Data processing method and device for monitoring activity time of ankylosing spondylitis patient by using wearable equipment

Abstract

The invention discloses a data processing method and device for monitoring activity time of an ankylosing spondylitis patient by using a wearable device, and the method comprises the steps: obtaining initial time data corresponding to each activity behavior of the ankylosing spondylitis patient by using the wearable device, the activity behaviors comprise a sedentariness behavior, a sleep behavior, a low-intensity physical activity behavior and a medium-high-intensity physical activity behavior; based on the initial time data, determining comparison characteristics among the activity behaviors; constructing a sleep quality regression classification model based on the comparison features; based on the sleep quality regression classification model, determining a target time allocation scheme corresponding to each activity behavior when the probability that the sleep quality of the ankylosing spondylitis user is good is maximum, the personalized target time data capable of improving the sleep quality can be allocated to the ankylosing spondylitis user based on the initial time data of various types of activity behaviors of the ankylosing spondylitis user.

Description

Technical Field

[0001] The present disclosure generally relates to the field of time allocation decision-making, and particularly relates to a processing method and device for monitoring activity time data of ankylosing spondylitis patients using a wearable device. Background Art

[0002] Ankylosing Spondylitis (AS) is a highly disabling disease that can cause disability due to the formation of spinal osteophytes and hip joint destruction. Its clinical manifestations include chronic back pain, fatigue, and functional limitations, which seriously affect the quality of life and daily activity ability of patients. In recent years, with the increasing incidence of ankylosing spondylitis, it has brought many challenges to the lives of patients. Although current treatment methods have made some progress in alleviating symptoms and delaying disease progression, there are still many problems with quality-of-life-related indicators such as the sleep quality of patients.

[0003] Sleep quality is one of the important indicators for measuring the quality of life of ankylosing spondylitis patients. Related research shows that physical activity has a positive effect on improving overall health and reducing inflammatory responses. Based on this, how to provide personalized activity behavior time allocation for ankylosing spondylitis patients to improve their sleep quality has become an urgent problem to be solved. Summary of the Invention

[0004] In view of the above-mentioned defects or deficiencies in the prior art, it is desirable to provide a processing method and device for monitoring activity time data of ankylosing spondylitis patients using a wearable device, which can allocate personalized target time data that can improve sleep quality for ankylosing spondylitis users based on the initial time data of various types of activity behaviors of ankylosing spondylitis users.

[0005] In a first aspect, an embodiment of the present application provides a processing method for monitoring activity time data of ankylosing spondylitis patients using a wearable device, including: Using the wearable device to obtain the initial time data corresponding to each activity behavior of an ankylosing spondylitis user, where the activity behaviors include sedentary behavior, sleep behavior, low-intensity physical activity behavior, and medium-to-high-intensity physical activity behavior; Based on the initial time data, determining the comparison features between each of the activity behaviors; Constructing a sleep quality regression classification model based on the comparison features; Based on the sleep quality regression classification model, determining the target time allocation plan corresponding to each of the activity behaviors when the probability of good sleep quality of the ankylosing spondylitis user is the highest.

[0006] In some embodiments, the determining the comparison features between each of the activity behaviors based on the initial time data includes: The contrast features between each activity behavior and other activity behaviors are obtained by using equidistant logarithmic ratio transformation.

[0007] In some embodiments, before determining the contrast features between each of the activity behaviors based on the initial time data, the method further includes: respectively performing standardization processing on the initial time data corresponding to the low-intensity physical activity behavior and the medium-high-intensity physical activity behavior obtained by the wearable device; and correcting the initial time data corresponding to the sedentary behavior obtained by the wearable device based on the sedentary correction data input by the ankylosing spondylitis user.

[0008] In some embodiments, the determining, based on the sleep quality regression classification model, the target time allocation scheme corresponding to each of the activity behaviors when the probability that the ankylosing spondylitis user has good sleep quality is the greatest includes: obtaining at least one time constraint added by the ankylosing spondylitis user to at least one of the activity behaviors; based on the at least one time constraint, determining the target time allocation scheme corresponding to each of the activity behaviors when the probability that the ankylosing spondylitis user has good sleep quality is the greatest, wherein the target time data of each activity behavior satisfies the corresponding time constraint.

[0009] In some embodiments, the time constraint includes at least one of a minimum time length and a maximum time length; or, the time constraint includes the association relationship between two types of activity behaviors.

[0010] In some embodiments, the method further includes: using the wearable device to collect in real time the duration data of the sedentary behavior of the ankylosing spondylitis user; when the duration data exceeds the target time data corresponding to the sedentary behavior, using the wearable device to send a timeout reminder to the ankylosing spondylitis user.

[0011] In a second aspect, an embodiment of the present application provides a processing device for monitoring the activity time data of an ankylosing spondylitis patient by using a wearable device, including: an acquisition module, configured to use a wearable device to acquire initial time data corresponding to each activity behavior of an ankylosing spondylitis user, where the activity behaviors include a sedentary behavior, a sleep behavior, a low-intensity physical activity behavior, and a high-intensity physical activity behavior; a determination module, configured to determine contrast features between each of the activity behaviors based on the initial time data; a construction module, configured to construct a sleep quality regression classification model based on the contrast features; A decision-making module, configured to determine, based on the sleep quality regression classification model, a target time allocation scheme corresponding to each of the activity behaviors when the probability that the sleep quality of the ankylosing spondylitis user is good is the highest.

[0012] In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the method described in the embodiment of the present application is implemented.

[0013] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the method described in the embodiment of the present application is implemented.

[0014] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, characterized in that when the computer program is executed by a processor, the method described in the embodiment of the present application is implemented.

[0015] The processing method and device for monitoring the activity time data of ankylosing spondylitis patients using a wearable device proposed in the embodiment of the application obtain the initial time data of different activity behavior types of ankylosing spondylitis users through the wearable device, construct a sleep quality regression model based on the initial time data, and use the regression classification model to determine the target time allocation scheme corresponding to each activity behavior when the probability that the sleep quality of the ankylosing spondylitis user is good is the highest, so as to provide a personalized target time allocation scheme for improving sleep quality for the ankylosing spondylitis user based on the actual initial time data of different activity behavior types of the ankylosing spondylitis user, so that the ankylosing spondylitis user can effectively improve sleep quality after implementing various activity behaviors according to the target time allocation scheme, thereby achieving the purpose of improving the quality of life of the ankylosing spondylitis user by using the activity behavior time allocation scheme.

[0016] Additional aspects and advantages of the present invention will be given in part in the following description, become apparent in part from the following description, or be understood through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] By reading the detailed description of the non-limiting embodiments with reference to the following drawings, other features, objects, and advantages of the present application will become more apparent: Figure 1 Shows the implementation environment architecture diagram of the processing method for monitoring the activity time data of ankylosing spondylitis patients provided by the embodiment of the present application; Figure 2 Shows the flowchart of the processing method for monitoring the activity time data of ankylosing spondylitis patients provided by an embodiment of the present application; Figure 3 The figure shows a schematic structural diagram of a processing device for monitoring the activity time data of ankylosing spondylitis patients by using a wearable device according to an embodiment of the present application; Figure 4 The figure shows a schematic structural diagram of a computer system of an electronic device or a server suitable for implementing the embodiments of the present application. Detailed implementation manners

[0018] The present application will be further described in detail below with reference to the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the related invention, rather than limiting the invention. In addition, it should be noted that, for the sake of convenience of description, only the parts related to the invention are shown in the drawings.

[0019] It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and embodiments.

[0020] In recent years, with the increasing incidence of ankylosing spondylitis, it has brought many challenges to the lives of patients. Physical activity (PA) is the physical activity generated by the contraction of skeletal muscles, as well as various occupational, leisure and other daily activities that cause an increase in energy consumption at the level of basal metabolism. As a disease characterized by inflammatory pain, PA can relieve the condition to a certain extent and be used as one of the treatment means to intervene in ankylosing spondylitis patients. Therefore, it has strong practical significance to study the correlation between PA and quality of life of ankylosing spondylitis patients.

[0021] Physical activity is one of the important factors affecting the disease progression and quality of life of ankylosing spondylitis patients. Physical activity patterns include sleep, sedentary, low-intensity physical activity, moderate-intensity physical activity and high-intensity physical activity. These activity patterns are closely related to the pain level, fatigue and functional status of patients. However, in the related technologies, usually more attention is paid to the relationship between disease activity and physical activity, and less attention is paid to the relationship between physical activity and the quality of life of ankylosing spondylitis patients, especially the sleep quality of ankylosing spondylitis patients.

[0022] Based on this, the present application proposes a processing method and device for monitoring the activity time data of ankylosing spondylitis patients by using a wearable device.

[0023] For the specific implementation environment of the processing method for monitoring the activity time data of ankylosing spondylitis patients by using a wearable device proposed in the present application, see Figure 1 . Figure 1The figure shows the implementation environment architecture diagram of the processing method for monitoring the activity time data of ankylosing spondylitis patients using a wearable device provided by an embodiment of the present application.

[0024] As Figure 1 shown, the implementation environment architecture includes: a wearable device 101 and a server 102.

[0025] The wearable device 101 is used to accurately collect various types of activity behavior parameters and activity time of ankylosing spondylitis users. Among them, the wearable device 101 at least includes a triaxial accelerometer. For example, a sports bracelet with a triaxial wrist accelerometer is a product that combines motion sensor technology with intelligent wearable devices. It can real-time monitor and record the user's motion data through the built-in triaxial accelerometer, providing support for health management, motion tracking, and daily activity analysis. A triaxial accelerometer is a sensor that can measure the acceleration changes of an object in three orthogonal directions (X, Y, and Z axes). Its core principle is based on microelectromechanical system (MEMS) technology. Through tiny mechanical structures (such as cantilever beams and mass blocks) and capacitive, piezoresistive, or piezoelectric detection methods, the acceleration signal is converted into an electrical signal. This is prior art and will not be elaborated further. The wearable device 101 can be a smart phone, a smart watch, smart glasses, and other devices that cooperate with the user's clothing, shoes, etc. for collecting the activity behavior of ankylosing spondylitis users, but is not limited thereto.

[0026] The server 102 is connected to the wearable device 101 and is used to receive the activity data collected by the wearable device 101, including but not limited to activity behavior parameters, activity time, etc., and execute the processing method for monitoring the activity time data of ankylosing spondylitis patients proposed by the embodiment of the present application based on the received activity data.

[0027] The server 102 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, as well as big data and artificial intelligence platforms.

[0028] The wearable device 101 is directly or indirectly connected to the server 102 through a wired or wireless communication method. Optionally, the above-mentioned wireless network or wired network uses standard communication technologies and / or protocols. The network is usually the Internet, or can be any network, including but not limited to any combination of a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a private network, or a virtual private network.

[0029] The processing method for monitoring the activity time data of ankylosing spondylitis patients using a wearable device proposed in this application can be implemented by a processing device for monitoring the activity time data of ankylosing spondylitis patients using a wearable device. The processing device for monitoring the activity time data of ankylosing spondylitis patients using a wearable device can be installed on the wearable device or the server.

[0030] To further illustrate the technical solutions provided in the embodiments of the present application, the following will be described in detail in conjunction with the accompanying drawings and specific implementation manners. Although the embodiments of the present application provide the method operation instruction steps as shown in the following embodiments or drawings, based on routine or non-creative labor, more or fewer operation instruction steps may be included in the method. In steps where there is no necessary causal relationship logically, the execution order of these steps is not limited to the execution order provided in the embodiments of the present application. When the method is actually processed or executed by the device, it can be executed in the order shown in the embodiments or drawings or executed in parallel.

[0031] It should be noted that the acquisition or use of the data in the embodiments of the present application requires the consent of the user. Relevant data can only be obtained after the user authorizes and permits it, and the acquisition or use of the data complies with the provisions of relevant laws and regulations.

[0032] Please refer to Figure 2 , Figure 2 which shows a schematic flowchart of the processing method for monitoring the activity time data of ankylosing spondylitis patients provided in an embodiment of the present application. As Figure 2 shown, the method includes: Step 201, using the wearable device to obtain the initial time corresponding to each activity behavior of the ankylosing spondylitis user, and the activity behaviors include sedentary behavior, sleep behavior, low-intensity physical activity behavior, and moderate-to-high-intensity physical activity behavior.

[0033] It should be noted that real-time behavior data and physical state data of ankylosing spondylitis users are obtained by using wearable devices. Among them, the behavior data includes, but is not limited to, parameter data such as behavior amplitude, behavior frequency, behavior intensity, and behavior time that can be used to identify the activity behavior types of ankylosing spondylitis users. The physical state data includes, but is not limited to, parameter data such as heart rate, blood oxygen, and blood pressure that can be used to identify the sleep behavior types of ankylosing spondylitis users. This application does not make specific limitations. Then, by performing type analysis on the real-time behavior data and physical state data, the activity behavior types to which each behavior data belongs and the duration corresponding to each activity behavior are obtained, such as sedentary behavior, sleep behavior, light physical activity behavior, and vigorous physical activity behavior. Among them, this application does not make specific limitations on the method for identifying the activity behavior types of ankylosing spondylitis users based on the real-time behavior data and physical state data collected by wearable devices.

[0034] It should be understood that in the embodiments of this application, the wearable device can continuously collect the real-time behavior data and physical state data of ankylosing spondylitis users for a period of time, such as 7 days, 15 days, or one month, etc. These data can all be used as the initial time for personalized activity behavior time allocation. That is to say, the time data corresponding to the user's activity behavior before the personalized activity behavior time allocation decision can all be used as the initial time data corresponding to the user's activity behavior.

[0035] In a specific embodiment, the wearable device can be a sports bracelet containing a three-axis wrist accelerometer, which is used to monitor the activity behavior data and physical state data of ankylosing spondylitis users for 24 hours. The user wears the sports bracelet on the wrist of the dominant hand starting from the starting time of the test day (such as after getting up) and wears it continuously for at least 24 hours. Then, according to the characteristics of the user's activity behavior data, such as intensity, the activity behavior data is divided into sedentary behavior (SED), light physical activity (LPA), moderate physical activity (MPA), vigorous physical activity (VPA), and sleep behavior (SLP) from weak to strong in terms of activity intensity. Among them, the sleep behavior includes night sleep and nap, and the moderate physical activity MPA and vigorous physical activity VPA are combined into moderate-to-high-intensity physical activity MVPA.

[0036] In a feasible embodiment, in order to further improve the reliability of the data collected by the wearable device, this application further proposes to correct the time data collected by the wearable device.

[0037] Optionally, the time data of the low-intensity physical activity behavior LPA and the moderate-to-high-intensity physical activity behavior MVPA obtained by the wearable device are respectively standardized. Specifically, the time data collected by the wearable device is standardized to the 24-hour time range, for example, when the actual wearing duration of the user wearing the wearable device meets the effective wearing duration but is less than 24 hours. Exemplarily, the following formula is used to standardize the low-intensity physical activity behavior LPA and the moderate-to-high-intensity physical activity behavior MVPA:

[0038]

[0039] where MVPA is the initial time after standardization of the moderate-to-high-intensity physical activity behavior, serving as the initial time data corresponding to the moderate-to-high-intensity physical activity behavior, is the initial time before standardization of the moderate-to-high-intensity physical activity behavior, LPA is the initial time after standardization of the low-intensity physical activity behavior, serving as the initial time data corresponding to the low-intensity physical activity behavior, is the initial time before standardization of the low-intensity physical activity behavior, SLP is the initial time corresponding to the sleep behavior, is the actual wearing time of the wearable device.

[0040] It should also be noted that in the embodiments of the present application, before standardizing the time data, it is further determined whether the effective wearing time of the user within 24 hours is greater than or equal to a preset time length. If the effective wearing time is greater than or equal to the effective wearing time length, it is confirmed that the time data collected by the user's wearable device is valid and can be further processed for time data standardization. If the effective wearing time is less than the effective wearing time length, it is confirmed that the time data collected by the user's wearable device on that day is invalid and needs to be deleted and cannot be used for subsequent data analysis. Among them, the effective wearing time length can be determined according to the time data accuracy. In the embodiments of the present application, the effective wearing time length is preferably 1200 minutes (20 hours). It should be understood that the effective wearing time length can be continuous or discontinuous, and the present application does not make specific limitations. In a feasible embodiment, the time when the wearable device collects the user's body state data (such as heart rate, blood oxygen, blood pressure) is determined as the effective time of the user wearing the wearable device.

[0041] It can be seen that in the standardization process of the embodiments of the present application, the low-intensity physical activity behavior LPA and the moderate-to-high-intensity physical activity behavior MVPA are standardized by ignoring the sedentary behavior SED. Based on this, the present application also proposes a method for correcting the initial time data of the sedentary behavior SED.

[0042] Specifically, the initial time data corresponding to the sedentary behavior obtained by the wearable device is corrected based on the sedentary correction data input by the ankylosing spondylitis user.

[0043] That is to say, for the sedentary behavior SED, in order to avoid the wearable device being unable to effectively and reasonably identify it, data correction is performed by the way of the ankylosing spondylitis user inputting the sedentary correction data by himself. For example, the sedentary correction data input by the ankylosing spondylitis user is obtained by means of the ankylosing spondylitis user manually inputting or through a questionnaire survey, etc., and it is used as the initial time data corresponding to the sedentary behavior. Optionally, in the embodiment of the present application, the ankylosing spondylitis user can input the sedentary correction data through a remote dual-terminal ankylosing spondylitis follow-up system or other ankylosing spondylitis management systems, and the present application does not make specific limitations.

[0044] It should be understood that, in the embodiment of the present application, the initial time data of the sleep behavior collected by the wearable device is directly used as the initial time data corresponding to the sleep behavior.

[0045] Step 202: Determine the comparison features between various activity behaviors based on the initial time data.

[0046] It should be understood that the initial time data of each activity behavior concerned in the embodiment of the present application are all non-negative data. There is collinearity between the initial time data corresponding to different activity actions, and the initial time data corresponding to multiple activity behaviors also has a fixed-sum constraint (closed time constraint condition). Therefore, when making a personalized activity behavior time allocation decision, increasing the implementation time of one activity behavior will correspondingly reduce the implementation time of at least one activity behavior, that is, more attention is paid to the relative change relationship between the time data of different activity behaviors rather than the absolute time data of each activity behavior data. Based on this, the present application determines the comparison features between various activity behaviors based on the initial time data, so as to pay attention to the change relationship between different activity behaviors when making a time allocation decision later.

[0047] In a feasible embodiment, the isometric log-ratio transformation is used to obtain the comparison features between each activity behavior and other activity behaviors.

[0048] It should be noted that the proportional values among the initial time data of each activity behavior exist in a proportional space (also known as a simplex space). Therefore, it is necessary to convert the proportional relationship among the initial time data of each activity behavior into a Euclidean space. Usually, isometric log-ratio (ILR), centred log-ratio (CLR), additive log-ratio (ALR), etc. can be used. In the embodiments of the present application, it is preferably to use the isometric log-ratio transformation ILR to obtain the comparison features among the initial time data of the activity behaviors that can be used for subsequent calculations.

[0049] Exemplarily, the comparison features obtained from the initial time data of sedentary behavior SED, sleep behavior SLP, low-intensity physical activity behavior LPA, and moderate-to-high-intensity physical activity behavior MVPA in the embodiments of the present application are:

[0050]

[0051]

[0052] Among them, SED is the initial time data of sedentary behavior, SLP is the initial time data of sleep behavior, LPA is the initial time data of low-intensity physical activity behavior, and MVPA is the initial time data of moderate-to-high-intensity physical activity behavior.

[0053] Based on this, the three-dimensional coordinate axes in the Euclidean space can be formed by using the initial time data corresponding to the four activity behaviors concerned in the embodiments of the present application. .

[0054] Step 203: Construct a sleep quality regression classification model based on the comparison features.

[0055] It should be noted that the present application constructs a sleep quality regression classification model by using the comparison features to determine the sleep quality of the user under different activity behavior time lengths through regression classification. Among them, in the embodiments of the present application, the sleep quality can be classified into two categories, including good sleep quality and poor sleep quality.

[0056] Optionally, the sleep quality can be evaluated by the Pittsburgh Sleep Quality Index (PSQI) for the participants. In some feasible embodiments, only Q1-Q5 in the Pittsburgh Sleep Quality Index PSQI can be used to evaluate the user's sleep quality. At this time, the scoring values of Q1-Q5 can be directly determined using the collected data of the wearable device without the user's additional participation. In some other feasible embodiments, Q1-Q9 in the Pittsburgh Sleep Quality Index PSQI can be used to evaluate the user's sleep quality. At this time, the user needs to complete the sleep information for at least one day corresponding to the initial time data.

[0057] Exemplarily, the sleep quality regression classification model constructed based on the comparison features can be:

[0058] Wherein, , , is to convert the initial time data corresponding to the four activity behaviors concerned in the embodiments of the present application into three-dimensional coordinate axes in the Euclidean space, p is the classification result, when p = 1, the user's sleep quality is good, and when p = 0, the user's sleep quality is poor. , , , are influence coefficients.

[0059] In some feasible embodiments, the influence coefficients in the present application can be solved using the maximum likelihood estimation method.

[0060] In a preferred embodiment, after obtaining the regression classification model, the embodiments of the present application further verify the regression classification model. Preferably, the present application uses the improved odds ratio (OR) to verify the model. Among them, the odds ratio OR is used to characterize the influence of the activity behavior on the probability of the change in sleep quality.

[0061] Specifically, the improved odds ratio is:

[0062] Wherein, is used for the normalization adjustment of the overall effect of the model in the three-dimensional coordinate system, j is the activity behavior corresponding to the current odds ratio OR, and k is the other activity behaviors except j.

[0063] It should be understood that, compared with the traditional odds ratio (OR), by adding a square root adjustment term to the odds ratio (OR) in the embodiments of the present application, it can be made such that the odds ratio (OR) no longer only focuses on the time change of a single activity behavior, but reflects the change after balanced adjustment among multiple activity behaviors. That is, because the time data corresponding to the activity behaviors in the embodiments of the present application are restricted by the closed time constraint of 24 hours (1440 minutes), increasing the implementation time of a certain type of activity behavior will necessarily reduce the implementation time of at least one other activity behavior, and the adjusted odds ratio (OR) can fully consider the combined influence of the time substitution among multiple activity behavior types.

[0064] Step 204: Based on the sleep quality regression classification model, determine the target time allocation scheme corresponding to each activity behavior when the probability of good sleep quality of the ankylosing spondylitis user is the largest.

[0065] Specifically, a target function for characterizing the probability of good sleep quality of the ankylosing spondylitis user can be constructed based on the sleep quality regression classification model, and by adjusting the time allocation of each type of activity behavior, the time allocation scheme of each activity behavior when the probability of good sleep quality of the user is the largest can be obtained, that is, the target time allocation scheme.

[0066] Exemplarily, the target function for characterizing the probability of good sleep quality of the ankylosing spondylitis user constructed based on the sleep quality regression classification model is:

[0067] And the constraint conditions are:

[0068] Wherein, are the target time data of sedentary behavior (SED), sleep behavior (SLP), low-intensity physical activity behavior (LPA), and moderate-to-high-intensity physical activity behavior (MVPA), that is, the target time data corresponding to each activity behavior in the target time allocation scheme. is the minimum time length limit of the target time data. is the maximum time length limit.

[0069] It should be understood that the above constraint conditions are used to constrain the sum of the target time data corresponding to each activity behavior to meet the closed time constraint, that is, the total time is 1440 minutes corresponding to 24 hours. And, the upper and lower limits of the target time data corresponding to the selected activity behavior type j are constrained. For example, based on the health guidelines, the time of moderate-to-high-intensity physical activity behavior (MVPA) should be greater than or equal to 30 minutes per day, and the sleep time should be greater than or equal to 4 hours, etc. The present application does not make specific limitations.

[0070] Based on this, the processing method for monitoring the activity time data of ankylosing spondylitis patients using a wearable device proposed in the embodiments of the present application obtains the initial time data of different activity behavior types of ankylosing spondylitis users through the wearable device, constructs a sleep quality regression model based on the initial time data, and uses the regression classification model to determine the target time allocation scheme corresponding to each activity behavior when the probability of good sleep quality of ankylosing spondylitis users is the highest, so as to provide a personalized target time allocation scheme for improving sleep quality for ankylosing spondylitis users based on their actual initial time data of different activity behavior types, enabling ankylosing spondylitis users to effectively improve their sleep quality after implementing various activity behaviors according to the target time allocation scheme, thereby achieving the purpose of improving the quality of life of ankylosing spondylitis users by using the activity behavior time allocation scheme.

[0071] In some embodiments, due to the problem of activity limitation caused by the disease in ankylosing spondylitis patients, such as being unable to perform medium- to high-intensity physical activity behaviors (MVPA) for a long time, etc., based on this, the present application can further configure a more accurate personalized target time allocation scheme based on the characteristics of ankylosing spondylitis users themselves.

[0072] Specifically, obtain at least one time constraint added by the ankylosing spondylitis user for at least one activity behavior, and based on the at least one time constraint, determine the target time allocation scheme corresponding to each activity behavior when the probability of good sleep quality of the ankylosing spondylitis user is the highest, and the target time data of each activity behavior data satisfies the corresponding time constraint.

[0073] Optionally, the time constraint includes at least one of a minimum time length and a maximum time length.

[0074] That is to say, before making a decision on personalized activity behavior time allocation, the ankylosing spondylitis user can add time constraints corresponding to various activity behaviors through the interaction interface of the follow-up system or management system, or a questionnaire, etc., such as the maximum time length of medium- to high-intensity physical activity behavior (MVPA), the minimum time length of sleep behavior (SLP), etc. Among them, the time constraints input by the ankylosing spondylitis user can be determined according to medical advice, or according to the disease condition of the ankylosing spondylitis user himself. For example, if the user is a long sleeper and needs to ensure sufficient sleep time, then set the minimum time length of sleep behavior (SLP), or if the user is severely ill and the muscle state cannot support medium- to high-intensity physical activity behavior (MVPA) for a long time, then set the maximum time length of medium- to high-intensity physical activity behavior (MVPA), etc.

[0075] Specifically, time constraints added by ankylosing spondylitis users for at least one activity behavior are used to construct constraint conditions for the objective function. During the process of solving the objective function, the constraint conditions are used to limit the solution of the objective function, and then the target time data corresponding to each activity behavior that meets the time constraints is obtained.

[0076] Thus, the embodiment of the present application can provide a personalized target time allocation scheme that meets the needs of ankylosing spondylitis users when they clarify the time limits for their own activity behaviors. On the basis of ensuring the improvement of sleep quality, it ensures the time requirements of ankylosing spondylitis users for various activity behaviors, and on the basis of improving the quality of life of ankylosing spondylitis users, it improves the user experience of ankylosing spondylitis users.

[0077] Optionally, the time constraint includes the association relationship between two types of activity behaviors, including but not limited to that the target time data of one type of activity behavior is greater than the target time data of another type of activity behavior, etc.

[0078] Specifically, when constructing the regression classification model, based on the association relationship between two types of activity behaviors input by ankylosing spondylitis users, interaction terms related to these two types of activity behaviors are generated, and constraint conditions are constructed based on the association relationship between the two types of activity behaviors.

[0079] Exemplarily, when the user adds a lot of low-intensity physical activity behaviors (LPA) and few moderate-to-high-intensity physical activity behaviors (MVPA), the regression classification model is:

[0080] Among them, is the interaction term between the low-intensity physical activity behavior (LPA) and the moderate-to-high-intensity physical activity behavior (MVPA), ≠0 indicates the existence of a synergistic effect between the low-intensity physical activity behavior (LPA) and the moderate-to-high-intensity physical activity behavior (MVPA).

[0081] And the newly constructed constraint condition is:

[0082] Thus, the embodiment of the present application can provide a personalized target time allocation scheme that meets the needs of ankylosing spondylitis users when they have clear time allocation preferences. On the basis of ensuring the improvement of sleep quality, it ensures the time requirements of ankylosing spondylitis users for various activity behaviors, and on the basis of improving the quality of life of ankylosing spondylitis users, it improves the user experience of ankylosing spondylitis users.

[0083] Further, in some embodiments, the wearable device is used to collect the duration data of the sedentary behavior of the ankylosing spondylitis user in real time. When the duration data exceeds the target time data corresponding to the sedentary behavior, the wearable device is used to send a timeout reminder to the ankylosing spondylitis user.

[0084] Among them, the duration data can be the duration of a single sedentary behavior or the total duration of multiple sedentary behaviors, and the present application does not make specific limitations.

[0085] That is to say, for sedentary behavior, the present application further provides a reminder mechanism to send a timeout reminder to the user when the duration of the sedentary behavior of the ankylosing spondylitis user exceeds the target time data. Thus, it can effectively prevent the ankylosing spondylitis user from maintaining a sedentary behavior for a long time, assist the ankylosing spondylitis user to relieve sedentary fatigue, etc., and further prevent the unnecessary deterioration of the condition.

[0086] It should be noted that although the operations of the method of the present invention are described in a specific order in the drawings, this does not require or imply that these operations must be performed in that specific order, or that all the shown operations must be performed to achieve the desired result.

[0087] Figure 3 The structural schematic diagram of the processing device for monitoring the activity time data of ankylosing spondylitis patients by using a wearable device provided in an embodiment of the present application is shown.

[0088] As Figure 3 shown, the processing device 10 for monitoring the activity time data of ankylosing spondylitis patients by using a wearable device provided in an embodiment of the present application includes: An acquisition module 11, configured to use the wearable device to acquire the initial time data corresponding to each activity behavior of the ankylosing spondylitis user, where the activity behaviors include sedentary behavior, sleep behavior, low-intensity physical activity behavior, and high-intensity physical activity behavior; A determination module 12, configured to determine the comparison characteristics between each of the activity behaviors based on the initial time data; A construction module 13, configured to construct a sleep quality regression classification model based on the comparison characteristics; A decision module 14, configured to determine the target time allocation scheme corresponding to each of the activity behaviors when the probability of good sleep quality of the ankylosing spondylitis user is the highest based on the sleep quality regression classification model.

[0089] In some embodiments, the determination module 12 is further configured to: Use isometric log-ratio transformation to obtain the comparison characteristics between each activity behavior and other activity behaviors.

[0090] In some embodiments, the determination module 12 is further configured to: Standardize the initial time data corresponding to the low-intensity physical activity behavior and the medium-high intensity physical activity behavior obtained by the wearable device respectively; and Correct the initial time data corresponding to the sedentary behavior obtained by the wearable device based on the sedentary correction data input by the ankylosing spondylitis user.

[0091] In some embodiments, the decision module 14 is further configured to:[[]] Obtain at least one time constraint added by the ankylosing spondylitis user to at least one of the activity behaviors; Based on at least one of the time constraints, determine the target time allocation scheme corresponding to each of the activity behaviors when the probability that the ankylosing spondylitis user has good sleep quality is the highest, wherein the target time data of each activity behavior satisfies the corresponding time constraint.

[0092] In some embodiments, the time constraint includes at least one of a minimum time length and a maximum time length; or, the time constraint includes the association relationship between two types of activity behaviors.

[0093] In some embodiments, the decision module 14 is further configured to:[[]] Use the wearable device to collect the duration data of the sedentary behavior of the ankylosing spondylitis user in real time; When the duration data exceeds the target time data corresponding to the sedentary behavior, use the wearable device to send an overtime reminder to the ankylosing spondylitis user.

[0094] It should be understood that the various modules recorded in the processing device 10 for monitoring the activity time data of ankylosing spondylitis patients by using a wearable device or the modules and the reference Figure 2 The steps in the described method correspond. Therefore, the operations and features described above for the method also apply to the processing device 10 for monitoring the activity time data of ankylosing spondylitis patients by using a wearable device and the modules included therein, and will not be repeated here. The processing device 10 for monitoring the activity time data of ankylosing spondylitis patients by using a wearable device can be pre-implemented in the browser or other secure applications of the electronic device, or can be loaded into the browser or its secure application of the electronic device by means of downloading, etc. The corresponding modules in the processing device 10 for monitoring the activity time data of ankylosing spondylitis patients by using a wearable device can cooperate with the modules in the electronic device to implement the solution of the embodiments of the present application.

[0095] Among the several modules or units mentioned in the above detailed description, such a division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0096] Reference is now made to Figure 4 , Figure 4 which shows a schematic structural diagram of a computer system of an electronic device or a server suitable for implementing the embodiments of the present application. As Figure 4 shown, the computer system includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage section 408 into the random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation instructions of the system are also stored. The CPU 401, ROM 402, and RAM 403 are connected to each other via a bus 404. The input / output (I / O) interface 405 is also connected to the bus 404.

[0097] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as required. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as required so that a computer program read from it can be installed into the storage section 408 as required.

[0098] Specifically, according to the embodiments of the present application, the process described above with reference to the flowchart Figure 2 can be implemented as a computer software program. For example, the embodiments of the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program codes for performing the method shown in the flowchart. In such an embodiment, the computer program includes program codes for performing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication section 409, and / or installed from the removable medium 411. When the computer program is executed by the central processing unit (CPU) 401, the above functions defined in the system of the present application are executed.

[0099] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of a computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this application, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. And in this application, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0100] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operation instructions of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram can represent a module, a program segment, or a part of code, and the foregoing module, program segment, or part of code contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two connected blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that executes the specified functions or operation instructions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0101] The units or modules involved in the embodiments described in this application can be implemented in software or in hardware. The described units or modules can also be provided in a processor. For example, it can be described as: A processor includes an acquisition module, a determination module, a construction module, and a decision module. Among them, the names of these units or modules do not constitute a limitation on the units or modules themselves in some cases. For example, the acquisition module can also be described as "using a wearable device to acquire the initial time data corresponding to the various activity behaviors of ankylosing spondylitis users, where the activity behaviors include sedentary behavior, sleep behavior, low-intensity physical activity behavior, and high-intensity physical activity behavior".

[0102] As another aspect, this application also provides a computer-readable storage medium. The computer-readable storage medium can be included in the electronic device described in the above embodiments, or can exist alone without being assembled into the electronic device. The above computer-readable storage medium stores one or more programs, and when the above programs are executed by one or more processors, they are used to implement the method for monitoring the activity time data of ankylosing spondylitis patients using a wearable device described in this application.

[0103] The above description is only a preferred embodiment of this application and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of disclosure involved in this application is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the foregoing disclosure concept. For example, the technical solutions formed by mutually replacing the above features with the (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A method for processing activity time data of ankylosing spondylitis patients using a wearable device, characterized in that: include: Using wearable devices to obtain initial time data corresponding to various activity behaviors of ankylosing spondylitis users, the activity behaviors include sedentary behavior, sleeping behavior, low-intensity physical activity behavior, and medium-to-high-intensity physical activity behavior; Based on the initial time data, determining comparative features between the activity behaviors; Constructing a sleep quality regression classification model based on the contrast features; Based on the sleep quality regression classification model, a target time allocation scheme corresponding to each of the activity behaviors when the probability of the ankylosing spondylitis user having good sleep quality is maximized is determined.

2. The method for processing activity time data of ankylosing spondylitis patients using a wearable device according to claim 1, characterized in that: The determining, based on the initial time data, the contrast features between the activity behaviors includes: The isometric log-ratio transformation is used to obtain the contrast characteristics between each activity behavior and other activity behaviors.

3. The method for processing activity time data of ankylosing spondylitis patients using a wearable device according to claim 1 or 2, characterized in that: Before determining the comparison features between the activity behaviors based on the initial time data, the method further includes: Standardizing the initial time data corresponding to the low-intensity physical activity behavior and the medium-to-high-intensity physical activity behavior acquired by the wearable device respectively; and The initial time data corresponding to the sedentary behavior acquired by the wearable device is corrected based on the sedentary correction data input by the ankylosing spondylitis user.

4. The method for processing activity time data of ankylosing spondylitis patients using a wearable device according to claim 1, characterized in that: The step of determining the target time allocation scheme corresponding to each of the activity behaviors when the probability of the ankylosing spondylitis user having good sleep quality is the largest based on the sleep quality regression classification model includes: Obtaining at least one time constraint added by the ankylosing spondylitis user to at least one of the activity behaviors; Based on at least one of the time constraints, a target time allocation scheme corresponding to each of the activity behaviors when the probability that the ankylosing spondylitis user has good sleep quality is maximized is determined, wherein the target time data of each activity behavior satisfies the corresponding time constraint.

5. The method for processing activity time data of ankylosing spondylitis patients using a wearable device according to claim 4, characterized in that: The time constraint includes at least one of a minimum time length and a maximum time length.

6. The method for processing activity time data of ankylosing spondylitis patients using a wearable device according to claim 5, characterized in that: Also includes: Using the time constraint added by the ankylosing spondylitis user to at least one activity behavior to construct a constraint condition for the objective function; In the process of solving the objective function, the constraint condition is used to restrict the objective function solution to obtain the target time data corresponding to each activity behavior that meets the time constraint.

7. The method for processing activity time data of ankylosing spondylitis patients using a wearable device according to claim 4, characterized in that: The time constraint includes the association relationship between two types of activity behaviors.

8. The method for processing activity time data of ankylosing spondylitis patients using a wearable device according to claim 7, characterized in that: Also includes: When constructing the regression classification model, based on the association relationship between the two types of activity behaviors input by the ankylosing spondylitis user, interaction terms related to the two types of activity behaviors are generated, and constraints are constructed based on the association relationship between the two types of activity behaviors.

9. The method for processing activity time data of ankylosing spondylitis patients using a wearable device according to claim 1, characterized in that: Also includes: Using the wearable device to collect the duration data of the sedentary behavior of the ankylosing spondylitis user in real time; When the duration data exceeds the target time data corresponding to the sedentary behavior, the wearable device is used to send a timeout reminder to the ankylosing spondylitis user.

10. A processing device for monitoring activity time data of ankylosing spondylitis patients using a wearable device, characterized in that: include: An acquisition module is used to acquire initial time data corresponding to various activity behaviors of ankylosing spondylitis users using a wearable device, wherein the activity behaviors include sedentary behavior, sleeping behavior, low-intensity physical activity behavior, and high-intensity physical activity behavior; A determination module, used for determining the contrast features between the activity behaviors based on the initial time data; A construction module, used for constructing a sleep quality regression classification model based on the contrast features; The decision module is used to determine, based on the sleep quality regression classification model, the target time allocation scheme corresponding to each of the activity behaviors when the probability of the ankylosing spondylitis user having good sleep quality is maximized.

Images