturing method of the above process embodiment; one or more units are stored in the memory, and when executed by the one or more modules, they execute the multifunctional intelligent mattress manufacturing method in any one of the above process embodiments; the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by one or more modules, it can also be the multifunctional intelligent mattress manufacturing method in any one of the above process embodiments.

[0149] Further, the computer-readable medium may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two above, and may be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device, including but not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. Among them, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, carrying computer-readable program code. The propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. It may also be any computer-readable medium other than the computer-readable storage medium. The computer-readable signal medium may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code that can be included can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0150] Further, the computer program is divided into multiple modules / units, and the multiple modules / units are stored in the memory and executed by each of the modules / units to complete the present invention; the multiple modules / units may be a series of computer program instructions capable of performing specific functions, and the instructions are used to describe the execution process of the computer program in each of the modules / units.

[0151] The present invention also provides a multifunctional intelligent mattress, which is realized by using the above-mentioned method for manufacturing a multifunctional intelligent mattress, and has the following functions: 1) Sleep monitoring and health management: Real-time monitoring of the user's sleep status such as heart rate, breathing rate, number of turns, number of body movements, and sleeping posture through built-in sensors, and through system intelligent algorithm analysis and processing, providing a detailed sleep report for the user to help the user understand their sleep quality and possibly providing improvement suggestions; 2) Personalized adjustment and support: Analyzing data through ergonomic modeling and AI algorithms based on the user's body shape, sleeping posture, and body pressure distribution, providing a personalized sleep support solution for the user, and automatically adjusting the softness and hardness of the mattress to adapt to the needs and preferences of different users, ensuring that the user obtains the best sleep experience; 3) Comfort and entertainment: Automatically adjusting the mattress angle at a preset wake-up time to gently wake up the user, or raising the head of the mattress to relieve snoring problems, and flexibly designing to imitate actions such as TV viewing, yoga, zero gravity, etc. so that the mattress can be arbitrarily adjusted to different action postures, making it have various entertainment modes, enhancing the user's sleep and leisure experience, and at the same time protecting the health of the user's neck and spine; 4) Massage and relaxation: Soothing the user's physical fatigue and promoting blood circulation through a built-in massage device to help the user better enter the sleep state.

[0152] Further explanation, the control device is composed of the above-related detection devices or apparatuses. According to the needs of intelligent mattress manufacturing enterprises, it can be made into a complete set of mattress automatic production lines together with intelligent mattress production detection equipment, or made into unit devices of each functional module belonging to each step or the entire control device, including robot composite module lines, automatic glue sprayers, automatic turning machines, automatic palletizers, three-dimensional elevators, automatic centering machines, automatic dust removal and sterilization machines, automatic roller machines, automatic packaging machines, etc. When installed, wireless connection is used to connect each control device with each intelligent mattress production detection equipment; the structures of these devices are not described in detail here; the control device can also be applied to professional intelligent mattress testing institutions to improve testing efficiency.

[0153] For those skilled in the art, it is obvious that this application is not limited to the details of the above-mentioned exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic characteristics of this application. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of this application is defined by the appended claims rather than the above description. Therefore, it is intended to cover all changes within the meaning and scope of the equivalent elements of the claims in this application.

[0154] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and not to limit them. Although the present application has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present application can be modified or equivalently replaced, and all of them should be included in the protection scope of the present application.

Claims

1. A method for making a multifunctional intelligent mattress, characterized in that: The method is applied to a multifunctional intelligent mattress manufacturing control system, the system comprising an information acquisition module, a model construction module, a model training module, a model evaluation module, a parameter determination module, a production application module, a wireless communication module, a memory, an alarm, a processing center, and an intelligent mobile terminal; the information acquisition module, the model construction module, the model training module, the model evaluation module, the parameter determination module, the production application module, the wireless communication module, the memory, and the alarm are respectively connected to the processing center; the intelligent mobile terminal is respectively connected to the wireless communication module wireless network within the range of a wireless network or the Internet; the method comprises the following steps: S10. Before production, the information acquisition module obtains normal and abnormal historical image data of the production quality of the smart mattress and performs preprocessing for subsequent model construction, and passes it to the model construction module; S20, the model building module determines the model architecture, designs the network hierarchy, adds auxiliary layers, defines model parameters, and builds the model according to the extracted feature information, and passes it to the model training module, including the following steps: S21, the network level unit uses the selected convolutional neural network as the model architecture and customizes and optimizes the network level structure according to the specific application scenarios and requirements for subsequent defect detection and quality identification, and passes it to the network parameter unit; S22, the network parameter unit adjusts the number of network layers, convolution kernel size, step size, padding method and selects the loss function and optimization algorithm according to the network hierarchy structure to ensure the performance and accuracy of the model, and passes it to the hierarchical optimization unit; S23, the hierarchical optimization unit adjusts the size and normalization of the input data by adding a zero padding layer and a normalization layer before and after the convolution layer to improve the model training speed and stability, and passes it to the data partitioning unit; S24, the data division unit divides the data set with key feature vectors after extraction into a training set, a validation set and a test set and establishes a convolutional neural network structure for subsequent model training; S30, the model training module trains the model according to the collected data and adjusts the model parameters to optimize the model performance to predetermine the production process parameters of the smart mattress, ensure the quality stability of the smart mattress, and pass it to the model evaluation module; S40, the model evaluation module performs model verification and evaluation based on the trained model, and adjusts and optimizes the model based on the verification results to improve the performance and accuracy of the model, and passes it to the parameter determination module; S50, the parameter determination module performs a production test based on the production process parameters predicted by the trained model to obtain the best production process parameters of the smart mattress to ensure the subsequent production quality, and transmits them to the production application module; S60, the production application module produces and performs various tests on the smart mattress according to the set production process parameters and the smart mattress production and testing equipment according to the program instructions to ensure that the smart mattress meets the quality requirements.

2. A method for making a multifunctional intelligent mattress according to claim 1, characterized in that : The system further comprises: the wireless communication module is provided with a wireless network unit, which is responsible for sending and receiving wireless signals and automatically networking with the intelligent mobile terminal within an effective network range; The alarm compares the actual evaluation score of the model with the evaluation score standard of the model stored in the memory, and automatically sounds an alarm and notifies to continue training if the standard is not met; and compares the quality information of the smart mattress with the production quality standard of the smart mattress stored in the memory, and automatically sounds an alarm and notifies to adjust the parameters for rework if the standard is not met; and compares the quality information of the smart mattress with the production quality standard of the smart mattress stored in the memory, and automatically sounds an alarm and notifies to rework if the standard is not met; The memory is responsible for storing information of the information acquisition module, the model construction module, the model training module, the model evaluation module, the parameter determination module, the production application module, the wireless communication module, and the alarm, as well as the model evaluation sub-standard and the smart mattress production quality standard; The processing center is responsible for the information acquisition module, model construction module, model training module, model evaluation module, parameter determination module, production application module, wireless communication module, alarm, and information transmission of the memory. It is the hub center of the system and compares the actual evaluation score of the model with the evaluation score standard of the model stored in the memory: if it meets the standard, it is the predetermined smart mattress production process parameter; if it does not meet the standard, it is passed to the alarm and notified to continue training; and compares the quality information of the smart mattress with the smart mattress production quality standard stored in the memory: if it meets the standard, it is set as the formal production process parameter; if it does not meet the standard, it is passed to the alarm and notified to adjust the parameters for rework; and compares the quality information of the smart mattress with the smart mattress production quality standard stored in the memory: if it meets the standard, it is notified that it can be packaged; if it does not meet the standard, it is passed to the alarm and notified to rework; The information acquisition module includes a data acquisition unit, a cleaning data unit, an enhancement data unit, an integration data unit, a conversion data unit, a filtering and denoising unit, a grayscale conversion unit, and a feature extraction unit, which are responsible for acquiring normal and abnormal historical image data of the quality of the smart mattress and preprocessing them, and passing them to the model building module; The model building module includes a network level unit, a network parameter unit, a hierarchical optimization unit, and a data partitioning unit, which are responsible for determining the model architecture, designing the network level structure, adding auxiliary layers, defining model parameters, and building the model according to the extracted feature information, and passing them to the model training module; The model training module includes an input filling unit, a convolution input unit, a pooling conversion unit, a fully connected layer unit, a normalized output unit, an output conversion unit, and a back-propagation unit, which is responsible for training the model according to the collected data and adjusting the model parameters to optimize the model performance to predetermine the production process parameters of the smart mattress and pass them to the model evaluation module; The model evaluation module includes a classification labeling unit, a learning training unit, and a model evaluation unit, which is responsible for model verification and evaluation based on the trained model, and adjusting and optimizing the model based on the verification results, and passing it to the parameter determination module; The parameter determination module includes a hardness adjustment unit, a temperature adjustment unit, a comfort index unit, a breathability index unit, a trial debugging unit, and an abnormality identification unit, which are responsible for conducting production tests based on the production process parameters predicted by the trained model to obtain the best smart mattress production process parameters and pass them to the production application module; The production application module includes a function design unit, a structure production unit, a system configuration unit, an appearance inspection unit, a function test unit, a safety test unit, and a durability test unit, which are responsible for producing and testing the smart mattresses according to the program instructions of the smart mattress production and testing equipment according to the set production process parameters to ensure that the smart mattresses meet the quality requirements; The step S40 comprises the following steps: S41, the classification and labeling unit classifies the quality abnormality categories of the smart mattress into corresponding data sample categories and labels them for subsequent machine learning of the model, and transmits them to the learning and training unit; S42, the learning training unit determines the training model according to the gradient descent data, and inputs various mattress quality data in the training set into the model for simulation training to ensure the accuracy of model recognition, and transmits it to the model evaluation unit; S43, the model evaluation unit obtains the comprehensive evaluation score F according to the model evaluation score calculation formula "F = 2 (Ac * Re) / (Ac + Re), F is the training model evaluation score, Ac is the precision, Re is the recall rate", and transmits it to the processing center; S44, the processing center compares the actual evaluation score of the model with the evaluation score standard of the model stored in the memory: if it meets the standard, it is the predetermined smart mattress production process parameter; if it does not meet the standard, it is transmitted to the alarm and notified to continue training.

3. The method for making a multifunctional intelligent mattress according to claim 1, characterized in that: The step S10 comprises the following steps: S11. The data acquisition unit obtains various quality data, user data and historical data of production process parameters of similar smart mattresses by connecting to the industry database for subsequent data cleaning and passing it to the cleaning data unit; S12, the cleaning data unit cleans the collected historical data to remove abnormal values, duplicate values ​​or missing values ​​in the data to improve the quality and accuracy of the data, and passes it to the enhanced data unit; S13, the enhanced data unit increases the quantity and diversity of the smart mattress training data through data enhancement methods such as rotation, scaling, flipping, cropping, and color transformation to improve the generalization ability of the model, and passes it to the integrated data unit; S14, the integrated data unit obtains the standardized smart mattress data according to the data standardization processing formula "z = (x-μ) / σ, z is the standardized data, x is the original data, μ is the mean of the data, σ is the standard deviation of the data" to improve the stability of the model, and passes it to the conversion data unit; S15. The conversion data unit obtains the normalized smart mattress data according to the normalization calculation formula "x' = (x-min(x)) / (max(x)-min(x)), x' is the normalized data, x is the original data, min(x) and max(x) are the minimum and maximum values ​​of the data respectively" to improve the model performance, and passes it to the filtering and denoising unit; S16, filtering and denoising unit is calculated according to the Gaussian filtering method" G(x,y) is the two-dimensional Gaussian function pixel, (x,y) is the pixel coordinate, and σ is the standard deviation” The denoised mattress image data is obtained for grayscale image conversion and passed to the grayscale conversion unit; S17, the grayscale conversion unit obtains the grayscale mattress image data according to the grayscale calculation formula "f(I,j) = max(R(I,j), G(I,j), B(I,j)), f(I,j) is the grayscale image, R(I,j), G(I,j), B(I,j) are the original images of three colors respectively", so as to facilitate the subsequent feature extraction, and transmits it to the feature extraction unit; S18, the feature extraction unit converts the labeled data into a feature vector useful for model training and extracts key features of shape features, color features, and intelligent element identification to improve the training speed and performance of the model; The step S50 comprises the following steps: S51, the hardness adjustment unit adjusts the mattress hardness according to the calculation formula "Ho=Hi+K*(H max -H min ), Ho is the mattress output hardness (kg / m 3 ),Hi is the mattress input hardness (kg / m 3 ), K is the mattress hardness adjustment coefficient, H max Maximum hardness of the mattress (kg / m 3 ),H min is the minimum hardness of the mattress (kg / m 3 )” to obtain the required hardness adjustment of the smart mattress for subsequent smart mattress testing and pass it to the temperature adjustment unit; S52, the temperature adjustment unit adjusts the mattress temperature according to the calculation formula "To=Ti+K*(T max -T min ), To is the mattress output temperature (℃), Ti is the mattress input temperature (℃), K is the mattress temperature adjustment coefficient, T max is the maximum temperature of the mattress (℃), T min The minimum temperature of the mattress (℃) is used to obtain the required adjustment temperature of the smart mattress for subsequent smart mattress testing and is passed to the comfort index unit; S53. The comfort index unit obtains the mattress comfort index according to the mattress comfort index calculation formula "Di = We*Se+Wh*Sh+Ws*Sp, Di is the mattress comfort index, We is the mattress environmental factor weight, Se is the mattress environmental factor score, Wh is the human perception weight, Sh is the human perception score, Ws is the mattress preference weight, Sp is the mattress preference score" for subsequent intelligent mattress testing, and transmits it to the air permeability index unit; S54, air permeability index unit is calculated according to the air permeability formula of the smart mattress "K = Q / (ΔP*A), K is the air permeability of the mattress (m 3 / m 2 ·KPa·h), Q is the mattress gas flow rate (m 3 / h), ΔP is the air permeability of the mattress porous material (KPa), A is the test area of ​​the mattress sample (m 2 )” to obtain the air permeability of the mattress for subsequent intelligent mattress testing and pass it to the trial debugging unit; S55, the trial debugging unit conducts trial production and testing of the smart mattress through the mattress production testing equipment according to the operation command and the predetermined smart mattress production process parameters to obtain quality information to ensure the quality accuracy of the smart mattress, and transmits it to the processing center; S56. The processing center compares the quality information of the smart mattress with the smart mattress production quality standards stored in the memory: if the standards are met, they are set as formal production process parameters; if the standards are not met, they are transmitted to the alarm and notified to adjust the parameters for rework. S57. The abnormality recognition unit matches the real-time acquired intelligent mattress production detection image with the corresponding image in the trained convolutional neural network model and confirms its abnormality category for subsequent production improvement and parameter adjustment.

4. The method for making a multifunctional intelligent mattress according to claim 1, characterized in that: The step S30 comprises the following steps: S31. The input filling unit obtains the filling data according to the filling size calculation formula of the mattress data "Ph = [(Ho-1)*Sh+Kh-Hi] / 2, Pw = [(Wo-1)*Sw+Kw-Wi] / 2, Ph and Pw are the filling sizes in the height / width direction, Hi and Wi are the height / width of the input feature map, Kh and Kw are the height / width of the convolution kernel, Sh and Sw are the values ​​of the step size in the height / width direction, Ho and Wo are the height and width of the output feature map", and passes it to the convolution input unit; S32, the convolution input unit obtains the convolution input value and activates the function input according to the convolution input calculation formula "z(t) = ∫x(m)y(tm)dm, z(t) is the output function, x(t) is the input function, y(t) is the convolution kernel function, and dm is the integral differential element of the variable m", and passes it to the pooling conversion unit; S33, the pooling conversion unit obtains the maximum pixel value after pooling according to the maximum pooling calculation formula "Z(I,j)=max(X[i*Ps(i+1)*Ps,j*Ps(j+1)*Ps]), Z(i,j) is a pixel value in the output feature map after pooling, i and j are the positions in the output feature map, max is the maximum value of all pixel values ​​in the input window, X is the input feature map, and Ps is the window size of the pooling operation" to enter the fully connected layer to retain important feature information and pass it to the fully connected layer unit; S34, the fully connected layer unit obtains the output data of the connection layer according to the fully connected layer calculation formula "y=f(∑(Wn*Xn)+b), y is the output result, f is the activation function, Wn is the weight of the nth input feature, Xn is the nth input feature, n is the dimension of the input feature, and b is the bias" and enters the output layer for subsequent output calculation and is passed to the normalized output unit; S35, the normalized output unit obtains the output of Batch Norm according to the Batch Norm layer calculation formula "h = φ (Bn (Wx + b)), h is the output of the fully connected layer, φ is the activation function, Bn is the batch normalization operator, W is the weight parameter, X is the input of the fully connected layer, and b is the bias parameter", and passes it to the output conversion unit; S36, the output conversion unit obtains the output value size after convolution according to the output layer conversion calculation formula "N = (P-F + 2C) / S + 1, N is the output size after convolution, P is the input size before convolution, F is the convolution kernel size, C is the number of layers of 0 added around the image, and S is the step size" for subsequent model analysis and training, and passes it to the back propagation unit; S37, the back propagation unit obtains the loss function value and back propagates according to the loss function calculation formula "L = max(0, m + y*(f(x) - b)", L is the loss function value, m is the hyperparameter, y is the sample label (0 or 1), f(x) is the predicted value of the model, and b is the classification boundary" to optimize the performance of the network model; The step S60 comprises the following steps: S61, the function design unit obtains various user data through sensors according to the user order information and matches the process parameters with the model to perform design, and transmits it to the structure production unit; S62, the structure production unit produces the basic structure of the mattress by quilting the quilting layer, making the base, buttoning the fabric and filling the mattress through the mattress automatic production line according to the control command and the predetermined production process parameters, and transmits it to the system configuration unit; S63, the system configuration unit configures a complete control system of various functions for the mattress according to the user information and the matching intelligent function parameters to fully meet the personalized needs of the user, and transmits it to the appearance detection unit; S64, the appearance detection unit obtains the quality information of the appearance and size deviation of the smart mattress through a high-definition camera and a three-coordinate measuring instrument according to the control command and the predetermined operation parameters to obtain the user's preference, and transmits it to the function test unit; S65. The functional testing unit obtains the test data of the temperature control, massage function, sleep monitoring, softness and hardness, air permeability, compressive strength, and edge support of the mattress through the functional testing equipment, and transmits it to the safety testing unit; S66. The safety test unit obtains the test data of electrical safety, material safety, fire safety, harmful substance content, and flame retardancy of the smart mattress through the mattress safety test equipment, and transmits it to the durability test unit; S67, the durability test unit obtains the test data of the durability test, temperature test, and humidity test of the smart mattress through the aging test equipment according to the operation command and the predetermined operation parameters, and transmits the data to the processing center; S68. The processing center compares the quality information of the smart mattress with the smart mattress production quality standards stored in the memory: if the standards are met, it is notified that it can be packaged; if the standards are not met, it is transmitted to the alarm and notified to rework.

5. A method for making a multifunctional intelligent mattress according to claims 1-4, characterized in that: The system also includes a computer-readable storage medium containing a memory; the memory stores a computer program, and when the functional modules execute the computer program, the steps of a multifunctional intelligent mattress manufacturing method described in any one of claims 1 to 4 are implemented; the computer-readable storage medium stores a computer program, and when the computer program is executed by the functional modules, the steps of a multifunctional intelligent mattress manufacturing method described in any one of claims 1 to 4 are implemented; and also includes a multifunctional intelligent mattress manufacturing control device, which is implemented by the multifunctional intelligent mattress manufacturing method described in any one of claims 1 to 4.

6. A multifunctional intelligent mattress, characterized in that: The invention is realized by adopting a method for manufacturing a multifunctional intelligent mattress as described in any one of claims 1 to 4 above.

Images