A method for collecting intelligent elderly care health data and a humanoid elderly care robot

Abstract

The present application discloses a method for collecting intelligent elderly care health data and a humanoid elderly care robot, which relates to the technical field of data processing. The method includes: obtaining the physiological data of a user; obtaining the current physiological change data of the user based on the physiological data of the user; performing time series clustering on the current physiological change data of the user based on the second physiological change data to obtain clustering clusters; obtaining similarity evaluation data of the first physiological change data based on the clustering clusters; and judging the abnormal condition of the user's physiological data based on the similarity evaluation data. The present application compares by analyzing the trend of the change of the user's out-of-range data and the synchronization of the changes of the data of other users of the same type. Compared with the previous method of simply judging the physical health status of a user from the out-of-range change of one-dimensional data, this determination method is more accurate.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and specifically to a method for collecting intelligent elderly care health data and a humanoid elderly care robot. Background Art

[0002] With the intensification of population aging, the elderly care problem of the elderly population faces more and more challenges. How to enable the elderly to be supported and enjoy themselves in their old age has become an urgent problem to be solved for the current elderly population. With the continuous development of big data and artificial intelligence, new opportunities have been provided for improving elderly care services. By using artificial intelligence technology to collect the health data of the elderly in real time, the needs and preferences of the elderly can be better understood, work efficiency and accuracy can be improved, and more personalized elderly care services can be provided for the elderly.

[0003] It should be clear that as the elderly age, all organs of their bodies gradually age. Therefore, it is necessary and essential to monitor various physiological data of the body at all times. And due to the aging of the body organs, the elderly usually have various chronic diseases. For humanoid elderly care robots, it is also necessary to collect the physiological data of the elderly in real time, analyze and judge, and give timely reminders and interventions for the physiological abnormalities reflected by the physiological data. However, in actual operation and use, during the collection of physiological data, if the elderly happen to have normal physiological activities, it may cause a drastic change in their physiological data. For example, when the blood sugar of the elderly drops after strenuous exercise, the change curve is similar to that of hypoglycemia. And because the drop in blood sugar of the elderly after strenuous exercise is a normal physiological drop in blood sugar, when the blood sugar change curve is similar to that of hypoglycemia, it will be misjudged as having a health risk and a reminder will be given. This reduces the monitoring accuracy of humanoid elderly care robots and affects users' trust in humanoid elderly care robots. Summary of the Invention

[0004] The purpose of this application is to provide a method for collecting intelligent elderly care health data and a humanoid elderly care robot to solve the technical problem of the low monitoring accuracy of humanoid elderly care robots in the prior art.

[0005] To achieve the above purpose, this application provides the following technical solutions:

[0006] In the first aspect, this application proposes a technical solution for a method for collecting intelligent elderly care health data. The method includes:

[0007] Obtain the physiological data of the user;

[0008] Based on the physiological data of the user, obtain the current physiological change data of the user; the current physiological change data includes first physiological change data and second physiological change data; the first physiological change data is any data in which the current physiological change data undergoes an out-of-range change; the second physiological change data is all data in the current physiological change data excluding the first physiological change data;

[0009] Based on the second physiological change data, perform time series clustering on the current physiological change data of the user to obtain clustering clusters;

[0010] Based on the clustering clusters, obtain similarity evaluation data for the first physiological change data;

[0011] Based on the similarity evaluation data, judge the abnormal condition of the user's physiological data.

[0012] As a specific solution in the technical solution of this application, the method is applied to a physiological data collection device and a humanoid elderly care robot, and the physiological data collection device includes a smart bracelet; the obtaining of the physiological data of the user includes:

[0013] Based on the physiological data collection device, collect the physiological data of the user at a preset time interval;

[0014] Transmit the physiological data of the user to the humanoid elderly care robot so that the humanoid elderly care robot can obtain the physiological data of the user.

[0015] As a specific solution in the technical solution of this application, the current physiological change data of the user includes the change curve of the user's physiological data based on time series or the change trend of the user's physiological data based on time series.

[0016] As a specific solution in the technical solution of this application, the performing time series clustering on the current physiological change data of the user based on the second physiological change data to obtain clustering clusters includes:

[0017] Construct a space model, and based on the second physiological change data, obtain the space change rate of the second physiological change data in the space model;

[0018] Based on the space change rate, perform clustering on the physiological data of the user to obtain clustering clusters.

[0019] As a specific solution in the technical solution of this application, the formula for constructing a space model and obtaining the space change rate of the second physiological change data in the space model based on the second physiological change data is as follows:

[0020]

[0021] in, represents the spatial change rate of the data point corresponding to the second physiological change data in the spatial model; Indicates Dimension The data value of the data point at that moment, Indicates Dimension The data value of the data point at that moment, Indicates the time series a moment, Indicates the time series a moment; Indicates that there are a total of dimensions, Respectively represent the time series The nearest extreme point around a moment.

[0022] As a specific solution in the technical solution of the present application, the obtaining of similarity evaluation data of the first physiological change data based on the clustering clusters includes:

[0023] Based on the cluster cluster, a first cluster density is acquired; the first cluster density is a cluster density of the first physiological change data of the user;

[0024] Based on the cluster, a second cluster density is obtained; the second cluster density is a mean value of cluster densities of the first physiological change data of all users in the cluster;

[0025] Based on the first clustering density and the second clustering density, similarity evaluation data of the first physiological change data is acquired.

[0026] As a specific solution in the technical solution of the present application, the calculation formula for obtaining the similarity evaluation data of the first physiological change data based on the first clustering density and the second clustering density is as follows:

[0027]

[0028] in, Similarity evaluation data of the user's first physiological change data; representing a spatial change rate of the second physiological change data of the user in the spatial model; Indicates The cluster density of the user’s physiological data at all times; Indicates The cluster density of the user’s physiological data at all times; Indicates that the size of the time variation curve is Sliding window of Denote the cluster density of the physiological data of user x in the clustering cluster at the cluster density of the physiological data of user x in the clustering cluster at the denote the number of users in the clustering cluster; denote the first clustering density; denote the second clustering density; denote the sigmoid function that maps the data to the interval (0, 1).

[0029] As a specific solution in the technical solution of this application, determining the abnormal condition of the user's physiological data based on the similarity evaluation data includes:

[0030] If the similarity evaluation data of the first physiological change data is greater than the first threshold, it is determined that the physiological data of the user is abnormal;

[0031] If the similarity evaluation data of the first physiological change data is less than or equal to the first threshold, it is determined that the physiological data of the user is normal.

[0032] In a second aspect, this application proposes a technical solution for a humanoid elderly care robot, and this humanoid elderly care robot includes:

[0033] An acquisition module, configured to acquire the physiological data of the user;

[0034] A processing module, configured to obtain the current physiological change data of the user based on the physiological data of the user; the current physiological change data includes first physiological change data and second physiological change data; the first physiological change data is any data in which the current physiological change data undergoes an out-of-range change; the second physiological change data is all data in the current physiological change data except the first physiological change data;

[0035] And, based on the second physiological change data, perform time series clustering on the current physiological change data of the user to obtain a clustering cluster;

[0036] And, based on the clustering cluster, obtain the similarity evaluation data of the first physiological change data;

[0037] And, based on the similarity evaluation data, determine the abnormal condition of the user's physiological data.

[0038] As a specific solution in the technical solution of this application, the acquisition module is configured to receive the physiological data of the user collected by the physiological data acquisition device at a preset time interval.

[0039] ​​As a specific solution in the technical solution of the present application, the current physiological change data of the user includes the change curve of the user's physiological data based on time series or the change trend of the user's physiological data based on time series.

[0040] As a specific solution in the technical solution of the present application, the processing module constructs a spatial model, and based on the second physiological change data, obtains the spatial change rate of the second physiological change data in the spatial model;

[0041] And, based on the spatial change rate, cluster the physiological data of the user to obtain clustering clusters.

[0042] As a specific solution in the technical solution of the present application, the processing module is further configured to obtain the spatial change rate of the second physiological change data in the spatial model based on the following formula:

[0043]

[0044] Wherein, represents the spatial change rate of the data point corresponding to the second physiological change data in the spatial model; represents the th th data value of the data point at the th moment in the th dimension, represents the data value of the data point at the th moment in the th dimension, represents the th moment in the time series, represents the th dimension in this spatial model, respectively represent the extreme points closest to the th moment in the time series.

[0045] As a specific solution in the technical solution of the present application, the processing module is further configured to obtain a first clustering density based on the clustering clusters; the first clustering density is the clustering density of the first physiological change data of the user;

[0046] And, obtain a second clustering density based on the clustering clusters; the second clustering density is the average of the clustering densities of the first physiological change data of all users in the clustering clusters;

[0047] And, based on the first clustering density and the second clustering density, obtain the similarity evaluation data of the first physiological change data.

[0048] As a specific solution in the technical solution of the present application, the processing module is further configured to obtain similarity evaluation data of the first physiological change data based on the following formula:

[0049]

[0050] Where is the similarity evaluation data of the first physiological change data of the user; represents the spatial change rate of the second physiological change data of the user in the spatial model; represents the cluster density of the physiological data of the user at the moment; represents the cluster density of the physiological data of the user at the moment; represents a sliding window of size on the time change curve; represents the cluster density of the physiological data of user x in the cluster at the moment, the cluster density of the physiological data of user x in the cluster at the moment, represents the number of users in the cluster; represents the first clustering density; represents the second clustering density;

[0051] As a specific solution in the technical solution of the present application, the processing module is further configured to determine that the physiological data of the user is abnormal if the similarity evaluation data of the first physiological change data is greater than a first threshold;

[0052] If the similarity evaluation data of the first physiological change data is less than or equal to the first threshold, it is determined that the physiological data of the user is normal.

[0053] Compared with the prior art, the beneficial effects of the present application are:

[0054] The present application compares by analyzing the trend of the user's out-of-range data change and the synchronization of the data changes of other users of the same type. Compared with the previous method of simply judging the user's physical health status from the out-of-range change of one-dimensional data, this determination method is more accurate. It can avoid misjudgment caused by the change of physiological data brought by the user's physiological activities, improve the accuracy of data judgment, and combine with other data to make the integrity of the data stronger. Description of the Drawings

[0055] Figure 1A schematic flow chart of a method for collecting intelligent elderly care health data proposed in an embodiment of the present application;

[0056] Figure 2 A schematic structural diagram of a humanoid elderly care robot proposed in an embodiment of the present application. Detailed implementation manners

[0057] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0058] Terms such as "first" and "second" in the specification, claims and above-mentioned drawings of the embodiments of the present application are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. For example, the first physiological change data and the second physiological change data proposed below belong to different data. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or modules does not necessarily need to be limited to those steps or modules clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. The division of modules in the embodiments of the present application is only a logical division. In actual implementation, there may be other division methods. For example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed couplings or direct couplings or communication connections to each other may be through some interfaces. The indirect couplings or communication connections between modules may be electrical or other similar forms, which are not limited in the embodiments of the present application. And, the modules or sub-modules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed to multiple circuit modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present application.

[0059] As Figure 1 shown, in order to solve the technical problem of low monitoring accuracy of humanoid elderly care robots in the prior art proposed in the present application, the present application proposes a method for collecting intelligent elderly care health data, which includes steps S100 to S500.

[0060] Step S100: Obtain the physiological data of the user.

[0061] It should be clear that in the embodiments of the present application, any method can be used to obtain the physiological data of the user. For example, the physiological data of the user can be obtained by manual input, or the physiological data of the user can be obtained by downloading. In order to monitor the health of the user in real time, in an embodiment of the present application, the method is applied to a physiological data collection device and a humanoid elderly care robot, and the physiological data collection device includes a smart bracelet; step S100 of obtaining the physiological data of the user includes step S110 and step S120.

[0062] Step S110: Based on the physiological data collection device, collect the physiological data of the user at a preset time interval.

[0063] Through the physiological data collection device worn by the user, such as a smart bracelet, etc., various physiological data of the user are collected in real time, and the physiological data status of the user is monitored in real time. Each physiological data of the user is based on a time series. The acquisition frequency of the data can be an empirical value or the best experimental value obtained through multiple experiments. In the embodiments of the present application, the acquisition frequency of the data can be set to 1 time / second or 2 times / second, and no specific setting is made. Finally, what we obtain is the time data series of the changes in various physiological data of the user.

[0064] Step S120: Transmit the physiological data of the user to the humanoid elderly care robot so that the humanoid elderly care robot can obtain the physiological data of the user.

[0065] In the embodiments of the present application, it should be clear that since most diseases are accompanied by a sharp change in blood sugar, the physiological data of the user can at least include blood sugar. Of course, the physiological data of the user can also include data such as the user's blood pressure, heart rate, body temperature, etc. In order to enable the humanoid elderly care robot to obtain this physiological data, real-time information transmission can be carried out between the smart bracelet and the humanoid elderly care robot. Since real-time wireless data transmission between the smart bracelet and the humanoid elderly care robot is a mature technology, no more details will be described here.

[0066] Step S200: Based on the physiological data of the user, obtain the current physiological change data of the user.

[0067] It should be clear that in the prior art, if the current physiological change data of a user changes beyond the normal range, it is considered that the user has a health problem (i.e., has a disease), and the humanoid elderly care robot will issue a health warning. However, after certain physiological activities, the physiological change data of the user often changes beyond the normal range. For example, the blood sugar of the elderly group will rise sharply after a meal, or the blood pressure will rise sharply during a meal, or the blood sugar will drop sharply during strenuous exercise. These may all cause the humanoid elderly care robot to misjudge that the physiological change data of the user has changed beyond the normal range, and then issue a health warning.

[0068] In the embodiments of the present application, the physiological change data changing beyond the normal range means that the physiological data exceeds the standard physiological data range value. For example, the standard data range value of blood sugar is 4.4 mmol / L to 6.1 mmol / L. If the blood sugar of a user is lower than 4.4 mmol / L or higher than 6.1 mmol / L, it is considered that the blood sugar of the user has changed beyond the normal range; the standard data range value of heart rate is 60 beats per minute to 100 beats per minute. If the heart rate of a user is lower than 60 beats per minute or higher than 100 beats per minute, it is considered that the heart rate of the user has changed beyond the normal range; the standard data range value of body temperature is 36°C to 37°C. If the body temperature of a user is lower than 36°C or higher than 37°C, it is considered that the body temperature of the user has changed beyond the normal range.

[0069] As can be seen from the foregoing, since the physiological data of the user obtained by the humanoid elderly care robot is the time data sequence of the changes in the user's various physiological data. Therefore, in the embodiments of the present application, the current physiological change data of the user includes the change curve of the user's physiological data based on time series or the change trend of the user's physiological data based on time series. It should be clear that the change trend of the user's physiological data based on time series refers to the slope of the change curve of the user's physiological data based on time series or the change value of the user's physiological data based on the change curve per unit time.

[0070] As can be seen from the foregoing, a sharp change (i.e., an out-of-range change) in a user's blood glucose may be caused by pathological reasons, such as diabetes or hypoglycemia, etc.; it may also be caused by normal physiological activities, such as eating or exercising, etc. It should be clear that if it is a normal physiological activity, when a physiological data has an out-of-range change, other physiological data will also have corresponding changes. And these changes are similar and traceable in the time series. In other words, if an out-of-range change in a user's physiological data is caused by normal physiological activities, other physiological data of the user will also have corresponding changes. In the embodiments of the present application, the data with out-of-range changes in the user's current physiological change data is defined as the first physiological change data, and the other data in the current physiological change data except the first physiological change data is defined as the second physiological change data.

[0071] It is easy to understand that different users will have similar physiological activities. In other words, in the embodiments of the present application, we can determine the cause of the first physiological change data (i.e., the physiological data with out-of-range changes) based on the second physiological change data of different users, thereby improving the accuracy of early warning.

[0072] Step S300: Based on the second physiological change data, perform time series clustering on the user's current physiological change data to obtain clustering clusters.

[0073] It should be clear that since the elderly population is a group prone to diseases, it is particularly important to monitor the health of the elderly. Therefore, in the embodiments of the present application, taking the elderly population as an example, a detailed description of the intelligent elderly care health data collection method proposed in the present application is given. For the users in the elderly population, the monitoring of blood glucose is crucial. Keeping track of the blood glucose value in real time is very important for health management and diet control. Generally speaking, due to the aging of organs in the elderly population, the changes in their various physiological data in response to the changes in the body condition are relatively sensitive. The blood glucose usually reaches a maximum value after a meal, and then the blood glucose begins to decline slowly until the intake of sugar in the next meal. The blood glucose of the elderly also decreases slowly after exercise. Also, because the living schedules and eating habits of the elderly population are relatively regular, that is, the blood glucose changes of the elderly have a certain similarity. When the difference in the blood glucose change curve of the monitored elderly and the blood glucose change curves of the rest of the elderly population is greater, that is, when the similarity between the blood glucose change curve of the target elderly and the blood glucose change curves of other elderly people is lower under the same state, it indicates that the blood glucose change of the elderly in the current state is more likely to be a pathological blood glucose decline rather than a physiological blood glucose decline, that is, the target elderly is more likely to have a disease and a health warning needs to be issued.

[0074] It should be clear that in the embodiments of the present application, the physiological data participating in clustering can be the physiological data of multiple different users or the physiological data of the same user within different time periods, and the time period is an integer multiple of 1 day.

[0075] It should be clear that in the embodiments of the present application, any algorithm can be used to perform time-series clustering on the physiological data of the user, and then clustering clusters can be obtained. For example, the K-means clustering algorithm can be used, or the graph community detection clustering algorithm can be used, etc.

[0076] In a specific embodiment of the present application, step S300, based on the second physiological change data, performing time-series clustering on the current physiological change data of the user to obtain clustering clusters includes steps S310 to S320.

[0077] Step S310: Construct a space model, and based on the second physiological change data, obtain the spatial change rate of the second physiological change data in the space model.

[0078] It should be noted that the human body system is an integrated whole, and the changes in various physiological data of the human body are correlated to a certain extent. They all reflect the health activity state of the human body. Different health activity states of the human body correspond to different changes in physiological data. For example, after each person performs strenuous exercise, there will be changes in physiological data such as an increase in breathing rate, blood pressure, heart rate, and body temperature. Therefore, according to the changes in other physiological data, a space model is constructed through the fluctuation changes of other physiological data. According to the spatial distribution of its various physiological data, it is judged whether the change in the user's physiological data is an abnormal change. Because for the same health activity state, the data points of its various physiological data are relatively concentrated in space, and when a person's health activity state is different, the various physiological data will change, and at this time, the data points between the health activity states will also change accordingly. Then the data points of its physiological data in different dimensions will show different aggregation states. Also, because in space, what we want to know more is the change in the time series of the data points in each dimension. Instead of the relative distance between the data points in the model space, when using the clustering algorithm, the clustering between the data points in the model space is represented by the instantaneous change rate of each data point in its respective dimension for clustering.

[0079] Specifically, to construct a space model and based on the second physiological change data, the calculation formula for obtaining the spatial change rate of the second physiological change data in the space model is as follows:

[0080]

[0081] Wherein, Indicates the spatial change rate of the data points corresponding to the second physiological change data in the spatial model; Indicates the value of the data point at the th moment in the th dimension, Indicates the value of the data point at the th moment in the th dimension, Indicates the th moment in the time series; Indicates that there are dimensions in this spatial model, respectively indicating the extreme points closest to the th moment in the time series.

[0082] It should be clear that in the above formula, indicates the difference between the value of the data point at the th moment and the value of the data point at the th moment in the same dimension. is the time interval between the th moment and the th moment in the current dimension. Indicates the change rate from the data point at the th moment to the data point at the th moment in the dimension. Indicates the weight. When the distance between the th moment and the th moment is farther, is larger, is smaller, and the influence weight of its change rate is smaller. Indicates the sum of the change rates of the extreme points closest to the data point at the th moment on both the left and right sides in the th dimension when traversing to the th data point. Indicates the time interval weight between adjacent extreme points in the data fluctuation curve where the data point at the th moment in the time series is located. When the distance between the th moment and the th moment is farther, is larger, is smaller, and its weight is smaller. Because of the different dimensions of the data points, its th The positions of the extreme points closest to the adjacent moments will also be different. That is, in the face of the same active state, the response degrees and response rates of data in different dimensions are different. The rates of some dimensions change more rapidly, while those of some are slower. Therefore, the distance between the extreme points is combined as the weight of the change rate of the data points in this dimension. Because there are many dimensions in the model space, the greater the fluctuation change of the data points in this dimension, the more sensitive the physiological data in this dimension is to the healthy activity state of the body. Therefore, its weight should be greater, that is the smaller, the weight of this dimension the greater. represents the sum of the change rates of each data point in the model space from the dimension to the th dimension.

[0083] Cluster the data points in the model space according to the calculated change rates of each data point in the model space to obtain clusters representing different change rates. The change rates in the same cluster are approximate, and the small difference indicates that the data points in this cluster represent a healthy activity state of the body.

[0084] Step S320: Based on the spatial change rate, cluster the physiological data of the user to obtain clustering clusters.

[0085] It should be clear that due to the large number of the elderly population and the regular daily routines and simple daily life states of the elderly, there must be similar healthy activity state living habits among the entire elderly population. That is to say, in terms of temporal changes, the temporal changes of each healthy activity state will correspond to the healthy activity states of other elderly groups. For example, the change in physiological data in a certain exercise state must exist in the physiological data changes of a large number of elderly people in this exercise state, and this change in physiological data is approximate. That is, in the entire time series, the living habits of the elderly can be roughly understood based on the changes in the clustering clusters, and this living habit can be found and used as a reference among the elderly population. It is easy to understand that if the physiological data of a certain elderly user changes beyond the normal range, and there are relatively few corresponding references to such changes in physiological data found among the elderly population, it indicates that the change beyond the normal range of the physiological data of this elderly user is very likely to be caused by a pathological condition, that is, it is necessary to give an early warning about the health condition of this elderly user.

[0086] It should be noted that the spatial change rate d of the second physiological change data in the spatial model is calculated based on the characteristic distribution of the second physiological change data of each user in each dimension. Furthermore, the clustering clusters obtained based on the spatial change rate include elderly user groups with relatively similar healthy activity states. That is, different users with relatively close second physiological change data are included in the same clustering cluster. Therefore, based on the clustering results, further feature analysis can be carried out on the reasons for the out-of-range changes in the first physiological change data of users in the elderly group.

[0087] Step S400: Based on the clustering clusters, obtain similarity evaluation data for the first physiological change data.

[0088] In the embodiments of the present application, we can obtain the similarity evaluation data for the first physiological change data based on the clustering clusters using any suitable algorithm. For example, the Euclidean distance algorithm, Manhattan distance algorithm, or cosine similarity algorithm can be used to obtain the similarity evaluation data for the first physiological change data.

[0089] In a specific embodiment of the present application, a graph is constructed with the time series change as the horizontal axis and the density of the cluster classes corresponding to different activity states as the vertical axis. Connect the different activity states to form a change curve of the activity state. Step S400, obtaining the similarity evaluation data for the first physiological change data based on the clustering clusters includes steps S410 to S430.

[0090] Step S410: Based on the clustering clusters, obtain the first clustering density.

[0091] It should be clear that the first clustering density is the clustering density of the first physiological change data of the user.

[0092] Step S420: Based on the clustering clusters, obtain the second clustering density.

[0093] It should be clear that the second clustering density is the mean value of the clustering densities of the first physiological change data of all users in the clustering cluster.

[0094] Step S430: Based on the first clustering density and the second clustering density, obtain the similarity evaluation data for the first physiological change data.

[0095] It should be clear that in the above steps, we obtained the changes in the physical and physiological data of the elderly in different activity states, and clustered the different changes of the physiological data of the elderly in the model space according to different healthy activity states. Different clusters represent different activity states. Then, through model reconstruction, the activity patterns of the elderly within a day were obtained based on the changes in time series, that is, the daily routines of the elderly. Since the lives of the elderly are simple and their routines are regular, there are a large number of healthy people in the entire elderly population whose living habits and daily routines are basically the same as those of the target elderly. Therefore, by comparing the state change curves of the elderly with those of healthy elderly people with similar living habits, calculating their similarity, and evaluating the similarity degree.

[0096] In a specific embodiment of the present application, in step S430, based on the first clustering density and the second clustering density, the calculation formula for obtaining the similarity evaluation data of the first physiological change data is as follows:

[0097]

[0098] Wherein, is the similarity evaluation data of the first physiological change data of the user; represents the spatial change rate of the second physiological change data of the user in the spatial model; represents the cluster density of the physiological data of the user at the moment; represents the cluster density of the physiological data of the user at the moment; represents a sliding window of size on the time change curve; represents the cluster density of the physiological data of user x in the cluster at the moment, the cluster density of the physiological data of user x in the cluster at the moment, represents the number of users in the cluster; represents the first clustering density; represents the second clustering density;

[0099] In this embodiment, represents the mean value of the change in the cluster density of the physiological data of the activity state within an activity window of size including the activity at the moment on the activity change curve of the elderly, that is, the first clustering density. represents, at the same time, the other The mean of the cluster density change of the physiological data of an elderly person within an activity window of size . It represents the mean of the cluster density change of the physiological data of the elderly population with the same activity state as that of the elderly person at the same time, that is, the second clustering density. When the change of the physiological status index of the elderly person in this activity state is closer to that of others in the group, that is, the change of the physiological data of the elderly person in this state is more similar to the change of other elderly people, it indicates that the change of the physiological data of the elderly person at the current moment is more normal, that is the closer it is to 1, then the smaller it is, that is, the smaller s is; on the contrary, it indicates that the physiological data state of the elderly person at the current moment is more abnormal, that is, the larger s is.

[0100] Step S500: Based on the similarity evaluation data, determine the abnormal condition of the user's physiological data.

[0101] It should be clear that in the embodiments of the present application, any method can be adopted to determine the abnormal condition of the user's physiological data based on the similarity evaluation data of the user's first physiological change data. For example, in a specific embodiment of the present application, in step S500, determining the abnormal condition of the user's physiological data based on the similarity evaluation data includes step S510 and step S520.

[0102] Step S510: If the similarity evaluation data of the first physiological change data is greater than the first threshold, it is determined that the physiological data of the user is abnormal.

[0103] Step S520: If the similarity evaluation data of the first physiological change data is less than or equal to the first threshold, it is determined that the physiological data of the user is normal.

[0104] In the embodiments of the present application, the first threshold can be an empirical value or an experimental value obtained through multiple experiments. For example, the first threshold can be any one of the values 0.65, 0.66, 0.67, 0.68, 0.69, 0.70, 0.71, 0.72, 0.73, 0.74, and 0.75, or any value between two adjacent above-mentioned values.

[0105] It should be clear that the method proposed in the embodiments of the present application is described with the elderly user group, but it does not mean that the method proposed in the embodiments of the present application is only applicable to the elderly user group, and it is also applicable to other user groups with regular living patterns. For example, student user groups or office white-collar user groups, etc.

[0106] It should be clear that in the embodiments of the intelligent elderly care health data collection method proposed in this application, the trend of the user's out-of-range data changes and the synchronization of the changes in other users' data of the same type are analyzed and compared. Compared with the previous method of simply judging the user's physical health status based on the out-of-range changes of one-dimensional data, this determination method is more accurate. It can avoid misjudgments caused by the changes in physiological data brought about by the user's physiological activities, improve the accuracy of data judgment, and combine with other data to make the integrity of the data stronger.

[0107] After introducing the embodiments of the intelligent elderly care health data collection method proposed in this application, the following introduces a humanoid elderly care robot proposed in this application, as Figure 2 shown. The humanoid elderly care robot 10 includes:

[0108] An acquisition module 11 for acquiring the user's physiological data;

[0109] A processing module 12 for obtaining the user's current physiological change data based on the user's physiological data;

[0110] And, based on the second physiological change data, performing time series clustering on the user's current physiological change data to obtain clustering clusters;

[0111] And, based on the clustering clusters, obtaining similarity evaluation data of the first physiological change data;

[0112] And, based on the similarity evaluation data, judging the abnormal condition of the user's physiological data.

[0113] As a specific embodiment in this application, the acquisition module 11 is used to receive the physiological data of the user collected by the physiological data collection device at preset time intervals.

[0114] As a specific embodiment in this application, the user's current physiological change data includes the change curve of the user's physiological data based on time series or the change trend of the user's physiological data based on time series.

[0115] As a specific embodiment in this application, the processing module 12 is further used to construct a space model and obtain the space change rate of the second physiological change data in the space model based on the second physiological change data;

[0116] And, based on the space change rate, clustering the user's physiological data to obtain clustering clusters.

[0117] As a specific embodiment in this application, the processing module 12 is further used to obtain the space change rate of the second physiological change data in the space model based on the following formula:

[0118]

[0119] Among them, represents the spatial change rate of the data point corresponding to the second physiological change data in the spatial model; represents the th data value of the data point at the th th moment in the th dimension, represents the th moment in the time series; represents that there are dimensions in the spatial model, respectively represent the extreme points closest to the th moment in the time series.

[0120] As a specific embodiment of the present application, the processing module 12 is further configured to obtain a first clustering density based on the clustering cluster; the first clustering density is the clustering density of the first physiological change data of the user;

[0121] and, obtain a second clustering density based on the clustering cluster; the second clustering density is the average of the clustering densities of the first physiological change data of all users in the clustering cluster;

[0122] and, obtain similarity evaluation data of the first physiological change data based on the first clustering density and the second clustering density.

[0123] As a specific embodiment of the present application, the processing module 12 is further configured to obtain similarity evaluation data of the first physiological change data based on the following formula:

[0124]

[0125] Among them, is the similarity evaluation data of the first physiological change data of the user; represents the spatial change rate of the second physiological change data of the user in the spatial model; represents the cluster density of the physiological data of the user at the th moment; represents the cluster density of the physiological data of the user at the th moment; represents a sliding window with a size of on the time change curve; Represents the cluster density of user x's physiological data in the cluster at the The cluster density of user x's physiological data in the cluster at the represents the number of users in the cluster; represents the first clustering density; represents the second clustering density; represents the sigmoid function that maps the data to the interval (0, 1).

[0126] As a specific embodiment in this application, the processing module 12 is further configured to determine that the user's physiological data is abnormal if the similarity evaluation data of the first physiological change data is greater than the first threshold;

[0127] If the similarity evaluation data of the first physiological change data is less than or equal to the first threshold, it is determined that the user's physiological data is normal.

[0128] It should be clear that the embodiment of the humanoid elderly care robot proposed in this application compares by analyzing the trend of the user's out-of-range data change and the synchronization of the data changes of other users of the same type. Compared with the previous method of simply judging the user's physical health status from the out-of-range change of one-dimensional data, this determination method is more accurate. It can avoid misjudgment caused by the change of physiological data brought by the user's physiological activities, improve the accuracy of data judgment, and combine with other data to make the integrity of the data stronger.

[0129] After introducing the embodiment of the humanoid elderly care robot proposed in this application, the following introduces a computer-readable storage medium proposed in this application. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the intelligent elderly care health data acquisition method described in any one of the above embodiments.

[0130] It should be clear that the computer-readable storage medium in this application includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory, or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassette tapes, magnetic tape magnetic disk storage, or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media do not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0131] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0132] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the methods, devices, and equipment described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0133] In several embodiments provided by the embodiments of this application, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or modules can be in electrical, mechanical, or other forms.

[0134] The modules described as separate components may or may not be physically separated. The components displayed as modules may or may not be physical modules, that is, they can be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0135] In addition, in each embodiment of this application, each functional module can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0136] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product.

[0137] The computer program product includes one or more computer instructions. When the computer program is loaded and executed on a computer, it generates in whole or in part the processes or functions described in the embodiments of this application. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid-state disk (SSD)).

[0138] Although the embodiments of this application have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principle and spirit of this application. The scope of this application is defined by the appended claims and their equivalents.

Claims

1. A method for collecting intelligent elderly care health data, characterized in that, Including: Obtain the physiological data of the user; Based on the physiological data of the user, obtain the current physiological change data of the user; The current physiological change data includes first physiological change data and second physiological change data; The first physiological change data is any data in which the current physiological change data undergoes an out-of-range change; The second physiological change data is all data in the current physiological change data except the first physiological change data; Based on the second physiological change data, perform time series clustering on the current physiological change data of the user to obtain clustering clusters; Based on the clustering clusters, obtain similarity evaluation data for the first physiological change data; Based on the similarity evaluation data, determine the abnormal condition of the user's physiological data; The performing time series clustering on the current physiological change data of the user based on the second physiological change data to obtain clustering clusters includes: Construct a spatial model, and based on the second physiological change data, obtain the spatial change rate of the second physiological change data in the spatial model. The calculation formula is as follows: Among them, represents the spatial change rate of the data point corresponding to the second physiological change data in the spatial model; represents the value of the data point at the th moment in the th dimension, represents the value of the data point at the th moment in the th dimension, represents the th moment in the time series, represents the number of dimensions in this spatial model, respectively represent the extreme points closest to the th moment in the time series; Based on the spatial change rate, perform clustering on the physiological data of the user to obtain clustering clusters.

2. The intelligent elderly care health data collection method according to claim 1, characterized in that The method is applied to a physiological data collection device and a humanoid elderly care robot. The physiological data collection device includes a smart bracelet; The obtaining the physiological data of the user includes: Based on the physiological data collection device, collect the physiological data of the user at a preset time interval; Transmit the physiological data of the user to the humanoid elderly care robot so that the humanoid elderly care robot can obtain the physiological data of the user.

3. The intelligent elderly care health data collection method according to claim 1, wherein, The current physiological change data of the user includes the change curve of the user's physiological data based on time series or the change trend of the user's physiological data based on time series.

4. The intelligent elderly care health data collection method according to claim 1, characterized in that The obtaining the similarity evaluation data for the first physiological change data based on the clustering clusters includes: Based on the clustering clusters, obtain a first clustering density; the first clustering density is the clustering density of the first physiological change data of the user; Based on the clustering clusters, obtain a second clustering density; the second clustering density is the average of the clustering densities of the first physiological change data of all users in the clustering clusters; Based on the first clustering density and the second clustering density, obtain the similarity evaluation data for the first physiological change data.

5. The intelligent elderly care health data collection method according to claim 4, wherein The calculation formula for obtaining the similarity evaluation data for the first physiological change data based on the first clustering density and the second clustering density is as follows: Among them, is the similarity evaluation data of the user's first physiological change data; represents the spatial change rate of the user's second physiological change data in the spatial model; represents the cluster density of the user's physiological data at the th moment; cluster density of the user's physiological data at the th moment; represents a sliding window of size on the time change curve; represents the cluster density of the physiological data of user x in the cluster at the th moment, cluster density of the physiological data of user x in the cluster at the th moment, represents the number of users in the cluster; represents the first cluster density; represents the sigmoid function that maps the data to the interval (0, 1).

6. The intelligent elderly care health data collection method according to claim 5, wherein, The determining the abnormal condition of the user's physiological data based on the similarity evaluation data includes: If the similarity evaluation data of the first physiological change data is greater than a first threshold, it is determined that the physiological data of the user is abnormal; If the similarity evaluation data of the first physiological change data is less than or equal to the first threshold, it is determined that the physiological data of the user is normal.

7. A humanoid elderly care robot, characterized in that, Including: An obtaining module, configured to obtain the physiological data of the user; A processing module, configured to obtain the current physiological change data of the user based on the physiological data of the user; The current physiological change data includes first physiological change data and second physiological change data; The first physiological change data is any data in which the current physiological change data has a change beyond the range; The second physiological change data is all data in the current physiological change data excluding the first physiological change data; And, based on the second physiological change data, perform time series clustering on the current physiological change data of the user to obtain clustering clusters; And, based on the clustering clusters, obtain similarity evaluation data of the first physiological change data; And, based on the similarity evaluation data, judge the abnormal condition of the user's physiological data.

8. The humanoid elderly care robot according to claim 7, wherein The processing module is further configured to construct a spatial model, and based on the second physiological change data, obtain the spatial change rate of the second physiological change data in the spatial model. The calculation formula is as follows: Among them, represents the spatial change rate of the data point corresponding to the second physiological change data in the spatial model; represents the th data value of the data point at the th dimension at the th moment, represents the th moment in the time series, represents the th moment in the time series; represents that there are dimensions in this spatial model, respectively represent the extreme points closest to the th moment in the time series; And, based on the spatial change rate, perform clustering on the physiological data of the user to obtain clustering clusters.

Images