Bedstead processing optimization method and system based on model analysis

Abstract

The invention discloses a bed frame processing optimization method and system based on model analysis. Pressure and load testing is conducted on the target bed frame, and pressure and temperature control data of different parts of the bed frame are collected through a preset sensor arrangement scheme. Performing pressure and temperature distribution analysis according to different load conditions, and generating a pressure distribution diagram and a temperature distribution diagram according to color depth mapping numerical values; a pressure and temperature control distribution diagram in an expected state is generated, the characteristic difference trend of the pressure and temperature distribution diagram and an expected diagram is evaluated through HOG characteristic extraction and difference degree calculation, and a pressure and temperature control expected difference curve is generated. And performing forward and reverse prediction on the difference curve by using a linear regression model, evaluating a distribution anomaly trend, screening an abnormal region in combination with a characteristic difference degree, and performing sensor layout anomaly traceability analysis according to the abnormal region. The performance of the intelligent bed frame can be accurately evaluated, and an effective basis is provided for optimization design and maintenance.

Description

Technical Field

[0001] The present invention relates to the field of intelligent production of bed frames, and more specifically, to a method and system for optimizing bed frame processing based on model analysis. Background Art

[0002] With the breakthroughs in technologies such as the Internet of Things, big data, and artificial intelligence, the smart home industry has entered a period of rapid development. As one of the core categories of smart homes, smart electric beds have realized functions such as bed angle adjustment, health monitoring, and intelligent linkage by integrating technologies such as sensors, motor drives, and wireless communication.

[0003] During the production process of smart bed frames, the sensors connected to them need to undergo many testing processes and steps to ensure the reasonable layout of the sensors on the bed frames. The layout of sensors in traditional technologies is often based on general requirements, and it is difficult to effectively test the sensors, resulting in poor production quality of the bed frames of smart beds. In addition, for the traditional layout of bed frame sensors and the load testing process of sensors, it is often based on a one-by-one comparison of single values, analyzing the numerical differences of each sensor and adjusting the layout based on manual experience. The process is time-consuming and laborious, and it is difficult to achieve intelligent test analysis, with low efficiency, further hindering the production and application of smart bed frames. Summary of the Invention

[0004] The present invention overcomes the defects of the prior art and proposes a method and system for optimizing bed frame processing based on model analysis.

[0005] The first aspect of the present invention provides a method for optimizing bed frame processing based on model analysis, including:

[0006] S1: In the first test cycle, perform pressure testing and load testing on the target bed frame, and collect pressure data and temperature control data of different bed frame parts through a preset sensor layout scheme;

[0007] S2: Under different load conditions, perform pressure and temperature distribution analysis based on the pressure data and temperature control data, map the distribution values with different color depths, and generate a pressure distribution map and a temperature distribution map of the target bed frame;

[0008] S3: Generate a first distribution map and a second distribution map based on pressure and temperature control in the expected state under different load conditions, perform regional HOG feature extraction and feature difference degree calculation on the pressure distribution map and the first distribution map, and evaluate the feature difference trend in the order of each monitoring area of the distribution map to generate a pressure expected difference curve. Obtain a temperature control expected difference curve based on HOG feature analysis of the temperature distribution map and the second distribution map;

[0009] S4: According to the expected difference curve, introduce a linear regression model for forward and reverse prediction, evaluate the abnormal trend of the distribution of pressure and temperature control, screen out the abnormal areas under different load conditions in combination with the feature difference degree, and conduct an analysis of the origin of abnormal sensor layout based on the abnormal areas.

[0010] In the present invention, the specific content of S1 is as follows:

[0011] In the production test of the intelligent bed frame, set the first test cycle and the preset sensor layout scheme based on the target bed frame;

[0012] In the preset sensor layout scheme, for different bed frame parts, there are no less than the preset number of temperature sensors and pressure sensors;

[0013] Based on various load conditions, collect the pressure data, temperature control data and test performance data of different bed frame parts, and perform data cleaning and outlier removal on the pressure data and temperature control data.

[0014] In the present invention, the specific content of S2 is as follows:

[0015] Set a blank distribution map based on the sensor layout scheme of the bed frame, map the pressure range to the preset color range [0 - 255], and obtain the associated mapping table;

[0016] Under a certain load pressure condition, according to the pressure data, mark the positions of the pressure sensors and the corresponding pressure monitoring values in the blank distribution map, introduce the associated mapping table, perform color value conversion on the pressure monitoring data values and fill them in the blank distribution map to obtain the initial distribution map;

[0017] Using the positions of the pressure sensors as monitoring points, in the initial distribution map, fill the colors in the areas outside the monitoring points. The filled color values are set according to the distance between the points in the area to be filled and the nearest monitoring point, and a pressure distribution map is generated;

[0018] Conduct corresponding distribution analysis according to the temperature control data to generate a temperature distribution map.

[0019] In the present invention, the specific content of S3 is as follows:

[0020] Based on a certain load pressure condition, set the numerical distribution of the pressure sensors and temperature sensors in the expected state, and perform color value mapping based on the numerical distribution to generate the first distribution map and the second distribution map;

[0021] Divide multiple monitoring areas in the distribution map;

[0022] In the pressure distribution map and the first distribution map, perform HOG feature extraction on the same monitoring area respectively, vectorize the HOG features to form the first feature vector and the second feature vector;

[0023] Calculate the difference degree between the first eigenvector and the second eigenvector based on the Manhattan distance, and obtain the eigenvector difference degree;

[0024] Analyze each monitoring area to obtain multiple eigenvector difference degrees;

[0025] Sort the pressure sensor density in the monitoring area, map the sorting result to the corresponding multiple eigenvector difference degrees, and obtain the difference degree sequence;

[0026] Perform curve fitting on the difference degree sequence to obtain the expected pressure difference curve;

[0027] Based on the HOG feature, compare the feature differences of the monitoring areas between the temperature distribution map and the second distribution map, and generate the expected temperature control difference curve.

[0028] In the present invention, the specific content of S4 is as follows:

[0029] Import the expected pressure difference curve and the expected temperature control difference curve into the linear regression model for linear regression fitting analysis respectively, and perform forward and reverse predictions based on the fitting results to evaluate the abnormal change trends of the sensors in the high-density area and the low-density area;

[0030] For the expected pressure difference curve, generate the first predicted difference value and the second predicted difference value. If the difference mean value between the first predicted difference value and the second predicted difference value is greater than the preset difference value, then compare the eigenvector difference degree of each monitoring area with the difference mean value, and screen out the abnormal pressure areas;

[0031] For the expected temperature control difference curve, generate the third predicted difference value and the fourth predicted difference value. If the difference mean value between the third predicted difference value and the fourth predicted difference value is greater than the preset difference value, then compare the eigenvector difference degree of each monitoring area with the difference mean value, and screen out the abnormal temperature control areas;

[0032] According to the abnormal pressure areas and the abnormal temperature control areas, perform abnormal traceability analysis on the pressure sensors and the temperature sensors, and adjust the preset sensor layout plan.

[0033] In the present invention, in S2, each load condition includes the corresponding pressure distribution map and temperature distribution map.

[0034] The second aspect of the present invention also provides a bed frame processing optimization system based on model analysis. The system includes: a memory and a processor. The memory includes a bed frame processing optimization program based on model analysis. When the bed frame processing optimization program based on model analysis is executed by the processor, the following steps are implemented:

[0035] S1: In the first test cycle, conduct pressure testing and load testing on the target bed frame, and collect pressure data and temperature control data of different bed frame parts through a preset sensor layout scheme;

[0036] S2: Under different load conditions, conduct pressure and temperature distribution analysis based on the pressure data and temperature control data, map the distribution values with different color depths, and generate a pressure distribution map and a temperature distribution map of the target bed frame;

[0037] S3: Generate a first distribution map and a second distribution map based on pressure and temperature control in the expected state under different load conditions, perform regional HOG feature extraction and feature difference degree calculation on the pressure distribution map and the first distribution map, and evaluate the feature difference trend in the order of each monitoring area of the distribution map to generate a pressure expected difference curve. Obtain a temperature control expected difference curve based on the HOG feature analysis of the temperature distribution map and the second distribution map;

[0038] S4: According to the expected difference curve, introduce a linear regression model for forward and reverse prediction, evaluate the abnormal trend of the pressure and temperature control distribution, screen out the abnormal areas under different load conditions in combination with the feature difference degree, and conduct sensor layout abnormal traceability analysis based on the abnormal areas.

[0039] The third aspect of the present invention also provides a computer-readable storage medium, which includes a bed frame processing optimization program based on model analysis. When the bed frame processing optimization program based on model analysis is executed by a processor, the steps of the bed frame processing optimization method based on model analysis as described in any one of the above are realized.

[0040] The present invention discloses a bed frame processing optimization method and system based on model analysis. Implement pressure and load testing on the target bed frame, and collect pressure and temperature control data of different parts of the bed frame through a preset sensor layout scheme. According to different load conditions, conduct pressure and temperature distribution analysis, and map the values with color depths to generate a pressure distribution map and a temperature distribution map. Generate pressure and temperature control distribution maps in the expected state, evaluate the feature difference trends of the pressure and temperature distribution maps and the expected maps through HOG feature extraction and difference degree calculation, and generate pressure and temperature control expected difference curves. Use a linear regression model to perform forward and reverse prediction on the difference curves, evaluate the abnormal distribution trend, screen out abnormal areas in combination with the feature difference degree, and conduct sensor layout abnormal traceability analysis based on the abnormal areas. The present invention can accurately evaluate the performance of intelligent bed frames and provide an effective basis for optimized design and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 Shows a flowchart of a bed frame processing optimization method based on model analysis of the present invention;

[0042] Figure 2The block diagram of an optimization system for bed frame processing based on model analysis according to the present invention is shown. Specific embodiments

[0043] In order to more clearly understand the above objects, features and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0044] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0045] Figure 1 The flowchart of an optimization method for bed frame processing based on model analysis according to the present invention is shown.

[0046] As Figure 1 shown, the first aspect of the present invention provides an optimization method for bed frame processing based on model analysis, including:

[0047] S1: In the first test cycle, perform pressure test and load test on the target bed frame, and collect pressure data and temperature control data of different bed frame parts through a preset sensor layout scheme;

[0048] S2: Under different load conditions, perform pressure and temperature distribution analysis according to the pressure data and temperature control data, map the distribution values with different color depths, and generate a pressure distribution map and a temperature distribution map of the target bed frame;

[0049] S3: Generate a first distribution map and a second distribution map based on pressure and temperature control in the expected state under different load conditions, perform regional HOG feature extraction and feature difference calculation on the pressure distribution map and the first distribution map, and evaluate the feature difference trend in the order of each monitoring area of the distribution map to generate a pressure expected difference curve, and obtain a temperature control expected difference curve based on HOG feature analysis of the temperature distribution map and the second distribution map;

[0050] S4: According to the expected difference curve, introduce a linear regression model for forward and reverse prediction, evaluate the abnormal trend of the pressure and temperature control distribution, screen out the abnormal areas under different load conditions in combination with the feature difference degree, and perform sensor layout abnormal traceability analysis according to the abnormal areas.

[0051] It should be noted that the HOG feature, that is, the histogram of oriented gradients, is an effective method for image feature extraction. In the present invention, it is applied to image color distribution analysis to effectively reflect the distribution state analysis of sensors.

[0052] According to an embodiment of the present invention, S1 specifically is as follows:

[0053] In the production test of the intelligent bed frame, set the first test cycle and the preset sensor layout plan based on the target bed frame;

[0054] In the preset sensor layout plan, for different bed frame parts, there are no less than the preset number of temperature sensors and pressure sensors;

[0055] Based on various load conditions, collect the pressure data, temperature control data, and test performance data of different bed frame parts, and perform data cleaning and outlier removal on the pressure data and temperature control data.

[0056] It should be noted that the target bed frame is an intelligent bed frame, including various types of sensors, such as temperature and pressure sensors, which are used for the intelligent bed to monitor the pressure of users, monitor the temperature control of motors, circuit areas, etc. At the same time, based on the monitoring data, functions such as personalized sleep monitoring analysis and individual adjustment of the intelligent bed can be realized.

[0057] The first test cycle includes those based on various load conditions. The load conditions include settings beyond a certain rated parameter range, which are used to evaluate the pressure and temperature control of the target bed frame and further optimize the layout analysis of the sensors.

[0058] According to an embodiment of the present invention, S2 specifically is as follows:

[0059] Set a blank distribution map based on the sensor layout plan of the bed frame, map the pressure range to the preset color range [0 - 255], and obtain the associated mapping table;

[0060] Under a certain load pressure condition, according to the pressure data, mark the positions of the pressure sensors and the corresponding pressure monitoring values in the blank distribution map, introduce the associated mapping table, perform color value conversion on the pressure monitoring data values and fill them in the blank distribution map to obtain the initial distribution map;

[0061] Using the positions of the pressure sensors as monitoring points, in the initial distribution map, fill the areas outside the monitoring points with colors. The filled color values are set according to the distances between the points in the area to be filled and the nearest monitoring points, and a pressure distribution map is generated;

[0062] Perform corresponding distribution analysis according to the temperature control data to generate a temperature distribution map.

[0063] It should be noted that in the numerical distribution filling outside the monitoring points, the color value is inversely proportional to the distance between the point in the area to be filled and the nearest monitoring point. The greater the distance, the smaller the color value. And the closer the point in the area to be filled is to the monitoring point, the closer its value is to the corresponding value of the monitoring point. In the temperature distribution map and the pressure distribution map, their color settings can be changed and set according to actual visualization requirements. The value settings are consistent with the associated mapping table, and the analysis and distribution map generation processes of the two are the same. Under each load condition, including the corresponding pressure distribution map and temperature distribution map, when the load conditions include pressure load, motor operation load, etc., corresponding load tests are carried out for different conditions and based on different working conditions and different functional tests.

[0064] According to an embodiment of the present invention, the specific content of S3 is as follows:

[0065] Based on a load pressure condition, set the numerical distributions of the pressure sensor and the temperature sensor in the expected state, and perform color value mapping based on the numerical distributions to generate a first distribution map and a second distribution map;

[0066] Divide multiple monitoring areas in the distribution map;

[0067] In the pressure distribution map and the first distribution map, perform HOG feature extraction on the same monitoring area respectively, vectorize the HOG features to form a first feature vector and a second feature vector;

[0068] Calculate the difference degree between the first feature vector and the second feature vector based on the Manhattan distance, and obtain the feature difference degree;

[0069] Analyze each monitoring area to obtain multiple feature difference degrees;

[0070] Sort the monitoring areas according to the density of the pressure sensors in the monitoring area, map the sorting results to the corresponding multiple feature difference degrees to obtain a difference degree sequence;

[0071] Perform curve fitting on the difference degree sequence to obtain a pressure expected difference curve;

[0072] Based on the HOG features, compare the feature differences of the monitoring areas in the temperature distribution map and the second distribution map, and generate a temperature control expected difference curve.

[0073] It should be noted that in the expected state, i.e., the ideal condition of the sensor, under a certain load pressure, the measured data of the corresponding sensor is consistent with the test data, and no numerical deviation occurs. The first distribution diagram and the second distribution diagram respectively correspond to the pressure and temperature distributions in the ideal state. A monitoring area corresponds to a bed frame part, which can be freely divided based on product requirements or functional requirements for refined analysis of the rationality of sensor layout and regional control anomalies in different bed parts. For example, multiple areas can be divided based on the up-down order, corresponding to the pressure monitoring of different parts of the human body. Here, the sensor density is used as the order for sequential analysis of different functional areas and different requirement areas of the intelligent bed, to judge the differential deviation curve, and to predict the deviation in the follow-up, which can further trace back to the abnormal sensor area. The regional sorting of the sensor density is generally from small to large. Curve fitting can be based on general linear fitting.

[0074] The expected difference curves of pressure and temperature control reflect the deviation changes in the sensor monitoring accuracy of the monitoring area in two dimensions of pressure and temperature control under the current sensor layout state of the bed frame, from simple requirements to complex requirements.

[0075] It is worth mentioning here that for the traditional sensor layout of the bed frame and the load test process of the sensor, it often relies on one-to-one comparison of single values, analyzes the numerical differences of each sensor, and adjusts the layout based on manual experience. The process is time-consuming and laborious, making it difficult to achieve intelligent test analysis, difficult to conduct expected difference analysis of sensors and predict abnormal difference trends for the target bed frame from the overall layout form and overall test state, lacking a regional sensor abnormal trend analysis process, difficult to capture potential abnormal sensor layout areas, and difficult to trace back the production process with problems, resulting in low production efficiency of the bed frame in the intelligent bed body.

[0076] According to the embodiment of the present invention, the specific content of S4 is as follows:

[0077] Respectively import the expected difference curve of pressure and the expected difference curve of temperature control into a linear regression model for linear regression fitting analysis, and conduct forward and reverse predictions based on the fitting results to evaluate the abnormal change trends of sensors in high-density areas and low-density areas;

[0078] For the expected difference curve of pressure, generate a first predicted difference value and a second predicted difference value. If the difference mean of the first predicted difference value and the second predicted difference value is greater than the preset difference value, then compare the characteristic difference degree of each monitoring area with the difference mean to screen out abnormal pressure areas;

[0079] For the temperature control expected difference curve, a third predicted difference value and a fourth predicted difference value are generated. If the difference mean value between the third predicted difference value and the fourth predicted difference value is greater than the preset difference value, the characteristic difference degree of each monitoring area is compared with the difference mean value to screen out the abnormal temperature control areas;

[0080] Based on the abnormal pressure areas and the abnormal temperature control areas, perform abnormal source tracing analysis on the pressure sensors and the temperature sensors, and adjust the preset sensor layout scheme.

[0081] It should be noted that in the analysis of the abnormal pressure areas and the abnormal temperature control areas, the corresponding two difference mean values represent different data. Here, in the forward and reverse predictions, the forward prediction is used to analyze the reasonable layout and abnormal conditions of the sensors in the high-density areas, while the reverse prediction is used to analyze the reasonable layout and abnormal conditions of the sensors in the low-density areas. The high and low density areas represent the high and low sensor density areas. The forward and reverse predictions are the sequence forward prediction and the reverse prediction, and respectively represent different regional trend analysis and abnormal change prediction directions.

[0082] According to the embodiment of the present invention, in the S2, each load condition includes a corresponding pressure distribution map and a temperature distribution map.

[0083] According to the embodiment of the present invention, for the order of each monitoring area in the distribution map, evaluating the characteristic difference trend further includes:

[0084] For each monitoring area, obtain the density value and the monitoring ratio;

[0085] Generate a characteristic vector of the monitoring area based on the density value and the monitoring ratio;

[0086] Using the characteristic vector of each monitoring area as sample data, perform clustering on the sample data based on the Kmeans clustering algorithm, set the number of groups K, and generate K area groups;

[0087] Based on the average monitoring ratio of the monitoring areas in each area group, sort the area groups, and determine the analysis order of the monitoring areas based on the sorting result.

[0088] It should be noted that the eigenvector is a two-dimensional vector, and the monitoring ratio is based on the demand degree corresponding to the monitoring area. Generally, the monitoring ratio of different monitoring areas is evaluated based on the functionality of different areas of the bed frame. In the present invention, sorting and predicting the monitoring areas based on density can effectively predict the differences in areas with different demand degrees. For a bed frame with more functions and a more complex sensor layout, the analysis order of the sensors can be evaluated and sorted based on two dimensions: density value and monitoring ratio. Here, the Kmeans clustering form is introduced to sort the sensor areas, which can generate a difference curve that better fits the actual bed frame layout characteristics in the subsequent process and effectively detect abnormal layout areas. K can be set based on the number of functional areas of the intelligent bed frame.

[0089] According to an embodiment of the present invention, it further includes:

[0090] Set the same color map for the pressure distribution map and the temperature distribution map for analysis;

[0091] For the pressure distribution map and the temperature distribution map, select a monitoring area, set a 3×3 convolution kernel with the sobel operator, and calculate the edge intensity of each window in the area. Serialize the calculated edge intensity to obtain two edge detection sequences;

[0092] Judge the correlation of the two edge detection sequences by the grey relational method. If there is a correlation, mark the one monitoring area as an associated area;

[0093] Perform correlation detection on all monitoring areas, and judge the rationality of the sensor layout based on the associated areas and adjust the sensor layout plan.

[0094] It should be noted that for the running test, due to the correlation between the bed pressure test and the motor running process, there is a certain correlation between the pressure points and the motor temperature control points. For the test process, effectively exploring this correlation can perform efficient sensor layout analysis and adjustment in the subsequent process. The window size is the size of the 3×3 convolution kernel. The edge intensity is the gradient amplitude.

[0095] The distribution maps in the correlation analysis are the pressure distribution map and the temperature distribution map corresponding to one load condition for analysis. For the associated areas, the deviation consistency, deviation trend correlation, etc. of the data collected by corresponding multiple sensors can be judged, and the sensor layout in the associated areas can be further reasonably optimized to enable the sensors to meet the functional requirements and monitoring requirements. The two edge detection sequences respectively correspond to the sequences of the pressure and temperature distribution maps.

[0096] Figure 2 Shows a block diagram of an optimization system for bed frame processing based on model analysis according to the present invention.

[0097] In the second aspect of the present invention, there is also provided an optimized system 2 for bed frame processing based on model analysis. The system includes: a memory 21 and a processor 22. The memory 21 includes an optimized program for bed frame processing based on model analysis. When the optimized program for bed frame processing based on model analysis is executed by the processor 22, the following steps are implemented:

[0098] S1: In the first test cycle, perform pressure testing and load testing on the target bed frame, and collect pressure data and temperature control data of different bed frame parts through a preset sensor layout scheme.

[0099] S2: Under different load conditions, perform pressure and temperature distribution analysis based on the pressure data and temperature control data, map the distribution values with different color depths, and generate a pressure distribution map and a temperature distribution map of the target bed frame.

[0100] S3: Generate a first distribution map and a second distribution map based on pressure and temperature control in the expected state under different load conditions, perform regional HOG feature extraction and feature difference calculation on the pressure distribution map and the first distribution map, and evaluate the feature difference trend in the order of each monitoring area of the distribution map to generate a pressure expected difference curve. Obtain a temperature control expected difference curve based on HOG feature analysis of the temperature distribution map and the second distribution map.

[0101] S4: According to the expected difference curve, introduce a linear regression model for forward and reverse prediction, evaluate the abnormal trend of pressure and temperature control distribution, screen out abnormal areas under different load conditions in combination with the feature difference degree, and perform abnormal source tracing analysis of sensor layout according to the abnormal areas.

[0102] It should be noted that the HOG feature, that is, the histogram of oriented gradients, is an effective method for image feature extraction. In the present invention, it is applied to image color distribution analysis to effectively reflect the distribution state analysis of sensors.

[0103] According to an embodiment of the present invention, the specific content of S1 is as follows:

[0104] In the production test of the intelligent bed frame, set the first test cycle and the preset sensor layout scheme based on the target bed frame.

[0105] In the preset sensor layout scheme, for different bed frame parts, there are no less than a preset number of temperature sensors and pressure sensors.

[0106] Based on multiple load conditions, collect pressure data, temperature control data, and test performance data of different bed frame parts, and perform data cleaning and outlier removal on the pressure data and temperature control data.

[0107] It should be noted that the target bed frame is an intelligent bed frame, including various types of sensors, such as temperature and pressure sensors, which are used for the intelligent bed to monitor the pressure of the user, monitor the temperature control of the motor, circuit area, etc. At the same time, based on the monitoring data, functions such as personalized sleep monitoring analysis and individualized adjustment of the intelligent bed can be realized.

[0108] The first test cycle includes under various load conditions. The load conditions include settings beyond a certain rated parameter range, which are used to evaluate the pressure and temperature control of the target bed frame and further optimize the layout analysis of the sensors.

[0109] According to an embodiment of the present invention, the specific content of S2 is as follows:

[0110] Set a blank distribution map based on the sensor layout scheme of the bed frame. Map the pressure range to the preset color range [0 - 255] and obtain the associated mapping table;

[0111] Under a load pressure condition, according to the pressure data, mark the positions of the pressure sensors and the corresponding pressure monitoring values in the blank distribution map. Introduce the associated mapping table, perform color value conversion on the pressure monitoring data values and fill them in the blank distribution map to obtain the initial distribution map;

[0112] Using the positions of the pressure sensors as monitoring points, in the initial distribution map, fill the area outside the monitoring points with colors. The filled color values are set according to the distance between the points in the area to be filled and the nearest monitoring point, and generate the pressure distribution map;

[0113] Conduct corresponding distribution analysis based on the temperature control data to generate the temperature distribution map.

[0114] It should be noted that in the numerical distribution filling of the area outside the monitoring points, the color value is inversely proportional to the distance between the points in the area to be filled and the nearest monitoring point. The greater the distance, the smaller the color value, and the closer the point in the area to be filled is to the monitoring point, the closer its value is to the value corresponding to the monitoring point. In the temperature distribution map and the pressure distribution map, the color settings can be changed and set according to the actual visualization requirements. The numerical settings are consistent with the associated mapping table, and the analysis and distribution map generation processes of both are the same. Under each load condition, including the corresponding pressure distribution map and temperature distribution map, when the load conditions include pressure load, motor operation load, etc., for different conditions and based on different working conditions, corresponding load tests are conducted for different functions.

[0115] According to an embodiment of the present invention, the specific content of S3 is as follows:

[0116] Based on a load pressure condition, set the numerical distribution of the pressure sensors and temperature sensors in the expected state, and perform color value mapping based on the numerical distribution to generate the first distribution map and the second distribution map;

[0117] Divide multiple monitoring areas in the distribution map;

[0118] In the pressure distribution map and the first distribution map, perform HOG feature extraction on the same monitoring area respectively, vectorize the HOG features, and form a first feature vector and a second feature vector;

[0119] Calculate the difference degree between the first feature vector and the second feature vector based on the Manhattan distance, and obtain the feature difference degree;

[0120] Analyze each monitoring area to obtain multiple feature difference degrees;

[0121] Sort the areas according to the pressure sensor density in the monitoring area, map the sorting results to the corresponding multiple feature difference degrees, and obtain a difference degree sequence;

[0122] Perform curve fitting on the difference degree sequence to obtain a pressure expected difference curve;

[0123] Based on the HOG features, compare the feature differences of the monitoring areas in the temperature distribution map and the second distribution map, and generate a temperature control expected difference curve.

[0124] It should be noted that in the expected state, that is, the ideal condition of the sensor, under a certain load pressure, the measured data of the corresponding sensor is consistent with the test data, and there is no numerical deviation. The first distribution map and the second distribution map respectively correspond to the pressure and temperature distributions in the ideal state. A monitoring area corresponds to a bed frame part, which can be freely divided based on product requirements or functional requirements for refined analysis of the rationality of the sensor layout and regional control anomalies in different bed body parts. For example, multiple areas can be divided based on the up and down order, corresponding to the pressure monitoring of different parts of the human body. Here, the sensor density is used as the order for sequential analysis of different functional areas and different demand areas of the smart bed, to judge the difference deviation curve, and to perform deviation prediction in the follow-up, which can further trace the abnormal sensor area. The area sorting of the sensor density size is generally sorted from small to large. Curve fitting can be based on general linear fitting.

[0125] The pressure and temperature control expected difference curves reflect the change of the sensor monitoring accuracy deviation in the monitoring area based on two dimensions of pressure and temperature control under the current sensor layout state of the bed frame, from simple requirements to complex requirements.

[0126] It is worth noting here that, regarding the traditional bed frame sensor layout and the load test process of sensors, it often involves one-to-one comparison based on a single value, analyzing the numerical differences of each sensor and adjusting the layout based on manual experience. This process is time-consuming and laborious, making it difficult to achieve intelligent test analysis. It is also difficult to conduct expected difference analysis of sensors and predict abnormal difference trends for the target bed frame from the overall layout form and overall test status. Moreover, there is a lack of a regionalized sensor abnormal trend analysis process, making it difficult to capture potential abnormal sensor layout areas and trace the production processes with problems, resulting in low production efficiency of the bed frame in the intelligent bed body.

[0127] According to an embodiment of the present invention, the specific content of S4 is as follows:

[0128] Import the pressure expected difference curve and the temperature control expected difference curve into a linear regression model for linear regression fitting analysis, and conduct forward and reverse predictions based on the fitting results to evaluate the abnormal change trends of sensors in high-density areas and low-density areas;

[0129] For the pressure expected difference curve, generate a first predicted difference value and a second predicted difference value. If the difference mean of the first predicted difference value and the second predicted difference value is greater than a preset difference value, then compare the characteristic difference degree of each monitoring area with the difference mean to screen out abnormal pressure areas;

[0130] For the temperature control expected difference curve, generate a third predicted difference value and a fourth predicted difference value. If the difference mean of the third predicted difference value and the fourth predicted difference value is greater than a preset difference value, then compare the characteristic difference degree of each monitoring area with the difference mean to screen out abnormal temperature control areas;

[0131] Based on the abnormal pressure areas and abnormal temperature control areas, conduct abnormal source tracing analysis on the pressure sensors and temperature sensors, and adjust the preset sensor layout scheme.

[0132] It should be noted that in the analysis of abnormal pressure areas and abnormal temperature control areas, the corresponding two difference means represent different data. In the forward and reverse predictions here, the forward prediction is used to analyze the reasonable layout and abnormal conditions of sensors in high-density areas, while the reverse prediction is used to analyze the reasonable layout and abnormal conditions of sensors in low-density areas. The high and low density areas represent high and low sensor density areas. The forward and reverse predictions are the sequence forward prediction and reverse prediction, and they represent different regional trend analysis and abnormal change prediction directions respectively.

[0133] According to an embodiment of the present invention, in S2, each load condition includes a corresponding pressure distribution map and a temperature distribution map.

[0134] In a third aspect of the present invention, there is also provided a computer-readable storage medium, which includes an optimization program for bed frame processing based on model analysis. When the optimization program for bed frame processing based on model analysis is executed by a processor, the steps of the method for optimizing bed frame processing based on model analysis as described in any one of the above are implemented.

[0135] The present invention discloses a method and system for optimizing bed frame processing based on model analysis. Pressure and load tests are performed on a target bed frame, and pressure and temperature control data of different parts of the bed frame are collected through a preset sensor layout scheme. According to different load conditions, pressure and temperature distribution analyses are carried out, and numerical values are mapped with color depth to generate a pressure distribution map and a temperature distribution map. A pressure and temperature control distribution map in an expected state is generated. Through HOG feature extraction and difference calculation, the characteristic difference trends of the pressure and temperature distribution maps and the expected maps are evaluated, and pressure and temperature control expected difference curves are generated. A linear regression model is used to perform forward and backward predictions on the difference curves, the abnormal distribution trend is evaluated, the abnormal regions are screened in combination with the characteristic difference degree, and the source of the abnormal sensor layout is analyzed based on the abnormal regions. The present invention can accurately evaluate the performance of an intelligent bed frame and provide an effective basis for optimized design and maintenance.

[0136] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed with each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be electrical, mechanical, or other forms.

[0137] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units; they can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0138] In addition, each functional unit in the embodiments of the present invention can be all integrated in a processing unit, or each unit can be separately used as a unit, or two or more units can be integrated in one unit; the above integrated units can be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.

[0139] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps including those of the above method embodiments; and the foregoing storage medium includes: various media that can store program codes, such as removable storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0140] Alternatively, if the above integrated unit of the present invention is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. And the foregoing storage medium includes: various media that can store program codes, such as removable storage devices, ROM, RAM, magnetic disks, or optical discs.

[0141] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention.

Claims

1. An optimization method for bed frame processing based on model analysis, characterized in that, Including: S1: In the first test cycle, conduct pressure testing and load testing on the target bed frame, and collect pressure data and temperature control data of different bed frame parts through a preset sensor layout scheme; S2: Under different load conditions, conduct pressure and temperature distribution analysis based on the pressure data and temperature control data, map the distribution values with different color depths, and generate a pressure distribution map and a temperature distribution map of the target bed frame; S3: Generate a first distribution map and a second distribution map based on pressure and temperature control in the expected state under different load conditions, extract HOG features regionally from the pressure distribution map and the first distribution map and calculate the feature difference degree, and evaluate the feature difference trend in the order of each monitoring area of the distribution map to generate a pressure expected difference curve, and obtain a temperature control expected difference curve based on the HOG feature analysis of the temperature distribution map and the second distribution map; S4: According to the expected difference curve, introduce a linear regression model for forward and backward prediction, evaluate the abnormal trend of the pressure and temperature control distribution, screen out the abnormal areas under different load conditions in combination with the feature difference degree, and conduct abnormal source tracing analysis of the sensor layout according to the abnormal areas.

2. The optimized method for bed frame processing based on model analysis according to claim 1, wherein The specific content of S1 is: In the production test of the intelligent bed frame, set the first test cycle and the preset sensor layout scheme based on the target bed frame; In the preset sensor layout scheme, each different bed frame part includes no less than the preset number of temperature sensors and pressure sensors; Based on multiple load conditions, collect pressure data, temperature control data and test performance data of different bed frame parts, and perform data cleaning and outlier removal on the pressure data and temperature control data.

3. A method for optimizing the processing of a bed frame based on model analysis according to claim 1, characterized in that, The specific content of S2 is: Set a blank distribution map based on the sensor layout scheme of the bed frame, map the pressure range to the preset color range [0 - 255], and obtain an associated mapping table; Under a certain load pressure condition, according to the pressure data, mark the positions of the pressure sensors and the corresponding pressure monitoring values in the blank distribution map, introduce the associated mapping table, perform color value conversion on the pressure monitoring data values and fill them in the blank distribution map to obtain an initial distribution map; Using the positions of the pressure sensors as monitoring points, in the initial distribution map, fill the colors in the areas outside the monitoring points, and the filled color values are set according to the distance between the points to be filled and the nearest monitoring point, and generate a pressure distribution map; Conduct corresponding distribution analysis according to the temperature control data to generate a temperature distribution map.

4. A method for optimizing the processing of a bed frame based on model analysis according to claim 3, characterized in that, The specific content of S3 is: Based on a certain load pressure condition, set the numerical distribution of the pressure sensors and temperature sensors in the expected state, and perform color value mapping based on the numerical distribution to generate a first distribution map and a second distribution map; Divide multiple monitoring areas in the distribution map; In the pressure distribution map and the first distribution map, extract HOG features for the same monitoring area respectively, vectorize the HOG features to form a first feature vector and a second feature vector; Calculate the difference degree between the first feature vector and the second feature vector based on the Manhattan distance, and obtain the feature difference degree; Analyze each monitoring area to obtain multiple feature difference degrees; Perform regional sorting on the density of pressure sensors in the monitoring area, map the sorting results to corresponding multiple feature difference degrees, and obtain a difference degree sequence; Perform curve fitting on the difference degree sequence to obtain a pressure expected difference curve; Based on HOG features, compare the feature differences of the temperature distribution map and the second distribution map in the monitoring area, and generate a temperature control expected difference curve.

5. A method for optimizing the processing of a bed frame based on model analysis according to claim 1, characterized in that Specifically, S4 is as follows: Import the pressure expected difference curve and the temperature control expected difference curve into a linear regression model for linear regression fitting analysis, and perform forward and reverse predictions based on the fitting results to evaluate the abnormal change trends of the sensors in the high-density area and the low-density area; For the pressure expected difference curve, generate a first predicted difference value and a second predicted difference value. If the difference mean of the first predicted difference value and the second predicted difference value is greater than the preset difference value, then compare the feature difference degree of each monitoring area with the difference mean, and screen out the abnormal pressure area; For the temperature control expected difference curve, generate a third predicted difference value and a fourth predicted difference value. If the difference mean of the third predicted difference value and the fourth predicted difference value is greater than the preset difference value, then compare the feature difference degree of each monitoring area with the difference mean, and screen out the abnormal temperature control area; According to the abnormal pressure area and the abnormal temperature control area, perform abnormal source tracing analysis on the pressure sensor and the temperature sensor, and adjust the preset sensor layout scheme.

6. The optimized method for bed frame processing based on model analysis according to claim 1, characterized in that, In S2, each load condition includes a corresponding pressure distribution map and a temperature distribution map.

7. An optimized system for bed frame processing based on model analysis, characterized in that, The system includes: a memory and a processor. The memory includes an optimization program for bed frame processing based on model analysis. When the optimization program for bed frame processing based on model analysis is executed by the processor, the following steps are implemented: S1: In the first test cycle, perform pressure testing and load testing on the target bed frame, and collect pressure data and temperature control data of different bed frame parts through the preset sensor layout scheme; S2: Under different load conditions, perform pressure and temperature distribution analysis based on the pressure data and the temperature control data, map the distribution values with different color depths for representation, and generate a pressure distribution map and a temperature distribution map of the target bed frame; S3: Generate a first distribution map and a second distribution map based on pressure and temperature control in the expected state under different load conditions. Perform HOG feature extraction and feature difference degree calculation on the pressure distribution map and the first distribution map regionally, and evaluate the feature difference trend in the order of each monitoring area of the distribution map to generate a pressure expected difference curve. Analyze the temperature distribution map and the second distribution map based on HOG features to obtain a temperature control expected difference curve; S4: According to the expected difference curve, introduce a linear regression model for forward and reverse predictions, evaluate the abnormal distribution trends of pressure and temperature control, combine the feature difference degrees to screen out the abnormal areas under different load conditions, and perform abnormal source tracing analysis on the sensor layout according to the abnormal areas.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes an optimized program for bed frame processing based on model analysis. When the optimized program for bed frame processing based on model analysis is executed by a processor, the steps of the optimized method for bed frame processing based on model analysis according to any one of claims 1 to 6 are implemented.

Images