Personalized sleep intervention and first aid method and system based on multi-modal data fusion

Abstract

The invention discloses a personalized sleep intervention and first aid method and system based on multi-modal data fusion. The method comprises the steps that physiological index data and motion data of a user are collected in real time through wearable equipment; generating a sleep quality score based on the physiological index data in combination with a preset sleep quality evaluation model; generating a personalized sleep intervention scheme according to the sleep quality score and the motion data; the sleep intervention module is started by manually triggering or automatically detecting the insomnia state of the user; according to the physiological index data monitored in the sleeping process, the indexes exceeding the standard are recorded, and a prompt is given out after waking up the next day, or a first-aid mode is triggered. The personalized dynamic sleep intervention scheme is generated by quantifying the physiological indexes of the user, and the limitation of a single sensor is broken through; sleep intervention can be triggered in multiple modes, the intervention intensity can be dynamically adjusted according to the real-time physiological state, the first-aid mode can be automatically started, and first-aid delay is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of sleep intervention, and particularly to a personalized sleep intervention and first aid method and system based on multi-modal data fusion. Background Art

[0002] With the acceleration of the modern life rhythm, sleep disorders have become an important issue affecting public health. In the prior art, sleep monitoring and intervention means mostly rely on a single sensor (such as heart rate monitoring or body movement sensor) for data collection. For example, the sleep duration and the frequency of shallow body movement of a user are monitored through a smart bracelet. However, such methods have significant limitations:

[0003] (1) The monitoring dimension is single, and it is impossible to comprehensively evaluate key physiological indicators such as the deep sleep duration, heart rate variability (HRV), and blood oxygen saturation of the user, resulting in inaccurate sleep quality assessment;

[0004] (2) The intervention plan lacks personalization. The prior art usually generates suggestions based on a general template (such as a fixed bedtime or music recommendation), without combining the user's age, medical history, cardiovascular risk and other individualized health data, and it is difficult to achieve precise intervention;

[0005] (3) The manual and automatic intervention means are separated. The traditional system can only trigger the intervention through a single method (such as playing music), and cannot dynamically adjust the intervention intensity according to the real-time physiological state. For example, when the user has insomnia, the ambient light, brain wave stimulation and music frequency are adjusted synchronously;

[0006] (4) The first aid response mechanism is missing. When the existing device monitors a sudden high-risk health event (such as a sudden drop in blood oxygen) during the user's sleep, it lacks the ability to link with the smart home and medical systems, resulting in delayed first aid.

[0007] In view of this, it is necessary to provide a personalized sleep intervention and first aid method and system based on multi-modal data fusion to overcome the above defects. Summary of the Invention

[0008] The object of the present invention is to provide a personalized sleep intervention and first aid method and system based on multi-modal data fusion, aiming to solve the problems of single monitoring dimension, lack of personalization of the intervention plan, and lack of first aid response mechanism in the existing sleep monitoring and intervention means, and being able to dynamically adjust the intervention intensity according to the real-time physiological state.

[0009] To achieve the above object, in the first aspect of the present invention, a personalized sleep intervention and first aid method based on multi-modal data fusion is provided, including the following steps:

[0010] Step S10: Real-time collect the user's physiological index data and exercise data through the wearable device, including age, height, weight, disease history, sleep heart rate, blood oxygen saturation, respiratory rate, HRV, body movement amplitude, and deep sleep duration;

[0011] Step S20: Generate a sleep quality score based on the physiological index data in combination with a preset sleep quality assessment model;

[0012] Step S30: Generate a personalized sleep intervention plan according to the sleep quality score and the exercise data, including the best bedtime, wake-up time, target sleep duration, deep sleep duration, lunch break sleep duration, sleep aid music type, and brain wave regulation parameters;

[0013] Step S40: Start the sleep intervention module by manually triggering or automatically detecting the user's insomnia state, including at least one of the following methods:

[0014] Release α / β waves through the sleep improvement electrode module built in the smart bracelet to regulate nerve relaxation;

[0015] Link the smart home system to adjust the light brightness to a preset threshold, close the curtains, and play hypnotherapy music that matches the user's preferences through the smart speaker;

[0016] Adjust the emission frequency through the brain wave sleep aid pillow to guide the user into deep sleep;

[0017] Step S50: According to the physiological index data monitored during the falling asleep process, and judge whether any index is outside the first threshold range, record the exceeded index and issue a reminder after waking up the next day; if any index is outside the second threshold range, trigger the first aid mode; the second threshold range is more deviated from the normal value compared to the first threshold range.

[0018] In a preferred embodiment, in step S20, the formula for the sleep quality assessment model to generate the sleep quality score is:

[0019]

[0020] In the formula, Qs is the sleep quality score, S d is the proportion of deep sleep duration, HRV s is the standard deviation of heart rate variability, A m is the body movement amplitude, A t is the preset body movement amplitude threshold, and α, β, γ are the weight coefficients of the corresponding items.

[0021] In a preferred embodiment, in the step S30, when generating the sleep intervention plan, it further includes:

[0022] Predicting the user's sleep cycle based on historical sleep data and a machine learning model, where the machine learning model uses an LSTM neural network, the input features include the heart rate variability trend, body movement frequency, and environmental temperature and humidity, and the output is the optimal intervention time period and intervention intensity parameters.

[0023] In a preferred embodiment, the manual sleep intervention method in step S40 specifically includes:

[0024] After detecting the user's manual trigger signal, start the sleep improvement electrode module to release alpha waves for 5 - 15 minutes, and then switch to beta waves for neural arousal inhibition; among them, the frequency range of alpha waves is 8Hz - 12Hz, and the frequency range of beta waves is 12Hz - 30Hz;

[0025] Dynamically adjust the waveform intensity according to the real - time collected galvanic skin response signal, and the adjustment formula is:

[0026]

[0027] In the formula, I w is the output current intensity of the sleep improvement electrode module, GSR is the real - time skin conductance value, GSR b is the skin conductance baseline value, and k is a preset calibration coefficient.

[0028] In a preferred embodiment, in step S50, when it is monitored that the user's blood oxygen saturation is lower than 70% or the resting heart rate continuously > 120 beats per minute, trigger the first - aid mode and link to execute the following steps:

[0029] Link to the smart home system to turn on all lights, play a distress message through the smart speaker and automatically call the preset emergency contact number or the first - aid phone number of a medical institution;

[0030] Synchronously upload the user's health data and location information to the cloud medical platform and start remote medical assistance.

[0031] In a preferred embodiment, in step S30, the personalized sleep intervention plan further integrates environmental parameters, including:

[0032] Collect environmental data through a temperature - humidity sensor and a light sensor, and calculate the comprehensive intervention weight in combination with physiological indicators;

[0033] If the environmental temperature > 28°C or the light intensity > 50 lux, give priority to starting the smart home adjustment function, otherwise give priority to starting the electroencephalogram regulation module.

[0034] In a preferred embodiment, it further includes the step of generating a personalized exercise prescription, specifically including:

[0035] Calculate the user's exercise load threshold through a dynamic intensity adaptation model, the model input includes resting heart rate, maximum oxygen uptake and exercise history data, and the output is weekly exercise frequency, target heart rate range and calorie consumption target;

[0036] Dynamically adjust personalized exercise prescriptions based on the user's real-time exercise data. If the monitored heart rate exceeds the preset safety threshold, the smart bracelet will vibrate to remind you and reduce the exercise intensity.

[0037] The second aspect of the present invention provides a personalized sleep intervention and emergency system based on multimodal data fusion, comprising:

[0038] The real-time data collection module is used to collect the user's physiological index data and motion data in real time through wearable devices, including age, height, weight, medical history, sleeping heart rate, blood oxygen saturation, respiratory rate, HRV, body movement amplitude and deep sleep duration;

[0039] A sleep quality assessment module, used to generate a sleep quality score based on the physiological indicator data in combination with a preset sleep quality assessment model;

[0040] An intervention plan generation module is used to generate a personalized sleep intervention plan based on the sleep quality score and the exercise data, including the best time to fall asleep, the time to wake up, the target sleep duration, the deep sleep duration, the lunch break sleep duration, the type of sleep-aiding music, and the brain wave control parameters;

[0041] The sleep intervention module is used to start by manually triggering or automatically detecting the user's insomnia state. Its intervention methods include at least one of the following methods: releasing α / β waves through the built-in sleep improvement electrode module of the smart bracelet to regulate nerve relaxation; linking the smart home system to adjust the light brightness to a preset threshold, close the curtains, and play hypnotic music that matches the user's preferences through the smart speaker; adjusting the emission frequency through the brain wave sleep-aiding pillow to guide the user into deep sleep;

[0042] The sleeping process monitoring module is used to determine whether any indicator is outside the first threshold range based on the physiological indicator data monitored during the sleeping process, record the indicators that exceed the standard and issue a reminder after waking up the next day; if any indicator is outside the second threshold range, the emergency mode is triggered; the second threshold range deviates more from the normal value than the first threshold range.

[0043] A third aspect of the present invention provides a terminal, comprising a memory, a processor, and a computer program stored in the memory, wherein the computer program, when executed by the processor, implements the various steps of the personalized sleep intervention and first aid method based on multimodal data fusion as described in any one of the above embodiments.

[0044] In the fourth aspect of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, each step of the personalized sleep intervention and first aid method based on multi-modal data fusion as described in any one of the above embodiments is implemented.

[0045] In the fifth aspect of the present invention, a computer program product is provided, including a computer program or instruction. When the computer program or instruction is executed by a processor, each step of the personalized sleep intervention and first aid method based on multi-modal data fusion as described in any one of the above embodiments is implemented.

[0046] The personalized sleep intervention and first aid method and system based on multi-modal data fusion provided by the present invention first generate a personalized dynamic sleep intervention plan by quantifying the physiological indicators of the user, integrate manual and automatic intervention means, and break through the limitations of a single sensor; and can trigger sleep intervention in various ways, dynamically adjust the intervention intensity according to the real-time physiological state, and synchronously adjust the ambient light, brain wave stimulation and music frequency when the user has insomnia. In addition, it can also monitor during sleep. When any index is seriously abnormal, the first aid mode is automatically activated to avoid delay in first aid. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0048] Figure 1 It is a flowchart of the personalized sleep intervention and first aid method based on multi-modal data fusion provided by the present invention;

[0049] Figure 2 It is a framework diagram of the personalized sleep intervention and first aid system based on multi-modal data fusion provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] In order to make the purpose, technical solutions and beneficial technical effects of the present invention clearer, the present invention will be further described in detail below with reference to the drawings and specific embodiments. It should be understood that the specific embodiments described in this specification are only for explaining the present invention and not for limiting the present invention.

[0051] It should also be understood that the terms used in the specification of the present invention are merely for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0052] It should be further understood that the term "and / or" used in the specification of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0053] Embodiment 1

[0054] In an embodiment of the present invention, a personalized sleep intervention and first aid method based on multimodal data fusion is provided, which is used to generate a personalized sleep intervention plan for the user's own physical health indicators and daily exercise data, improve the user's sleep quality, and can also monitor sleep during the falling asleep process, record abnormal index situations, and issue a first aid reminder when major abnormalities occur. Further, this method can also generate a corresponding exercise plan in combination with the sleep intervention plan to achieve the improvement of sleep quality by combining movement and rest.

[0055] As Figure 1 shown, the personalized sleep intervention and first aid method based on multimodal data fusion includes the following steps S10 - S50.

[0056] Step S10: Real - time collect the user's physiological index data and exercise data through a wearable device, including age, height, weight, disease history, sleep heart rate, blood oxygen saturation, respiratory rate, HRV, body movement amplitude, and deep sleep duration.

[0057] Step S20: Generate a sleep quality score based on the physiological index data in combination with a preset sleep quality assessment model. Wherein, the formula for the sleep quality assessment model to generate the sleep quality score is:

[0058]

[0059] In the formula, Qs is the sleep quality score, S d is the proportion of deep sleep duration, HRV s is the standard deviation of heart rate variability, A m is the body movement amplitude, A t is the preset body movement amplitude threshold, and α, β, γ are the weight coefficients of the corresponding items.

[0060] Therefore, by fusing multimodal physiological data (such as heart rate variability, blood oxygen saturation, body movement amplitude, etc.), the comprehensiveness and accuracy of sleep quality assessment can be improved.

[0061] Step S30: Generate a personalized sleep intervention plan based on the sleep quality score and the exercise data, including the optimal bedtime, wake-up time, target sleep duration, deep sleep duration, lunch break sleep duration, sleep aid music type, and brain wave regulation parameters. Therefore, generating a dynamic intervention plan based on the user's personalized health data (such as medical history, cardiovascular risk) can significantly improve the pertinence and effectiveness of the intervention.

[0062] Furthermore, when generating the sleep intervention plan, it includes: predicting the user's sleep cycle based on historical sleep data and a machine learning model. The machine learning model uses an LSTM neural network (Long Short-Term Memory network), and the input features include the heart rate variability trend, body movement frequency, and environmental temperature and humidity. The output is the optimal intervention period and intervention intensity parameters. Therefore, using the LSTM neural network to perform time series analysis on historical sleep data and environmental parameters (such as temperature and humidity) can accurately predict the user's sleep cycle and the optimal intervention period; by dynamically adjusting the intervention intensity parameters (such as music volume, brain wave frequency), ineffective interventions can be avoided, and resource allocation and user sleep efficiency can be optimized.

[0063] Furthermore, the personalized sleep intervention plan further integrates environmental parameters, including: collecting environmental data through temperature and humidity sensors and light sensors, calculating the comprehensive intervention weight in combination with physiological indicators; if the environmental temperature > 28°C or the light intensity > 50 lux, the smart home adjustment function is preferentially activated, otherwise the brain wave regulation module is preferentially activated. In this embodiment, by integrating physiological signals and environmental parameters (such as temperature and humidity, light intensity), dynamic priority adjustment of the intervention plan is achieved (such as preferentially activating air conditioner adjustment in a high-temperature environment); the problem of one-sidedness of single-sensor data is solved, the accuracy and environmental adaptability of sleep intervention are improved, and the overall sleep experience of the user is optimized.

[0064] Step S40: Manually trigger or automatically detect the user's insomnia state and activate the sleep intervention module, including at least one of the following (1)-(3) or a combination of multiple methods.

[0065] (1) Release α / β waves through the sleep improvement electrode module built into the smart bracelet to regulate nerve relaxation.

[0066] Specifically, after detecting the user's manual trigger signal, activate the sleep improvement electrode module to release α waves for 5 - 15 minutes, and then switch to β waves for nerve arousal inhibition; among them, the frequency range of α waves is 8 Hz - 12 Hz, and the frequency range of β waves is 12 Hz - 30 Hz;

[0067] Dynamically adjust the waveform intensity according to the real-time collected galvanic skin response signal, and the adjustment formula is:

[0068]

[0069] where Iw is the output current intensity of the sleep improvement electrode module, GSR is the real-time galvanic skin response value, and GSR b is the baseline value of the galvanic skin response, and k is a preset calibration coefficient.

[0070] Therefore, by dynamically adjusting the α / β wave current intensity (I w in a closed-loop control) based on real-time galvanic skin signal feedback, it is possible to avoid user discomfort or intervention failure caused by fixed parameters. At the same time, by combining the neural arousal inhibition mechanism (β wave switching), the user's sleep onset time can be shortened and the duration of deep sleep can be extended.

[0071] (2) Link the smart home system to adjust the light brightness to a preset threshold, close the curtains, and play hypnotic music that matches the user's preferences through a smart speaker.

[0072] (3) Adjust the transmission frequency through the electroencephalogram sleep aid pillow to guide the user into deep sleep.

[0073] Therefore, by integrating manual and automatic intervention means (such as electroencephalogram regulation, environmental adjustment, music playback), multi-dimensional collaborative intervention can be achieved, enhancing the user experience and the success rate of intervention.

[0074] Step S50: Based on the physiological index data monitored during the sleep process, determine whether any index is outside the normal range, record the exceeded index, and issue a reminder after waking up the next day; if any index is outside the second threshold range, trigger the first aid mode; the second threshold range is more deviated from the normal value compared to the first threshold range, that is, exceeding the second threshold range indicates a major abnormality in this index and a high health risk.

[0075] Specifically, when it is detected that the user's blood oxygen saturation is lower than 70% or the resting heart rate continuously > 120 beats per minute, trigger the first aid mode and link to execute the following steps: Link the smart home system to turn on all lights, play a distress message through the smart speaker, and automatically call a preset emergency contact number or the emergency call of a medical institution (such as 120); simultaneously upload the user's health data and location information to the cloud medical platform and initiate remote medical assistance. Or it can be remotely controlled by a pre-bound relative to turn on the smart light to emit light (brightness adjusted to the maximum, and it can also be strengthened by flashing), the smart speaker to broadcast a distress message (which can include an emergency call, volume decibel adjusted to the maximum, such as 130 dB), the smart bracelet to vibrate (vibration force adjusted to the maximum), etc. to achieve a first aid reminder. In addition, the system can also be connected to government emergency agencies. For example, when the government agency reminds that an earthquake, mudslide, etc. will occur in this area, the first aid mode will also be triggered, so that the user can escape from the emergency.

[0076] In an emergency scenario, through the three-level linkage of "wearable device - smart home - medical system" (such as automatically turning on the lights, broadcasting alarms, and uploading location data), the emergency response time is significantly shortened; the user's health data is synchronously pushed to the cloud medical platform, providing real-time basis for remote diagnosis and emergency decision-making, and improving the success rate of treatment.

[0077] Furthermore, in one embodiment, the method further includes the step of generating a personalized exercise prescription, which specifically includes: calculating the user's exercise load threshold through a dynamic intensity adaptation model, the inputs of the model including resting heart rate, maximum oxygen uptake, and exercise history data, and the outputs being weekly exercise frequency, target heart rate range, and calorie consumption target; dynamically adjusting the personalized exercise prescription according to the user's real-time exercise data, and if it is monitored that the heart rate exceeds the preset safety threshold, vibrating the smart bracelet to remind and reducing the exercise intensity.

[0078] Therefore, the method calculates the user's exercise load threshold (such as VO2max, resting heart rate) based on the dynamic intensity adaptation model to ensure the safety and scientific nature of the exercise prescription; real-time monitors the heart rate and triggers an early warning mechanism to prevent health risks (such as cardiovascular and cerebrovascular accidents) caused by exercise overload. Among them, the dynamic intensity adaptation model can refer to the prior art, and the present invention does not limit it here.

[0079] In summary, the personalized sleep intervention and first aid method and system based on multimodal data fusion provided by the present invention first generate a personalized dynamic sleep intervention plan by quantifying the user's physiological indicators, integrate manual and automatic intervention means, and break through the limitation of a single sensor; and can trigger sleep intervention in various ways, dynamically adjust the intervention intensity according to the real-time physiological state, and synchronously adjust the ambient light, brain wave stimulation, and music frequency when the user has insomnia. In addition, it can also monitor during sleep, and when any index is seriously abnormal, the first aid mode is automatically activated to avoid first aid delay.

[0080] Embodiment 2

[0081] The present invention provides a personalized sleep intervention and first aid system 100 based on multimodal data fusion, which is used to generate a personalized sleep intervention plan for the user's own physical health indicators and daily exercise data, and improve the user's sleep quality. It should be noted that the implementation principle and specific implementation method of the personalized sleep intervention and first aid system 100 based on multimodal data fusion can refer to the above-mentioned personalized sleep intervention and first aid method based on multimodal data fusion, and will not be elaborated below.

[0082] As Figure 2 shown, the personalized sleep intervention and first aid system 100 based on multimodal data fusion includes:

[0083] The real-time data acquisition module 10 is used to collect the physiological index data and exercise data of the user in real time through a wearable device, including age, height, weight, disease history, sleep heart rate, blood oxygen saturation, respiratory rate, HRV, body movement amplitude, and deep sleep duration;

[0084] The sleep quality assessment module 20 is used to generate a sleep quality score based on the physiological index data in combination with a preset sleep quality assessment model;

[0085] The intervention plan generation module 30 is used to generate a personalized sleep intervention plan according to the sleep quality score and the exercise data, including the best bedtime, wake-up time, target sleep duration, deep sleep duration, lunch break sleep duration, sleep aid music type, and brain wave regulation parameters;

[0086] The sleep intervention module 40 is used to be started by manually triggering or automatically detecting the user's insomnia state, and its intervention methods include at least one of the following methods: releasing α / β waves through the sleep improvement electrode module built in the smart bracelet to regulate nerve relaxation; linking the smart home system to adjust the light brightness to a preset threshold, closing the curtains, and playing hypnotic music that matches the user's preferences through the smart speaker; adjusting the emission frequency of the brain wave sleep aid pillow to guide the user into deep sleep;

[0087] The sleep process monitoring module 50 is used to judge whether any index is outside the normal range according to the physiological index data monitored during the sleep process, record the exceeded index and send a reminder after waking up the next day; if any index is outside the second threshold range, trigger the first aid mode; the second threshold range is more deviated from the normal value than the first threshold range.

[0088] Embodiment III

[0089] The present invention provides a terminal, which includes a memory, a processor, and a computer program stored in the memory. When the computer program is executed by the processor, it realizes each step of the personalized sleep intervention and first aid method based on multi-modal data fusion as described in any one of the above embodiments.

[0090] Embodiment IV

[0091] The present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it realizes each step of the personalized sleep intervention and first aid method based on multi-modal data fusion as described in any one of the above embodiments.

[0092] Embodiment V

[0093] The present invention provides a computer program product, including a computer program or instructions, which, when processed and executed, implement the steps of the personalized sleep intervention and first aid method based on multi-modal data fusion according to any one of the above-mentioned embodiments.

[0094] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be assigned to different functional units and modules according to needs, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the foregoing method embodiments and will not be elaborated here.

[0095] In the above-mentioned embodiments, the descriptions of each embodiment have their own emphases. For the parts not described or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0096] Those of ordinary skill in the art can realize that the units and method steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in the form of hardware or software depends on the specific application and design constraints of the technical solution. Professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0097] In the embodiments provided by the present invention, it should be understood that the disclosed system or device / terminal device and method can be implemented in other ways. For example, the system or device / terminal device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of the system or unit can be in an electrical, mechanical or other form.

[0098] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or may be distributed over multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0099] In addition, each functional unit in various embodiments of the present invention may be integrated in a processing unit, may also exist separately as individual physical units, or two or more units may be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0100] The present invention is not limited only to what is described in the specification and embodiments. Therefore, for those skilled in the art, additional advantages and modifications can be easily achieved. Thus, without departing from the spirit and scope of the general concept defined by the claims and their equivalents, the present invention is not limited to specific details, representative devices, and the illustrative examples shown and described herein.

Claims

1. A personalized sleep intervention and first aid method based on multi-modal data fusion, characterized in that It includes the following steps: Step S10: Real-time collect the user's physiological index data and exercise data through a wearable device, including age, height, weight, disease history, sleep heart rate, blood oxygen saturation, respiratory rate, HRV, body movement amplitude, and deep sleep duration; Step S20: Generate a sleep quality score based on the physiological index data in combination with a preset sleep quality assessment model; Step S30: Generate a personalized sleep intervention plan according to the sleep quality score and the exercise data, including the best bedtime, wake-up time, target sleep duration, deep sleep duration, lunch break sleep duration, sleep aid music type, and brain wave regulation parameters; Step S40: Start the sleep intervention module by manually triggering or automatically detecting the user's insomnia state, including at least one of the following methods: Release α / β waves through the sleep improvement electrode module built in the smart bracelet to regulate nerve relaxation; Link the smart home system to adjust the light brightness to a preset threshold, close the curtains, and play hypnotic music that matches the user's preferences through the smart speaker; Adjust the emission frequency through the brain wave sleep aid pillow to guide the user into deep sleep; Step S50: According to the physiological index data monitored during the falling asleep process, and judge whether any index is outside the first threshold range, record the exceeded index and send a reminder after waking up the next day; if any index is outside the second threshold range, trigger the first aid mode; the second threshold range is more deviated from the normal value than the first threshold range.

2. The personalized sleep intervention and first aid method based on multi-modal data fusion according to claim 1, characterized in that, In step S20, the formula for the sleep quality assessment model to generate the sleep quality score is: Where Qs is the sleep quality score, S d is the proportion of deep sleep duration, HRV s is the standard deviation of heart rate variability, A m is the body movement amplitude, A t is the preset body movement amplitude threshold, and α, β, γ are the weight coefficients of the corresponding items.

3. The personalized sleep intervention and first aid method based on multi-modal data fusion according to claim 1, characterized in that, In the step S30, when generating the sleep intervention plan, it further includes: Predict the user's sleep cycle based on historical sleep data and a machine learning model. The machine learning model uses an LSTM neural network, and the input features include the heart rate variability trend, body movement frequency, and environmental temperature and humidity. The output is the best intervention period and intervention intensity parameters.

4. The personalized sleep intervention and first aid method based on multimodal data fusion according to claim 1, characterized in that, The specific manual sleep intervention method in the step S40 includes: After detecting the user's manual trigger signal, start the sleep improvement electrode module to release α waves for 5-15 minutes, and then switch to β waves for nerve wake-up inhibition; among them, the frequency range of α waves is 8Hz-12Hz, and the frequency range of β waves is 12Hz-30Hz; Dynamically adjust the waveform intensity according to the real-time collected galvanic skin signal, and the adjustment formula is: Where I w is the output current intensity of the sleep improvement electrode module, GSR is the real-time skin conductance value, and GSR b is the skin conductance baseline value, and k is a preset calibration coefficient.

5. The personalized sleep intervention and first aid method based on multi-modal data fusion according to claim 1, characterized in that, In step S50, when it is detected that the user's blood oxygen saturation is lower than 70% or the resting heart rate continuously > 120 beats / minute, trigger the first aid mode and link to execute the following steps: Link the smart home system to turn on all the lights, play a distress message through the smart speaker and automatically dial the preset emergency contact number or the emergency medical service number of a medical institution; Synchronously upload the user's health data and location information to the cloud medical platform to start remote medical assistance.

6. The personalized sleep intervention and first aid method based on multi-modal data fusion according to claim 1, characterized in that, In step S30, the personalized sleep intervention plan further integrates environmental parameters, including: Collect environmental data through a temperature and humidity sensor and a light sensor, and calculate the comprehensive intervention weight in combination with physiological indexes; If the ambient temperature > 28°C or the light intensity > 50 lux, the smart home adjustment function is preferentially activated; otherwise, the electroencephalogram regulation module is preferentially activated.

7. The personalized sleep intervention and first aid method based on multi-modal data fusion according to claim 1, characterized in that, It further includes the step of generating a personalized exercise prescription, specifically including: Calculating the user's exercise load threshold through a dynamic intensity adaptation model, where the model inputs include resting heart rate, maximum oxygen uptake, and exercise history data, and the outputs are weekly exercise frequency, target heart rate range, and calorie consumption target; Dynamically adjusting the personalized exercise prescription according to the user's real-time exercise data. If it is detected that the heart rate exceeds the preset safety threshold, the smart bracelet vibrates to give a reminder and reduce the exercise intensity.

8. A personalized sleep intervention and first aid system based on multimodal data fusion, characterized in that, It includes: A data real-time acquisition module for real-time collecting the user's physiological index data and exercise data through wearable devices, including age, height, weight, disease history, sleep heart rate, blood oxygen saturation, respiratory rate, HRV, body movement amplitude, and deep sleep duration; A sleep quality assessment module for generating a sleep quality score based on the physiological index data in combination with a preset sleep quality assessment model; An intervention plan generation module for generating a personalized sleep intervention plan according to the sleep quality score and the exercise data, including the best bedtime, wake-up time, target sleep duration, deep sleep duration, lunch break sleep duration, sleep aid music type, and electroencephalogram regulation parameters; A sleep intervention module for being activated by manually triggering or automatically detecting the user's insomnia state, and its intervention methods include at least one of the following: releasing α / β waves through the sleep improvement electrode module built in the smart bracelet to regulate nerve relaxation; linking the smart home system to adjust the light brightness to a preset threshold, closing the curtains, and playing hypnogenic music matching the user's preference through the smart speaker; adjusting the emission frequency of the electroencephalogram sleep aid pillow to guide the user into deep sleep; An in-sleep process monitoring module for judging whether any index is outside the first threshold range according to the physiological index data monitored during the sleep process, recording the exceeded index and giving a reminder after waking up the next day; if any index is outside the second threshold range, triggering an emergency mode; the second threshold range is more deviated from the normal value compared with the first threshold range.

9. A terminal, characterized in that, The terminal includes a memory, a processor, and a computer program stored in the memory. When the computer program is executed by the processor, it realizes each step of the personalized sleep intervention and first aid method based on multi-modal data fusion as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, it realizes each step of the personalized sleep intervention and first aid method based on multi-modal data fusion as described in any one of claims 1-7.

Images