Intelligent perception-driven sleep-aiding scheme intelligent analysis method

Abstract

The invention discloses an intelligent analysis method for a sleep-aiding scheme driven by intelligent perception, and relates to the technical field related to data processing.The method comprises the steps that pressure sensing data and temperature sensing data of sleep of a user are sensed and collected through a sensor array arranged in sleep equipment in advance; performing integrated comfort analysis to obtain pressure comfort information and temperature comfort information of the user; performing screening and body position change analysis on the first user body position information sequence and the second user body position information sequence to obtain a body position change frequency; analyzing and calculating the sleep-aiding comfort level of the sleep-aiding scheme to obtain the sleep-aiding comfort level as an analysis result of the sleep-aiding scheme. The technical problems that in the prior art, it is difficult to comprehensively perceive and analyze the sleep state of the user to reflect the comfort level of the user, dynamic optimization based on body position changes is lacked, and consequently the scientificity and individuation of the sleep scheme of the user are insufficient are solved, and the technical effect of improving the analysis scientificity and individuation adaptation capacity of the sleep scheme is achieved.

Description

Technical Field

[0001] The present application relates to the technical field related to data processing, and in particular to an intelligent analysis method for sleep-aiding solutions driven by intelligent perception. Background Art

[0002] With the acceleration of people's pace of life and the increase of pressure, sleep problems have become one of the main factors affecting the health of modern people. As an important means to improve sleep quality, sleep aid devices have been widely used in recent years. However, most of the existing sleep aid solutions are based on fixed modes or simple parameter adjustments, such as adjusting the ambient brightness, humidity, temperature or mattress hardness, etc. Sleep aid devices usually lack the ability to fully perceive and dynamically analyze the user's sleep state, and cannot realize the integrated analysis of multi-dimensional data such as pressure distribution, temperature changes and body position adjustment, which makes it difficult to achieve the ideal level of sleep aid effect. Specifically, the sleep data collection in the existing technology is not comprehensive, especially during sleep, the perception of pressure distribution and temperature distribution data is omitted or inaccurate; lack of multi-dimensional comfort comprehensive evaluation, it is difficult to provide a comprehensive comfort analysis from multiple aspects such as pressure, temperature and body position changes; thus, the sleep aid solution does not fully consider the dynamic characteristics of the user's body position changes, and cannot optimize the sleep aid strategy according to the user's body position adjustment and change frequency, affecting the sleep aid effect and user experience.

[0003] At present, there are technical problems in the technologies related to sleep aid plan analysis, such as difficulty in comprehensively perceiving and analyzing the user's sleep state to reflect the user's comfort level, and lack of dynamic optimization based on changes in body position, which leads to the lack of scientificity and personalization of the user's sleep plan. Summary of the invention

[0004] This application solves the technical problems in the prior art that it is difficult to comprehensively perceive and analyze the user's sleep state to reflect the user's comfort, lacks dynamic optimization based on changes in body position, and leads to insufficient scientificity and personalization of the user's sleep plan by providing an intelligent analysis method for sleep aid plans driven by intelligent perception. This achieves the technical effect of improving the scientificity of sleep plan analysis and the personalized adaptation capabilities.

[0005] The present application provides an intelligent analysis method for a sleep aid scheme driven by intelligent perception, comprising: under the current sleep aid scheme, sensing and collecting pressure sensing data and temperature sensing data of a user's sleep through a sensor array pre-deployed in a sleep device, and obtaining a pressure distribution sequence and a temperature distribution sequence; performing an integrated comfort analysis based on the pressure distribution sequence and the temperature distribution sequence, and obtaining the user's pressure comfort information and temperature comfort information, wherein a perception integrity analysis is performed on the pressure distribution sequence and the temperature distribution sequence, and a pressure data complete coefficient sequence and a temperature data complete coefficient sequence are obtained, and an integrated comfort analysis is performed; user body position fitting is performed on the pressure distribution sequence and the temperature distribution sequence, and a first user body position information sequence and a second user body position information sequence are obtained, and the first user body position information sequence and the second user body position information sequence are screened and analyzed for body position changes based on the pressure data complete coefficient sequence and the temperature data complete coefficient sequence, and a body position change frequency is obtained; and a sleep aid comfort analysis and calculation of the sleep aid scheme is performed based on the pressure comfort information, the temperature comfort information, and the body position change frequency, and a sleep aid comfort is obtained as an analysis result of the sleep aid scheme.

[0006] In a possible implementation, under the current sleep-aiding scheme, through a sensor array pre-deployed in the sleep device, the pressure sensing data and temperature sensing data of the user's sleep are sensed and collected to obtain a pressure distribution sequence and a temperature distribution sequence, and the following processing is also performed: under the current sleep-aiding scheme, through a pressure sensor array pre-deployed in the sleep device, the pressure sensing data of multiple time nodes during the user's sleep are sensed and collected, wherein the sleep device includes a mattress; based on the position information array of the pressure sensor array and the pressure sensing data of multiple time nodes, multiple pressure distributions are constructed to obtain a pressure distribution sequence; through a temperature sensor array pre-deployed in the sleep device, the temperature sensing data of multiple time nodes during the user's sleep are sensed and collected to construct a temperature distribution sequence.

[0007] In a possible implementation, an integrated comfort analysis is performed based on the pressure distribution sequence and the temperature distribution sequence to obtain the user's pressure comfort information and temperature comfort information, and the following processing is also performed: a minimum pressure threshold and a minimum temperature threshold for the user to perform a sleep test are obtained, and the user's standard distribution ratio is obtained, wherein the standard distribution ratio is the ratio of pressure sensing data and temperature sensing data greater than or equal to the minimum pressure threshold and the minimum temperature threshold in the pressure distribution and the temperature distribution during the user's sleep; the ratio of pressure sensing data greater than or equal to the minimum pressure threshold in each pressure distribution in the pressure distribution sequence is screened to obtain a pressure distribution ratio sequence. ; Calculate the ratio of multiple pressure distribution proportions in the pressure distribution proportion sequence to the standard distribution proportion to obtain a complete coefficient sequence of pressure data; Screen the proportion of temperature sensor data greater than or equal to the minimum temperature threshold in each temperature distribution in the temperature distribution sequence to obtain a temperature distribution proportion sequence; Calculate the ratio of multiple temperature distribution proportions in the temperature distribution proportion sequence to the standard distribution proportion to obtain a complete coefficient sequence of temperature data; According to the complete coefficient sequence of pressure data and the complete coefficient sequence of temperature data, perform integrated comfort analysis on the pressure distribution sequence and the temperature distribution sequence to obtain the user's pressure comfort information and temperature comfort information.

[0008] In a possible implementation, an integrated comfort analysis is performed on the pressure distribution sequence and the temperature distribution sequence according to the complete coefficient sequence of pressure data and the complete coefficient sequence of temperature data, and the following processing is also performed: pressure comfort analysis is performed separately according to the multiple pressure distributions in the pressure distribution sequence to obtain multiple independent pressure comfort information; multiple pressure data weights are allocated according to the sizes of the multiple pressure data complete coefficients in the pressure data complete coefficient sequence, and the multiple independent pressure comfort information are weightedly calculated to obtain the pressure comfort information of the user; temperature comfort analysis is performed separately according to the multiple temperature distributions in the temperature distribution sequence to obtain multiple independent temperature comfort information; multiple temperature data weights are allocated according to the sizes of the multiple temperature data complete coefficients in the temperature data complete coefficient sequence, and the multiple independent temperature comfort information are weightedly calculated to obtain the temperature comfort information of the user.

[0009] In a possible implementation, pressure comfort analysis is performed separately according to the multiple pressure distributions in the pressure distribution sequence to obtain multiple independent pressure comfort information, and the following processing is also performed: based on the sleep test data of the user in the historical time, a sample pressure distribution set is collected, and the user's comfort level under different sample pressure distributions is collected to obtain a sample independent pressure comfort information set; the sample pressure distribution set and the sample independent pressure comfort information set are used to train a pressure comfort analyzer until the training converges; the multiple pressure distributions in the pressure distribution sequence are respectively input into the trained pressure comfort analyzer to identify and obtain multiple independent pressure comfort information.

[0010] In a possible implementation, user body position fitting is performed on the pressure distribution sequence and the temperature distribution sequence to obtain a first user body position information sequence and a second user body position information sequence, and the following processing is also performed: pressure sensing data greater than or equal to the minimum pressure threshold in each pressure distribution in the pressure distribution sequence is screened, and the corresponding sensor position information is indexed to obtain multiple user pressure position distributions; the multiple user pressure position distributions are fitted to obtain multiple first user body position graphics as first user body position information, and a first user body position information sequence is generated, wherein the first user body position information sequence corresponds to the complete coefficient sequence of the pressure data; temperature sensing data greater than or equal to the minimum temperature threshold in each temperature distribution in the temperature distribution sequence is screened, and the corresponding sensor position information is indexed to obtain multiple user temperature position distributions; the multiple user temperature position distributions are fitted to obtain multiple second user body position graphics as multiple second user body position information, and a second user body position information sequence is generated, wherein the second user body position information sequence corresponds to the complete coefficient sequence of the temperature data.

[0011] In a possible implementation, the first user body position information sequence and the second user body position information sequence are screened and the body position change analysis is performed on the complete coefficient sequence of pressure data and the complete coefficient sequence of temperature data to obtain the body position change frequency, and the following processing is also performed: according to the complete coefficient sequence of pressure data and the complete coefficient sequence of temperature data, the first user body position information and the second user body position information corresponding to the complete coefficient of pressure data and the complete coefficient of temperature data that are greater than or equal to a preset complete coefficient threshold value are screened to obtain a first qualified user body position information sequence and a second qualified user body position information sequence; according to the first qualified user body position information sequence and the second qualified user body position information sequence, the first change number and the second change number of qualified user body position information changes are respectively extracted; the first change number and the second change number are divided by the total time of the first qualified user body position information sequence and the second qualified user body position information sequence, respectively, to obtain the first body position change frequency and the second body position change frequency; the mean of the first body position change frequency and the second body position change frequency are calculated to obtain the body position change frequency.

[0012] In a possible implementation, the sleep aid comfort analysis and calculation of the sleep aid scheme is performed based on the pressure comfort information, temperature comfort information and body position change frequency to obtain the sleep aid comfort as the analysis result of the sleep aid scheme, and the following processing is also performed: based on the body position change frequency, the body position comfort is obtained by classification, wherein a sample body position change frequency set and a sample body position comfort set are collected, a mapping classification table is constructed, and the body position change frequency is input into the mapping classification table to obtain the body comfort by classification; the pressure comfort information, temperature comfort information and body position comfort are weightedly calculated to obtain the sleep aid comfort as the analysis result of the sleep aid scheme.

[0013] The intelligent analysis method of the sleep aid program driven by intelligent perception proposed in this application is to sense and collect the pressure sensor data and temperature sensor data of the user's sleep through the sensor array pre-deployed in the sleep device; perform integrated comfort analysis to obtain the user's pressure comfort information and temperature comfort information; screen the first user's body position information sequence and the second user's body position information sequence and perform body position change analysis to obtain the body position change frequency; perform sleep aid comfort analysis and calculation of the sleep aid program to obtain the sleep aid comfort as the analysis result of the sleep aid program. It solves the technical problems existing in the prior art that it is difficult to fully perceive and analyze the user's sleep state to reflect the user's comfort, lacks dynamic optimization based on body position changes, and leads to insufficient scientificity and personalization of the user's sleep program, and achieves the technical effect of improving the scientificity of sleep program analysis and personalized adaptation capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A schematic diagram of a process of an intelligent analysis method of a sleep-aiding solution driven by intelligent perception provided in an embodiment of the present application; Figure 2 A schematic diagram of the process of performing user posture fitting in the intelligent analysis method of the intelligent perception-driven sleep aid solution provided in an embodiment of the present application. DETAILED DESCRIPTION

[0016] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0017] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0018] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0019] The present application embodiment provides an intelligent analysis method for a sleep aid solution driven by intelligent perception, such as Figure 1 As shown, the method includes: Step S100, under the current sleep aid solution, the pressure sensing data and temperature sensing data of the user's sleep are sensed and collected through the sensor array pre-deployed in the sleep device to obtain the pressure distribution sequence and the temperature distribution sequence.

[0020] Preferably, the sensor array includes a plurality of pressure sensors and temperature sensors, and the sensor array is arranged according to a certain spacing and arrangement rules to achieve comprehensive coverage of the user's body contact area. Specifically, under the current sleep aid scheme, pressure sensors arranged on the surface or inside of the sleep device (such as a mattress, pillow), and temperature sensors arranged on the surface of the sleep device or close to the user's body area are used to sense and collect the pressure value when the user's body contacts the device (such as the back, shoulders, buttocks, etc.), the temperature of the user's body in contact with the mattress, and the temperature of other empty areas, and the temperature and pressure values ​​at the user's location are greater than those in other empty areas, and the temperature and pressure values ​​are sensed at a certain time interval (such as once per second). The device collects pressure values ​​and temperature values ​​to form a continuous time series, and then generates a pressure distribution sequence and a temperature distribution sequence. The pressure distribution sequence reflects the force applied to different parts of the user's body on the sleep device, such as the pressure distribution of the shoulders, back and buttocks, and can detect high-pressure areas (such as excessive local pressure due to improper posture) or low-pressure areas (such as the device does not effectively support the body). For example, when the user lies on his side, the pressure on the shoulders and buttocks is greater, forming a high-pressure area, and the pressure on the back is less, forming a low-pressure area; the temperature distribution sequence reflects the temperature changes during the user's sleep, including the user's local body temperature and ambient temperature, monitors the temperature difference changes, and determines whether the device effectively adjusts the temperature (such as cooling or heating functions).

[0021] Furthermore, step S100 also includes step S110, under the current sleep aid scheme, sensing and collecting pressure sensing data at multiple time nodes during the user's sleep through a pressure sensor array pre-deployed in the sleep device, wherein the sleep device includes a mattress; step S120, constructing multiple pressure distributions according to the position information array of the pressure sensor array and the pressure sensing data of multiple time nodes to obtain a pressure distribution sequence; step S130, sensing and collecting temperature sensing data at multiple time nodes during the user's sleep through a temperature sensor array pre-deployed in the sleep device to construct a temperature distribution sequence.

[0022] Preferably, the pressure sensor array is pre-arranged on the surface or inside of the sleeping device (mattress), covering the user contact area, such as the head, back, waist and buttocks. Multiple time nodes are set during the sleep process to monitor the user's body support and contact pressure changes during sleep, that is, the pressure sensor senses the pressure size at each position in real time and outputs it as a digital signal. The position coordinates of the pressure sensor in the mattress are used to mark the position of each sensor. Each time node corresponds to a pressure distribution matrix, which describes the pressure distribution of the user's body at that moment. The pressure distribution matrices at different time nodes are arranged in chronological order to form a pressure distribution sequence; similarly, the temperature sensor array is arranged on the mattress surface or in an area close to the user's body to sense local body temperature and ambient temperature. It is usually arranged in the user's main contact area, such as the head, back and buttocks, to monitor the dynamic changes of body temperature and device temperature. The same time node is set, and each sensor records the temperature value at the current position. Each time node corresponds to a temperature distribution matrix, which describes the temperature distribution of the user's body and the mattress. The temperature distribution matrices at different time nodes are arranged in chronological order to form a temperature distribution sequence.

[0023] Step S200, performing an integrated comfort analysis based on the pressure distribution sequence and the temperature distribution sequence to obtain the user's pressure comfort information and temperature comfort information, wherein a perceptual integrity analysis is performed on the pressure distribution sequence and the temperature distribution sequence to obtain a complete coefficient sequence of pressure data and a complete coefficient sequence of temperature data, and an integrated comfort analysis is performed.

[0024] Preferably, the user's pressure comfort and temperature comfort are analyzed respectively according to the pressure distribution sequence and the temperature distribution sequence, that is, the pressure distribution sequence and the temperature distribution sequence are subjected to a perceptual integrity analysis to determine incomplete pressure data and temperature data, thereby obtaining a complete coefficient sequence of pressure data and a complete coefficient sequence of temperature data, and performing an integrated comfort analysis to obtain the user's pressure comfort information and temperature comfort information. Specifically, the sensor array may have data acquisition errors or short-term failures, resulting in incomplete collected pressure data and temperature data. The perceptual integrity analysis is to evaluate the pressure and temperature data collected by the sensor to determine whether the data is complete and reliable, and eliminate the interference of incomplete or erroneous data on the comfort analysis, that is, to check whether there are missing data points or abnormal data (such as pressure values ​​beyond a reasonable range) in the pressure distribution sequence, and to check whether there are mutations or inconsistent data (such as excessively large or low temperature differences) in the temperature distribution sequence, to quantify the integrity of the pressure and temperature data, and to generate a complete coefficient sequence of pressure data and a complete coefficient sequence of temperature data.

[0025] Preferably, pressure comfort information analysis is performed to evaluate whether the pressure distribution of various parts of the user's body is uniform during sleep, identify potential discomfort areas, that is, detect the pressure concentration areas of the user's body (such as shoulders and buttocks), determine whether they exceed the comfort range, and at the same time determine whether the pressure distribution is uniform and check whether the support is reasonable; temperature comfort information analysis is performed to evaluate whether the user's temperature distribution is within the comfort range, determine whether the ambient temperature and body temperature are balanced, that is, analyze the temperature difference of various parts of the user's body, check whether there is local overcooling or overheating, and evaluate the stability of the temperature distribution, and identify sudden temperature changes; then integrated comfort analysis, that is, comprehensive analysis of pressure comfort and temperature comfort, to form an overall comfort evaluation, specifically, according to the goals of the sleep aid program and user needs, set the weights of pressure comfort and temperature comfort, and weight multiple independent pressure comfort and independent temperature comfort of multiple distribution analyses to improve data accuracy, for example, the pressure comfort weight is 0.6, and the temperature comfort weight is 0.4, wherein, if the integrity of the pressure or temperature data is low (such as more missing data or more outliers), the corresponding weight needs to be reduced to reduce the interference of incomplete data on the results.

[0026] Further, step S200 also includes step S210, obtaining the minimum pressure threshold and minimum temperature threshold of the user for the sleep test, and obtaining the standard distribution ratio of the user, wherein the standard distribution ratio is the ratio of the pressure sensor data and temperature sensor data greater than or equal to the minimum pressure threshold and the minimum temperature threshold in the pressure distribution and the temperature distribution during the user's sleep; step S220, screening the ratio of the pressure sensor data greater than or equal to the minimum pressure threshold in each pressure distribution in the pressure distribution sequence to obtain a pressure distribution ratio sequence; step S230, calculating the ratios of multiple pressure distributions and the standard distribution ratio in the pressure distribution ratio sequence Step S240, screening the proportion of temperature sensing data greater than or equal to the minimum temperature threshold in each temperature distribution in the temperature distribution sequence to obtain a temperature distribution proportion sequence; Step S250, calculating the ratio of multiple temperature distribution proportions in the temperature distribution proportion sequence to the standard distribution proportion to obtain a complete temperature data coefficient sequence; Step S260, performing integrated comfort analysis on the pressure distribution sequence and the temperature distribution sequence according to the complete pressure data coefficient sequence and the complete temperature data coefficient sequence to obtain the user's pressure comfort information and temperature comfort information.

[0027] Preferably, the lowest support pressure value that the user feels comfortable during sleep is obtained through a sleep test as the minimum pressure threshold, and the lowest temperature value that the user feels comfortable during sleep is obtained as the minimum temperature threshold, and the standard distribution proportion of the user is calculated, that is, the proportion of pressure sensor data and temperature sensor data that are greater than or equal to the minimum pressure threshold and the minimum temperature threshold in the pressure distribution and temperature distribution during the user's sleep. The larger the user's body shape, the larger the proportion. Then, for each pressure distribution in the pressure distribution sequence, the sensor data that meets the minimum pressure threshold is screened out, and the proportion that meets the threshold in each pressure distribution is calculated to obtain a pressure distribution proportion sequence. The ratio of multiple pressure distribution proportions to the standard distribution proportion in the pressure distribution proportion sequence is calculated to obtain a complete coefficient sequence of pressure data. If the ratio is equal to or even greater than 1, it is complete, and if it is less than 1, it is incomplete, which may be due to temporary failure of some sensors or acquisition errors.

[0028] Preferably, for each temperature distribution in the temperature distribution sequence, the sensor data that meets the minimum temperature threshold is screened out, the proportion of each temperature distribution that meets the threshold is calculated to obtain a temperature distribution proportion sequence, and then the degree of matching between each temperature distribution proportion and the standard distribution proportion is measured, that is, the ratio of multiple temperature distribution proportions to the standard distribution proportion in the temperature distribution proportion sequence is calculated to obtain a complete coefficient sequence of temperature data, and based on the complete coefficient sequences of pressure and temperature data, the pressure distribution sequence and the temperature distribution sequence are comprehensively analyzed, that is, the complete coefficient sequence of pressure data and the complete coefficient sequence of temperature data are weightedly calculated to quantify the user's comfort, and the user's pressure comfort information and temperature comfort information are obtained.

[0029] Furthermore, step S260 also includes step S261, performing pressure comfort analysis respectively according to multiple pressure distributions in the pressure distribution sequence to obtain multiple independent pressure comfort information; step S262, allocating multiple pressure data weights according to the sizes of multiple pressure data complete coefficients in the pressure data complete coefficient sequence, weightedly calculating the multiple independent pressure comfort information to obtain the user's pressure comfort information; step S263, performing temperature comfort analysis respectively according to multiple temperature distributions in the temperature distribution sequence to obtain multiple independent temperature comfort information; step S264, allocating multiple temperature data weights according to the sizes of multiple temperature data complete coefficients in the temperature data complete coefficient sequence, weightedly calculating the multiple independent temperature comfort information to obtain the user's temperature comfort information.

[0030] Preferably, a pressure comfort analysis is performed on multiple pressure distributions in the pressure distribution sequence, that is, for the pressure distribution matrix of each time node, the uniformity of pressure values, high pressure areas and low pressure areas are detected to evaluate the impact of the pressure distribution at each time point on user comfort, each time point corresponds to an independent pressure comfort value, forming multiple independent pressure comfort information, and then according to the size of the coefficients in the complete coefficient sequence of pressure data, weights are assigned and the user pressure comfort information is calculated; a temperature comfort analysis is performed on multiple temperature distributions in the temperature distribution sequence, that is, for the temperature distribution matrix of each time node, whether the temperature difference is uniform and whether it is within the ideal temperature range is analyzed to evaluate the impact of the temperature distribution at each time point on user comfort, each time point corresponds to an independent temperature comfort value, forming multiple independent temperature comfort information, and according to the size of the coefficients in the complete coefficient sequence of temperature data, weights are assigned and the user temperature comfort information is calculated.

[0031] Furthermore, step S261 also includes step S261a, collecting a sample pressure distribution set based on the user's sleep test data in the historical time, and collecting the user's comfort level under different sample pressure distributions to obtain a sample independent pressure comfort information set; step S261b, using the sample pressure distribution set and the sample independent pressure comfort information set to train the pressure comfort analyzer until the training converges; step S261c, respectively inputting the multiple pressure distributions in the pressure distribution sequence into the trained pressure comfort analyzer to identify and obtain multiple independent pressure comfort information.

[0032] Preferably, multiple groups of pressure distributions in the user's historical sleep test data constitute a sample pressure distribution set, and each group of pressure distribution reflects the pressure distribution characteristics of the user's body at different time points or sleep conditions, wherein the pressure distribution matrix of the user under multiple test conditions (such as different mattress hardness, different sleeping postures) is recorded by the pressure sensor array on the mattress, and the user's comfort level under different sample pressure distributions is collected at the same time, that is, the user's subjective comfort evaluation of each sample pressure distribution, for example, the user scores each pressure distribution sample according to his feelings (such as 1 to 10 points), and outputs a sample independent pressure comfort information set, and then by learning the sample pressure distribution set and the corresponding comfort level, a prediction model is constructed based on machine learning (such as linear regression, decision tree, neural network, etc.), and the prediction model is trained until convergence with the sample pressure distribution as the input feature and the sample independent pressure comfort information as the target value to obtain a pressure comfort analyzer, and finally each pressure distribution in the real-time collected pressure distribution sequence is input into the pressure comfort analyzer to calculate and obtain multiple independent pressure comfort information.

[0033] Step S300, performing user body position fitting on the pressure distribution sequence and the temperature distribution sequence to obtain a first user body position information sequence and a second user body position information sequence, and screening and performing body position change analysis on the first user body position information sequence and the second user body position information sequence according to the pressure data complete coefficient sequence and the temperature data complete coefficient sequence to obtain a body position change frequency.

[0034] Preferably, according to the position of the detected higher temperature and pressure data, the image contour of the user's sleeping position on the mattress can be fitted and obtained, and then the frequency of the user's position change can be analyzed, wherein, according to the complete coefficient sequence of the pressure data and the complete coefficient sequence of the temperature data, the pressure distribution and temperature distribution with complete coefficients greater than the threshold value are screened to fit the user's position graphic contour to improve accuracy. Specifically, the user position fitting is to infer the user's specific position (such as supine, side-lying, prone) during sleep and its related information based on the model trained with historical data (such as decision tree, support vector machine) by analyzing the pressure distribution sequence and the temperature distribution sequence. The first user body position information sequence and the second user body position information sequence are generated by the changes in pressure values ​​of different parts of the body, wherein the distribution of support points of the user's body is judged by using the changes in pressure values ​​of different parts. For example, if the pressure on the shoulders and hips is higher and distributed on both sides, it may be side lying, and if the pressure on the back is evenly distributed, it may be supine. The change information of the user's body position (such as the change in body position caused by pressure change) is used as the first user body position information sequence; the temperature change of different parts of the body is used to assist in judging the user's body position. For example, if the temperature of the abdomen and chest is higher, it may be prone lying, and the temperature characteristics of the body position change (such as local temperature change caused by side lying) are used as the second user information sequence.

[0035] Preferably, the first user's body position information sequence and the second user's body position information sequence are screened and the body position change analysis is performed based on the pressure data integrity coefficient sequence and the temperature data integrity coefficient sequence. The pressure data integrity coefficient and the temperature data integrity coefficient are used to screen reliable body position information sequences and eliminate incorrect fitting caused by missing or abnormal data. Specifically, if the pressure data integrity coefficient of a certain time period is lower than a threshold, the pressure data of the time period is considered unavailable and the corresponding body position information is eliminated. Similarly, if the temperature data integrity coefficient is lower than a threshold, the temperature body position information of the time period is eliminated. For the same time period, if both the pressure and temperature data pass the screening, the two types of body position information are merged to further improve the accuracy of body position fitting. Body position change analysis refers to analyzing the changes in the user's body position during sleep, including the frequency, amplitude and regularity of the position changes. Specifically, the first user's body position information sequence is compared with the second user's body position information sequence to identify the time when the position change occurs. For example, the time point when changing from side lying to supine can be detected by the redistribution of pressure distribution and temperature change. Then, it is determined whether the amplitude of the position change is a local adjustment (such as slight movement of the shoulder) or an overall change (such as changing from supine to prone). The frequency of body position change is then obtained, that is, the number of times the user's body position changes per unit time. For example, a high frequency of position change (such as more than 10 times per hour) may indicate that the user's sleeping environment is not comfortable or the body is uncomfortable.

[0036] Further, such as Figure 2 As shown, step S300 also includes step S310, screening the pressure sensing data greater than or equal to the minimum pressure threshold in each pressure distribution in the pressure distribution sequence, and indexing the corresponding sensor position information to obtain multiple user pressure position distributions; step S320, fitting the multiple user pressure position distributions, obtaining multiple first user body position graphics as first user body position information, and generating a first user body position information sequence, wherein the first user body position information sequence corresponds to the complete coefficient sequence of the pressure data; step S330, screening the temperature sensing data greater than or equal to the minimum temperature threshold in each temperature distribution in the temperature distribution sequence, and indexing the corresponding sensor position information to obtain multiple user temperature position distributions; step S340, fitting the multiple user temperature position distributions, obtaining multiple second user body position graphics as multiple second user body position information, and generating a second user body position information sequence, wherein the second user body position information sequence corresponds to the complete coefficient sequence of the temperature data.

[0037] Preferably, data greater than or equal to a minimum pressure threshold is screened out from each pressure distribution, indicating that the user's body contacts the support area of ​​the mattress, and the sensor position information is indexed at the same time, that is, for each screened pressure data point, its corresponding position index is recorded, and a corresponding user pressure position distribution is generated at each time point, which is represented as a set of sensor positions, thereby obtaining multiple user pressure position distributions, and based on the user pressure position distribution, a fitting algorithm (such as polygon fitting or contour line generation) is used to draw a pressure graph of the user according to the sensor position, and a body contour graph of the user is fitted to reflect the sleeping position as the first user position information, and the user position information at each time point is arranged in chronological order to form the first user position information. information sequence; similarly, data greater than or equal to the minimum temperature threshold is screened out from each temperature distribution, indicating the contact area or high temperature area between the user's body and the mattress, and for each screened temperature data point, its corresponding position index is recorded, and a user temperature position distribution is generated at each time point, which is represented as a set of sensor positions, and multiple user temperature position distributions are obtained. Then, based on the user temperature position distribution, a fitting algorithm (such as Gaussian fitting or curve interpolation) is used to draw the user's temperature graph, and the user's temperature position graph is fitted to reflect the temperature characteristics of the body contact area as the second user position information, and then the user temperature position information at each time point is arranged in chronological order to form a second user position information sequence.

[0038] Furthermore, step S300 also includes step S350, screening the first user body position information and the second user body position information corresponding to the pressure data complete coefficient and the temperature data complete coefficient that are greater than or equal to a preset complete coefficient threshold value according to the pressure data complete coefficient sequence and the temperature data complete coefficient sequence, to obtain a first qualified user body position information sequence and a second qualified user body position information sequence; step S360, respectively extracting the first change number and the second change number of qualified user body position information changes according to the first qualified user body position information sequence and the second qualified user body position information sequence; step S370, respectively dividing the first change number and the second change number by the total time of the first qualified user body position information sequence and the second qualified user body position information sequence to obtain a first body position change frequency and a second body position change frequency; step S380, calculating the average of the first body position change frequency and the second body position change frequency to obtain the body position change frequency.

[0039] Preferably, according to the complete coefficient sequence of pressure data and the complete coefficient sequence of temperature data, the pressure and temperature body position information that meets the preset complete coefficient threshold value is screened out, that is, the influence of low-integrity data on the analysis is eliminated, and the data greater than or equal to the preset complete coefficient threshold value is retained to obtain the first qualified user body position information sequence and the second qualified user body position information sequence, and the number of changes of the user's body position in the qualified body position information sequence is analyzed, wherein, if the body position information of two adjacent time points is different, it is counted as one body position change, such as comparing body position graphics (for example, the similarity of contours, the proportion of overlapping areas), such as when the area of ​​the graphics change exceeds 10%, it is considered that a body position change has occurred, and the changes that have occurred are extracted , or if the similarity is lower than a preset threshold, it is determined to be a body position change, and then the first change number and the second change number of the qualified user's body position information are extracted according to the first qualified user body position information sequence and the second qualified user body position information sequence, which respectively represent the change times of pressure body position and temperature body position; then the first change number and the second change number are divided by the total time of the first qualified user body position information sequence and the second qualified user body position information sequence, respectively, to obtain the first body position change frequency and the second body position change frequency, reflecting the user's dynamic body position adjustment under the sleep aid program; finally, the average of the first body position change frequency and the second body position change frequency is calculated to obtain the body position change frequency.

[0040] Step S400, performing sleep aid comfort analysis and calculation of the sleep aid program according to the pressure comfort information, the temperature comfort information and the body position change frequency, and obtaining sleep aid comfort as the analysis result of the sleep aid program.

[0041] Preferably, the sleep comfort of the user is quantified by comprehensively analyzing multi-dimensional data to evaluate the effect of the current sleep aid program, that is, the sleep comfort analysis and calculation of the sleep aid program is performed according to the pressure comfort information, temperature comfort information and body position change frequency, which means weighting the pressure comfort, temperature comfort and body position comfort corresponding to the body position change frequency to obtain the final sleep aid comfort, wherein the sleep aid comfort is used to quantify the overall sleep comfort of the user under the current sleep aid program, reflecting the comprehensive impact of pressure, temperature and body position changes on sleep quality. Specifically, the pressure comfort information, temperature comfort information and body position change comfort are used as input data and are standardized to unify their numerical ranges (such as 0 to 1), wherein the body position change comfort is used to evaluate whether the body position change is in an appropriate range, that is, to set an ideal body position change frequency range ( The deviation between the actual frequency and the ideal range is calculated. The closer the score is to the ideal range, the higher the comfort level is. Then, according to the goal of the sleep aid program, a weight is assigned to the comfort level of each dimension. For example, a weight of 0.5 for pressure comfort, 0.3 for temperature comfort, and 0.2 for frequency of position change. The sleep aid comfort level is calculated comprehensively to quantify the user's overall experience under the current sleep aid program. The sleep aid comfort level is usually between 0 and 1. The higher the score, the better the effect of the current sleep aid program. For example, a sleep aid comfort level between 0.8 and 1 indicates that the sleep aid program is very effective and the user sleeps well. A sleep aid comfort level between 0.6 and 0.8 indicates that the sleep aid program is effective but there is still room for optimization. A sleep aid comfort level below 0.6 indicates that the sleep aid program needs to be adjusted and the user may feel uncomfortable. This is used as the analysis result of the sleep aid program.

[0042] Furthermore, step S400 also includes step S410, classifying and obtaining body position comfort according to the body position change frequency, wherein a sample body position change frequency set and a sample body position comfort set are collected, a mapping classification table is constructed, and the body position change frequency is input into the mapping classification table to classify and obtain the body position comfort; step S420, weighted calculation of the pressure comfort information, temperature comfort information and body position comfort is performed to obtain sleep aid comfort as the analysis result of the sleep aid program.

[0043] Preferably, the body position comfort is obtained according to the body position change frequency classification, that is, a sample body position change frequency set and a sample body position comfort set are collected from historical data, and a mapping classification table is constructed according to the sample body position change frequency and the sample body position comfort, which is used to infer new body position comfort, and can more accurately quantify the user's body position comfort. Specifically, the sample body position change frequency is divided into several intervals, and a corresponding body position comfort value is defined for each interval. Then, the body position change frequency is input into the mapping classification table, and the corresponding body position comfort value is found; finally, the pressure comfort information, temperature comfort information and body comfort are weightedly calculated to obtain the sleep-aid comfort. Specifically, according to the design goal of the sleep-aid program, the weights of the three are assigned, and the sleep-aid comfort is weightedly calculated as the analysis result of the sleep-aid program.

[0044] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. An intelligent analysis method for sleep-aiding solutions driven by intelligent perception, characterized in that: The method comprises: Under the current sleep aid solution, the pressure sensing data and temperature sensing data of the user's sleep are sensed and collected through the sensor array pre-deployed in the sleep device to obtain the pressure distribution sequence and temperature distribution sequence; Performing integrated comfort analysis according to the pressure distribution sequence and the temperature distribution sequence to obtain the user's pressure comfort information and temperature comfort information, wherein the pressure distribution sequence and the temperature distribution sequence are subjected to a perception integrity analysis to obtain a pressure data complete coefficient sequence and a temperature data complete coefficient sequence, and performing integrated comfort analysis; Performing user body position fitting on the pressure distribution sequence and the temperature distribution sequence to obtain a first user body position information sequence and a second user body position information sequence, and screening and performing body position change analysis on the first user body position information sequence and the second user body position information sequence according to the pressure data complete coefficient sequence and the temperature data complete coefficient sequence to obtain a body position change frequency; The sleep aid comfort analysis and calculation of the sleep aid scheme is performed according to the pressure comfort information, the temperature comfort information and the frequency of body position changes to obtain the sleep aid comfort as the analysis result of the sleep aid scheme.

2. The intelligent analysis method for sleep-aiding programs driven by intelligent perception according to claim 1, characterized in that: In the current sleep aid solution, the sensor array pre-installed in the sleep device senses and collects the user's sleep pressure sensing data and temperature sensing data to obtain the pressure distribution sequence and temperature distribution sequence, including: Under the current sleep aid solution, a pressure sensor array pre-deployed in a sleep device is used to sense and collect pressure sensing data at multiple time points during the user's sleep, wherein the sleep device includes a mattress; According to the position information array of the pressure sensor array, multiple pressure distributions are constructed in combination with the pressure sensing data of multiple time nodes to obtain a pressure distribution sequence Through the temperature sensor array pre-deployed in the sleep device, the temperature sensing data of multiple time nodes during the user's sleep is sensed and collected to construct a temperature distribution sequence.

3. The intelligent analysis method for sleep-aiding programs driven by intelligent perception according to claim 1 is characterized in that: According to the pressure distribution sequence and the temperature distribution sequence, an integrated comfort analysis is performed to obtain the pressure comfort information and the temperature comfort information of the user, including: Obtaining a minimum pressure threshold and a minimum temperature threshold for a user to perform a sleep test, and obtaining a standard distribution ratio of the user, wherein the standard distribution ratio is a ratio of pressure sensing data and temperature sensing data greater than or equal to the minimum pressure threshold and the minimum temperature threshold in the pressure distribution and the temperature distribution during the user's sleep; Screening the proportion of pressure sensing data in each pressure distribution in the pressure distribution sequence that is greater than or equal to the minimum pressure threshold to obtain a pressure distribution proportion sequence; Calculating the ratios of multiple pressure distribution ratios in the pressure distribution ratio sequence to the standard distribution ratio to obtain a complete coefficient sequence of pressure data; Screening the proportion of temperature sensing data greater than or equal to the minimum temperature threshold in each temperature distribution in the temperature distribution sequence to obtain a temperature distribution proportion sequence; Calculating the ratio of multiple temperature distribution proportions in the temperature distribution proportion sequence to the standard distribution proportion to obtain a complete coefficient sequence of temperature data; According to the complete coefficient sequence of pressure data and the complete coefficient sequence of temperature data, an integrated comfort analysis is performed on the pressure distribution sequence and the temperature distribution sequence to obtain the pressure comfort information and temperature comfort information of the user.

4. The intelligent analysis method for sleep-aiding programs driven by intelligent perception according to claim 3 is characterized in that: According to the complete coefficient sequence of the pressure data and the complete coefficient sequence of the temperature data, an integrated comfort analysis is performed on the pressure distribution sequence and the temperature distribution sequence, including: According to the multiple pressure distributions in the pressure distribution sequence, respectively, pressure comfort analysis is performed to obtain multiple independent pressure comfort information; According to the sizes of the multiple pressure data complete coefficients in the pressure data complete coefficient sequence, multiple pressure data weights are allocated, and the multiple independent pressure comfort information are weightedly calculated to obtain the pressure comfort information of the user; According to the multiple temperature distributions in the temperature distribution sequence, respectively, temperature comfort analysis is performed to obtain multiple independent temperature comfort information; According to the sizes of multiple temperature data complete coefficients in the temperature data complete coefficient sequence, multiple temperature data weights are allocated, and the multiple independent temperature comfort information are weightedly calculated to obtain the user's temperature comfort information.

5. The intelligent analysis method for sleep-aiding programs driven by intelligent perception according to claim 4 is characterized in that: According to the multiple pressure distributions in the pressure distribution sequence, pressure comfort analysis is performed respectively to obtain multiple independent pressure comfort information, including: According to the sleep test data of the user in the historical time, a sample pressure distribution set is collected, and the user's comfort level under different sample pressure distributions is collected to obtain a sample independent pressure comfort information set; Using the sample pressure distribution set and the sample independent pressure comfort information set, training a pressure comfort analyzer until training converges; The multiple pressure distributions in the pressure distribution sequence are respectively input into a trained pressure comfort analyzer to identify and obtain multiple independent pressure comfort information.

6. The intelligent analysis method for sleep-aiding programs driven by intelligent perception according to claim 3 is characterized in that: Performing user body position fitting on the pressure distribution sequence and the temperature distribution sequence to obtain a first user body position information sequence and a second user body position information sequence includes: Filtering the pressure sensing data in each pressure distribution in the pressure distribution sequence that is greater than or equal to the minimum pressure threshold, and indexing the corresponding sensor position information to obtain pressure position distributions of multiple users; Fitting the pressure position distributions of the multiple users to obtain multiple first user body position graphics as first user body position information, and generating a first user body position information sequence, wherein the first user body position information sequence corresponds to the complete coefficient sequence of the pressure data; Filtering the temperature sensing data greater than or equal to the minimum temperature threshold in each temperature distribution in the temperature distribution sequence, and indexing the corresponding sensor position information to obtain temperature position distributions of multiple users; Fit the temperature position distributions of the multiple users to obtain multiple second user body position graphics as multiple second user body position information, and generate a second user body position information sequence, wherein the second user body position information sequence corresponds to the complete coefficient sequence of the temperature data.

7. The intelligent analysis method for sleep-aiding programs driven by intelligent perception according to claim 6, characterized in that: According to the complete coefficient sequence of pressure data and the complete coefficient sequence of temperature data, the first user body position information sequence and the second user body position information sequence are screened and body position change analysis is performed to obtain a body position change frequency, including: According to the pressure data complete coefficient sequence and the temperature data complete coefficient sequence, first user body position information and second user body position information corresponding to pressure data complete coefficients and temperature data complete coefficients that are greater than or equal to a preset complete coefficient threshold value are screened to obtain a first qualified user body position information sequence and a second qualified user body position information sequence; According to the first qualified user body position information sequence and the second qualified user body position information sequence, respectively extracting a first change number and a second change number of changes in the qualified user body position information; The first change number and the second change number are divided by the total time of the first qualified user body position information sequence and the second qualified user body position information sequence to obtain a first body position change frequency and a second body position change frequency; The average of the first body position change frequency and the second body position change frequency is calculated to obtain the body position change frequency.

8. The intelligent analysis method for sleep-aiding programs driven by intelligent perception according to claim 7, characterized in that: According to the pressure comfort information, the temperature comfort information and the frequency of body position changes, the sleep aid comfort analysis and calculation of the sleep aid scheme is performed to obtain the sleep aid comfort as the analysis result of the sleep aid scheme, including: According to the body position change frequency, the body position comfort is obtained by classification, wherein a sample body position change frequency set and a sample body position comfort set are collected, a mapping classification table is constructed, and the body position change frequency is input into the mapping classification table to obtain the body position comfort by classification; The pressure comfort information, temperature comfort information and body position comfort are weightedly calculated to obtain the sleep-aiding comfort as the analysis result of the sleep-aiding scheme.

Images