A sleep environment adjustment system and method based on personalized data analysis

By classifying and analyzing the operation data of the hotel check-in users, predicting and matching suitable intelligent adjustment devices, the problem of delay and error of sleep environment regulation in the hotel environment is solved, ensuring that the equipment works effectively, and optimizing the user's sleep environment. Improved the stay experience.

CN117672542BActive Publication Date: 2024-11-15JIANGSU SUHAO TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311633514.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-12-01
Publication Date
2024-11-15
Estimated Expiration
2043-12-01

AI Technical Summary

Technical Problem

When hotels and other accommodation environments face different user check-in, it is difficult to analyze sign status data in real time, resulting in delays and errors in equipment adjustments, affecting the quality of sleep of users. Moreover, the sleep environment cannot be effectively adjusted when users do not wear sign status monitoring equipment, which adds equipment. Difficulty in regulation.

Method used

By classifying the operating data of occupants, analyzing their sleep adjustment needs, building an association model, predicting and matching suitable intelligent adjustment devices, ensuring that the device can work effectively after the user falls asleep and maximizes the optimization under stateless data conditions. Sleeping environment.

Benefits of technology

It realizes accurate prediction of the sleep environment adjustment of newly occupants, avoids the situation where the device cannot work, improves the user experience, and optimizes the sleep environment in the absence of state data, and improves the sleep quality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117672542B_ABST
    Figure CN117672542B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of sleep environment regulation, and specifically to a sleep environment regulation system and method based on personalized data analysis, comprising a data acquisition module, a user classification module, an optimal sleep evaluation value analysis module, a correlation analysis module and a new user response module; the data acquisition module is used to acquire check-in events and operation behavior data of users after check-in; the user classification module is used to classify users of each type of monitoring space based on check-in events and operation behavior data; the optimal sleep evaluation value analysis module is used to analyze the optimal sleep evaluation value corresponding to each type of user; the correlation analysis module is used to construct a correlation relationship model between user operation behavior data and optimal sleep evaluation value, and output correlation determination results; the new user response module is used to predict the intelligent regulation equipment required by the newly checked-in users and perform monitoring responses.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of sleep environment regulation, and in particular to a sleep environment regulation system and method based on personalized data analysis. Background Art

[0002] Sleep is an essential physiological activity for the human body, and good sleep is a basic condition for maintaining good health. However, due to work pressure, irregular lifestyle and other reasons, most people have poor sleep quality. Therefore, other methods are needed to assist people in sleeping and help them improve their sleep quality. With the development of artificial intelligence, smart homes can not only bring convenience to daily life, but also realize intelligent adjustment based on the Internet of Things in sleep assistance, such as adjusting the user's sleeping environment through single or multiple environmental factors such as sound and temperature to help users sleep. However, these sets of smart homes often exist in the user's personal residence, which can realize the formulation of corresponding sleeping environment adjustment strategies based on the user's own sleeping habits. For other places such as hotels, when facing different occupants, it is often necessary to analyze the physical state data in real time, and then passively adjust the equipment to change the sleeping environment, which will not only increase the delay and error rate of equipment adjustment, but also may cause unexpected situations when the equipment needs to execute the adjustment instructions, which will affect the sleeping environment of the occupants and bring immeasurable losses to the hotel. Summary of the invention

[0003] The purpose of the present invention is to provide a sleep environment adjustment system and method based on personalized data analysis to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for adjusting a sleeping environment based on personalized data analysis, comprising the following analysis steps:

[0005] Step S100: Marking monitoring spaces containing the same intelligent adjustment device as the same type of monitoring space, obtaining check-in events recorded in each type of monitoring space and operation behavior data of users after check-in; and classifying users of each type of monitoring space based on check-in events and operation behavior data;

[0006] Step S200: Based on the classified users, obtain the physical sign status data and sleep adjustment data of each type of user; and analyze the optimal sleep evaluation value corresponding to each type of user;

[0007] Step S300: constructing a correlation relationship model between the user operation behavior data and the optimal sleep evaluation value based on the optimal sleep evaluation value, and outputting a correlation determination result;

[0008] Step S400: Based on the association determination result, the intelligent adjustment equipment required by the newly added user is predicted and a monitoring response is performed.

[0009] Furthermore, users of each type of monitored space are classified based on check-in events and operation behavior data, including the following analysis steps:

[0010] Step S110: obtaining the number of occupants corresponding to the occupancy event record of the same monitoring space, and storing the occupancy events corresponding to the same number of occupants into an analysis set; the operation behavior data refers to the data recorded by the user manually adjusting the intelligent adjustment device, and the operation behavior data includes the operation object and the adjustment data;

[0011] Step S120: Mark the initial data group A1 with the same record operation object corresponding to the check-in event in the i-th analysis set, Among them U i represents the i-th analysis set, represents the jth group of operation objects in the i-th analysis set; extracts the adjustment data corresponding to each check-in event of the initial data group A1, and the adjustment data includes the number of adjustments, the adjustment deviation value and the adjustment time; uses the formula:

[0012]

[0013] Calculate the same set of operands The dynamic index of the user's sleeping environment corresponding to the next k-th check-in event where d k represents the total number of times the user operates the intelligent adjustment device corresponding to the k-th check-in event, D ij Indicates that the object is being operated on Record the average number of times each user operates the smart adjustment device in all check-in events; k represents the average adjustment deviation value of the user-operated intelligent adjustment device corresponding to the k-th check-in event. The adjustment deviation value refers to the absolute value of the difference between the state value recorded by the device before adjustment and the state value recorded by the device after adjustment; F ij Indicates that the object is being operated on The average adjustment deviation value of each user operating the intelligent adjustment device in all check-in events is recorded below; t k T represents the time interval between the last manual adjustment of the device by the user corresponding to the k-th check-in event and the first adjustment of the intelligent adjustment device starting the autonomous adjustment function; ijmax Indicates that the object is being operated on The maximum time interval between the last manual adjustment of the device by the user and the first adjustment of the self-regulation function of the intelligent adjustment device in all check-in events is recorded below; the larger the ratio, the higher the demand for the intelligent adjustment device, the higher the attention paid by the user in the check-in event, the more obvious the adjustment purpose, and the certain requirements for the sleeping environment;

[0014] Step S130: Calculate the average deviation value R of all sleep environment dynamic indexes recorded in the i-th analysis set i ,

[0015]

[0016] in represents the number of combinations consisting of 2 selected from n sleep environment dynamic indexes, and n represents the total number of check-in events included in the i-th analysis set; represents the sleep environment dynamic index of the i-th analysis set corresponding to the k-th check-in event, represents the sleep environment dynamic index of the i-th analysis set corresponding to the k+r-th check-in event, It means to sum the difference between any two sleep environment dynamic indexes in the traversal analysis set, where r is any non-zero natural number less than or equal to n-1;

[0017] Step S140: Classify the check-in events corresponding to any two sleep environment dynamic indexes included in the same initial data set A1 whose difference is less than the average deviation value into one category to construct a target data set A2. It represents the mean value of a corresponding sleep environment dynamic index; each target data group represents a type of user.

[0018] Furthermore, analyzing the optimal sleep evaluation value corresponding to each type of user includes the following analysis steps:

[0019] Step S210: Divide the user's sleep stage into four stages, namely, falling asleep stage, light sleep stage, deep sleep stage and deep sleep stage; extract sleep adjustment data recorded for different users in each sleep stage, where the sleep adjustment data refers to the amplitude adjusted by the intelligent adjustment device based on the physical sign state data; and use the sleep adjustment data that reaches the standard physical sign sleep state after amplitude adjustment as the effective adjustment data;

[0020] Step S220: extracting the maximum value L of the change value of the physical sign state data corresponding to the same amplitude in the effective adjustment data in each sleep stage max , calculate the adjustment ratio G corresponding to each type of amplitude, G = L max / B, B represents the adjustment amplitude; when the output adjustment ratio G is the largest, the corresponding intelligent adjustment device is the target adjustment device, and the maximum value L of the change value of the corresponding vital sign state data of the target adjustment device is obtainedmax As the target change value;

[0021] Step S230: Obtain the target change value for each sleep stage and calculate the optimal sleep evaluation value Q corresponding to each type of user, Q = ∑L max ;∑L max It means summing up the target change values ​​corresponding to each of the four stages.

[0022] Calculating the adjustment ratio can quickly analyze the users of the same type who are most affected by the adjustment amplitude. Taking the target change value as the conditional parameter of the optimal sleep evaluation value can reflect the maximum impact level of a type of users under the adjustment of the smart adjustment device.

[0023] Further, step S300 includes the following analysis process:

[0024] The average value of the sleep environment dynamic index and the optimal sleep evaluation value of each type of user constitute the analysis pair E. Obtain analysis pairs corresponding to all types of users; use the correlation analysis model to analyze the correlation between the sleep environment dynamic index and the optimal sleep evaluation value, and use the correlation analysis model as an association relationship model;

[0025] The correlation analysis model outputs the association determination result, which includes the existence of association and the non-existence of association.

[0026] Furthermore, step S400 includes the following analysis process:

[0027] When the association determination result is that there is no association, the smart adjustment device of the corresponding user with the greatest similarity is matched based on the vital sign status data of the newly added user as the smart adjustment device required by the newly added user;

[0028] When the association determination result is that there is an association, the user operation behavior data recorded before the newly added user enters the room before entering the sleep state is obtained, and the user's real-time sleep environment dynamic index is calculated;

[0029] Based on the real-time sleep environment dynamic index matching and the target data group A2 with the smallest difference in the mean of the sleep environment dynamic index, the real-time user is classified into the corresponding type of user;

[0030] Extract the target adjustment device recorded by the matched user type as the smart adjustment device required by the newly added user;

[0031] And transmit the remaining power information and device status of the intelligent adjustment device to the management end, monitor and respond to whether the remaining power information is available for amplitude adjustment after the new user enters sleep and whether the device status is in working condition.

[0032] On the one hand, predicting the required intelligent adjustment equipment can avoid the situation where the intelligent equipment required to execute the adjustment needs cannot work and adjust after the user falls asleep, which affects the user's sleep and makes the user's living experience poor; on the other hand, it can avoid the situation where the user is not accustomed to or forgets to wear the vital sign status monitoring equipment and cannot effectively perform intelligent monitoring and adjustment of the sleeping environment based on the user status data, so that it is possible to adjust the equipment to the greatest extent without status data to increase the possibility of optimizing the user's sleeping environment.

[0033] A sleep environment adjustment system, including a data acquisition module, a user classification module, an optimal sleep evaluation value analysis module, a correlation analysis module and a new user response module;

[0034] The data acquisition module is used to obtain check-in events and the user's operation behavior data after check-in;

[0035] The user classification module is used to classify users of each type of monitoring space based on check-in events and operation behavior data;

[0036] The optimal sleep evaluation value analysis module is used to analyze the optimal sleep evaluation value corresponding to each type of user;

[0037] The correlation analysis module is used to construct a correlation model between user operation behavior data and optimal sleep evaluation value, and output the correlation determination result;

[0038] The new user response module is used to predict the intelligent adjustment equipment required by new users and conduct monitoring responses.

[0039] A further user classification module includes an analysis set storage unit, an initial data group analysis unit, a sleep environment dynamic index analysis unit and a target data group analysis unit;

[0040] The analysis set storage unit is used to obtain the number of occupants corresponding to the occupancy event record of the same monitoring space, and store the occupancy events corresponding to the same number of occupants into an analysis set;

[0041] The initial data group analysis unit is used to mark the initial data group with the same record operation object corresponding to the check-in event in the analysis set;

[0042] The sleep environment dynamic index analysis unit is used to extract the adjustment data corresponding to each check-in event of the initial data group, the adjustment data including the number of adjustments, the adjustment deviation value and the adjustment time, and calculate the sleep environment dynamic index using the adjustment data;

[0043] The target data group analysis unit is used to classify the check-in events corresponding to any two sleep environment dynamic indexes contained in the same initial data group whose difference is less than the average deviation value into one category, and construct a target data group, each target data group representing a category of users.

[0044] Further, the optimal sleep evaluation value analysis module includes a sleep stage division unit, an effective adjustment data determination unit, an adjustment ratio calculation unit, a target adjustment device determination unit and an optimal sleep evaluation value calculation unit;

[0045] The sleep stage division unit is used to divide the user's sleep stage into four stages;

[0046] The effective adjustment data determination unit is used to take the sleep adjustment data that reaches the standard physical sign sleep state after amplitude adjustment as the effective adjustment data;

[0047] The adjustment ratio calculation unit is used to extract the maximum value of the change value of the physical sign state data corresponding to the same amplitude in the effective adjustment data in each sleep stage, and calculate the adjustment ratio corresponding to each type of amplitude;

[0048] The target regulating device determining unit is used to output the intelligent regulating device corresponding to the maximum regulating ratio as the target regulating device;

[0049] The optimal sleep evaluation value calculation unit is used to obtain the target change value of each sleep stage and calculate the optimal sleep evaluation value corresponding to each type of user.

[0050] Furthermore, the newly added user response module includes a result analysis unit, an intelligent adjustment device matching unit and a monitoring response unit;

[0051] The result analysis unit is used to analyze whether the association determination result is an association;

[0052] The intelligent adjustment device matching unit is used to, when the association determination result is that there is no association, match the intelligent adjustment device of the corresponding user with the greatest similarity based on the vital sign status data of the newly added user as the intelligent adjustment device required by the newly added user; when the association determination result is that there is an association, obtain the user operation behavior data recorded by the newly added user before entering the sleep state, and calculate the user's real-time sleep environment dynamic index, and classify the real-time user as a user of the corresponding type based on the real-time sleep environment dynamic index matching and the target data group with the smallest difference in the mean of the sleep environment dynamic index; extract the target adjustment device recorded by the user type after matching as the intelligent adjustment device required by the newly added user;

[0053] The monitoring and response unit is used to transmit the remaining power information and device status of the intelligent adjustment device to the management end, and monitor whether the remaining power information is available for amplitude adjustment after the newly added user enters sleep and whether the device status is in a working state.

[0054] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention analyzes the operation data of the occupants before falling asleep, classifies user groups with different attention to the intelligent adjustment device, analyzes the vital sign status data and sleep adjustment data after falling asleep based on each classified user group, thereby obtaining the most effective sleep evaluation value with data characteristics as the representative of a type of user, and performs quantitative relationship analysis on the degree of user attention to the sleep adjustment device and the sleep evaluation value to determine the degree of correlation, thereby realizing the determination of the judgment basis for the adjustment of the sleep environment of the newly added occupants, realizing the prediction of the adjustment device required for the user's sleep based on the user's operation and operation data, avoiding the situation that the intelligent device required to execute the adjustment demand cannot work and adjust after the user falls asleep, causing an impact on the user's sleep and making the user's living experience poor; on the other hand, it avoids the situation that the user is not accustomed to or forgets to wear the vital sign status monitoring device and cannot effectively perform intelligent monitoring and adjustment of the sleep environment based on the user's status data, so that the device can be adjusted to the greatest extent without status data to increase the possibility of optimizing the user's sleep environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0056] Figure 1 It is a structural schematic diagram of a sleep environment adjustment system based on personalized data analysis of the present invention. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] See also Figure 1 The present invention provides a technical solution: a method for adjusting a sleeping environment based on personalized data analysis, comprising the following analysis steps:

[0059] Step S100: Marking monitoring spaces containing the same intelligent adjustment device as the same type of monitoring space, obtaining check-in events recorded in each type of monitoring space and operation behavior data of users after check-in; and classifying users of each type of monitoring space based on check-in events and operation behavior data;

[0060] Step S200: Based on the classified users, the vital sign status data and sleep adjustment data of each type of user are obtained; the sleep adjustment data is acquired and the device performs operations through the Internet of Things system and sensors built in the monitoring space; such as temperature and humidity sensors; the vital sign status data can be collected by the user wearing a smart device integrated with the Internet of Things architecture, such as a smart bracelet; the optimal sleep assessment value corresponding to each type of user is analyzed;

[0061] Step S300: constructing a correlation relationship model between the user operation behavior data and the optimal sleep evaluation value based on the optimal sleep evaluation value, and outputting a correlation determination result;

[0062] Step S400: Based on the association determination result, the intelligent adjustment equipment required by the newly added user is predicted and a monitoring response is performed.

[0063] Classify users of each type of monitored space based on check-in events and operation behavior data, including the following analysis steps:

[0064] Step S110: obtaining the number of occupants corresponding to the occupancy event record of the same monitoring space, and storing the occupancy events corresponding to the same number of occupants into an analysis set; the operation behavior data refers to the data recorded by the user manually adjusting the intelligent adjustment device, and the operation behavior data includes the operation object and the adjustment data;

[0065] Step S120: Mark the initial data group A1 with the same record operation object corresponding to the check-in event in the i-th analysis set, Among them U i represents the i-th analysis set, represents the jth group of operation objects in the i-th analysis set; the data with the same operation objects in the check-in events are counted as one group; the adjustment data corresponding to each check-in event of the initial data group A1 is extracted, and the adjustment data includes the number of adjustments, the adjustment deviation value and the adjustment time; using the formula:

[0066]

[0067] Calculate the same set of operands The dynamic index of the user's sleeping environment corresponding to the next k-th check-in event where d k represents the total number of times the user operates the intelligent adjustment device corresponding to the k-th check-in event, D ij Indicates that the object is being operated on Record the average number of times each user operates the smart adjustment device in all check-in events; k represents the average adjustment deviation value of the user-operated intelligent adjustment device corresponding to the k-th check-in event. The adjustment deviation value refers to the absolute value of the difference between the state value recorded by the device before adjustment and the state value recorded by the device after adjustment; Fij Indicates that the object is being operated on The average adjustment deviation value of each user operating the intelligent adjustment device in all check-in events is recorded below; t k T represents the time interval between the last manual adjustment of the device by the user corresponding to the kth check-in event and the first adjustment by the intelligent adjustment device starting the autonomous adjustment function; the autonomous adjustment function is based on the system monitoring the user's sleep state to obtain the vital sign state data to adjust the sleep environment; ijmax Indicates that the object is being operated on The maximum time interval between the last manual adjustment of the device by the user and the first adjustment of the self-regulation function of the intelligent adjustment device in all check-in events is recorded below; the larger the ratio, the higher the demand for the intelligent adjustment device, the higher the attention paid by the user in the check-in event, the more obvious the adjustment purpose, and the certain requirements for the sleeping environment;

[0068] Step S130: Calculate the average deviation value R of all sleep environment dynamic indexes recorded in the i-th analysis set i ,

[0069]

[0070] in represents the number of combinations consisting of 2 selected from n sleep environment dynamic indexes, and n represents the total number of check-in events included in the i-th analysis set; represents the sleep environment dynamic index of the k-th check-in event corresponding to the i-th analysis set, represents the sleep environment dynamic index of the i-th analysis set corresponding to the k+r-th check-in event, It means to sum the difference between any two sleep environment dynamic indexes in the traversal analysis set, where r is any non-zero natural number less than or equal to n-1;

[0071] Step S140: Classify the check-in events corresponding to any two sleep environment dynamic indexes included in the same initial data set A1 whose difference is less than the average deviation value into one category to construct a target data set A2. It represents the mean value of a corresponding sleep environment dynamic index; each target data group represents a type of user.

[0072] As shown in the examples:

[0073] The existence monitoring space is a standard room, in which intelligent lighting, intelligent temperature and humidity control equipment are installed;

[0074] Based on the check-in events recorded in standard rooms, they are divided into single occupancy and double occupancy;

[0075] When analyzing a single user, an initial data set can be obtained based on the operational behavior data recorded in the check-in event; and

[0076] If we calculate R i =0.45;

[0077] like Record three groups of user data; and based on the calculation of the sleep environment dynamic index and deviation value, the users can be divided into two categories, forming the target data group

[0078] like Record two sets of user data; and based on the calculation of the sleep environment dynamic index and deviation value, the two sets of user data are classified into one category, forming a target data group

[0079] In summary, by analyzing the check-in events based on standard rooms, three target data groups are constructed, so the user data can be divided into three categories.

[0080] Analyzing the optimal sleep evaluation value for each type of user includes the following analysis steps:

[0081] Step S210: Divide the user's sleep stage into four stages, namely, falling asleep stage, light sleep stage, deep sleep stage and deep sleep stage; extract sleep adjustment data recorded for different users in each sleep stage, where the sleep adjustment data refers to the amplitude adjusted by the intelligent adjustment device based on the physical sign state data; and use the sleep adjustment data that reaches the standard physical sign sleep state after amplitude adjustment as the effective adjustment data;

[0082] The public sleep data model is trained with artificial intelligence using physical sign status data and sleep environment data to obtain the user sleep model; after obtaining the user sleep model, the user's sleep data (such as breathing rate, heart rate, turning over frequency, eye movement frequency, electroencephalogram curve, etc.) is collected, that is, the physical sign status data during sleep, and the user's sleep stage is judged according to the user sleep model. When the user shows non-standard physical sign status data in a certain sleep stage, the artificial intelligence quickly analyzes the cause, judges the degree of influence of environmental factors on this situation, and adjusts the corresponding environment in time according to the user's sleep model, so that the user enters the corresponding sleep stage again. The decision factors for adjustment are made with reference to the public's sleep environment needs and the user's own characteristics. The adjustment method adopts a gradual and tentative adjustment strategy. During the adjustment process, the user's sleep feedback is judged in real time, and the adjustment strategy is fine-tuned in time according to the feedback, and finally a sleep model suitable for the user is formed;

[0083] The standard physical sign sleep state indicates the judgment standard corresponding to each sleep stage. For example, if the user's brain wave frequency slows down and the amplitude decreases during the falling asleep stage, this is regarded as the standard physical sign sleep state of the falling asleep stage.

[0084] Step S220: extracting the maximum value L of the change value of the physical sign state data corresponding to the same amplitude in the effective adjustment data in each sleep stage max , calculate the adjustment ratio G corresponding to each type of amplitude, G = L max / B, B represents the adjustment amplitude; when the output adjustment ratio G is the largest, the corresponding intelligent adjustment device is the target adjustment device, and the maximum value L of the change value of the corresponding vital sign state data of the target adjustment device is obtained max As the target change value; when there are two people, take the maximum value of the average value when analyzing the change value of the vital sign status data;

[0085] Step S230: Obtain the target change value for each sleep stage and calculate the optimal sleep evaluation value Q corresponding to each type of user, Q = ∑L max ;∑L max It means summing up the target change values ​​corresponding to each of the four stages.

[0086] For example, when the vital sign status data is respiratory rate or heart rate, the same vital sign status data will be different in each stage, and different users will also have differences in the same stage. When the temperature adjustment amplitude is 3 degrees, the calculated adjustment ratio reflects the change value of respiratory rate or heart rate corresponding to each degree of adjustment under the unit adjustment data.

[0087] Calculating the adjustment ratio can quickly analyze the users of the same type who are most affected by the adjustment amplitude. Taking the target change value as the conditional parameter of the optimal sleep evaluation value can reflect the maximum impact level of a type of users under the adjustment of the smart adjustment device.

[0088] Step S300 includes the following analysis process:

[0089] The average value of the sleep environment dynamic index and the optimal sleep evaluation value of each type of user constitute the analysis pair E. Obtain analysis pairs corresponding to all types of users; use the correlation analysis model to analyze the correlation between the sleep environment dynamic index and the optimal sleep evaluation value, and use the correlation analysis model as an association relationship model;

[0090] The correlation analysis model outputs the association determination result, which includes the existence of association and the non-existence of association.

[0091] The correlation analysis model can be to use Matlab to draw a curve to analyze the correlation or to verify the correlation through chi-square analysis; if chi-square analysis is used, the sleep environment dynamic index is divided into a sleep environment dynamic index greater than or equal to the mean and a sleep environment dynamic index less than the mean based on all user data, and the optimal sleep assessment value is divided into an optimal sleep assessment value greater than or equal to the mean and less than the mean; find the number of users who meet the requirements.

[0092] Step S400 includes the following analysis process:

[0093] When the association determination result is that there is no association, the smart adjustment device of the corresponding user with the greatest similarity is matched based on the vital sign status data of the newly added user as the smart adjustment device required by the newly added user;

[0094] When the association determination result is that there is an association, the user operation behavior data recorded before the newly added user enters the room before entering the sleep state is obtained, and the user's real-time sleep environment dynamic index is calculated;

[0095] Based on the real-time sleep environment dynamic index matching and the target data group A2 with the smallest difference in the mean of the sleep environment dynamic index, the real-time user is classified into the corresponding type of user;

[0096] Extract the target adjustment device recorded by the matched user type as the smart adjustment device required by the newly added user;

[0097] And transmit the remaining power information and device status of the intelligent adjustment device to the management end, monitor and respond to whether the remaining power information is available for amplitude adjustment after the new user enters sleep and whether the device status is in working condition.

[0098] On the one hand, predicting the required intelligent adjustment equipment can avoid the situation where the intelligent equipment required to execute the adjustment needs cannot work and adjust after the user falls asleep, which affects the user's sleep and makes the user's living experience poor; on the other hand, it can avoid the situation where the user is not accustomed to or forgets to wear the vital sign status monitoring equipment and cannot effectively perform intelligent monitoring and adjustment of the sleeping environment based on the user status data, so that it is possible to adjust the equipment to the greatest extent without status data to increase the possibility of optimizing the user's sleeping environment.

[0099] A sleep environment adjustment system, including a data acquisition module, a user classification module, an optimal sleep evaluation value analysis module, a correlation analysis module and a new user response module;

[0100] The data acquisition module is used to obtain check-in events and the user's operation behavior data after check-in;

[0101] The user classification module is used to classify users of each type of monitoring space based on check-in events and operation behavior data;

[0102] The optimal sleep evaluation value analysis module is used to analyze the optimal sleep evaluation value corresponding to each type of user;

[0103] The correlation analysis module is used to construct a correlation model between user operation behavior data and optimal sleep evaluation value, and output the correlation determination result;

[0104] The new user response module is used to predict the intelligent adjustment equipment required by new users and conduct monitoring responses.

[0105] A further user classification module includes an analysis set storage unit, an initial data group analysis unit, a sleep environment dynamic index analysis unit and a target data group analysis unit;

[0106] The analysis set storage unit is used to obtain the number of occupants corresponding to the occupancy event record of the same monitoring space, and store the occupancy events corresponding to the same number of occupants into an analysis set;

[0107] The initial data group analysis unit is used to mark the initial data group with the same record operation object corresponding to the check-in event in the analysis set;

[0108] The sleep environment dynamic index analysis unit is used to extract the adjustment data corresponding to each check-in event of the initial data group, the adjustment data including the number of adjustments, the adjustment deviation value and the adjustment time, and calculate the sleep environment dynamic index using the adjustment data;

[0109] The target data group analysis unit is used to classify the check-in events corresponding to any two sleep environment dynamic indexes contained in the same initial data group whose difference is less than the average deviation value into one category, and construct a target data group, each target data group representing a category of users.

[0110] The optimal sleep evaluation value analysis module includes a sleep stage division unit, an effective adjustment data determination unit, an adjustment ratio calculation unit, a target adjustment device determination unit and an optimal sleep evaluation value calculation unit;

[0111] The sleep stage division unit is used to divide the user's sleep stage into four stages;

[0112] The effective adjustment data determination unit is used to take the sleep adjustment data that reaches the standard physical sign sleep state after amplitude adjustment as the effective adjustment data;

[0113] The adjustment ratio calculation unit is used to extract the maximum value of the change value of the physical sign state data corresponding to the same amplitude in the effective adjustment data in each sleep stage, and calculate the adjustment ratio corresponding to each type of amplitude;

[0114] The target regulating device determining unit is used to output the intelligent regulating device corresponding to the maximum regulating ratio as the target regulating device;

[0115] The optimal sleep evaluation value calculation unit is used to obtain the target change value of each sleep stage and calculate the optimal sleep evaluation value corresponding to each type of user.

[0116] The newly added user response module includes a result analysis unit, an intelligent adjustment device matching unit, and a monitoring response unit;

[0117] The result analysis unit is used to analyze whether the association determination result is an association;

[0118] The intelligent adjustment device matching unit is used to, when the association determination result is that there is no association, match the intelligent adjustment device of the corresponding user with the greatest similarity based on the vital sign status data of the newly added user as the intelligent adjustment device required by the newly added user; when the association determination result is that there is an association, obtain the user operation behavior data recorded by the newly added user before entering the sleep state, and calculate the user's real-time sleep environment dynamic index, and classify the real-time user as a user of the corresponding type based on the real-time sleep environment dynamic index matching and the target data group with the smallest difference in the mean of the sleep environment dynamic index; extract the target adjustment device recorded by the user type after matching as the intelligent adjustment device required by the newly added user;

[0119] The monitoring and response unit is used to transmit the remaining power information and device status of the intelligent adjustment device to the management end, and monitor whether the remaining power information is available for amplitude adjustment after the newly added user enters sleep and whether the device status is in a working state.

[0120] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0121] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for adjusting a sleeping environment based on personalized data analysis, characterized in that: The analysis steps include: Step S100: Marking monitoring spaces containing the same intelligent adjustment device as the same type of monitoring space, obtaining check-in events recorded in each type of monitoring space and operation behavior data of users after check-in; and classifying users of each type of monitoring space based on check-in events and operation behavior data; The method of classifying users of each type of monitoring space based on check-in events and operation behavior data includes the following analysis steps: Step S110: obtaining the number of occupants corresponding to the occupancy event record of the same monitoring space, and storing the occupancy events corresponding to the same number of occupants into an analysis set; the operation behavior data refers to the data recorded by the user manually adjusting the intelligent adjustment device, and the operation behavior data includes the operation object and the adjustment data; Step S120: Mark the initial data group A1 with the same record operation object corresponding to the check-in event in the i-th analysis set, Among them U i represents the i-th analysis set, represents the jth group of operation objects in the i-th analysis set; extracts the adjustment data corresponding to each check-in event of the initial data group A1, wherein the adjustment data includes the number of adjustments, the adjustment deviation value and the adjustment time; uses the formula: Calculate the same set of operands The dynamic index of the user's sleeping environment corresponding to the next k-th check-in event where d k represents the total number of times the user operates the intelligent adjustment device corresponding to the k-th check-in event, D ij Indicates that the object is being operated on Record the average number of times each user operates the smart adjustment device in all check-in events; k represents the average adjustment deviation value of the user-operated intelligent adjustment device corresponding to the k-th check-in event, where the adjustment deviation value refers to the absolute value of the difference between the state value recorded by the device before adjustment and the state value recorded by the device after adjustment; F ij Indicates that the object is being operated on The following records the average adjustment deviation value of the intelligent adjustment device operated by each user in all check-in events; t k T represents the time interval between the last manual adjustment of the device by the user corresponding to the k-th check-in event and the first adjustment of the intelligent adjustment device starting the autonomous adjustment function; ijmax Indicates that the object is being operated on The maximum time interval between the last manual adjustment of the device by the user and the first adjustment of the self-regulation function of the intelligent adjustment device in all check-in events is recorded below; Step S130: Calculate the average deviation value R of all sleep environment dynamic indexes recorded in the i-th analysis set i , in represents the number of combinations consisting of 2 selected from n sleep environment dynamic indexes, and n represents the total number of check-in events included in the i-th analysis set; represents the sleep environment dynamic index of the i-th analysis set corresponding to the k-th check-in event, represents the sleep environment dynamic index of the i-th analysis set corresponding to the k+r-th check-in event, It means to sum the difference between any two sleep environment dynamic indexes in the traversal analysis set, where r is any non-zero natural number less than or equal to n-1; Step S140: Classify the check-in events corresponding to any two sleep environment dynamic indexes included in the same initial data set A1 whose difference is less than the average deviation value into one category to construct a target data set A2. represents the mean value of a corresponding sleep environment dynamic index; each target data group represents a type of user; Step S200: Based on the classified users, obtain the physical sign status data and sleep adjustment data of each type of user; and analyze the optimal sleep evaluation value corresponding to each type of user; Step S300: constructing a correlation relationship model between the user operation behavior data and the optimal sleep evaluation value based on the optimal sleep evaluation value, and outputting a correlation determination result; Step S400: Based on the association determination result, the intelligent adjustment equipment required by the newly added user is predicted and a monitoring response is performed.

2. The method for adjusting a sleeping environment based on personalized data analysis according to claim 1, characterized in that: The analysis of the optimal sleep evaluation value corresponding to each type of user includes the following analysis steps: Step S210: Divide the user's sleep stage into four stages, namely, falling asleep stage, light sleep stage, deep sleep stage and deep sleep stage; extract sleep adjustment data recorded for different users in each sleep stage, wherein the sleep adjustment data refers to the amplitude adjusted by the intelligent adjustment device based on the physical sign state data; and use the sleep adjustment data that reaches the standard physical sign sleep state after amplitude adjustment as the effective adjustment data; Step S220: extracting the maximum value L of the change value of the physical sign state data corresponding to the same amplitude in the effective adjustment data in each sleep stage max , calculate the adjustment ratio G corresponding to each type of amplitude, G = L max / B, B represents the adjustment amplitude; When the output adjustment ratio G is the largest, the corresponding intelligent adjustment device is the target adjustment device, and the maximum value L of the change value of the vital sign state data corresponding to the target adjustment device is obtained. max As the target change value; Step S230: Obtain the target change value for each sleep stage and calculate the optimal sleep evaluation value Q corresponding to each type of user, Q = ∑L max ;∑L max It means summing up the target change values ​​corresponding to each of the four stages.

3. The method for adjusting a sleeping environment based on personalized data analysis according to claim 2, characterized in that: The step S300 includes the following analysis process: The average value of the sleep environment dynamic index and the optimal sleep evaluation value of each type of user constitute the analysis pair E. Obtain analysis pairs corresponding to all types of users; use the correlation analysis model to analyze the correlation between the sleep environment dynamic index and the optimal sleep evaluation value, and use the correlation analysis model as an association relationship model; The association determination result is output based on the correlation analysis model, and the association determination result includes whether there is an association or not.

4. The method for adjusting a sleeping environment based on personalized data analysis according to claim 3, characterized in that: The step S400 includes the following analysis process: When the association determination result is that there is no association, the smart adjustment device of the corresponding user with the greatest similarity is matched based on the vital sign status data of the newly added user as the smart adjustment device required by the newly added user; When the association determination result is that there is an association, the user operation behavior data recorded before the newly added user enters the room before entering the sleep state is obtained, and the user's real-time sleep environment dynamic index is calculated; Based on the real-time sleep environment dynamic index matching and the target data group A2 with the smallest difference in the mean of the sleep environment dynamic index, the real-time user is classified into the corresponding type of user; Extract the target adjustment device recorded by the matched user type as the smart adjustment device required by the newly added user; The remaining power information and device status of the intelligent adjustment device are transmitted to the management end, and the remaining power information is monitored to determine whether it is available for amplitude adjustment after the newly added user enters sleep and whether the device status is in working condition.

5. A sleeping environment adjustment system using a sleeping environment adjustment method based on personalized data analysis as claimed in any one of claims 1 to 4, characterized in that: It includes data acquisition module, user classification module, optimal sleep assessment value analysis module, correlation relationship analysis module and new user response module; The data acquisition module is used to acquire check-in events and user operation behavior data after check-in; The user classification module is used to classify users of each type of monitoring space based on check-in events and operation behavior data; The optimal sleep evaluation value analysis module is used to analyze the optimal sleep evaluation value corresponding to each type of user; The association relationship analysis module is used to construct an association relationship model between the user operation behavior data and the optimal sleep evaluation value, and output an association determination result; The new user response module is used to predict the intelligent adjustment equipment required by the new occupants and perform monitoring response.

6. The sleeping environment adjustment system according to claim 5, characterized in that: The user classification module includes an analysis set storage unit, an initial data group analysis unit, a sleep environment dynamic index analysis unit and a target data group analysis unit; The analysis set storage unit is used to obtain the number of occupants corresponding to the occupancy event records of the same monitoring space, and store the occupancy events corresponding to the same number of occupants into an analysis set; The initial data group analysis unit is used to mark the initial data group with the same record operation object corresponding to the check-in event in the analysis set; The sleep environment dynamic index analysis unit is used to extract the adjustment data corresponding to each check-in event of the initial data group, wherein the adjustment data includes the number of adjustments, the adjustment deviation value and the adjustment time, and calculate the sleep environment dynamic index using the adjustment data; The target data group analysis unit is used to classify check-in events corresponding to any two sleep environment dynamic indexes included in the same initial data group whose difference is less than the average deviation value into one category, and construct target data groups, each of which represents a category of users.

7. The sleeping environment adjustment system according to claim 6, characterized in that: The optimal sleep evaluation value analysis module includes a sleep stage division unit, an effective adjustment data determination unit, an adjustment ratio calculation unit, a target adjustment device determination unit and an optimal sleep evaluation value calculation unit; The sleep stage division unit is used to divide the user's sleep stage into four stages; The effective adjustment data determination unit is used to take the sleep adjustment data that reaches the standard physical sign sleep state after amplitude adjustment as the effective adjustment data; The adjustment ratio calculation unit is used to extract the maximum value of the change value of the physical sign state data corresponding to the same amplitude in the effective adjustment data in each sleep stage, and calculate the adjustment ratio corresponding to each type of amplitude; The target regulating device determining unit is used to output the intelligent regulating device corresponding to the maximum regulating ratio as the target regulating device; The optimal sleep evaluation value calculation unit is used to obtain the target change value of each sleep stage and calculate the optimal sleep evaluation value corresponding to each type of user.

8. The sleeping environment adjustment system according to claim 7, characterized in that: The newly added user response module includes a result analysis unit, an intelligent adjustment device matching unit and a monitoring response unit; The result analysis unit is used to analyze whether the association determination result indicates that there is an association; The intelligent adjustment device matching unit is used to, when the association determination result is that there is no association, match the intelligent adjustment device of the corresponding user with the greatest similarity based on the vital sign state data of the newly added user as the intelligent adjustment device required by the newly added user; when the association determination result is that there is an association, obtain the user operation behavior data recorded by the newly added user before entering the sleep state, and calculate the user's real-time sleep environment dynamic index, and classify the real-time user into a corresponding type of user based on the real-time sleep environment dynamic index matching and the target data group with the smallest difference in the mean of the sleep environment dynamic index; Extract the target adjustment device recorded by the matched user type as the smart adjustment device required by the newly added user; The monitoring and response unit is used to transmit the remaining power information and device status of the intelligent adjustment device to the management end, and monitor and respond to whether the remaining power information is available for amplitude adjustment after the newly added user enters sleep and whether the device status is in a working state.