A method and system for recommending health preservation knowledge for the elderly

Abstract

The present invention relates to the field of health monitoring technology, and specifically to a method and system for recommending health and wellness knowledge for the elderly, comprising: obtaining a final confidence level of heart rate signal data based on the difference between data in a heart rate data sequence of a target frequency, the difference between adjacent elements in a time interval sequence, and the energy distribution of all reference frequencies; obtaining the degree of heart rate abnormality in each group of reference heart rate data sequences based on the difference between the trend distribution of data in each group of reference heart rate data sequences and the heart rate data sequence of the target frequency, the difference between the trend distribution of the heart rate signal data of the elderly and the consumed energy signal data, and the final confidence level of the heart rate signal data; and recommending health and wellness knowledge for the elderly based on the degree of heart rate abnormality in all groups of reference heart rate data sequences. The present invention improves the accuracy of detecting heart rate abnormalities in the elderly and improves the accuracy of recommending health and wellness knowledge for the elderly.

Description

Technical Field

[0001] The present invention relates to the technical field of health monitoring, and in particular to a method and system for recommending health and wellness knowledge to the elderly. Background Art

[0002] Many countries and regions are facing the challenge of an aging society, with the proportion of elderly people continuously increasing. In this context, the health and wellness of the elderly are becoming increasingly prominent. Heart rate is a key indicator of cardiovascular function. An elderly person's heart rate can reflect heart health and efficiency. Abnormal heart rates may indicate heart problems such as arrhythmias and myocardial ischemia. Therefore, by monitoring and analyzing heart rate data for the elderly, we can understand heart rate fluctuations, infer their physical condition and health status, and effectively monitor their health and wellness.

[0003] In the process of detecting abnormal heart rates of the elderly through heart rate monitoring instruments, temperature changes will affect the performance of the sensors in the heart rate monitoring instruments. The sensitivity and stability at different temperatures may change, which will affect the accuracy of the monitoring results and make it impossible to accurately detect abnormal heart rates of the elderly, thereby reducing the accuracy of health and wellness knowledge recommendations for the elderly. Summary of the Invention

[0004] The present invention provides a method and system for recommending health and wellness knowledge for the elderly to solve the existing problems.

[0005] The present invention provides a method and system for recommending health and wellness knowledge to the elderly using the following technical solutions:

[0006] An embodiment of the present invention provides a method for recommending health and wellness knowledge to the elderly, the method comprising the following steps:

[0007] Obtain the heart rate signal data and energy consumption signal data of the elderly;

[0008] Obtain a frequency spectrum corresponding to the heart rate signal data, select a target frequency and several reference frequencies from the frequency spectrum, and obtain a heart rate data sequence and a time interval sequence of the target frequency through the target frequency; obtain an initial confidence level of the heart rate signal data based on the differences between data in the heart rate data sequence of the target frequency and the differences between adjacent elements in the time interval sequence; and correct the initial confidence level of the heart rate signal data based on the energy distribution of all reference frequencies to obtain a final confidence level of the heart rate signal data;

[0009] In the heart rate signal data, data other than the heart rate data sequence of the target frequency is recorded as reference heart rate signal data, and the connected reference heart rate signal data are combined into a reference heart rate data sequence in chronological order to obtain a plurality of groups of reference heart rate data sequences; the degree of heart rate abnormality in each group of reference heart rate data sequences is obtained based on the difference in trend distribution between the data in each group of reference heart rate data sequences and the heart rate data sequence of the target frequency, the difference in trend distribution between the heart rate signal data of the elderly and the energy consumption signal data, and the final confidence level of the heart rate signal data;

[0010] Recommendations on health and wellness knowledge for the elderly are made based on the degree of heart rate abnormality in all groups of reference heart rate data sequences.

[0011] Furthermore, the step of obtaining a frequency spectrum corresponding to the heart rate signal data, selecting a target frequency and several reference frequencies from the frequency spectrum, and obtaining a heart rate data sequence and a time interval sequence of the target frequency through the target frequency includes the following specific steps:

[0012] The heart rate signal data in the time domain is Fourier transformed to obtain a spectrum in the frequency domain, the frequency with the largest energy in the spectrum is recorded as the target frequency, and all frequencies except the target frequency are recorded as reference frequencies;

[0013] Determine a trigonometric function of the target frequency based on the energy of the target frequency in the spectrum, determine all heart rate signal data in the time domain corresponding to the maximum amplitude of the trigonometric function, and sort all the heart rate signal data in chronological order to form a set of sequences, which are recorded as the heart rate data sequence of the target frequency;

[0014] The time intervals corresponding to adjacent data in the heart rate data sequence of the target frequency are grouped into a set of sequences according to the data order in the heart rate data sequence, and recorded as the time interval sequence of the target frequency.

[0015] Furthermore, the initial confidence level of the heart rate signal data is obtained based on the differences between the data in the heart rate data sequence of the target frequency and the differences between adjacent elements in the time interval sequence, including the following specific steps:

[0016] Obtaining an initial confidence level of the heart rate signal data according to the mean of the differences between all data and the mean of all data in the heart rate data sequence of the target frequency and the cumulative sum of the differences between all adjacent elements in the time interval sequence of the target frequency;

[0017] Among them, the mean of the difference between all data in the heart rate data sequence of the target frequency and the mean of all data is negatively correlated with the initial confidence level of the heart rate signal data, and the cumulative sum of the differences between all adjacent elements in the time interval sequence of the target frequency is negatively correlated with the initial confidence level of the heart rate signal data.

[0018] Furthermore, the initial confidence level of the heart rate signal data is corrected according to the energy distribution of all reference frequencies to obtain the final confidence level of the heart rate signal data, including the following specific steps:

[0019] Count the number of all reference frequencies whose energy of the reference frequency before each reference frequency in the spectrum is less than the energy of each reference frequency, and record it as the reverse order number of each reference frequency;

[0020] Correcting the initial confidence level of the heart rate signal data by accumulating the reverse order numbers of all reference frequencies to obtain the final confidence level of the heart rate signal data;

[0021] The cumulative sum of the reverse order numbers of all reference frequencies is negatively correlated with the final confidence level of the heart rate signal data.

[0022] Furthermore, the method of obtaining the degree of heart rate abnormality in each set of reference heart rate data sequences based on the difference in trend distribution between the data in each set of reference heart rate data sequences and the heart rate data sequences of the target frequency, the difference in trend distribution between the heart rate signal data of the elderly and the consumed energy signal data, and the final confidence level of the heart rate signal data includes the following specific steps:

[0023] Obtaining the heart rate abnormality factor in each set of reference heart rate data sequences based on the difference between the trend distribution of the data in each set of reference heart rate data sequences and the heart rate data sequences of the target frequency and the final confidence level of the heart rate signal data;

[0024] According to the difference in trend distribution between the elderly's heart rate signal data and the consumed energy signal data and the heart rate abnormality factor in each set of reference heart rate data sequences, the degree of heart rate abnormality in each set of reference heart rate data sequences is obtained.

[0025] Furthermore, the method of obtaining the heart rate abnormality factor in each set of reference heart rate data sequences based on the difference between the trend distribution of the data in each set of reference heart rate data sequences and the heart rate data sequences of the target frequency and the final confidence level of the heart rate signal data includes the following specific steps:

[0026] All data in each set of reference heart rate data sequence are curve-fitted using a quintic polynomial using the least squares method to obtain each set of reference heart rate curves and all extreme points on each set of reference heart rate curves are obtained; similarly, curve-fitting is performed on the target frequency heart rate data sequence to obtain all extreme points on the curve corresponding to the target frequency heart rate data sequence;

[0027] Obtaining the heart rate abnormality factor in each set of reference heart rate data sequences based on the difference between the distances between adjacent extreme value points on the curve corresponding to each set of reference heart rate data sequences and the mean value of the distances between all adjacent extreme value points on the curve corresponding to the target frequency heart rate data sequences, and the final confidence level of the heart rate signal data;

[0028] Among them, the difference between the distance between adjacent extreme points on the curve corresponding to each group of reference heart rate data sequence and the mean of the distance between all adjacent extreme points on the curve corresponding to the heart rate data sequence of the target frequency is positively correlated with the heart rate abnormality factor, and the final confidence level of the heart rate signal data is negatively correlated with the heart rate abnormality factor.

[0029] Furthermore, the method of obtaining the degree of heart rate abnormality in each set of reference heart rate data sequences based on the difference in trend distribution between the elderly person's heart rate signal data and the consumed energy signal data and the heart rate abnormality factor in each set of reference heart rate data sequences includes the following specific steps:

[0030] Sorting the heart rate signal data and energy signal data of the elderly in chronological order to obtain a heart rate signal data sequence and an energy signal data sequence of the elderly;

[0031] According to the correlation coefficient between the heart rate signal data sequence and the energy signal data sequence of the elderly and the heart rate abnormality factor in each set of reference heart rate data sequence, the degree of heart rate abnormality in each set of reference heart rate data sequence is obtained;

[0032] Among them, the correlation coefficient between the elderly's heart rate signal data sequence and the energy signal data sequence is negatively correlated with the degree of heart rate abnormality in each set of reference heart rate data sequence, and the heart rate abnormality factor in each set of reference heart rate data sequence is positively correlated with the degree of heart rate abnormality in each set of reference heart rate data sequence.

[0033] Furthermore, the method of recommending health and wellness knowledge for the elderly based on the degree of heart rate abnormality in all groups of reference heart rate data sequences includes the following specific steps:

[0034] Obtain the health index factor of the elderly according to the degree of heart rate abnormality in all groups of reference heart rate data series;

[0035] When the elderly's health index factor is greater than the preset threshold When the health index factor of the elderly is less than or equal to the preset threshold, no health knowledge will be recommended to the elderly. When the elderly are ill, it is necessary to recommend health and wellness knowledge to them.

[0036] Furthermore, the step of obtaining the health index factor of the elderly based on the degree of heart rate abnormality in all groups of reference heart rate data sequences includes the following specific steps:

[0037] The ratio of the number of all data in each group of reference heart rate data sequence to the number of all data in the heart rate signal data sequence of the elderly is recorded as the first number ratio of each group. The product of the first number ratio of each group and the degree of heart rate abnormality in each group of reference heart rate data sequence is recorded as the first value of each group. The cumulative sum of the first values of all groups is recorded as the second value. The second value is negatively correlated and normalized to obtain the health index factor of the elderly.

[0038] The present invention also provides a system for recommending health and wellness knowledge for the elderly, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the system implements the steps of any one of the above-mentioned methods for recommending health and wellness knowledge for the elderly.

[0039] The beneficial effects of the technical solution of the present invention are: the present invention obtains the initial confidence level of the heart rate signal data based on the difference between the data in the heart rate data sequence of the target frequency and the difference between the adjacent elements in the time interval sequence; corrects the initial confidence level of the heart rate signal data according to the energy distribution of all reference frequencies to obtain the final confidence level of the heart rate signal data; determines the degree of interference when collecting the heart rate signal data of the elderly through the final confidence level of the heart rate signal data; obtains the degree of heart rate abnormality in each group of reference heart rate data sequences based on the difference between the trend distribution of data in each group of reference heart rate data sequences and the heart rate data sequence of the target frequency, the difference in the trend distribution between the heart rate signal data of the elderly and the consumed energy signal data, and the final confidence level of the heart rate signal data, and the abnormal heart rate of the elderly can be accurately detected through the abnormal heart rate in each group of reference heart rate data sequences; recommends health and wellness knowledge for the elderly through the abnormal heart rate in all groups of reference heart rate data sequences, thereby improving the accuracy of the recommendation of health and wellness knowledge for the elderly. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1 This is a flowchart of the steps of a method for recommending health and wellness knowledge to the elderly according to the present invention;

[0042] Figure 2 Recommended flow chart for health and wellness knowledge for the elderly. DETAILED DESCRIPTION

[0043] To further illustrate the technical means and effects employed by the present invention to achieve the intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail a method and system for recommending health and wellness knowledge for the elderly, including its specific implementation, structure, features, and effects. In the following description, references to different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0044] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0045] The following describes in detail a method and system for recommending health and wellness knowledge to the elderly provided by the present invention with reference to the accompanying drawings.

[0046] See also Figure 1 , which shows a flowchart of a method for recommending health and wellness knowledge for the elderly provided by one embodiment of the present invention, the method comprising the following steps:

[0047] Step S001: Collect the heart rate signal data and energy consumption signal data of the elderly.

[0048] It should be noted that in order to improve the health of the elderly, it is necessary to recommend and publicize health care knowledge to the elderly. However, some methods of health care are known to some elderly people, but some elderly people do not know. Therefore, it is necessary to publicize through health tests of the elderly. When the health status of the elderly is not very good, it is even more necessary to publicize and recommend health care methods. Therefore, it is necessary to first collect the physical data of the elderly and recommend health care knowledge based on the normal and abnormal data.

[0049] Specifically, at a time interval of 1 second, a heart rate monitoring device is used to collect the heart rate signal data and exercise energy consumption signal data of the elderly within one week.

[0050] At this point, the heart rate signal data and energy signal data of the elderly are obtained.

[0051] Step S002: Obtain a frequency spectrum corresponding to the heart rate signal data, select a target frequency and several reference frequencies from the frequency spectrum, and obtain a heart rate data sequence and a time interval sequence of the target frequency through the target frequency; obtain an initial confidence level of the heart rate signal data based on the differences between data in the heart rate data sequence of the target frequency and the differences between adjacent elements in the time interval sequence; correct the initial confidence level of the heart rate signal data based on the energy distribution of all reference frequencies to obtain a final confidence level of the heart rate signal data.

[0052] It should be noted that due to the different temperatures in the environment at different times, the degree of interference to the heart rate monitoring instrument is different. However, due to a certain periodicity in the acquisition process, that is, there is a periodic pattern of one day, the heart rate data and energy data at the same time in different cycles have certain similarities. Therefore, by converting the heart rate signal data and energy signal data in the time domain into a spectrum in the frequency domain, the heart rate data of the elderly are analyzed and detected for abnormalities through the periodicity of the spectrum in the frequency domain.

[0053] It's important to note that for periodic signals, if there are distinct peaks in the spectrum, this indicates that the signal may exhibit periodic variations at the frequencies corresponding to these peaks. Therefore, by assigning the maximum amplitude of the frequencies corresponding to these peaks to data points in the time domain, we can analyze whether the data in the time domain exhibits periodicity.

[0054] Specifically, the heart rate signal data in the time domain is Fourier transformed to obtain a frequency spectrogram in the frequency domain. The frequency with the highest energy in the frequency spectrogram is recorded as the target frequency, and all frequencies other than the target frequency are recorded as reference frequencies. The abscissa of the frequency spectrogram is frequency, and the ordinate is energy. The Fourier transform is a well-known technique and will not be described in detail here.

[0055] The trigonometric function of the target frequency is determined based on the energy of the target frequency in the spectrum diagram, and the maximum amplitude of the trigonometric function is determined to correspond to all the heart rate signal data in the time domain. All the heart rate signal data are sorted in chronological order to form a set of sequences, which are recorded as the heart rate data sequence of the target frequency.

[0056] It should be noted that when the difference between the data in the heart rate data sequence of the target frequency is small, and there is a similar time interval between the times corresponding to the data in the heart rate data sequence of the target frequency, the initial confidence level of the heart rate signal data can be obtained by the difference between the data in the heart rate data sequence of the target frequency and the difference between the time intervals between the corresponding times.

[0057] Specifically, the time intervals corresponding to adjacent data in the heart rate data sequence of the target frequency are grouped into a set of sequences according to the order of the data in the heart rate data sequence, and recorded as the time interval sequence of the target frequency.

[0058] As an embodiment, the specific calculation method of the initial confidence level of the heart rate signal data is: according to the mean of the differences between all data and the mean of all data in the heart rate data sequence of the target frequency, and the cumulative sum of the differences between all adjacent elements in the time interval sequence of the target frequency, the initial confidence level of the heart rate signal data is obtained; wherein, the mean of the differences between all data and the mean of all data in the heart rate data sequence of the target frequency is negatively correlated with the initial confidence level of the heart rate signal data, and the cumulative sum of the differences between all adjacent elements in the time interval sequence of the target frequency is negatively correlated with the initial confidence level of the heart rate signal data.

[0059] In one embodiment of the present invention, it is specifically expressed by the formula:

[0060]

[0061] Where, The first data, Represents the mean of all data in the heart rate data sequence of the target frequency, Indicates the number of all data in the heart rate data sequence of the target frequency, The number of all elements in the time interval sequence representing the target frequency, is the absolute value symbol, The first time interval in the time interval sequence representing the target frequency elements, The first time interval in the time interval sequence representing the target frequency elements, Indicates the initial confidence level of the heart rate signal data, represents an exponential function with a natural constant as the base. Information entropy is a well-known technology and will not be described in detail here.

[0062] in, The difference between the data in the heart rate data sequence of the target frequency is represented. When the difference is smaller, it means that the elderly person's heart rate signal data is less interfered with, that is, the initial confidence level of the heart rate signal data is greater; when the difference is larger, it means that the elderly person's heart rate signal data is more interfered with, that is, the initial confidence level of the heart rate signal data is smaller. The difference in the time intervals between the times corresponding to adjacent data in the heart rate data sequence of the target frequency is represented. The smaller the difference, the less interference the elderly person's heart rate signal data is subject to, and the greater the initial confidence level of the heart rate signal data; conversely, the greater the interference the elderly person's heart rate signal data is subject to, and the smaller the initial confidence level of the heart rate signal data.

[0063] At this point, the initial confidence level of the heart rate signal data is obtained.

[0064] It should be noted that, in general, the energy of frequencies in a spectrum decreases as the frequency increases. Therefore, the degree of interference in the heart rate signal data can be analyzed by analyzing the energy levels of all reference frequencies before each reference frequency.

[0065] Specifically, the number of all reference frequencies whose energy before each reference frequency in the spectrum diagram is less than the energy of each reference frequency is recorded as the reverse number of each reference frequency; the initial confidence level of the heart rate signal data is corrected according to the reverse number of all reference frequencies to obtain the final confidence level of the heart rate signal data.

[0066] As an embodiment, the specific calculation method of the final confidence level of the heart rate signal data is: correcting the initial confidence level of the heart rate signal data by adding up the number of inverses of all reference frequencies to obtain the final confidence level of the heart rate signal data; wherein, the sum of the number of inverses of all reference frequencies is negatively correlated with the final confidence level of the heart rate signal data.

[0067] In one embodiment of the present invention, it is specifically expressed by the formula:

[0068]

[0069] Where, Indicates the The number of inverse order of reference frequencies, Indicates the number of all reference frequencies, Indicates the initial confidence level of the heart rate signal data, represents an exponential function with a natural constant as the base, Indicates the final confidence level of the heart rate signal data.

[0070] in, It represents the cumulative sum of the reverse numbers of all reference frequencies. The larger the cumulative sum is, the less the energy change of the reference frequency decreases with the increase of frequency. Therefore, the greater the interference received during the collection of heart rate signal data, that is, the lower the final confidence level of the heart rate signal data; conversely, the smaller the interference received during the collection of heart rate signal data, that is, the greater the final confidence level of the heart rate signal data.

[0071] At this point, the final confidence level of the heart rate signal data is obtained.

[0072] Step S003: In the heart rate signal data, data other than the heart rate data sequence of the target frequency is recorded as reference heart rate signal data, and the connected reference heart rate signal data are arranged in chronological order to form a reference heart rate data sequence to obtain several groups of reference heart rate data sequences; the degree of heart rate abnormality in each group of reference heart rate data sequences is obtained based on the difference between the trend distribution of data in each group of reference heart rate data sequences and the heart rate data sequence of the target frequency, the difference in the trend distribution between the heart rate signal data of the elderly and the consumed energy signal data, and the final confidence level of the heart rate signal data.

[0073] It should be noted that the greater the difference between the data distribution trend in the heart rate data sequence of the target frequency and the distribution trends of other continuous heart rate data, the greater the possibility that the heart rate data is abnormal; the smaller the difference between the data distribution trend in the heart rate data sequence of the target frequency and the distribution trends of other continuous heart rate data, the smaller the possibility that the heart rate data is abnormal.

[0074] Specifically, the data in the heart rate signal data, excluding the heart rate data sequence at the target frequency, is recorded as reference heart rate signal data. The connected reference heart rate signal data are then grouped into a sequence in chronological order, which is recorded as a reference heart rate data sequence. Thus, several groups of reference heart rate data sequences are obtained. Therefore, the heart rate abnormality factor in each reference heart rate data sequence is determined based on the difference in data trend distribution between each reference heart rate data sequence and the heart rate data sequence at the target frequency, as well as the final confidence level of the heart rate signal data.

[0075] All data in each set of reference heart rate data sequences are curve-fitted using a quintic polynomial using the least squares method to obtain each set of reference heart rate curves. All extreme points on each set of reference heart rate curves are obtained, where extreme points include maximum and minimum points. The least squares method is a well-known technique and will not be described in detail here.

[0076] Similarly, curve fitting is performed on the heart rate data sequence of the target frequency to obtain all extreme value points on the curve corresponding to the heart rate data sequence of the target frequency.

[0077] As an embodiment, the specific calculation method of the heart rate abnormality factor in each set of reference heart rate data sequences is as follows: the heart rate abnormality factor in each set of reference heart rate data sequences is obtained based on the difference between the distance between adjacent extreme value points on the curve corresponding to each set of reference heart rate data sequences and the mean of the distance between all adjacent extreme value points on the curve corresponding to the heart rate data sequence of the target frequency, and the final confidence level of the heart rate signal data; wherein, the difference between the distance between adjacent extreme value points on the curve corresponding to each set of reference heart rate data sequences and the mean of the distance between all adjacent extreme value points on the curve corresponding to the heart rate data sequence of the target frequency is positively correlated with the heart rate abnormality factor, and the final confidence level of the heart rate signal data is negatively correlated with the heart rate abnormality factor. In this embodiment, all distances are Euclidean distances.

[0078] In one embodiment of the present invention, it is specifically expressed by the formula:

[0079]

[0080] Where, Indicates the The first The extreme point and The distance between extreme points, Indicates the The number of all extreme points in the group reference heart rate data series, The mean of the distances between all adjacent extreme points in the heart rate data sequence representing the target frequency, is the absolute value symbol, represents the linear normalization function, Indicates the final confidence level of the heart rate signal data, Indicates the Heart rate abnormality factor in a group of reference heart rate data series.

[0081] in, This represents the difference between the distances between adjacent extreme points in each reference heart rate data sequence and the mean distance between all adjacent extreme points in the target frequency heart rate data sequence. A smaller difference indicates a smaller difference in the target frequency heart rate data sequence with respect to the periodicity, indicating that the reference heart rate data sequence also exhibits periodicity, and the likelihood of an anomaly is lower. Conversely, a lower difference indicates a higher likelihood of an anomaly. A higher final confidence level for the heart rate signal data indicates a lower likelihood of an anomaly; a lower final confidence level for the heart rate signal data indicates a higher likelihood of an anomaly.

[0082] At this point, the heart rate abnormality factor in each set of reference heart rate data sequence is obtained.

[0083] It should be noted that when an elderly person's heart rate increases, it indicates that the elderly person may be walking or exercising, and at this time, the elderly person will definitely consume energy. Therefore, the trend of heart rate changes and the trend of energy consumption of the elderly person must be the same. Therefore, the degree of abnormality in the elderly person's heart rate signal data is analyzed by the trend changes between the elderly person's heart rate signal data and the energy signal data. Therefore, based on the difference in the trend distribution between the elderly person's heart rate signal data and the energy consumption signal data, and the heart rate abnormality factor in each set of reference heart rate data series, the degree of heart rate abnormality in each set of reference heart rate data series is obtained.

[0084] Specifically, the heart rate signal data and energy signal data of the elderly are sorted in chronological order to obtain the heart rate signal data sequence and energy signal data sequence of the elderly.

[0085] The correlation coefficient between the heart rate signal data sequence and the energy signal data sequence of the elderly is calculated. The correlation coefficient between the two sequences is obtained by calculating the Pearson correlation coefficient, which is a well-known technology and will not be described in detail here.

[0086] As an embodiment, the specific calculation method for the degree of heart rate abnormality in each group of reference heart rate data sequences is as follows: based on the correlation coefficient between the elderly person's heart rate signal data sequence and the energy signal data sequence, and the heart rate abnormality factor in each group of reference heart rate data sequences, the degree of heart rate abnormality in each group of reference heart rate data sequences is obtained; wherein, the correlation coefficient between the elderly person's heart rate signal data sequence and the energy signal data sequence is negatively correlated with the degree of heart rate abnormality in each group of reference heart rate data sequences, and the heart rate abnormality factor in each group of reference heart rate data sequences is positively correlated with the degree of heart rate abnormality in each group of reference heart rate data sequences.

[0087] In one embodiment of the present invention, it is specifically expressed by the formula:

[0088]

[0089] Where, Indicates the The heart rate abnormality factor in the group reference heart rate data series, Represents the correlation coefficient between the heart rate signal data sequence and the energy signal data sequence of the elderly, Indicates the The degree of heart rate abnormality in the group reference heart rate data series, Represents an exponential function with a natural constant as its base.

[0090] The larger the correlation coefficient between the elderly person's heart rate signal data sequence and the energy signal data sequence, the smaller the likelihood of an abnormality; conversely, the greater the likelihood of an abnormality. The smaller the heart rate abnormality factor in each set of reference heart rate data sequences, the smaller the degree of heart rate abnormality in each set of reference heart rate data sequences; conversely, the greater the degree of heart rate abnormality in each set of reference heart rate data sequences.

[0091] At this point, the degree of heart rate abnormality in each set of reference heart rate data sequences is obtained.

[0092] Step S004: recommending health and wellness knowledge for the elderly based on the degree of heart rate abnormality in all groups of reference heart rate data sequences.

[0093] It should be noted that, when the degree of heart rate abnormality in all groups of reference heart rate data sequences is greater, it means that the elderly's health status is not very good, that is, the elderly lack health and wellness knowledge in their daily life, and at this time it is necessary to recommend health and wellness knowledge to the elderly; when the degree of heart rate abnormality in all groups of reference heart rate data sequences is smaller, it means that the elderly's health status is better, that is, the elderly know more about health and wellness knowledge in their daily life, and at this time there is no need to recommend health and wellness knowledge to the elderly.

[0094] Specifically, the health index factor of the elderly is obtained according to the degree of heart rate abnormality in each set of reference heart rate data sequences and the number of data in each set of reference heart rate data sequences.

[0095] As an example, the specific calculation method of the health index factor of the elderly is as follows:

[0096] The ratio of the number of all data in each group of reference heart rate data sequence to the number of all data in the heart rate signal data sequence of the elderly is recorded as the first number ratio of each group. The product of the first number ratio of each group and the degree of heart rate abnormality in each group of reference heart rate data sequence is recorded as the first value of each group. The cumulative sum of the first values of all groups is recorded as the second value. The second value is negatively correlated and normalized to obtain the health index factor of the elderly.

[0097] In one embodiment of the present invention, it is specifically expressed by the formula:

[0098]

[0099] Where, Indicates the The degree of heart rate abnormality in the group reference heart rate data series, Indicates the number of all data in the elderly’s heart rate signal data sequence, Indicates the The number of all data in the group reference heart rate data sequence, Represents the total number of reference heart rate data sequences of all groups, represents an exponential function with a natural constant as the base, Represents the health indicator factor of the elderly.

[0100] Among them, when the degree of heart rate abnormality in each set of reference heart rate data sequence is greater, it means that the elderly person's health status is not very good, that is, the elderly person lacks health and wellness knowledge in daily life, and at this time it is necessary to recommend health and wellness knowledge to the elderly; when the degree of heart rate abnormality in each set of reference heart rate data sequence is smaller, it means that the elderly person's health status is better, that is, the elderly person knows more about health and wellness knowledge in daily life, and at this time there is no need to recommend health and wellness knowledge to the elderly. middle As The weight of , when the number of data in each set of reference heart rate data sequence is more, The greater the weight.

[0101] At this point, the health index factors of the elderly are obtained.

[0102] Preset a threshold , wherein this embodiment is based on This example is described as an example, and this embodiment is not specifically limited. It may depend on the specific implementation situation.

[0103] When the elderly's health index factor is greater than the preset threshold When the health index factor of the elderly is less than or equal to the preset threshold, health and wellness knowledge needs to be recommended to the elderly.

[0104] Among them, the recommended flow chart of health and wellness knowledge for the elderly is as follows Figure 2 shown.

[0105] It should be noted that the The model is only used to represent negative correlation and constrain the output of the model to be in In the specific implementation, it can be replaced by other models with the same purpose. This embodiment is only based on The model is described as an example without any specific limitation. is the input to the model.

[0106] This embodiment provides a health and wellness knowledge recommendation system for the elderly, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, a health and wellness knowledge recommendation method for the elderly in steps S001 to S004 is implemented.

[0107] At this point, this embodiment is completed.

[0108] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for recommending health and wellness knowledge for the elderly, characterized in that: The method comprises the following steps: Obtain the heart rate signal data and energy consumption signal data of the elderly; The heart rate signal data in the time domain is Fourier transformed to obtain a frequency spectrum in the frequency domain, the frequency with the largest energy in the frequency spectrum is recorded as the target frequency, and all frequencies except the target frequency are recorded as reference frequencies. The trigonometric function of the target frequency is determined based on the energy of the target frequency in the frequency spectrum, and all heart rate signal data in the time domain corresponding to the maximum amplitude of the trigonometric function are determined. All heart rate signal data are sorted in chronological order to form a set of sequences, which are recorded as the heart rate data sequence of the target frequency; the time intervals corresponding to adjacent data in the heart rate data sequence of the target frequency are sorted into a set of sequences according to the order of the data in the heart rate data sequence, which are recorded as the time interval sequence of the target frequency; the initial confidence level of the heart rate signal data is obtained based on the difference between the data in the heart rate data sequence of the target frequency and the difference between adjacent elements in the time interval sequence; the initial confidence level of the heart rate signal data is corrected based on the energy distribution of all reference frequencies to obtain the final confidence level of the heart rate signal data; wherein the final confidence level is expressed by the formula: Where, Indicates the The reverse order number of the reference frequencies is the number of all reference frequencies whose energy before each reference frequency in the statistical spectrum is less than the energy of each reference frequency. Indicates the number of all reference frequencies, represents an exponential function with a natural constant as the base, Indicates the final confidence level of the heart rate signal data, It represents the initial confidence level of the heart rate signal data. The initial confidence level is expressed as follows: Where, The first data, Represents the mean of all data in the heart rate data sequence of the target frequency, Indicates the number of all data in the heart rate data sequence of the target frequency, The number of all elements in the time interval sequence representing the target frequency, is the absolute value symbol, The first time interval in the time interval sequence representing the target frequency elements, The first time interval in the time interval sequence representing the target frequency elements, represents an exponential function with a natural constant as its base; In the heart rate signal data, data other than the heart rate data sequence of the target frequency is recorded as reference heart rate signal data, and the connected reference heart rate signal data are arranged in chronological order to form a reference heart rate data sequence to obtain several groups of reference heart rate data sequences; based on the difference between the trend distribution of data in each group of reference heart rate data sequences and the heart rate data sequence of the target frequency, and the final confidence level of the heart rate signal data, the heart rate abnormality factor in each group of reference heart rate data sequences is obtained; the heart rate signal data and energy signal data of the elderly are sorted in chronological order to obtain the heart rate signal data sequence and energy signal data sequence of the elderly; based on the correlation coefficient between the heart rate signal data sequence and the energy signal data sequence of the elderly and the heart rate abnormality factor in each group of reference heart rate data sequences, the heart rate abnormality degree in each group of reference heart rate data sequences is obtained; wherein, the correlation coefficient between the heart rate signal data sequence and the energy signal data sequence of the elderly is negatively correlated with the heart rate abnormality degree in each group of reference heart rate data sequences, and the heart rate abnormality factor in each group of reference heart rate data sequences is positively correlated with the heart rate abnormality degree in each group of reference heart rate data sequences; Obtain the health index factor of the elderly according to the degree of heart rate abnormality in all groups of reference heart rate data series; When the health index factor of the elderly is greater than the preset threshold δ, no health and wellness knowledge will be recommended to the elderly; when the health index factor of the elderly is less than or equal to the preset threshold δ, health and wellness knowledge will be recommended to the elderly.

2. A method for recommending health and wellness knowledge for the elderly according to claim 1, characterized in that: The method of obtaining the heart rate abnormality factor in each set of reference heart rate data sequences based on the difference between the trend distribution of the data in each set of reference heart rate data sequences and the heart rate data sequences of the target frequency and the final confidence level of the heart rate signal data includes the following specific steps: All data in each set of reference heart rate data sequence are curve-fitted using a quintic polynomial using the least squares method to obtain each set of reference heart rate curves and all extreme points on each set of reference heart rate curves are obtained; similarly, curve-fitting is performed on the target frequency heart rate data sequence to obtain all extreme points on the curve corresponding to the target frequency heart rate data sequence; Obtaining the heart rate abnormality factor in each set of reference heart rate data sequences based on the difference between the distances between adjacent extreme value points on the curve corresponding to each set of reference heart rate data sequences and the mean value of the distances between all adjacent extreme value points on the curve corresponding to the target frequency heart rate data sequences, and the final confidence level of the heart rate signal data; Among them, the difference between the distance between adjacent extreme points on the curve corresponding to each group of reference heart rate data sequence and the mean of the distance between all adjacent extreme points on the curve corresponding to the heart rate data sequence of the target frequency is positively correlated with the heart rate abnormality factor, and the final confidence level of the heart rate signal data is negatively correlated with the heart rate abnormality factor.

3. A method for recommending health and wellness knowledge for the elderly according to claim 1, characterized in that: The specific steps of obtaining the health index factor of the elderly based on the degree of heart rate abnormality in all groups of reference heart rate data sequences are as follows: The ratio of the number of all data in each group of reference heart rate data sequence to the number of all data in the heart rate signal data sequence of the elderly is recorded as the first number ratio of each group. The product of the first number ratio of each group and the degree of heart rate abnormality in each group of reference heart rate data sequence is recorded as the first value of each group. The cumulative sum of the first values of all groups is recorded as the second value. The second value is negatively correlated and normalized to obtain the health index factor of the elderly.

4. A health and wellness knowledge recommendation system for the elderly, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method for recommending health and wellness knowledge for the elderly as described in any one of claims 1 to 3 are implemented.

Images