Intelligent bed snore stopping system, control method and device

Abstract

The invention relates to the technical field of sleep detection, in particular to an intelligent bed snore stopping system and a control method and device.The system comprises an intelligent bed and a control unit; a detection sensor and an air bag are arranged on the intelligent bed; a sound signal acquisition sensor in the detection sensor acquires sound signals in a sleep environment of a user and extracts related acoustic characteristic parameters from the sound signals; a body information acquisition sensor in the detection sensor monitors multi-dimensional body information of a user and judges the sleep state of the user; the control unit carries out quantitative analysis on the snoring condition of the user based on data sent by the detection sensor so as to obtain an air bag adjusting strategy, and sends a control instruction to the multiple air bags so as to carry out air bag inflation and deflation work. The sleep state of the user can be monitored in an all-around mode, the snoring reason is accurately analyzed, efficient snoring stopping is achieved through intelligent adjustment, and the overall sleep quality is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of sleep detection, and particularly to an intelligent bed anti-snoring system, a control method and a device. Background Art

[0002] Snoring, as a common sleep problem, not only affects the rest of others, but also has an adverse impact on one's own health and sleep quality.

[0003] Existing anti-snoring products and methods are still insufficient in terms of accuracy, intelligence, and comprehensive consideration of improving the overall sleep quality. In terms of accuracy, many traditional anti-snoring products lack precise analysis of the causes and specific conditions of snoring. For example, some simple anti-snoring monitoring devices can only detect the presence or absence of snoring and the approximate volume, and it is difficult to accurately obtain key data such as the association with breathing, making the anti-snoring measures lack a precise basis. In terms of the degree of intelligence, most current anti-snoring products have a low level of intelligence and usually require manual operation by the user to adjust. For example, manually adjusting the height or angle of an anti-snoring pillow. During sleep, it is often difficult for the user to detect their own snoring situation and intervene manually in a timely manner. As for the comprehensive consideration of improving the overall sleep quality, existing anti-snoring methods are generally lacking. Some strong anti-snoring measures may, to a certain extent, suppress snoring, but due to overly drastic intervention, the user's sleep is frequently interrupted.

[0004] Therefore, there is an urgent need for a technology that can comprehensively monitor the user's sleep state, accurately analyze the causes of snoring, and achieve efficient anti-snoring and improve the overall sleep quality through intelligent adjustment. Summary of the Invention

[0005] In view of this, the present invention provides an intelligent bed anti-snoring system, a control method and a device to solve the problems that existing anti-snoring products and methods are still insufficient in terms of accuracy, intelligence, and comprehensive consideration of improving the overall sleep quality.

[0006] In a first aspect, the present invention provides an intelligent bed anti-snoring system, the system comprising: an intelligent bed and a control unit; the intelligent bed is provided with detection sensors and is evenly distributed with a plurality of airbags; the detection sensors include a sound signal acquisition sensor and a body information acquisition sensor;

[0007] The sound signal acquisition sensor is configured to acquire sound signals in the user's sleep environment and extract relevant acoustic feature parameters from the sound signals;

[0008] The body information acquisition sensor is configured to monitor multi-dimensional body information in the user's sleep environment and determine the sleep state of the user;

[0009] The control unit is used to perform quantitative analysis on the user's snoring condition based on the relevant acoustic characteristic parameters, the multi-dimensional body information and the sleep state to obtain an airbag adjustment strategy, and issue control instructions to the multiple airbags according to the airbag adjustment strategy to control the multiple airbags to inflate and deflate.

[0010] In an optional embodiment, the relevant acoustic characteristic parameters include the average loudness of snoring, the duration of snoring, and the number of snoring times per unit time;

[0011] The multi-dimensional body information includes respiratory movement information, chest rise and fall information, body posture information and micro-movement information;

[0012] The sleep state includes light sleep, deep sleep and rapid eye movement sleep.

[0013] In an optional embodiment, the multiple airbags are respectively arranged at the shoulder position, back position, waist position, buttocks position, thigh position and calf position.

[0014] In an optional embodiment, the system further comprises an air pump and an air tube assembly;

[0015] The air pump is used to provide a gas source for the multiple airbags and adjust the air pressure according to the control instructions issued by the control unit;

[0016] The air tube assembly is used to connect the air pump with each air bag to transport gas.

[0017] In a second aspect, the present invention provides a smart bed anti-snoring control method, the control method is applied to a control unit of a smart bed anti-snoring system as described above;

[0018] The control method comprises:

[0019] Acquiring relevant acoustic characteristic parameters emitted by the sound signal acquisition sensor, and multi-dimensional body information and sleep status emitted by the body information acquisition sensor; the relevant acoustic characteristic parameters are extracted by the sound signal acquisition sensor from the sound signals collected in the user's sleep environment; the sleep status is obtained by the body information acquisition sensor from the multi-dimensional body information monitored in the user's sleep environment;

[0020] Based on the relevant acoustic characteristic parameters, the multi-dimensional body information and the sleep state, quantitatively analyzing the snoring condition of the user to obtain an airbag adjustment strategy;

[0021] According to the airbag adjustment strategy, control instructions are issued to the multiple airbags to control the multiple airbags to perform inflation and deflation operations.

[0022] In an alternative embodiment, the quantifying and analyzing the snoring condition of the user based on the relevant acoustic feature parameters, the multi-dimensional body information, and the sleep state to obtain an airbag adjustment strategy includes:

[0023] Obtaining a comprehensive snoring condition evaluation index in the user's sleep environment based on the relevant acoustic feature parameters and the respiratory movement information in the multi-dimensional body information;

[0024] Dividing the snoring condition into different levels based on the value of the comprehensive snoring condition evaluation index; the levels of the snoring condition include a non-snoring or mild snoring level, a moderate snoring level, and a severe snoring level;

[0025] Obtaining an airbag adjustment strategy based on the level of the snoring condition and the sleep state.

[0026] In an alternative embodiment, the comprehensive snoring condition evaluation index is obtained through the following formula:

[0027] S = k 1 L + k 2 T + k 3 N + k 4 (f 正常 - f) + k 5 M;

[0028] where S represents the comprehensive snoring condition evaluation index, L represents the average loudness of snoring, T represents the duration of snoring, N represents the number of snoring times per unit time, f 正常 represents the average respiratory rate in the normal respiratory state, f represents the current respiratory rate monitored by the body information acquisition sensor, M represents the characteristic parameter reflecting the degree of respiratory obstruction monitored by the body information acquisition sensor, k 1 represents the weight coefficient corresponding to L, k 2 represents the weight coefficient corresponding to T, k 3 represents the weight coefficient corresponding to N, k 4 represents the weight coefficient corresponding to (f 正常 - f), k 5 represents the weight coefficient corresponding to M.

[0029] In an alternative embodiment, the obtaining an airbag adjustment strategy based on the level of the snoring condition and the sleep state includes:

[0030] When the level of the snoring condition is a non-snoring or mild snoring level and the sleep state indicates that the current is an airbag adjustable stage, the airbag adjustment strategy is obtained through the following formula:

[0031] P 肩=P 0肩 +ΔP 1 ×S / S 1 ;

[0032] P 背 =P 0背 +ΔP 1 ×S / S 1 ;

[0033] When the level of the snoring condition is the moderate snoring level and the sleep state indicates that the current is the airbag adjustable stage, the airbag adjustment strategy is obtained through the following formula:

[0034] P 肩 =P 0肩 +ΔP 2 (S - S 1 ) / (S 2 - S 1 );

[0035] P 背 =P 0背 +ΔP 2 (S - S 1 ) / (S 2 - S 1 );

[0036] When the level of the snoring condition is the severe snoring level and the sleep state indicates that the current is the airbag adjustable stage, the airbag adjustment strategy is obtained through the following formula:

[0037] P 肩 =P 0肩 +ΔP 3 (S - S 2 ) / (S max - S 2 );

[0038] P 背 =P 0背 +ΔP 3 (S - S 2 ) / (S max - S 2 );

[0039] Wherein, P 肩 and P 背 respectively represent the target inflation pressures of the shoulder airbag and the back airbag, P 0肩 and P 0背 respectively represent the initial inflation pressures of the shoulder airbag and the back airbag, S 1 , S 2 respectively represent the first snoring threshold and the second snoring threshold, and S 1 < S 2, S represents the comprehensive snoring condition evaluation index, ΔP 1 represents the air pressure adjustment step corresponding to the initially set non-snoring or mild snoring level, ΔP 2 represents the air pressure adjustment step corresponding to the initially set moderate snoring level, ΔP 3 represents the air pressure adjustment step corresponding to the initially set severe snoring level, S max represents the initially set maximum value of the snoring condition evaluation index.

[0040] In a third aspect, the present invention provides an intelligent bed anti-snoring control device, and the control device is applied to the control unit of an intelligent bed anti-snoring system as described above;

[0041] The control device includes:

[0042] An information acquisition module, configured to acquire relevant acoustic feature parameters sent by a sound signal acquisition sensor, as well as multi-dimensional body information and sleep state sent by a body information acquisition sensor; the relevant acoustic feature parameters are extracted by the sound signal acquisition sensor from the sound signals in the user's sleep environment collected; the sleep state is obtained by the body information acquisition sensor from the multi-dimensional body information in the user's sleep environment monitored;

[0043] An airbag adjustment strategy acquisition module, configured to perform quantitative analysis on the user's snoring condition based on the relevant acoustic feature parameters, the multi-dimensional body information, and the sleep state, so as to obtain an airbag adjustment strategy;

[0044] An inflation and deflation operation module, configured to send a control instruction to the plurality of airbags according to the airbag adjustment strategy, so as to control the plurality of airbags to perform inflation and deflation operations.

[0045] In a fourth aspect, the present invention provides a computer device, including: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the above-mentioned intelligent bed anti-snoring control method.

[0046] In a fifth aspect, the present invention provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to cause a computer to execute the above-mentioned intelligent bed anti-snoring control method.

[0047] In a sixth aspect, the present invention provides a computer program product, including computer instructions, and the computer instructions are used to cause a computer to execute the intelligent bed anti-snoring control method in the first aspect or any corresponding embodiment thereof.

[0048] The technical solution provided by the present invention may include the following beneficial effects:

[0049] The present invention combines a sound signal acquisition sensor and a body information acquisition sensor, which can comprehensively collect sleep data. The sound signal acquisition sensor accurately extracts acoustic features such as the loudness, duration, and frequency of snoring, and the body information acquisition sensor monitors multi-dimensional body information such as respiratory movement and chest undulation. Based on this, a comprehensive evaluation index is constructed to accurately classify the snoring level, providing a reliable basis for subsequent precise intervention. Moreover, according to the snoring level, sleep state, and AI analysis results, the present invention obtains an airbag adjustment strategy, intelligently adjusts the airbag pressure and inflation / deflation time. The whole process is automated and precise, and can effectively address the snoring problem in different sleep scenarios. In addition, the present invention fully considers the sleep state during the adjustment process, and only adjusts the airbag when the sleep state indicates that the current stage is the airbag adjustable stage, avoiding interfering with the user's normal sleep. At the same time, the adjustment strategy can be optimized according to the change of the sleep state after adjustment, not only reducing snoring, but also improving the sleep quality as a whole, enabling the user to obtain more sufficient and high-quality rest. Brief Description of the Drawings

[0050] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0051] Figure 1 is a schematic structural diagram of an intelligent bed anti-snoring system according to an embodiment of the present invention;

[0052] Figure 2 is a schematic flowchart of an intelligent bed anti-snoring control method according to an embodiment of the present invention;

[0053] Figure 3 is a schematic flowchart of another intelligent bed anti-snoring control method according to an embodiment of the present invention;

[0054] Figure 4 is a schematic block diagram of an intelligent bed anti-snoring control device according to an embodiment of the present invention;

[0055] Figure 5 is a schematic hardware structure diagram of a computer device according to an embodiment of the present invention. Detailed Embodiments

[0056] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0057] It should be noted that the present invention aims to utilize the powerful data analysis ability of the AI deep learning algorithm, combined with the intelligent bed airbag adjustment mechanism, to overcome the limitations of existing products and provide innovative ideas for improving the user's sleep quality. The main purpose of the present invention is to construct an intelligent bed anti-snoring system and control method based on intelligent bed airbag adjustment. By integrating a sound signal acquisition sensor (such as a microphone), a body information acquisition sensor (such as a 60G millimeter-wave radar), and an AI deep learning algorithm, it deeply monitors the snoring condition and various sleep state information of the user during sleep, and intelligently controls the working state of the shoulder and back airbags on the intelligent bed. While accurately reducing the snoring condition, it records and analyzes the changes in the user's sleep state (such as the reduction of snoring and the improvement of sleep quality are regarded as gains) based on deep learning, continuously optimizes the adjustment strategy, and finally achieves the goal of improving the overall sleep quality of the user and ensuring the comfort, safety, and automatic operation of the whole process.

[0058] In this embodiment, an intelligent bed anti-snoring system is provided. Figure 1 It is a schematic structural diagram of an intelligent bed anti-snoring system according to an embodiment of the present invention. As Figure 1 shown, the system includes: an intelligent bed and a control unit (i.e., Figure 1 the control system in ); multiple airbags are evenly distributed on the intelligent bed, and detection sensors are provided; the detection sensors include a sound signal acquisition sensor and a body information acquisition sensor.

[0059] The sound signal acquisition sensor is used to acquire the sound signal in the user's sleep environment and extract relevant acoustic feature parameters from the sound signal; the relevant acoustic feature parameters include the average loudness of snoring, the duration of snoring, and the number of snoring times per unit time.

[0060] The body information acquisition sensor is used to monitor the multi-dimensional body information in the user's sleep environment and judge the sleep state of the user; the multi-dimensional body information includes respiratory movement information, chest wall undulation information, body posture information, and micro-movement conditions; the sleep state includes light sleep, deep sleep, and rapid eye movement sleep.

[0061] The control unit is used to quantitatively analyze the user's snoring condition based on the relevant acoustic feature parameters, the multi-dimensional body information, and the sleep state, so as to obtain an airbag adjustment strategy, and send control instructions to the multiple airbags according to the airbag adjustment strategy to control the multiple airbags to inflate and deflate. The airbag adjustment strategy includes airbag adjustment parameters, and the airbag adjustment parameters include airbag inflation and deflation pressure, airbag inflation and deflation time, inflation and deflation cycle interval, etc.

[0062] Furthermore, in this embodiment, a vital sign detection sensor combination composed of a sound signal acquisition sensor (such as a microphone) and a body information acquisition sensor (such as a 60G millimeter-wave radar) is installed on the bed frame to comprehensively collect key data during sleep. Among them, the microphone is used to collect the sound signal in the user's sleep environment, and advanced signal processing algorithms (such as technologies based on wavelet transform, adaptive filtering, etc.) are used to accurately extract the snoring signal, effectively filter out the environmental background noise, and accurately obtain multiple relevant acoustic feature parameters of the snoring, including the average loudness of the snoring (L, unit: decibel, dB), the snoring duration (T, unit: minute, min), and the number of snoring times per unit time (N, unit: times / minute). The 60G millimeter-wave radar can interact with the human body through electromagnetic waves in the millimeter-wave band to non-contact monitor the user's multi-dimensional body information, covering respiratory movement, chest undulation, body posture, and micro-movement conditions, etc., so as to accurately judge the sleep state of the user (such as light sleep, deep sleep, rapid eye movement sleep, etc.), and can assist in analyzing the relationship between snoring and breathing and the degree of respiratory obstruction, etc., providing rich data support for comprehensively evaluating the user's snoring condition and sleep quality.

[0063] Furthermore, as the core of the entire system, the control unit is built-in with a high-performance microprocessor RK3568, which not only pre-stores an anti-snoring control program and conventional relevant algorithm models, but also integrates an AI deep learning algorithm module. The control unit receives the signals transmitted from the vital sign detection sensors. On the one hand, it quantitatively analyzes the user's snoring condition using conventional algorithms and combines the sleep state information fed back by the millimeter-wave radar; on the other hand, it inputs these real-time collected data into the AI deep learning algorithm module. The AI module continuously optimizes the judgment accuracy of the current user's snoring condition and sleep state and the rationality of the airbag adjustment strategy through learning and analysis of a large amount of historical data (including information such as snoring, sleep state, and airbag adjustment parameters during multiple sleep processes of different users), and then sends precise control instructions to the air pump of the airbag to finely adjust parameters such as the inflation state, deflation state, and air pressure of the shoulder airbag and the back airbag, realizing a weak and just-right adjustment of the user's body posture and the surrounding environment of the upper respiratory tract, achieving the goal of reducing snoring, and ensuring that the user's normal sleep will not be disturbed throughout the process.

[0064] In an alternative embodiment, the plurality of airbags are respectively disposed at the shoulder position, the back position, the waist position, the hip position, the thigh position, and the calf position.

[0065] Furthermore, 6 airbags can be evenly distributed on the intelligent bed of this embodiment, located at the 6 positions of the shoulder position, the back position, the waist position, the hip position, the thigh position, and the calf position respectively. In this embodiment, a material that is soft, highly elastic, and meets medical safety standards (such as medical polyurethane material) can be selected to manufacture the airbags, so that they have good airtightness, durability, and a comfortable touch, and can be stably inflated and deflated within a preset air pressure range, which can not only moderately adjust the user's body posture but also will not cause discomfort to the user, ensuring a good user experience.

[0066] In an alternative embodiment, the system further includes an air pump and a tracheal assembly;

[0067] The air pump is used to provide a gas source for the plurality of airbags according to the control instructions issued by the control unit and perform air pressure regulation;

[0068] The tracheal assembly is used to connect the air pump with each airbag for gas transmission.

[0069] Furthermore, the air pump of this embodiment is responsible for the key duty of providing a gas source for each airbag, has a high-precision air pressure regulation function, and can accurately control the flow rate and air pressure of the output gas in strict accordance with the instructions issued by the control unit. The tracheal assembly is responsible for firmly connecting the air pump with each airbag to ensure that the gas can be smoothly and stably transported to the corresponding airbag, and the trachea is made of high-quality materials with good flexibility and compressive resistance, effectively preventing accidental situations such as bending and rupture during daily use, ensuring that the system can continue to operate normally.

[0070] Furthermore, the system can further include a data storage and cloud interaction module (such as Figure 1 a mobile phone), which is used to store the detailed data of each user's sleep process, including but not limited to the relevant acoustic characteristic parameters of snoring (loudness, duration, frequency, etc.), sleep status (duration of each sleep stage, transition time, etc.), airbag adjustment parameters (air pressure, inflation and deflation time, cycle interval, etc.), and the analysis results of the AI deep learning algorithm, etc. At the same time, it can interact with the cloud server through the network to realize functions such as data backup, sharing, and remote update of the AI model, facilitating subsequent in-depth optimization of the system and expansion of personalized services.

[0071] In summary, this embodiment combines a sound signal acquisition sensor and a body information acquisition sensor to comprehensively collect sleep data. The sound signal acquisition sensor accurately extracts acoustic features such as the loudness, duration, and frequency of snoring. The body information acquisition sensor monitors multi-dimensional body information such as respiratory movement and chest rise and fall, and constructs a comprehensive evaluation index based on this to accurately classify the snoring level, providing a reliable basis for subsequent precise intervention. Moreover, based on the snoring level, sleep state, and AI analysis results, this embodiment obtains an airbag adjustment strategy, intelligently adjusts the airbag pressure and inflation / deflation time, and the whole process is automated and precise, effectively coping with snoring problems in different sleep scenarios. In addition, this embodiment fully considers the sleep state during the adjustment process and only adjusts the airbag when the sleep state indicates that the current stage is the airbag adjustable stage, avoiding interfering with the user's normal sleep. At the same time, the adjustment strategy can be optimized according to the change in the sleep state after adjustment, not only reducing snoring but also improving the overall sleep quality, enabling the user to obtain more sufficient and high-quality rest.

[0072] According to an embodiment of the present invention, there is provided an embodiment of a snoring control method for a smart bed. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0073] In this embodiment, a snoring control method for a smart bed is provided, and the control method is applied to Figure 1 the control unit of a smart bed snoring system shown; Figure 2 is a schematic flowchart of a snoring control method for a smart bed according to an embodiment of the present invention, as Figure 2 shown, the control method includes:

[0074] Step S201, obtaining relevant acoustic feature parameters sent by the sound signal acquisition sensor, as well as multi-dimensional body information and sleep state sent by the body information acquisition sensor; the relevant acoustic feature parameters are extracted by the sound signal acquisition sensor from the sound signals in the user's sleep environment collected; the sleep state is obtained by the body information acquisition sensor from the multi-dimensional body information in the user's sleep environment monitored.

[0075] Furthermore, the sound signal acquisition sensor (i.e., microphone) in the intelligent bed anti-snoring system continuously acquires the sound signals in the user's sleep environment. It uses advanced signal processing algorithms such as wavelet transform and adaptive filtering to accurately extract the acoustic feature parameters related to snoring from these sound signals, including the average loudness of snoring (L), the duration of snoring (T), and the number of snoring times per unit time (N). The body information acquisition sensor (i.e., 60G millimeter-wave radar) non-contactedly monitors the multi-dimensional body information of the user by means of the interaction between millimeter-wave band electromagnetic waves and the human body, covering respiratory movement, chest rise and fall, body posture, and micro-movement conditions, etc. Based on this rich body information, the millimeter-wave radar can accurately judge the sleep state of the user, such as light sleep, deep sleep, rapid eye movement sleep and other stages. The control unit receives and obtains the data collected and processed by these two types of sensors respectively, and these data provide a comprehensive and accurate basis for the subsequent in-depth analysis of the user's snoring condition.

[0076] Step S202: Based on the relevant acoustic feature parameters, the multi-dimensional body information, and the sleep state, quantitatively analyze the user's snoring condition to obtain the airbag adjustment strategy.

[0077] Furthermore, the control unit starts to quantitatively analyze the user's snoring condition based on the received relevant acoustic feature parameters, multi-dimensional body information, and sleep state data. First, calculate the snoring condition evaluation index (S) according to a pre-set formula, comprehensively consider multiple factors related to snoring, and obtain a quantitative index that can comprehensively reflect the snoring condition. Then, according to the calculated S value, the control unit classifies the snoring condition into different levels: no snoring or mild snoring level (S < S1), moderate snoring level (S1 ≤ S < S2), severe snoring level (S ≥ S2), where S1 and S2 are pre-determined thresholds. After that, combining the user's sleep state (such as whether in the deep sleep stage) and the analysis results of the AI deep learning algorithm on a large amount of historical data (including information such as snoring, sleep state, and airbag adjustment parameters during multiple sleep processes of different users), the control unit determines the corresponding airbag adjustment strategy. For example, if it is judged as mild snoring and in the deep sleep stage suitable for adjustment, adjust the inflation pressure of the shoulder and back airbags according to a specific formula; for moderate and severe snoring, there are also corresponding formulas and adjustment logics, and the air pressure adjustment step size will change according to the adaptive adjustment of the AI.

[0078] Step S203: Send control commands to the multiple airbags according to the airbag adjustment strategy to control the inflation and deflation of the multiple airbags.

[0079] Further, according to the determined airbag adjustment strategy, the control unit issues control instructions to multiple airbags distributed on the intelligent bed (such as airbags located at the shoulders, back, etc.). These control instructions are executed through the air pump and the air pipe assembly. The air pump has a high-precision air pressure adjustment function and strictly controls the flow rate and air pressure of the output gas according to the instructions issued by the control unit. When inflation of the airbag is required, the air pump delivers gas to the corresponding airbag to make the airbag reach the calculated inflation air pressure value; when the user stops snoring or deflation is required according to the adjustment strategy, the air pump stops inflating and starts to slowly deflate until the airbag basically returns to the initial state. During the entire inflation and deflation process, the air pipe assembly is responsible for firmly connecting the air pump to each airbag to ensure that the gas can be smoothly and stably transported, guarantee the normal operation of the system, and ultimately achieve the purpose of reducing snoring by adjusting the airbag to adjust the user's body posture and the surrounding environment of the upper respiratory tract.

[0080] In summary, this embodiment combines a sound signal acquisition sensor and a body information acquisition sensor to comprehensively collect sleep data. The sound signal acquisition sensor accurately extracts acoustic features such as the loudness, duration, and number of snores, and the body information acquisition sensor monitors multi-dimensional body information such as respiratory movement and chest undulation, thereby constructing a comprehensive evaluation index to accurately classify the snoring level and providing a reliable basis for subsequent precise intervention. Moreover, based on the snoring level, sleep state, and AI analysis results, this embodiment obtains an airbag adjustment strategy, intelligently adjusts the air pressure of the airbag and the inflation and deflation time. The whole process is automated and precise, and can effectively address snoring problems in different sleep scenarios. In addition, this embodiment fully considers the sleep state during the adjustment process and only adjusts the airbag when the sleep state indicates that the current stage is the adjustable stage for the airbag, avoiding interfering with the user's normal sleep. At the same time, the adjustment strategy can be optimized according to the change in the sleep state after adjustment, not only reducing snoring, but also improving the overall sleep quality and allowing the user to obtain more sufficient and high-quality rest.

[0081] In this embodiment, a snoring control method for an intelligent bed is provided. This control method is applied to Figure 1 the control unit of a snoring prevention system for an intelligent bed shown in; Figure 3 is a schematic flowchart of another snoring control method for an intelligent bed according to an embodiment of the present invention, as shown in Figure 3 shown, this control method includes:

[0082] Step S301, obtaining relevant acoustic feature parameters sent by the sound signal acquisition sensor, as well as multi-dimensional body information and sleep state sent by the body information acquisition sensor; the relevant acoustic feature parameters are extracted by the sound signal acquisition sensor from the sound signals in the user's sleep environment collected; the sleep state is obtained by the body information acquisition sensor from the multi-dimensional body information in the user's sleep environment monitored.

[0083] Step S302: Based on the relevant acoustic feature parameters and the breathing movement information in the multi-dimensional body information, obtain an evaluation index for the comprehensive snoring condition in the user's sleep environment;

[0084] In an alternative embodiment, the comprehensive snoring condition evaluation index is obtained through the following formula:

[0085] S = k 1 L + k 2 T + k 3 N + k 4 (f 正常 - f) + k 5 M;

[0086] where S represents the comprehensive snoring condition evaluation index, L represents the average loudness of snoring (dB), T represents the duration of snoring (min), N represents the number of snoring times per unit time (times / minute), f 正常 represents the average breathing frequency in the normal breathing state (a reference value estimated based on the user's basic body information such as age, gender, etc., unit: times / minute), f represents the current breathing frequency monitored by the body information acquisition sensor (times / minute), M represents the characteristic parameter reflecting the degree of breathing obstruction monitored by the body information acquisition sensor (dimensionless, obtained by analyzing the waveform, amplitude, etc. of the breathing movement, and the value range is set between 0 - 1, 0 indicates smooth breathing, and 1 indicates severe breathing obstruction), k 1 represents the weight coefficient corresponding to L, k 2 represents the weight coefficient corresponding to T, k 3 represents the weight coefficient corresponding to N, k 4 represents the weight coefficient corresponding to (f 正常 - f), k 5 represents the weight coefficient corresponding to M. k 1 、k 2 、k 3 、k 4 、k 5 are weight coefficients carefully determined based on a large amount of experimental data and clinical experience, k 1 = 0.3, k 2 = 0.25, k 3 = 0.2, k 4 = 0.15, k 5 = 0.1.

[0087] Further, in this embodiment, the acoustic characteristic parameters of snoring collected by the microphone and the respiration-related data monitored by the 60G millimeter-wave radar are integrated to construct a comprehensive snoring condition evaluation index (S). According to the magnitude of this comprehensive snoring condition evaluation index (S), the snoring condition is carefully divided into different levels, and the specific division rules are as follows:

[0088] S < S 1 , no snoring or mild snoring;

[0089] S 1 ≤ S < S 2 , moderate snoring;

[0090] S ≥ S 2 , severe snoring.

[0091] Among them, S 1 , S 2 are thresholds determined in advance through rigorous experiments and rich clinical experience. S 1 = 15, S 2 = 30.

[0092] Step S303, based on the value of this comprehensive snoring condition evaluation index, divide the snoring condition into different levels; the levels of this snoring condition include no snoring or mild snoring level, moderate snoring level, and severe snoring level.

[0093] Step S304, based on the level of this snoring condition and this sleep state, obtain an airbag adjustment strategy.

[0094] In an alternative embodiment, after determining the snoring condition level in this embodiment, a comprehensive judgment is made by combining the user's sleep state information monitored by the millimeter-wave radar and the analysis result of the AI deep learning algorithm, so as to execute the corresponding airbag adjustment strategy. Therefore, this step S304 includes:

[0095] (1) When the level of this snoring condition is no snoring or mild snoring level, and this sleep state indicates that the current is the airbag adjustable stage, the airbag adjustment strategy is obtained through the following formula:

[0096] P 肩 = P 0肩 + ΔP 1 × S / S 1 ;

[0097] P 背 = P 0背 + ΔP 1 × S / S 1 ;

[0098] That is to say, if it is mild snoring (S < S 1) and is in a suitable adjustment stage, specifically as follows:

[0099] The AI deep learning algorithm first determines whether the current time is suitable for airbag adjustment based on historical data and some user sleep characteristics collected currently (for example, comprehensively considering factors such as the response of the user to mild snoring adjustment during recent sleep and the current overall sleep stability). If it is determined to be suitable for adjustment and the user is in the deep sleep stage (judged by millimeter-wave radar, for example, determined according to body micro-motion characteristics, breathing patterns, etc.), this is considered a more favorable stage for adjusting the airbag. The inflation pressure of the shoulder airbag (P 肩 , unit: kilopascal, kPa) and the inflation pressure of the back airbag (P 背 , unit: kPa) are adjusted according to the above formula. The inflation time (t 充 , unit: second, s) and the deflation time (t 放 , unit: s) are dynamically adjusted according to the real-time monitoring of the user's snoring situation by the millimeter-wave radar. When the radar detects that the user is snoring, the air pump continuously inflates the airbag slowly to keep the airbag pressure at the corresponding pressure value calculated above; once the radar detects that the user stops snoring, the air pump immediately stops inflating and starts to deflate slowly until the airbag basically returns to the initial state (close to the pressure corresponding to P 肩 and P 背 ). The time of the deflation process is determined according to factors such as the deflation rate of the air pump and the volume of the airbag to ensure smooth deflation and no obvious noise or other impacts that interfere with the user's sleep.

[0100] After completing one or more airbag adjustments, record the snoring status of the user before and after the adjustment (such as changes in snoring loudness, duration, frequency, etc.) and the changes in sleep status (such as the proportion of the duration of each sleep stage, sleep interruption situation, etc.), and use these as feedback data for further learning and analysis. Based on this feedback information, through the deep learning model, adaptively adjust the air pressure adjustment step size according to the response of the current user to this adjustment. For example, if it is found that although the snoring situation has been reduced but is still obvious after the current adjustment and has not had a negative impact on sleep quality, appropriately increase ΔP 1 (such as adjusting it to 0.25 kPa) in order to more effectively reduce snoring in the next round of adjustment; on the contrary, if the number of sleep interruptions of the user increases after the adjustment, it means that the adjustment may have caused certain interference to sleep, then appropriately reduce ΔP 1 (such as adjusting it to 0.15 kPa), and then continue the airbag adjustment operation according to the adjusted step size to continuously optimize the anti-snoring strategy.

[0101] If it is determined that the current is not an appropriate time for adjustment or the user is in the light sleep or rapid eye movement sleep stage, the airbag adjustment operation will be temporarily delayed, and continuous monitoring will be carried out. Wait for a more appropriate time (for example, entering deep sleep and the AI determines that adjustment is beneficial) and then adjust according to the above formula to avoid waking up the user and improve the effectiveness of the adjustment.

[0102] (2) When the level of the snoring condition is the moderate snoring level and the sleep state indicates that the current is the airbag adjustable stage, the airbag adjustment strategy is obtained through the following formula:

[0103] P 肩 =P 0肩 +ΔP 2 (S - S 1 ) / (S 2 - S 1 );

[0104] P 背 =P 0背 +ΔP 2 (S - S 1 ) / (S 2 - S 1 );

[0105] That is to say, if it is moderate snoring (S 1 ≤S < S 2 ) and in the appropriate adjustment stage, it is as follows:

[0106] Similarly, when the AI deep learning algorithm combines with the millimeter wave radar to determine that the user is in the deep sleep state and the current is a suitable situation for adjustment, the airbag air pressure is adjusted according to the above formula. The inflation time (t 充 , unit: second, s) and the deflation time (t 放 , unit: second, s) are also dynamically adjusted according to the real-time monitoring of the radar for the snoring situation, that is, inflate to maintain the air pressure during snoring and deflate to the initial state when snoring stops, ensuring smooth operation without affecting sleep.

[0107] After the adjustment is completed, the AI algorithm will collect relevant feedback data, evaluate the impact of this adjustment on the user's snoring and sleep quality, and adaptively adjust through the deep learning model based on this. For example, if the reduction amplitude of the snoring times does not reach the expectation and the sleep quality is stable, it can be appropriately increased; if there are signs of a decline in sleep quality, such as a significant reduction in the light sleep duration, it will be correspondingly reduced, and subsequent adjustments will be made according to the adjusted parameters to gradually improve the anti-snoring effect. If it is in the light sleep or rapid eye movement sleep stage or the AI determines that the current is not suitable for adjustment, first keep monitoring, and then implement the adjustment after entering deep sleep and meeting the appropriate adjustment conditions (including detecting the start of snoring), ensuring that the entire process does not interfere with the user's sleep and maximizing the accuracy of the adjustment.

[0108] (3) When the level of the snoring condition is the severe snoring level and the sleep state indicates that it is currently the airbag adjustable stage, the airbag adjustment strategy is obtained through the following formula:

[0109] P 肩 = P 0肩 + ΔP 3 (S - S 2 ) / (S max - S 2 );

[0110] P 背 = P 0背 + ΔP 3 (S - S 2 ) / (S max - S 2 );

[0111] Wherein, P 肩 and P 背 respectively represent the target inflation pressures of the shoulder airbag and the back airbag, P 0肩 and P 0背 respectively represent the initial inflation pressures of the shoulder airbag and the back airbag (P 0肩 = 1.0 kPa, P 0背 = 1.0 kPa), S 1 , S 2 respectively represent the first snoring threshold and the second snoring threshold, and S 1 < S 2 , S represents the comprehensive snoring condition evaluation index, ΔP 1 represents the pressure adjustment step corresponding to the initial setting of no snoring or mild snoring level (the initial value ΔP 1 = 0.2 kPa, and will be adaptively adjusted according to AI later), ΔP 2 represents the pressure adjustment step corresponding to the initial setting of moderate snoring level (the initial value ΔP 2 = 0.4 kPa, and will be adaptively adjusted according to AI later), ΔP 3 represents the pressure adjustment step corresponding to the initial setting of severe snoring level (the initial value ΔP 3 = 0.6 kPa, and will be adaptively adjusted according to AI later), S max represents the initial setting of the maximum snoring condition evaluation index value (which can be determined according to actual test conditions, and the initial value S max = 50).

[0112] That is to say, if it is severe snoring (S ≥ S 2 ) and in the appropriate adjustment stage, then specifically as follows:

[0113] For severe snoring cases, when the AI deep learning algorithm and millimeter-wave radar jointly confirm that the user is in the deep sleep stage and is suitable for adjustment, the airbag pressure is adjusted according to the above formula. The inflation time (t 充 , unit: second, s) and deflation time (t 放 , unit: s) vary dynamically according to the real-time detection results of the user's snoring, that is, the air pressure is maintained by inflation during snoring, and the airbag is deflated to the initial state when snoring stops, ensuring that the whole process is stable and does not affect the user's sleep.

[0114] After each adjustment, the changes in snoring and sleep states before and after the adjustment are also analyzed, and the adjustment is adaptively optimized based on whether there is a "gain" (such as reduced snoring, improved sleep quality, etc.). Through continuous learning and adjustment, efforts are made to reduce the user's severe snoring problem while ensuring that the sleep quality is not affected.

[0115] If the user is in the light sleep or rapid eye movement sleep stage or it is determined that the current adjustment is not appropriate, wait for the right time (enter the deep sleep, meet the adjustment conditions and detect the start of snoring) before making the adjustment, to ensure that the user's sleep is not affected to the greatest extent, and the anti-snoring effect is improved by leveraging the intelligent optimization ability of AI.

[0116] Through the algorithm that combines the sleep state and the AI deep learning algorithm for comprehensive judgment and dynamic optimization, according to the user's real-time snoring condition, the sleep stage they are in, and the feedback of past adjustment effects, the parameters such as the air pressure, inflation and deflation time of the shoulder and back airbags are dynamically and carefully adjusted, realizing a weak and precise adjustment of the upper respiratory tract surrounding environment. While effectively reducing the snoring condition, it strictly avoids waking up the user due to airbag operation, and continuously improves the anti-snoring effect and the overall sleep quality.

[0117] Step S305, send a control command to the multiple airbags according to the airbag adjustment strategy to control the multiple airbags to perform inflation and deflation operations.

[0118] In summary, this embodiment combines a sound signal acquisition sensor and a body information acquisition sensor to comprehensively collect sleep data. The sound signal acquisition sensor accurately extracts acoustic features such as the loudness, duration, and frequency of snoring. The body information acquisition sensor monitors multi-dimensional body information such as respiratory movement and chest rise and fall, and constructs a comprehensive evaluation index based on this to accurately classify the snoring level, providing a reliable basis for subsequent precise intervention. Moreover, this embodiment obtains an airbag adjustment strategy based on the snoring level, sleep state, and AI analysis results, and intelligently adjusts the airbag pressure and inflation / deflation time. The entire process is automated and precise, effectively addressing snoring problems in different sleep scenarios. In addition, this embodiment fully considers the sleep state during the adjustment process and only adjusts the airbag when the sleep state indicates that the current stage is suitable for airbag adjustment, avoiding disturbing the user's normal sleep. At the same time, it can optimize the adjustment strategy according to the changes in the sleep state after adjustment, not only reducing snoring but also improving the overall sleep quality, enabling the user to obtain more sufficient and high-quality rest.

[0119] In this embodiment, an intelligent bed anti-snoring control device is also provided. This device is used to implement the above-described embodiment and preferred implementation manners, and those that have been described will not be repeated. As used hereinafter, the term "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0120] This embodiment provides an intelligent bed anti-snoring control device, and this control device is applied to Figure 1 the control unit of an intelligent bed anti-snoring system shown; as Figure 4 shown, it includes:

[0121] An acquisition information obtaining module 401, configured to obtain relevant acoustic feature parameters sent by a sound signal acquisition sensor, as well as multi-dimensional body information and sleep state sent by a body information acquisition sensor; the relevant acoustic feature parameters are extracted by the sound signal acquisition sensor from the sound signals in the user's sleep environment collected; the sleep state is obtained by the body information acquisition sensor from the multi-dimensional body information in the user's sleep environment monitored;

[0122] An airbag adjustment strategy obtaining module 402, configured to perform quantitative analysis on the user's snoring condition based on the relevant acoustic feature parameters, the multi-dimensional body information, and the sleep state, so as to obtain an airbag adjustment strategy;

[0123] An inflation / deflation working module 403, configured to send control instructions to the multiple airbags according to the airbag adjustment strategy to control the multiple airbags to perform inflation / deflation work.

[0124] In an alternative embodiment, the airbag adjustment strategy acquisition module 402 is further configured to:

[0125] Based on the relevant acoustic feature parameters and the breathing movement information in the multi-dimensional body information, obtain an evaluation index for the comprehensive snoring condition in the user's sleep environment;

[0126] Based on the value of the comprehensive snoring condition evaluation index, divide the snoring condition into different levels; the levels of the snoring condition include no snoring or mild snoring level, moderate snoring level, and severe snoring level;

[0127] Based on the level of the snoring condition and the sleep state, obtain an airbag adjustment strategy.

[0128] In an alternative embodiment, the comprehensive snoring condition evaluation index is obtained through the following formula:

[0129] S = k 1 L + k 2 T + k 3 N + k 4 (f 正常 - f) + k 5 M;

[0130] Wherein, S represents the comprehensive snoring condition evaluation index, L represents the average loudness of snoring, T represents the duration of snoring, N represents the number of snoring times per unit time, f 正常 represents the average breathing frequency in the normal breathing state, f represents the current breathing frequency monitored by the body information acquisition sensor, M represents the characteristic parameter reflecting the degree of breathing obstruction monitored by the body information acquisition sensor, k 1 represents the weight coefficient corresponding to L, k 2 represents the weight coefficient corresponding to T, k 3 represents the weight coefficient corresponding to N, k 4 represents the weight coefficient corresponding to (f 正常 - f), k 5 represents the weight coefficient corresponding to M.

[0131] In an alternative embodiment, the airbag adjustment strategy acquisition module 402 is further configured to:

[0132] When the level of the snoring condition is no snoring or mild snoring level, and the sleep state indicates that the current is the airbag adjustable stage, obtain the airbag adjustment strategy through the following formula:

[0133] P 肩 = P 0肩 + ΔP 1 × S / S 1 ;

[0134] P背 = P 0背 + ΔP 1 × S / S 1 ;

[0135] When the level of the snoring condition is the moderate snoring level and the sleep state indicates that the current stage is the airbag adjustable stage, the airbag adjustment strategy is obtained through the following formula:

[0136] P 肩 = P 0肩 + ΔP 2 (S - S 1 ) / (S 2 - S 1 );

[0137] P 背 = P 0背 + ΔP 2 (S - S 1 ) / (S 2 - S 1 );

[0138] When the level of the snoring condition is the severe snoring level and the sleep state indicates that the current stage is the airbag adjustable stage, the airbag adjustment strategy is obtained through the following formula:

[0139] P 肩 = P 0肩 + ΔP 3 (S - S 2 ) / (S max - S 2 );

[0140] P 背 = P 0背 + ΔP 3 (S - S 2 ) / (S max - S 2 );

[0141] Wherein, P 肩 and P 背 respectively represent the target inflation pressures of the shoulder airbag and the back airbag, P 0肩 and P 0背 respectively represent the initial inflation pressures of the shoulder airbag and the back airbag, S 1 , S 2 respectively represent the first snoring threshold and the second snoring threshold, and S 1 < S 2 , S represents the comprehensive snoring condition evaluation index, ΔP 1 represents the pressure adjustment step corresponding to the initially set no snoring or mild snoring level, ΔP 2Indicates the air pressure adjustment step size, ΔP, corresponding to the initially set moderate snoring level 3 Indicates the air pressure adjustment step size, S, corresponding to the initially set severe snoring level max Indicates the maximum snoring condition evaluation index value set initially.

[0142] The further function descriptions of each of the above modules and units are the same as those in the corresponding above embodiments, and will not be elaborated herein.

[0143] In summary, this embodiment combines a sound signal acquisition sensor and a body information acquisition sensor to comprehensively collect sleep data. The sound signal acquisition sensor accurately extracts acoustic features such as the loudness, duration, and frequency of snoring, and the body information acquisition sensor monitors multi-dimensional body information such as respiratory movement and chest undulation. Based on this, a comprehensive evaluation index is constructed to accurately classify the snoring level, providing a reliable basis for subsequent precise intervention. Moreover, this embodiment obtains an airbag adjustment strategy based on the snoring level, sleep state, and AI analysis results, and intelligently adjusts the airbag pressure and inflation / deflation time. The whole process is automated and precise, and can effectively address snoring problems in different sleep scenarios. In addition, this embodiment fully considers the sleep state during the adjustment process and only adjusts the airbag when the sleep state indicates that the current stage is the airbag adjustable stage, avoiding interfering with the user's normal sleep. At the same time, the adjustment strategy can be optimized according to the change in the sleep state after adjustment, not only reducing snoring but also improving the overall sleep quality, enabling the user to obtain more sufficient and high-quality rest.

[0144] The embodiment of the present invention also provides a computer device. Please refer to Figure 5 , Figure 5 is a schematic structural diagram of a computer device provided by an optional embodiment of the present invention. As shown in Figure 5 , the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including a high-speed interface and a low-speed interface. Each component communicates with each other using different buses and can be installed on a common main board or installed in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in the memory or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional implementation manners, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (such as an array of servers, a set of blade servers, or a multi-processor system). Figure 5 In

[0145] The processor 10 may be a central processing unit, a network processor, or a combination thereof. Among them, the processor 10 may further include a hardware chip. The above-mentioned hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The above-mentioned programmable logic device may be a complex programmable logic device, a field-programmable gate array, a generic array logic, or any combination thereof.

[0146] Among them, the memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiments.

[0147] The memory 20 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may further include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some alternative embodiments, the memory 20 may optionally include a memory remotely provided with respect to the processor 10, and these remote memories may be connected to the computer device through a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0148] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk, or a solid-state drive; the memory 20 may further include a combination of the above types of memories.

[0149] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or communication networks.

[0150] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or be implemented as computer code that can be recorded on a storage medium, or be implemented as computer code originally stored in a remote storage medium or a non-transitory machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium may be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid-state drive, etc.; further, the storage medium may further include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code, and when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method shown in the above embodiments is implemented.

[0151] A part of the present invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the present invention through the operations of the computer. Those skilled in the art should understand that the forms in which computer program instructions exist in a computer-readable medium include but are not limited to source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include but are not limited to: the computer directly executes the instructions, or the computer compiles the instructions and then executes the corresponding compiled program, or the computer reads and executes the instructions, or the computer reads and installs the instructions and then executes the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to the computer.

[0152] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations all fall within the defined scope.

Claims

1. A smart bed anti-snoring system, characterized in that: The system comprises: a smart bed and a control unit; the smart bed is provided with a detection sensor and a plurality of air bags evenly distributed; the detection sensor comprises a sound signal collection sensor and a body information collection sensor; The sound signal acquisition sensor is used to collect sound signals in the user's sleeping environment and extract relevant acoustic characteristic parameters from the sound signals; The body information collection sensor is used to monitor the multi-dimensional body information of the user in the sleeping environment and determine the sleeping state of the user; The control unit is used to perform quantitative analysis on the user's snoring condition based on the relevant acoustic characteristic parameters, the multi-dimensional body information and the sleep state to obtain an airbag adjustment strategy, and issue control instructions to the multiple airbags according to the airbag adjustment strategy to control the multiple airbags to inflate and deflate.

2. The system according to claim 1, characterized in that The relevant acoustic characteristic parameters include the average loudness of snoring, the duration of snoring, and the number of snoring times per unit time; The multi-dimensional body information includes respiratory movement information, chest rise and fall information, body posture information and micro-movement information; The sleep state includes light sleep, deep sleep and rapid eye movement sleep.

3. The system according to claim 1, characterized in that The multiple air bags are respectively arranged at the shoulder position, the back position, the waist position, the buttocks position, the thigh position and the calf position.

4. The system according to claim 1, characterized in that The system also includes an air pump and an air pipe assembly; The air pump is used to provide a gas source for the multiple airbags and adjust the air pressure according to the control instructions issued by the control unit; The air tube assembly is used to connect the air pump with each air bag to transport gas.

5. A smart bed snoring control method, characterized in that: The control method is applied to a control unit of a smart bed anti-snoring system according to any one of claims 1 to 4; The control method comprises: Acquiring relevant acoustic characteristic parameters emitted by the sound signal acquisition sensor, and multi-dimensional body information and sleep status emitted by the body information acquisition sensor; the relevant acoustic characteristic parameters are extracted by the sound signal acquisition sensor from the sound signals collected in the user's sleep environment; the sleep status is obtained by the body information acquisition sensor from the multi-dimensional body information monitored in the user's sleep environment; Based on the relevant acoustic characteristic parameters, the multi-dimensional body information and the sleep state, quantitatively analyzing the snoring condition of the user to obtain an airbag adjustment strategy; According to the airbag adjustment strategy, control instructions are issued to the multiple airbags to control the multiple airbags to perform inflation and deflation operations.

6. The method according to claim 5, characterized in that The quantitative analysis of the user's snoring condition based on the relevant acoustic characteristic parameters, the multi-dimensional body information and the sleep state to obtain an airbag adjustment strategy includes: Based on the relevant acoustic feature parameters and the respiratory movement information in the multi-dimensional body information, obtaining a comprehensive snoring condition evaluation index in the user's sleeping environment; Based on the value of the comprehensive snoring condition evaluation index, the snoring condition is divided into different levels; the snoring condition levels include no snoring or mild snoring level, moderate snoring level and severe snoring level; An airbag adjustment strategy is obtained based on the level of the snoring condition and the sleeping state.

7. The method according to claim 6, characterized in that The comprehensive snoring condition evaluation index is obtained by the following formula: S=k1L+k2T+k3N+k4(f 正常 -f)+k5 M; Wherein, S represents the comprehensive snoring condition evaluation index, L represents the average loudness of snoring, T represents the duration of snoring, N represents the number of snoring times per unit time, and f 正常 represents the average respiratory rate under normal breathing conditions, f represents the current respiratory rate monitored by the body information acquisition sensor, M represents the characteristic parameter reflecting the degree of respiratory obstruction monitored by the body information acquisition sensor, k1 represents the weight coefficient corresponding to L, k2 represents the weight coefficient corresponding to T, k3 represents the weight coefficient corresponding to N, k4 represents (f 正常 -f) corresponding to the weight coefficient, k5 represents the weight coefficient corresponding to M.

8. The method according to claim 6, characterized in that The obtaining of the airbag adjustment strategy based on the level of the snoring condition and the sleeping state includes: When the snoring level is no snoring or mild snoring, and the sleep state indicates that the airbag is currently in an adjustable stage, the airbag adjustment strategy is obtained by the following formula: P 肩 =P 0肩 +ΔP1×S / S1; P 背 =P 0背 +ΔP1×S / S1; When the snoring level is a moderate snoring level, and the sleep state indicates that the airbag is currently in an adjustable stage, the airbag adjustment strategy is obtained by the following formula: P 肩 =P 0肩 +ΔP2(S-S1) / (S2-S1); P 背 =P 0背 +ΔP2(S-S1) / (S2-S1); When the level of the snoring condition is a severe snoring level, and the sleep state indicates that the current stage is an airbag adjustable stage, the airbag adjustment strategy is obtained by the following formula: P 肩 =P 0肩 +ΔP3(S-S2) / (S max -S2); P 背 =P 0背 +ΔP3(S-S2) / (S max -S2); Among them, P 肩 and P 背 respectively represent the target inflation pressures of the shoulder airbag and the back airbag, P 0肩 and P 0背 respectively represent the initial inflation pressures of the shoulder airbag and the back airbag, S1 and S2 respectively represent the first snoring threshold and the second snoring threshold, and S1 < S2, S represents the comprehensive snoring condition evaluation index, ΔP1 represents the pressure adjustment step corresponding to the initially set no-snoring or mild-snoring level, ΔP2 represents the pressure adjustment step corresponding to the initially set moderate-snoring level, ΔP3 represents the pressure adjustment step corresponding to the initially set severe-snoring level, S max represents the initially set maximum value of the snoring condition evaluation index.

9. An intelligent bed snoring control device, characterized in that: The control device is applied to a control unit of a smart bed anti-snoring system according to any one of claims 1 to 4; The control device comprises: The information acquisition module is used to acquire relevant acoustic characteristic parameters emitted by the sound signal acquisition sensor, and multi-dimensional body information and sleep status emitted by the body information acquisition sensor; the relevant acoustic characteristic parameters are extracted by the sound signal acquisition sensor from the sound signal collected in the user's sleep environment; the sleep status is acquired by the body information acquisition sensor from the multi-dimensional body information in the monitored user's sleep environment; An airbag adjustment strategy acquisition module, configured to quantitatively analyze the user's snoring condition based on the relevant acoustic characteristic parameters, the multi-dimensional body information, and the sleep state, so as to acquire an airbag adjustment strategy; The inflation and deflation working module is used to send control instructions to the multiple airbags according to the airbag adjustment strategy to control the multiple airbags to perform inflation and deflation work.

10. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the smart bed snoring control method according to any one of claims 5 to 8 by executing the computer instructions.

Images