A sleep environment control method and system based on intelligent perception
Through the intelligent perception module, the user and sleep space is perceived in real time, and the sleep environment is adjusted based on the predetermined sleep time zone and perceived data. Combined with sleep risk constraints, the problem of lack of real-time and dynamic sleep environment control in the prior art is solved, and the sleep environment control is achieved. Real-time dynamic monitoring and adaptive adjustment of user sleep environment improve sleep quality.
Patent Information
- Application Number
- CN202411335279.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-24
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-09-24
AI Technical Summary
The prior art lacks real-time and dynamic nature in sleep environment control, and cannot adjust the sleep environment adaptively according to the user's real-time sleep state and sleep risk, resulting in the inability to meet the needs of users at different sleep stages and physical states.
By receiving sleep instructions from the target user, using the intelligent perception module to perceive the user and the sleep space in real time, predict the sleep stage based on the predetermined sleep time zone, extract multiple stage time zones, adjust the sleep environment based on the perceived data, and dynamically adjust it in combination with sleep risk constraints. Realize real-time dynamic monitoring and adaptive adjustment.
It improves the quality of users' sleep, and adjusts the sleep environment in real time through real-time perception and dynamic adjustment, adapts to the user's real-time sleep state and risks, provides personalized sleep environment control, and improves the real-time and dynamic nature of the sleep environment.
Smart Images

Figure CN118859744B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of smart home technology, and in particular to a method and system for controlling a sleeping environment with intelligent perception. Background Art
[0002] In the scenario of sleep environment control, people's demand for high-quality sleep is increasing day by day, and the real-time and dynamic control of the sleep environment is particularly prominent. The contradiction of satisfying users' needs to adaptively adjust the sleep environment according to their real-time sleep status and sleep risks is also more prominent. Developing an intelligent perception sleep environment control method to achieve real-time dynamic adjustment and adaptive control of the sleep environment has become a crucial link in solving people's demand for high-quality sleep. Traditional sleep environment control is often relatively simple and fixed, relying more on manual adjustment or preset modes. It lacks real-time perception of the user's sleep state, lacks in-depth analysis and utilization of the user's real-time sleep state and sleep risks, and is difficult to accurately adjust the sleep environment according to the user's actual situation. There are unreasonable situations in the control of the sleep environment, which makes it impossible to meet the needs of users in different sleep stages and different physical conditions. The formulation of the sleep environment control plan is relatively simple and cannot cope well with the user's changing sleep situation.
[0003] At present, relevant technologies have the technical problem that the sleep environment control lacks real-time and dynamic characteristics and cannot adjust the sleep environment according to the user's real-time sleep status and sleep risk adaptability. Summary of the invention
[0004] The present application provides a method and system for controlling a sleep environment using intelligent perception, which receives sleep instructions of a target user (including a predetermined sleep time zone and space), uses an intelligent perception module to perceive and acquire data of the target user and the sleep space in real time, predicts the sleep stage based on the predetermined sleep time zone to determine multiple stage time zones, extracts one of the stage time zones, adjusts the expected deviation of the sleep environment according to the time zone and the perception data to generate an adjustment plan, controls the sleep environment of the target user according to the plan and obtains continuous perception data, analyzes sleep risks according to the data and adjusts the sleep environment in combination with risk constraints, thereby adjusting the sleep environment according to the user's real-time sleep state and sleep risk, achieving real-time dynamic monitoring and adaptive adjustment of the sleep environment, and improving the user's sleep quality.
[0005] The present application provides a method for controlling a sleeping environment with intelligent perception, comprising:
[0006] The method comprises: receiving a sleep instruction of a target user, wherein the sleep instruction includes a predetermined sleep time zone and a predetermined sleep space; performing real-time perception of the target user and the predetermined sleep space according to an intelligent perception module, respectively, to obtain user vital sign perception data and sleep space environment perception data; performing sleep stage prediction based on the predetermined sleep time zone, and determining Q stage sleep time zones, wherein Q is a positive integer greater than 1; extracting the qth stage sleep time zone according to the Q stage sleep time zones, wherein q is a positive integer, 1≤q≤Q; adjusting the sleep environment expectation deviation based on the qth stage sleep time zone according to the user vital sign perception data and the sleep space environment perception data, and generating a qth stage sleep environment adjustment scheme; controlling the sleep environment of the target user according to the qth stage sleep time zone and the predetermined sleep space according to the qth stage sleep environment adjustment scheme, and obtaining qth stage continuous perception data based on the intelligent perception module; performing multi-feature sleep risk analysis on the target user according to the qth stage continuous perception data, obtaining a qth stage sleep risk analysis result, and adjusting the sleep environment of the target user in combination with multi-feature sleep risk constraints.
[0007] The present application also provides an intelligent sensing sleep environment control system, including:
[0008] a sleep instruction module, the sleep instruction module is used to receive the sleep instruction of the target user, wherein the sleep instruction includes a predetermined sleep time zone and a predetermined sleep space; a space perception module, the space perception module is used to perceive the target user and the predetermined sleep space in real time according to the intelligent perception module, and obtain user physical sign perception data and sleep space environment perception data; a sleep stage prediction module, the sleep stage prediction module is used to predict the sleep stage based on the predetermined sleep time zone, and determine Q stage sleep time zones, wherein Q is a positive integer greater than 1; a sleep time zone extraction module, the sleep time zone extraction module is used to extract the qth stage sleep time zone according to the Q stage sleep time zones, wherein q is a positive integer, 1≤q≤Q; a deviation adjustment module, the deviation adjustment module The sleep module is used to adjust the sleep environment expectation deviation based on the qth stage sleep time zone according to the user's physical sign perception data and the sleep space environment perception data, and generate a qth stage sleep environment adjustment plan; the sleep environment control module is used to control the sleep environment of the target user based on the qth stage sleep time zone and the predetermined sleep space according to the qth stage sleep environment adjustment plan, and obtain the qth stage continuous perception data based on the intelligent perception module; the risk analysis module is used to perform multi-feature sleep risk analysis on the target user according to the qth stage continuous perception data, obtain the qth stage sleep risk analysis result, and adjust the sleep environment of the target user in combination with multi-feature sleep risk constraints. An intelligent perception sleep environment control method and system proposed in the present application first receives the target user's sleep instructions (including a predetermined sleep time zone and space), uses the intelligent perception module to perceive the target user and the sleep space in real time to obtain data, predicts the sleep stage based on the predetermined sleep time zone to determine multiple stage time zones, extracts one of the stage time zones, adjusts the sleep environment expectation deviation according to the time zone and the perception data to generate an adjustment plan, controls the sleep environment of the target user according to the plan and obtains continuous perception data, analyzes the sleep risk according to the data and adjusts the sleep environment in combination with risk constraints, thereby achieving the technical effect of adjusting the sleep environment according to the user's real-time sleep state and sleep risk, achieving real-time dynamic monitoring and adaptive adjustment of the sleep environment, and improving the user's sleep quality. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.
[0010] Figure 1 A schematic diagram of a flow chart of an intelligent sensing sleep environment control method provided in an embodiment of the present application;
[0011] Figure 2 A schematic diagram of the structure of an intelligent sensing sleep environment control system provided in an embodiment of the present application.
[0012] Explanation of the accompanying drawings: sleep instruction module 10, space perception module 20, sleep stage prediction module 30, sleep time zone extraction module 40, deviation adjustment module 50, sleep environment control module 60, risk analysis module 70. DETAILED DESCRIPTION
[0013] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.
[0014] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.
[0015] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.
[0016] The present application embodiment provides a method for controlling a sleeping environment through intelligent perception, such as Figure 1 As shown, the method includes:
[0017] Step S100: receiving a sleep instruction of a target user, wherein the sleep instruction includes a predetermined sleep time zone and a predetermined sleep space. Specifically, when the target user issues a sleep instruction, the scheduled sleep time zone and scheduled sleep space contained therein lay the foundation for the entire intelligent perception sleep environment control solution. The scheduled sleep time zone clarifies the time range when the user plans to fall asleep and get up, which helps the system predict the sleep stage and adjust the environment at the appropriate time to ensure that the user can enjoy the best sleep environment when falling asleep and sleeping. The scheduled sleep space allows the system to understand the specific area where environmental control is required. Different sleep spaces may have different physical characteristics and environmental conditions. The system needs to perform targeted perception and adjustment according to their characteristics. After receiving the sleep instruction, the system prepares for subsequent links and provides a target range for real-time perception, so that the intelligent perception module can perform targeted environmental perception of the scheduled sleep space and obtain user vital sign data; provide a time frame for sleep stage prediction, so that the system can more accurately predict different sleep stages based on historical data in the scheduled sleep time zone and the current time point; provide a basis for the generation and implementation of sleep environment adjustment plans. The system can accurately adjust the environment of the scheduled sleep space at the appropriate time according to different sleep stages, user vital signs and sleep space environment to meet the personalized needs of users.
[0018] Step S200, according to the intelligent perception module, the target user and the predetermined sleeping space are respectively perceived in real time to obtain user vital sign perception data and sleeping space environment perception data. Specifically, in the intelligent perception sleeping environment control scheme, when the system receives the sleep instruction of the target user, the intelligent perception module is quickly started to perceive the target user and the predetermined sleeping space in real time. For the target user, wearable devices or non-contact sensors are used to perceive vital sign data such as heart rate, respiratory rate, and body temperature. The change of data reflects the user's physical state and sleep state change. For the predetermined sleeping space, various environmental sensors are arranged to monitor environmental parameters such as temperature, humidity, light, and noise in real time. Environmental conditions affect the user's sleep quality. The intelligent perception module continuously collects and pre-processes these data and transmits them to the system central processing unit through wireless communication technology or wired connection. The transmission process uses encryption and security authentication mechanisms to ensure user privacy and data security. After receiving the data, the system stores it and uses data analysis algorithms and models for in-depth analysis, including calculating indicators, predicting sleep quality, and performing correlation analysis, etc., to provide a basis for subsequent sleep environment control decisions.
[0019] Step S300, based on the predetermined sleep time zone, the sleep stage prediction is performed to determine Q stage sleep time zones, where Q is a positive integer greater than 1. Specifically, in the intelligent perception sleep environment control solution, the predetermined sleep time zone is the key basic information. A large amount of sleep-related data is collected and analyzed to find out the characteristics and rules of different sleep stages. Based on this, a sleep stage prediction model is established. After receiving the predetermined sleep time zone, the current time point and the user's real-time physiological characteristics and environmental data are input into the model to determine the current sleep stage and divide the predetermined sleep time zone into Q stage sleep time zones. Each stage corresponds to a specific sleep stage, which helps to provide users with personalized sleep environment control and accurately adjust the environment according to the characteristics of different stages; realize dynamic adjustment of the sleep environment, and adjust it in real time as the sleep stage changes; it can also optimize sleep quality assessment, comprehensively analyze the sleep situation by statistically analyzing the indicators of each stage, and provide personalized suggestions and improvement plans to improve the user's sleep quality and health level.
[0020] In one possible implementation, sleep stage prediction is performed based on the predetermined sleep time zone to determine Q sleep time zones, where Q is a positive integer greater than 1. Step S300 further includes step S310, performing a global retrieval of sleep stage records based on the target user to obtain a sample sleep time zone set and a sample sleep stage division record set. Specifically, in the intelligent perception sleep environment control solution, first, a global search of sleep stage records is performed based on the target user. Global search means not only retrieving the sleep stage records of the target user himself, but also including the sleep stage records of multiple users of the same type. Through extensive search, richer data samples can be obtained to improve the accuracy and reliability of subsequent sleep stage predictions. The objects of the search include the sleep stage records of the target user and multiple users of the same type who have similar characteristics (such as age, gender, living habits, etc.) to the target user. The data source for the search is determined, which can be sleep monitoring data stored on a local device or cloud server, a medical health database, etc. From the large number of sleep stage records retrieved, the sample sleep time zone information is extracted to form a sample sleep time zone set. The sample sleep time zone reflects the sleep stage distribution of different users in different time periods. The corresponding sample sleep stage division record set is obtained, which records the specific sleep stage corresponding to each sample sleep time zone, such as light sleep, deep sleep, rapid eye movement sleep, etc.
[0021] Step S320, supervised training is performed on the LSTM neural network using the sample sleep time zone set as input data and the sample sleep stage division record set as output data, and a sleep stage prediction error coefficient is obtained each time the training is performed for a predetermined number of times. Specifically, supervised training is performed on the long short-term memory (LSTM) neural network using the sample sleep time zone set as input data and the sample sleep stage division record set as output data. The LSTM neural network is a deep learning model suitable for processing time series data, and can effectively learn the law of sleep stage changes over time. The training process is set to determine the training parameters, such as learning rate, batch size, number of training times, etc. The sample sleep time zone set is input into the LSTM neural network one by one, and the network calculates the output result, i.e., the predicted sleep stage division, according to the current weight and bias. The sleep stage prediction error coefficient is calculated each time the training is performed for a predetermined number of times. The coefficient is usually determined by comparing the difference between the predicted sleep stage division output by the network and the actual sample sleep stage division record set. Common error calculation methods are used, such as mean square error (MSE), mean absolute error (MAE), etc. The smaller the error coefficient, the closer the prediction result of the network is to the actual data.
[0022] Step S330, if the sleep stage prediction error coefficient is less than the sleep stage prediction error threshold, a sleep stage prediction model is generated. Specifically, when the sleep stage prediction error coefficient is less than the preset sleep stage prediction error threshold, it is considered that the LSTM neural network has learned a sufficiently accurate sleep stage prediction pattern, and a sleep stage prediction model can be generated. Before determining the generated model, the model needs to be evaluated and verified, and a portion of sample data that has not participated in the training is used for testing to check the prediction performance of the model on the new data. If the model performs well on the test data, that is, the prediction error coefficient is still less than the threshold, then it can be determined to generate a sleep stage prediction model, and the generated sleep stage prediction model can be stored in a suitable location for subsequent calls in actual applications. The model can be deployed on a local device or provided to users through cloud services.
[0023] Step S340, based on the predetermined sleep time zone, according to the sleep stage prediction model, the Q stage sleep time zones are generated. Specifically, based on the predetermined sleep time zone, according to the generated sleep stage prediction model, Q stage sleep time zones are generated, and the predetermined sleep time zone set by the target user is provided as input data to the sleep stage prediction model. The sleep stage prediction model predicts the distribution of sleep stages in this time period based on the input predetermined sleep time zone and the previously learned sleep stage law. According to the prediction results of the model, the predetermined sleep time zone is divided into Q stage sleep time zones, and each stage sleep time zone corresponds to a specific sleep stage, providing an accurate time frame for subsequent sleep environment control. Through a series of steps such as global retrieval of sleep stage records, supervised training of LSTM neural network, generation of sleep stage prediction model, and generation of Q stage sleep time zones according to predetermined sleep time zones, the sleep stage prediction function in the intelligent perception sleep environment control solution is realized, which provides an important foundation for personalized sleep environment control.
[0024] Step S400, extracting the qth stage sleep time zone according to the Q stage sleep time zones, where q is a positive integer, 1≤q≤Q. Specifically, in the intelligent perception sleep environment control solution, the determined Q stage sleep time zones provide a detailed time division framework for the sleep process, q is a positive integer and 1≤q≤Q, and the qth stage sleep time zone can be selected and extracted according to the current time's position in the predetermined sleep time zone or the user's real-time physiological characteristics, environmental factors, etc., and traversal and screening can be achieved through programming. After extracting the qth stage sleep time zone, personalized sleep environment adjustments can be made according to the characteristics of different sleep stages, and the sleep environment can be dynamically controlled in real time during the sleep process. It can also more accurately evaluate the sleep quality and provide users with personalized sleep suggestions and improvement plans.
[0025] Step S500, based on the qth stage sleep time zone, the sleep environment expectation deviation is adjusted according to the user's physical sign perception data and the sleep space environment perception data, and the qth stage sleep environment adjustment plan is generated. Specifically, in the intelligent perception sleep environment control plan, the qth stage sleep time zone is a key time node, and the user's physical sign perception data (such as heart rate, respiratory rate, body temperature, etc., which reflect the user's physical state and needs) and the sleep space environment perception data (such as temperature, humidity, light, noise, etc., which directly affect sleep quality) are used to determine the qth stage sleep environment expectation in combination with the user's personal preferences, historical sleep data and sleep health standards, and dynamically adjust according to these data, compare the current sleep space environment perception data with the sleep environment expectation to calculate the deviation, and after comprehensive evaluation, generate the qth stage sleep environment adjustment plan according to the deviation evaluation result, including specific adjustment measures for each environmental parameter, and can also consider the user's sleep state and demand change trend for forward-looking adjustment to achieve personalized and intelligent sleep environment control.
[0026] In a possible implementation, based on the qth stage sleep time zone, the sleep environment expectation deviation is adjusted according to the user's physical sign perception data and the sleep space environment perception data, and the qth stage sleep environment adjustment scheme is generated. Step S500 further includes step S510, based on the qth stage sleep time zone, the environment of the predetermined sleep space is predicted according to the sleep space environment perception data, and the qth stage predicted sleep environment is obtained. Specifically, based on the qth stage sleep time zone, the environment of the predetermined sleep space is predicted according to the sleep space environment perception data, and the qth stage predicted sleep environment is obtained, and the time reference is determined. The qth stage sleep time zone provides a specific time range for the environment prediction, and clarifies the time period for the environment analysis of the sleep space in this stage. The sleep space environment perception data includes parameters such as temperature, humidity, light, and noise. Through the analysis and trend prediction of the data, the possible environmental state of the predetermined sleep space in the qth stage sleep time zone can be inferred, so as to obtain the qth stage predicted sleep environment. For example, if the current temperature is on an upward trend, and it is judged that it may continue to rise in the qth stage according to the time and historical data, then the temperature in the predicted sleep environment will also be adjusted accordingly.
[0027] Step S520, basic user information of the target user is obtained. Specifically, basic user information of the target user is obtained, which may include age, gender, health status, sleeping habits, etc. Basic user information is crucial for understanding the user's sleep needs and preferences, and can be obtained through information provided by the user during registration, analysis of previous sleep records, or interactive questions and answers with the user.
[0028] Step S530, based on the qth stage sleep time zone, the sleep environment expectation is parsed according to the user basic information and the user vital sign perception data, and the qth stage expected sleep environment is determined. Specifically, based on the qth stage sleep time zone, the sleep environment expectation is parsed according to the user basic information and the user vital sign perception data, and the qth stage expected sleep environment is determined. Considering the user basic information, the user's special needs can be understood. For example, older users may require a warmer temperature. At the same time, user vital sign perception data such as heart rate, breathing rate, body temperature, etc. can also reflect the user's current physical state and demand for the sleep environment. For example, a user with a higher body temperature may expect a lower sleep space temperature. The parsing process includes determining the user's expected sleep environment conditions in the qth stage sleep time zone through a comprehensive analysis of these factors, including the expected range of specific parameters such as temperature, humidity, light, and noise.
[0029] Step S540, based on the predicted sleep environment of the qth stage and the expected sleep environment of the qth stage, a sleep environment expectation deviation depth evaluation is performed to obtain the sleep environment expectation deviation index of the qth stage. Specifically, based on the predicted sleep environment of the qth stage and the expected sleep environment of the qth stage, a sleep environment expectation deviation depth evaluation is performed to obtain the sleep environment expectation deviation index of the qth stage, compare the actual and expected, compare the predicted sleep environment with the expected sleep environment, analyze the degree of difference of each environmental parameter, calculate the deviation index, and synthesize the difference into a sleep environment expectation deviation index, which can quantify the gap between the actual environment and the expected environment.
[0030] Step S550, judging whether the expected deviation index of the sleep environment at the qth stage is greater than / equal to the expected deviation index of the sleep environment. Specifically, judging whether the expected deviation index of the sleep environment at the qth stage is greater than / equal to the expected deviation index of the sleep environment at the predetermined stage, setting the standard that the expected deviation index of the sleep environment at the predetermined stage is a pre-set threshold value, representing an acceptable range of sleep environment deviation, comparing the calculated expected deviation index of the sleep environment at the qth stage with the predetermined threshold value to determine whether the current sleep environment deviation exceeds the acceptable range, and making a judgment, comparing the calculated expected deviation index of the sleep environment at the qth stage with the predetermined threshold value to determine whether the current sleep environment deviation exceeds the acceptable range.
[0031] Step S560: If the sleep environment expectation deviation index of the qth stage is greater than / equal to the predetermined sleep environment expectation deviation index, the sleep environment expectation adjustment model is activated. Specifically, if the sleep environment expectation deviation index of the qth stage is greater than / equal to the predetermined sleep environment expectation deviation index, the sleep environment expectation adjustment model is activated. When the deviation index exceeds the acceptable range, the adjustment mechanism is triggered. The sleep environment expectation adjustment model is a pre-trained model that can generate a corresponding adjustment plan based on the difference between the actual environment and the expected environment. At this time, the model is activated to prepare for generating the sleep environment adjustment plan for the qth stage.
[0032] Step S570, based on the qth stage expected sleep environment and the qth stage predicted sleep environment, according to the sleep environment expectation adjustment model, obtain the qth stage sleep environment adjustment plan. Specifically, the qth stage expected sleep environment and the qth stage predicted sleep environment are provided as input data to the sleep environment expectation adjustment model, and the data provides the model with the adjustment target and the current actual situation. The model calculates and analyzes the input data to generate a sleep environment adjustment plan for the qth stage sleep time zone, and the plan explicitly includes specific adjustment measures for environmental parameters such as temperature, humidity, light, and noise, aiming to narrow the gap between the actual environment and the expected environment, and provide the user with a more comfortable sleep environment.
[0033] In a possible implementation, based on the qth stage sleep time zone, the sleep environment expectation is parsed according to the user basic information and the user vital sign perception data to determine the qth stage expected sleep environment, and step S530 further includes step S531, obtaining a sleep comfort environment sample library, wherein the sleep comfort environment sample library includes multiple sleep comfort environment samples corresponding to multiple sample feature labels, and each sample feature label includes a user basic information sample, a user vital sign data sample, and a stage sleep time zone sample. Specifically, the sleep comfort environment sample library is a collection of many sleep comfort environment samples, each sample has a feature label, and this label is composed of a user basic information sample (such as age, gender, health status, etc.), a user vital sign data sample (such as heart rate, respiratory rate, body temperature, etc.) and a stage sleep time zone sample (time range corresponding to different sleep stages). The sample library provides a reference basis for the subsequent determination of the target user's expected sleep environment at a specific stage. By analyzing a large number of samples, the comfortable sleep environment characteristics under similar conditions to the target user can be found.
[0034] Step S532, based on the qth stage sleep time zone and the user physical sign perception data, the physical sign prediction data of the target user is performed to obtain the qth stage user physical sign prediction data. Specifically, the physical sign of the target user in the qth stage is predicted by using the time range information of the qth stage sleep time zone, combined with the current user physical sign perception data of the target user (such as real-time monitored heart rate, breathing and other data), to obtain the qth stage user physical sign prediction data, which can help more accurately determine the user's needs for the sleep environment at this stage.
[0035] Step S533, based on the user basic information, the qth stage user vital signs prediction data and the qth stage sleep time zone, the multiple sample feature labels are registered and identified to obtain multiple sample label registration coefficients. Specifically, the user basic information of the target user, the qth stage user vital signs prediction data and the qth stage sleep time zone are used as standards, and compared with each sample feature label in the sleep comfort environment sample library. Registration and identification is actually looking for samples similar to the target user. Multiple sample label registration coefficients are calculated by comparison. This coefficient reflects the similarity between each sample and the target user. The higher the similarity, the greater the registration coefficient.
[0036] Step S534, based on the predetermined label registration constraint, according to the multiple sample label registration coefficients, the sleep comfort environment sample library is selected to establish the sleep environment expectation space. Specifically, the predetermined label registration constraint is a pre-set standard for determining which samples are similar enough to the target user and can be selected into the sleep environment expectation space. According to the multiple sample label registration coefficients, samples that meet the predetermined label registration constraint are selected from the sleep comfort environment sample library. The selected samples constitute the sleep environment expectation space, which represents the range of sleep environment that the target user may expect under the current situation.
[0037] Step S535, traverse the sleep environment expectation space to perform confidence evaluation, and obtain multiple environment sample confidence coefficients. Specifically, a confidence evaluation is performed on each sample in the established sleep environment expectation space. The evaluation process is to determine to what extent each sample can be trusted as the target user's expected sleep environment, and multiple environment sample confidence coefficients are obtained, which reflect the reliability and credibility of each sample.
[0038] Step S536: Based on the environmental sample confidence constraint and the multiple environmental sample confidence coefficients, the sleep environment expectation space is cleaned to generate a confident sleep environment expectation space. Specifically, the environmental sample confidence constraint is a standard for determining sample reliability. Only samples whose confidence coefficients meet or exceed this standard will be retained. According to the multiple environmental sample confidence coefficients, samples that do not meet the environmental sample confidence constraint are removed from the sleep environment expectation space. After cleaning, a confident sleep environment expectation space is generated. The samples in this space are more reliable and can better represent the target user's actual expected sleep environment.
[0039] Step S537, performing multimodal concentrated interval analysis based on the expected space of the confident sleep environment to generate the expected sleep environment of the qth stage. Specifically, performing multimodal concentrated interval analysis on the expected space of the confident sleep environment, the analysis method comprehensively considers the characteristics of each sample in the space, finds a concentrated interval, and this interval represents the range of sleep environment parameters that the target user is most likely to expect in the qth stage, and finally generates the expected sleep environment of the qth stage, providing specific goals and directions for subsequent sleep environment adjustments.
[0040] Step S600, based on the qth stage sleep time zone and the predetermined sleep space, the sleep environment of the target user is controlled according to the qth stage sleep environment adjustment scheme, and based on the intelligent perception module, the qth stage continuous perception data is obtained. Specifically, in the intelligent perception sleep environment control scheme, the sleep environment of the target user is first controlled according to the qth stage sleep time zone and the predetermined sleep space, based on the qth stage sleep environment adjustment scheme, specifically including adjusting the temperature by controlling air conditioning and other equipment, starting a humidifier or dehumidifier to adjust the humidity, adjusting the light brightness or using blackout curtains to control the light, taking sound insulation measures to reduce noise, etc. The intelligent perception module continues to play a role in the whole process, constantly perceiving the target user and the predetermined sleep space in real time, and obtaining the qth stage continuous perception data, including the environmental parameters of the sleep space and the user's vital signs data, and providing real-time feedback to the system, so that the system can dynamically adjust the sleep environment control strategy according to the actual situation to ensure that the user is in the best sleep environment.
[0041] Step S700, according to the qth stage continuous perception data, multi-feature sleep risk analysis is performed on the target user to obtain the qth stage sleep risk analysis result, and the sleep environment of the target user is adjusted in combination with the multi-feature sleep risk constraint. Specifically, in the intelligent sleep environment control scheme, the qth stage continuous perception data, including the sleep space environment parameters and the target user's vital sign data, is obtained through the intelligent perception module, and the multi-feature sleep risk analysis is performed using the data. The environmental parameters and vital sign data are analyzed by specific algorithms and models to obtain the qth stage sleep risk analysis result. Combined with the multi-feature sleep risk constraint, that is, according to the sleep health standard and the user's special needs set limit conditions, the target user's sleep environment is adjusted. If the analysis result shows that there is a sleep risk and exceeds the constraint condition, the system takes corresponding measures to adjust, such as adjusting the temperature, quietness, etc., continuously monitors the continuous perception data during sleep, continuously performs risk analysis, and dynamically adjusts the sleep environment according to the results and constraints to ensure safety and comfort, reduce sleep risks, and improve the user's sleep quality and health level.
[0042] In one possible implementation, a multi-feature sleep risk analysis is performed on the target user according to the qth stage continuous perception data to obtain the qth stage sleep risk analysis result, and the sleep environment of the target user is adjusted in combination with the multi-feature sleep risk constraints, and step S700 further includes step S710, and the qth stage continuous perception data includes the qth stage user vital sign data and the qth stage sleep environment perception data. Specifically, the qth stage continuous perception data consists of two parts. The qth stage user vital sign data includes the target user's heart rate, breathing rate, body temperature and other physiological indicators at this stage, which reflect the user's physical state. The qth stage sleep environment perception data covers environmental parameters such as temperature, humidity, light, noise and other environmental parameters of the sleeping space, which directly affect the user's sleep quality and safety.
[0043] Step S720, based on the user's physical sign data of the qth stage and the sleep environment perception data of the qth stage, sleep quality interference identification is performed to obtain the sleep quality interference identification result of the qth stage. Specifically, the user's physical sign data of the qth stage and the sleep environment perception data are used to identify the sleep quality interference. For example, if the user's physical sign data shows that the heart rate fluctuates greatly, or the noise in the sleep environment perception data is too high, it may be considered as an interference factor to the sleep quality. By analyzing these data, the sleep quality interference identification result of the qth stage is obtained, and the result can clearly indicate which factors may interfere with the sleep quality at this stage, such as a specific environmental noise source or abnormal changes in the user's body.
[0044] Step S730, based on the sleep quality interference identification result of the qth stage, sleep quality risk prediction is performed to obtain the sleep quality risk coefficient of the qth stage. Specifically, the sleep quality risk prediction is performed based on the sleep quality interference identification result of the qth stage. If the identification result shows that there are many interference factors, then the sleep quality risk may be high. The sleep quality risk coefficient of the qth stage is calculated through a specific algorithm and model. The coefficient is a quantitative value that reflects the degree of risk faced by sleep quality. The higher the coefficient, the greater the threat to sleep quality.
[0045] Step S740, based on the user's vital sign data of the qth stage and the sleep environment perception data of the qth stage, sleep safety interference identification is performed to obtain the sleep safety interference identification result of the qth stage. Specifically, the user's vital sign data of the qth stage and the sleep environment perception data are also used to identify sleep safety interference. For example, if the user's vital sign data shows abnormal breathing, or there are potential safety hazards in the sleep environment perception data (such as excessively high temperatures that may cause fire risks), they are all sleep safety interference factors. After analysis, the sleep safety interference identification result of the qth stage is obtained, and the result clarifies the specific factors that may affect sleep safety at this stage.
[0046] Step S750, based on the qth stage sleep safety interference identification result, a sleep safety risk prediction is performed to obtain the qth stage sleep safety risk coefficient. Specifically, the sleep safety risk prediction is performed based on the qth stage sleep safety interference identification result. If the identification result shows that there are more safety interference factors, the sleep safety risk will increase accordingly. The qth stage sleep safety risk coefficient is obtained by calculation. The coefficient quantifies the risk level of sleep safety. The higher the coefficient, the greater the sleep safety risk.
[0047] Step S760, adding the sleep quality interference identification result of the qth stage, the sleep quality risk coefficient of the qth stage, the sleep safety interference identification result of the qth stage, and the sleep safety risk coefficient of the qth stage to the sleep risk analysis result of the qth stage. Specifically, the sleep quality interference identification result, the sleep quality risk coefficient, the sleep safety interference identification result, and the sleep safety risk coefficient obtained in the previous steps are integrated, and the data is added to the sleep risk analysis result of the qth stage, so that this result more comprehensively and accurately reflects the sleep risk status of the target user in the qth stage, including risk information in both sleep quality and sleep safety.
[0048] In a possible implementation, the qth stage sleep quality interference identification result, the qth stage sleep quality risk coefficient, the qth stage sleep safety interference identification result and the qth stage sleep safety risk coefficient are added to the qth stage sleep risk analysis result, and step S760 further includes step S761, extracting sleep quality risk constraints according to the multi-feature sleep risk constraints. Specifically, the multi-feature sleep risk constraint is a comprehensive constraint set, which includes different aspects of restrictions such as sleep quality risk constraints and sleep safety risk constraints. The constraints are set according to sleep health standards and special needs of users, aiming to ensure the safety and comfort of the sleeping environment. The sleep quality risk constraint is extracted from the multi-feature sleep risk constraint. The sleep quality risk constraint mainly focuses on factors affecting sleep quality, such as environmental noise level, suitable temperature range, light intensity and other parameter restrictions that may have adverse effects on sleep quality.
[0049] Step S762, judging whether the sleep quality risk coefficient of the qth stage meets the sleep quality risk constraint. Specifically, the sleep quality risk coefficient of the qth stage is used as the evaluation object, and is compared with the sleep quality risk constraint. The sleep quality risk coefficient of the qth stage is a quantitative value obtained by risk prediction of the sleep quality interference identification result of the qth stage, reflecting the risk level of sleep quality at this stage. It is judged whether the sleep quality risk coefficient of the qth stage is within the range specified by the sleep quality risk constraint. If the coefficient is within the constraint range, it means that the current sleep quality risk is at an acceptable level; if it is not within the constraint range, it means that there is a greater risk in the sleep quality, and further measures need to be taken to adjust it.
[0050] Step S763: If the sleep quality risk coefficient of the qth stage does not meet the sleep quality risk constraint, the sleep environment compensation is performed according to the sleep quality interference identification result of the qth stage, and the sleep environment compensation scheme of the qth stage is obtained. Specifically, when the judgment result shows that the sleep quality risk coefficient of the qth stage does not meet the sleep quality risk constraint, the sleep environment compensation mechanism is started, which means that there are factors that affect the sleep quality in the current sleep environment, and adjustments need to be made to reduce the risk. Specific compensation measures are determined according to the sleep quality interference identification result of the qth stage. The sleep quality interference identification result points out which factors have interfered with the sleep quality at this stage, such as excessive noise, unsuitable temperature, etc. A corresponding sleep environment compensation scheme is formulated for the interference factors. By analyzing and processing the interference factors, a sleep environment compensation scheme of the qth stage is generated. The scheme clarifies specific adjustment measures, such as methods for reducing noise levels (such as using sound insulation equipment), strategies for adjusting temperature (such as adjusting air conditioning temperature), etc., to improve sleep quality.
[0051] Step S764, adjusting the sleep environment of the target user according to the qth stage sleep environment compensation scheme. Specifically, the sleep environment of the target user is adjusted with the qth stage sleep environment compensation scheme as a guide, and the environmental parameters of the sleep space are adjusted according to the specific measures in the scheme to eliminate or reduce the interference factors on the sleep quality. After the sleep environment is adjusted, the sleep quality risk coefficient and the sleep quality interference identification results are continuously monitored to evaluate the effect of the adjustment measures. If the sleep quality risk constraint is still not met, it may be necessary to further optimize the compensation scheme and make adjustments until the ideal sleep quality state is achieved. By extracting the sleep quality risk constraint, judging whether the risk coefficient meets the constraint, performing the sleep environment compensation and implementing the adjustment, the sleep quality risk can be effectively managed and controlled, and a more comfortable and high-quality sleep environment can be provided for the target user.
[0052] In a possible implementation, the q-th stage sleep quality interference identification result, the q-th stage sleep quality risk coefficient, the q-th stage sleep safety interference identification result and the q-th stage sleep safety risk coefficient are added to the q-th stage sleep risk analysis result, and step S760 further includes step S765, extracting sleep safety risk constraints according to the multi-feature sleep risk constraints. Specifically, the multi-feature sleep risk constraint is a comprehensive set of constraints, covering multiple aspects such as sleep quality risk constraints and sleep safety risk constraints, which are set based on sleep health standards and special needs of users, and are intended to comprehensively ensure the safety and comfort of the sleep process. Sleep safety risk constraints are specifically extracted from the multi-feature sleep risk constraints. Sleep safety risk constraints mainly focus on factors that may affect sleep safety, such as potential dangerous factors in the environment (such as excessively high temperatures that may cause fires, concentrations of harmful gases, etc.), safety indicators of the user's body (such as abnormal heart rate or breathing patterns that may indicate health problems), and other restrictions.
[0053] Step S766, determine whether the sleep safety risk coefficient of the qth stage meets the sleep safety risk constraint. Specifically, the sleep safety risk coefficient of the qth stage is used as the evaluation object. The coefficient is a quantitative value obtained by risk prediction of the sleep safety interference identification result of the qth stage, which reflects the risk level of sleep safety in this stage. The sleep safety risk coefficient of the qth stage is compared with the sleep safety risk constraint to determine whether it is within the range specified by the constraint. If the coefficient is within the constraint range, it means that the current sleep safety risk is at an acceptable level; if it is not within the constraint range, it means that there is a greater risk to sleep safety and further measures need to be taken.
[0054] Step S767: If the sleep safety risk coefficient of the qth stage does not meet the sleep safety risk constraint, a sleep safety warning instruction of the qth stage is generated. Specifically, when the judgment result shows that the sleep safety risk coefficient of the qth stage does not meet the sleep safety risk constraint, the warning mechanism is triggered, which means that there are factors in the current sleeping environment or user status that may endanger sleep safety, and timely action is needed to generate a sleep safety warning instruction of the qth stage. The instruction serves as a trigger signal for subsequent processing, reminding the system and the user to pay attention to sleep safety issues and initiate corresponding countermeasures.
[0055] Step S768: Based on the qth stage sleep safety warning instruction, the sleep environment is associated according to the qth stage sleep safety interference identification result, the environment-associated sleep safety interference factor is determined, and the sleep environment is adjusted based on the environment-associated sleep safety interference factor. Specifically, after receiving the qth stage sleep safety warning instruction, the system performs a sleep environment association analysis according to the qth stage sleep safety interference identification result. The sleep safety interference identification result points out the specific factors that may affect sleep safety at this stage, such as specific environmental conditions or changes in the user's physical condition. Through the association analysis, the environment-associated sleep safety interference factor is determined. The sleep safety interference factor is an environmental factor directly related to the sleep safety problem, such as excessive temperature, the presence of harmful gases, and excessive noise levels. Based on the determined environment-associated sleep safety interference factor, corresponding sleep environment adjustment measures are taken, including adjusting the temperature, improving ventilation, reducing noise, etc., to eliminate or reduce the impact of interference factors on sleep safety and ensure the user's sleep safety. By extracting sleep safety risk constraints, judging whether the risk coefficient meets the constraints, generating warning instructions, and associating and adjusting the sleep environment, it is possible to effectively monitor and manage sleep safety risks and provide users with a safe and reliable sleeping environment.
[0056] The embodiment of the present application adopts the method of receiving the sleep instruction of the target user (including the predetermined sleep time zone and space), using the intelligent perception module to perceive the target user and the sleep space in real time to obtain data, predicting the sleep stage based on the predetermined sleep time zone to determine multiple stage time zones, extracting one of the stage time zones, adjusting the expected deviation of the sleep environment according to the time zone and the perception data to generate an adjustment plan, controlling the sleep environment of the target user according to the plan and obtaining continuous perception data, analyzing the sleep risk according to the data and adjusting the sleep environment in combination with the risk constraints, and adjusting the sleep environment according to the user's real-time sleep state and sleep risk, thereby achieving the technical effect of real-time dynamic monitoring and adaptive adjustment of the sleep environment and improving the user's sleep quality.
[0057] In the above, refer to Figure 1 A method for controlling a sleeping environment based on intelligent perception according to an embodiment of the present invention is described in detail. Figure 2 An intelligent sensing sleeping environment control system according to an embodiment of the present invention is described.
[0058] An intelligent perception sleep environment control system according to an embodiment of the present invention is used to solve the technical problem that the sleep environment control in the prior art lacks real-time and dynamic performance and cannot adjust the sleep environment according to the user's real-time sleep state and sleep risk adaptability. The sleep environment is adjusted by the user's real-time sleep state and sleep risk, achieving the technical effect of real-time dynamic monitoring and adaptive adjustment of the sleep environment and improving the user's sleep quality. An intelligent perception sleep environment control system includes: a sleep instruction module 10, a space perception module 20, a sleep stage prediction module 30, a sleep time zone extraction module 40, a deviation adjustment module 50, a sleep environment control module 60, and a risk analysis module 70.
[0059] The sleep instruction module 10 is used to receive a sleep instruction of a target user, wherein the sleep instruction includes a predetermined sleep time zone and a predetermined sleep space.
[0060] The space perception module 20 is used to perceive the target user and the predetermined sleeping space in real time according to the intelligent perception module, and obtain user vital sign perception data and sleeping space environment perception data.
[0061] The sleep stage prediction module 30 is used to perform sleep stage prediction based on the predetermined sleep time zones, and determine Q sleep time zones, where Q is a positive integer greater than 1.
[0062] The sleep time zone extraction module 40 is used to extract the qth stage sleep time zone according to the Q stages sleep time zones, where q is a positive integer, 1≤q≤Q.
[0063] The deviation adjustment module 50 is used to adjust the sleep environment expectation deviation based on the qth stage sleep time zone according to the user's physical sign perception data and the sleep space environment perception data, and generate a qth stage sleep environment adjustment plan.
[0064] The sleeping environment control module 60 is used to control the sleeping environment of the target user according to the qth stage sleeping time zone and the predetermined sleeping space according to the qth stage sleeping environment adjustment plan, and obtain the qth stage continuous perception data based on the intelligent perception module.
[0065] The risk analysis module 70 is used to perform multi-feature sleep risk analysis on the target user according to the qth stage continuous perception data, obtain the qth stage sleep risk analysis result, and adjust the sleep environment of the target user in combination with the multi-feature sleep risk constraints.
[0066] The specific configuration of the sleep stage prediction module 30 will be described in detail below. As described above, based on the predetermined sleep time zone, the sleep stage prediction is performed to determine Q stage sleep time zones, where Q is a positive integer greater than 1, and the sleep stage prediction module 30 further includes: a global retrieval unit, the global retrieval unit is used to perform a global retrieval of the sleep stage records based on the target user, and obtain a sample sleep time zone set and a sample sleep stage division record set; a supervised training unit, the supervised training unit is used to supervise the LSTM neural network with the sample sleep time zone set as input data and the sample sleep stage division record set as output data, and obtain the sleep stage prediction error coefficient after each predetermined number of trainings; a prediction model generation unit, the prediction model generation unit is used to generate a sleep stage prediction model if the sleep stage prediction error coefficient is less than the sleep stage prediction error threshold; a sleep time zone generation unit, the sleep time zone generation unit is used to generate the Q stage sleep time zones based on the predetermined sleep time zone and the sleep stage prediction model.
[0067] The specific configuration of the deviation adjustment module 50 will be described in detail below. As described above, based on the qth stage sleep time zone, the sleep environment expectation deviation adjustment is performed according to the user's vital sign perception data and the sleep space environment perception data to generate the qth stage sleep environment adjustment plan. The deviation adjustment module 50 further includes: an environment prediction unit, the environment prediction unit is used to perform environment prediction on the predetermined sleep space based on the qth stage sleep time zone and the sleep space environment perception data to obtain the qth stage predicted sleep environment; a basic information acquisition unit, the basic information acquisition unit is used to obtain the user basic information of the target user; an expectation parsing unit, the expectation parsing unit is used to perform sleep environment expectation parsing based on the qth stage sleep time zone and the user's vital sign perception data to determine the qth stage expected sleep environment; a deviation depth evaluation unit, The deviation depth evaluation unit is used to perform a sleep environment expectation deviation depth evaluation based on the qth stage predicted sleep environment and the qth stage expected sleep environment, and obtain the qth stage sleep environment expectation deviation index; a deviation index judgment unit, the deviation index judgment unit is used to judge whether the qth stage sleep environment expectation deviation index is greater than / equal to the predetermined sleep environment expectation deviation index; an adjustment model activation unit, the adjustment model activation unit is used to activate the sleep environment expectation adjustment model if the qth stage sleep environment expectation deviation index is greater than / equal to the predetermined sleep environment expectation deviation index; an adjustment scheme acquisition unit, the adjustment scheme acquisition unit is used to obtain the qth stage sleep environment adjustment scheme according to the sleep environment expectation adjustment model based on the qth stage expected sleep environment and the qth stage predicted sleep environment.
[0068] Wherein, based on the qth stage sleep time zone, the sleep environment expectation analysis is performed according to the user basic information and the user vital sign perception data to determine the qth stage expected sleep environment, and the expectation analysis unit further includes: a sample library acquisition subunit, the sample library acquisition subunit is used to obtain a sleep comfort environment sample library, wherein the sleep comfort environment sample library includes a plurality of sleep comfort environment samples corresponding to a plurality of sample feature labels, and each sample feature label includes a user basic information sample, a user vital sign data sample and a stage sleep time zone sample; a vital sign prediction subunit, the vital sign prediction subunit is used to perform vital sign prediction on the target user based on the qth stage sleep time zone and the user vital sign perception data to obtain the qth stage user vital sign prediction data; a registration recognition subunit is used to perform a registration recognition subunit based on the user basic information, the qth stage user vital sign prediction data and the qth stage user vital sign prediction data. The sleep time zone of the qth stage is formed by aligning and identifying the multiple sample feature labels to obtain multiple sample label alignment coefficients; a sample library selection subunit is used to select the sleep comfort environment sample library based on the predetermined label alignment constraints and the multiple sample label alignment coefficients to establish the expected sleep environment space; a confidence evaluation subunit is used to traverse the expected sleep environment space to perform confidence evaluation and obtain multiple environmental sample confidence coefficients; an expected space cleaning subunit is used to clean the expected sleep environment space based on the environmental sample confidence constraints and the multiple environmental sample confidence coefficients to generate a confident expected sleep environment space; an interval parsing subunit is used to perform multimodal centralized interval parsing based on the confident expected sleep environment space to generate the expected sleep environment of the qth stage.
[0069] The specific configuration of the risk analysis module 70 will be described in detail below. As described above, the target user is subjected to a multi-feature sleep risk analysis based on the qth stage continuous perception data to obtain the qth stage sleep risk analysis result, and the target user's sleep environment is adjusted in combination with the multi-feature sleep risk constraints. The risk analysis module 70 further includes: a continuous perception data composition unit, the continuous perception data composition unit is used for the qth stage continuous perception data including the qth stage user vital sign data and the qth stage sleep environment perception data; an interference identification unit, the interference identification unit is used to identify sleep quality interference based on the qth stage user vital sign data and the qth stage sleep environment perception data to obtain the qth stage sleep quality interference identification result; a sleep quality risk prediction unit, the sleep quality risk prediction unit is used to predict sleep quality based on the qth stage sleep quality interference identification result. a sleep quality interference identification result acquisition unit, the interference identification result acquisition unit is used to perform sleep safety interference identification based on the qth stage user vital sign data and the qth stage sleep environment perception data, and obtain the qth stage sleep safety interference identification result; a safety risk coefficient acquisition unit, the safety risk coefficient acquisition unit is used to perform sleep safety risk prediction based on the qth stage sleep safety interference identification result, and obtain the qth stage sleep safety risk coefficient; a sleep risk analysis result adding unit, the sleep risk analysis result adding unit is used to add the qth stage sleep quality interference identification result, the qth stage sleep quality risk coefficient, the qth stage sleep safety interference identification result and the qth stage sleep safety risk coefficient to the qth stage sleep risk analysis result.
[0070] The sleep quality interference identification result of the qth stage, the sleep quality risk coefficient of the qth stage, the sleep safety interference identification result of the qth stage and the sleep safety risk coefficient of the qth stage are added to the sleep risk analysis result of the qth stage, and the sleep risk analysis result adding unit further includes: a risk constraint extraction subunit, the risk constraint extraction subunit is used to extract the sleep quality risk constraint according to the multi-feature sleep risk constraint; a risk coefficient judgment subunit, the risk coefficient judgment subunit is used to judge whether the sleep quality risk coefficient of the qth stage meets the sleep quality risk constraint; a sleep environment compensation subunit, the sleep environment compensation subunit is used to perform sleep environment compensation according to the sleep quality interference identification result of the qth stage if the sleep quality risk coefficient of the qth stage does not meet the sleep quality risk constraint, and obtain the sleep environment compensation scheme of the qth stage; a sleep environment adjustment subunit, the sleep environment adjustment subunit is used to adjust the sleep environment of the target user according to the sleep environment compensation scheme of the qth stage.
[0071] Among them, the sleep risk analysis result adding unit also includes: a sleep safety risk constraint extraction subunit, the sleep safety risk constraint extraction subunit is used to extract the sleep safety risk constraint according to the multi-feature sleep risk constraint; a sleep safety risk constraint judgment subunit, the sleep safety risk constraint judgment subunit is used to judge whether the qth stage sleep safety risk coefficient meets the sleep safety risk constraint; a safety warning instruction generation subunit, the safety warning instruction generation subunit is used to generate a qth stage sleep safety warning instruction if the qth stage sleep safety risk coefficient does not meet the sleep safety risk constraint; a sleep environment association subunit, the sleep environment association subunit is used to associate the sleep environment based on the qth stage sleep safety warning instruction and the qth stage sleep safety interference identification result, determine the environment-associated sleep safety interference factor, and adjust the sleep environment based on the environment-associated sleep safety interference factor.
[0072] An intelligent perception sleeping environment control system provided by an embodiment of the present invention can execute an intelligent perception sleeping environment control method provided by any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.
[0073] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server, and the various units and modules included are only divided according to the functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention. The above specific implementation does not constitute a limitation on the scope of protection of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the scope of protection of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and the desired results can still be achieved. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
Claims
1. A method for controlling a sleeping environment based on intelligent perception, characterized in that: The method comprises: receiving a sleep instruction of a target user, wherein the sleep instruction includes a predetermined sleep time zone and a predetermined sleep space; According to the intelligent perception module, the target user and the predetermined sleeping space are respectively perceived in real time to obtain user vital sign perception data and sleeping space environment perception data; Predicting sleep stages based on the predetermined sleep time zones to determine Q sleep time zones, where Q is a positive integer greater than 1; According to the Q stage sleep time zones, extracting the qth stage sleep time zone, wherein q is a positive integer, 1≤q≤Q; Based on the qth stage sleep time zone, adjusting the sleep environment expectation deviation according to the user's physical sign perception data and the sleep space environment perception data, and generating a qth stage sleep environment adjustment plan; Based on the qth stage sleep time zone and the predetermined sleep space, the sleep environment of the target user is controlled according to the qth stage sleep environment adjustment plan, and based on the intelligent perception module, the qth stage continuous perception data is obtained; Performing a multi-feature sleep risk analysis on the target user according to the qth stage continuous perception data, obtaining a qth stage sleep risk analysis result, and adjusting the sleep environment of the target user in combination with the multi-feature sleep risk constraints; The step of predicting the sleep stage based on the predetermined sleep time zone to determine Q sleep time zones includes: Perform a global search of the sleep stage records based on the target user to obtain a sample sleep time zone set and a sample sleep stage division record set; Using the sample sleep time zone set as input data and the sample sleep stage division record set as output data, supervised training is performed on the LSTM neural network, and a sleep stage prediction error coefficient is obtained after each predetermined number of trainings; If the sleep stage prediction error coefficient is less than the sleep stage prediction error threshold, generating a sleep stage prediction model; Based on the predetermined sleep time zone, and according to the sleep stage prediction model, generating the Q stage sleep time zones; Wherein, based on the qth stage sleep time zone, adjusting the sleep environment expectation deviation according to the user's physical sign perception data and the sleep space environment perception data, and generating the qth stage sleep environment adjustment plan include: Based on the qth stage sleep time zone, performing environmental prediction on the predetermined sleep space according to the sleep space environment perception data to obtain a qth stage predicted sleep environment; Obtaining basic user information of the target user; Based on the qth stage sleep time zone, performing sleep environment expectation analysis according to the user basic information and the user vital sign perception data, and determining the qth stage expected sleep environment; Performing a sleep environment expectation deviation depth evaluation based on the predicted sleep environment at the qth stage and the expected sleep environment at the qth stage to obtain a sleep environment expectation deviation index at the qth stage; Determining whether the sleep environment expectation deviation index of the qth stage is greater than / equal to a predetermined sleep environment expectation deviation index; If the sleep environment expectation deviation index of the qth stage is greater than / equal to the predetermined sleep environment expectation deviation index, activating the sleep environment expectation adjustment model; Based on the qth stage expected sleep environment and the qth stage predicted sleep environment, obtaining the qth stage sleep environment adjustment plan according to the sleep environment expectation adjustment model; Wherein, based on the qth stage sleep time zone, performing sleep environment expectation analysis according to the user basic information and the user vital sign perception data to determine the qth stage expected sleep environment includes: Obtaining a sleeping comfort environment sample library, wherein the sleeping comfort environment sample library includes a plurality of sleeping comfort environment samples corresponding to a plurality of sample feature labels, and each sample feature label includes a user basic information sample, a user vital sign data sample, and a stage sleep time zone sample; Performing physical sign prediction on the target user based on the qth stage sleep time zone and the user physical sign perception data to obtain the qth stage user physical sign prediction data; Based on the user basic information, the qth stage user physical sign prediction data and the qth stage sleep time zone, the multiple sample feature labels are registered and identified to obtain multiple sample label registration coefficients; Based on the predetermined label registration constraint and according to the plurality of sample label registration coefficients, the sleeping comfort environment sample library is selected to establish the expected sleeping environment space; Traversing the sleep environment expectation space to perform confidence evaluation and obtain confidence coefficients of multiple environment samples; Based on the environmental sample confidence constraint and according to the multiple environmental sample confidence coefficients, cleaning the sleep environment expectation space to generate a confident sleep environment expectation space; A multimodal concentrated interval analysis is performed based on the confident sleep environment expectation space to generate the qth stage expected sleep environment.
2. The intelligent sensing sleep environment control method according to claim 1, characterized in that: Performing a multi-feature sleep risk analysis on the target user according to the qth stage continuous sensing data to obtain a qth stage sleep risk analysis result, including: The qth stage continuous perception data includes the qth stage user vital sign data and the qth stage sleep environment perception data; Perform sleep quality interference identification based on the qth stage user physical sign data and the qth stage sleep environment perception data to obtain the qth stage sleep quality interference identification result; Performing sleep quality risk prediction based on the sleep quality interference identification result of the qth stage to obtain the sleep quality risk coefficient of the qth stage; Perform sleep safety interference identification based on the qth stage user vital sign data and the qth stage sleep environment perception data to obtain the qth stage sleep safety interference identification result; Performing sleep safety risk prediction based on the qth stage sleep safety interference identification result to obtain the qth stage sleep safety risk coefficient; The qth stage sleep quality interference identification result, the qth stage sleep quality risk coefficient, the qth stage sleep safety interference identification result and the qth stage sleep safety risk coefficient are added to the qth stage sleep risk analysis result.
3. The intelligent sensing sleep environment control method according to claim 2, characterized in that: Performing a multi-feature sleep risk analysis on the target user according to the qth stage continuous sensing data to obtain a qth stage sleep risk analysis result, and adjusting the sleep environment of the target user in combination with the multi-feature sleep risk constraint, including: Extracting sleep quality risk constraints according to the multi-feature sleep risk constraints; Determining whether the sleep quality risk coefficient of the qth stage meets the sleep quality risk constraint; If the sleep quality risk coefficient of the qth stage does not meet the sleep quality risk constraint, perform sleep environment compensation according to the sleep quality interference identification result of the qth stage to obtain a sleep environment compensation plan for the qth stage; The sleep environment of the target user is adjusted according to the qth stage sleep environment compensation scheme.
4. The intelligent sensing sleep environment control method according to claim 2, characterized in that: Performing a multi-feature sleep risk analysis on the target user according to the qth stage continuous sensing data to obtain a qth stage sleep risk analysis result, and adjusting the sleep environment of the target user in combination with the multi-feature sleep risk constraint, including: Extracting sleep safety risk constraints according to the multi-feature sleep risk constraints; Determining whether the sleep safety risk coefficient of the qth stage satisfies the sleep safety risk constraint; If the sleep safety risk coefficient of the qth stage does not satisfy the sleep safety risk constraint, generating a sleep safety warning instruction for the qth stage; Based on the qth stage sleep safety warning instruction, sleep environment association is performed according to the qth stage sleep safety interference identification result, an environment-associated sleep safety interference factor is determined, and the sleep environment is adjusted based on the environment-associated sleep safety interference factor.
5. An intelligent sensing sleeping environment control system, characterized in that: The system is used to implement the intelligent sensing sleep environment control method according to any one of claims 1 to 4, and the system comprises: A sleep instruction module, the sleep instruction module is used to receive a sleep instruction of a target user, wherein the sleep instruction includes a predetermined sleep time zone and a predetermined sleep space; A space perception module, which is used to perceive the target user and the predetermined sleeping space in real time according to the intelligent perception module, and obtain user vital sign perception data and sleeping space environment perception data; A sleep stage prediction module, the sleep stage prediction module is used to predict the sleep stage based on the predetermined sleep time zone, and determine Q stage sleep time zones, wherein Q is a positive integer greater than 1; A sleep time zone extraction module, the sleep time zone extraction module is used to extract the qth stage sleep time zone according to the Q stage sleep time zones, wherein q is a positive integer, 1≤q≤Q; a deviation adjustment module, the deviation adjustment module being used to adjust the sleep environment expectation deviation based on the qth stage sleep time zone and according to the user's physical sign perception data and the sleep space environment perception data, and generate a qth stage sleep environment adjustment plan; a sleeping environment control module, the sleeping environment control module being used to control the sleeping environment of the target user according to the qth stage sleeping environment adjustment scheme based on the qth stage sleeping time zone and the predetermined sleeping space, and to obtain the qth stage continuous sensing data based on the intelligent sensing module; A risk analysis module, wherein the risk analysis module is used to perform multi-feature sleep risk analysis on the target user according to the qth stage continuous perception data, obtain the qth stage sleep risk analysis result, and adjust the sleep environment of the target user in combination with the multi-feature sleep risk constraints.
