An information management system based on refined nursing of circadian rhythm

Abstract

The present invention relates to the technical field of health care, and particularly relates to an information management system based on refined nursing of circadian rhythm, including: an acquisition module for acquiring circadian rhythm data; a feature analysis module for determining the circadian rhythm feature index of each measurement and obtaining an initial user group according to the feature fluctuations; a nursing effect analysis module for determining the nursing effect coefficient of the user under the corresponding measurement according to the numerical change of the circadian rhythm feature index of adjacent measurements; and an adjustment module for combining the nursing effect coefficients of the same measurement in the same initial user group to obtain a nursing intervention value, and determining whether to adjust the nursing plan according to the nursing intervention value. This application can effectively improve the reliability of nursing, improve the accuracy and pertinence of the update of the nursing plan, and enhance the nursing effect.

Description

Technical Field

[0001] The present invention relates to the technical field of health care, and particularly to an information management system based on refined care of circadian rhythm. Background Art

[0002] Circadian rhythm is an important reflection of the user's physiological state, including the periodic characteristics of physiological activities such as sleep, body temperature, and heart rate. By analyzing the circadian rhythm, the normal or abnormal state of the user can be identified. Due to the individual differences and specific needs of users, in order to achieve refined care, personalized and precise care plans can be formulated and implemented according to the circadian rhythm of users to optimize their health management and care effects.

[0003] In the related art, an information management system is used to sort out the circadian rhythm information of all users, and the nursing plan is adjusted directly according to whether the value of each circadian information meets the preset standard. In this way, since the circadian rhythm changes over time and there are large variations in the individual differences of different users, the preset standard cannot accurately reflect this characteristic, and the accuracy and pertinence of the update of the nursing plan are poor. Summary of the Invention

[0004] In order to solve the technical problems in the related art that since the circadian rhythm changes over time and there are large variations in the individual differences of different users, the preset standard cannot accurately reflect this characteristic, and the accuracy and pertinence of the update of the nursing plan are poor, the present invention provides an information management system based on refined care of circadian rhythm, and the specific technical solutions adopted are as follows:

[0005] The present invention proposes an information management system based on refined care of circadian rhythm, and the system includes:

[0006] An acquisition module, configured to acquire circadian rhythm data of different users measured at different times, where the circadian rhythm data at least includes sleep, body temperature, and heart rate;

[0007] A feature analysis module, configured to determine the circadian rhythm feature index of each measurement according to the difference between the value of each circadian rhythm data and the ideal value in the same measurement, and form a feature sequence according to the time sequence; determine the initial user group with similar fluctuations of rhythm features according to the fluctuations of the feature sequences of different users in the same time period;

[0008] A nursing effect analysis module, configured to cluster the circadian rhythm feature indexes of all users measured at the same time to determine the target user group with similar circadian rhythm feature indexes; determine the rhythm change value of each measurement based on the numerical change of the circadian rhythm feature indexes of the same user in adjacent measurements; in the same target user group, determine the nursing effect coefficient of the user at the corresponding measurement according to the distribution of the rhythm change values between adjacent measurements of users;

[0009] An adjustment module, configured to determine the initial intervention value of each user according to the care effect coefficients of the same measurement in the same initial user group, and perform intervention update by combining the changes in the initial intervention values of each user in all measurements to obtain the care intervention value, and determine whether to adjust the care plan according to the care intervention value.

[0010] Further, the ideal value is a known preset value, and the ideal values corresponding to different types of circadian rhythm data are different; according to the difference between the value of each item of circadian rhythm data and the ideal value under the same measurement, the circadian rhythm characteristic index of each measurement is determined, including:

[0011] Calculate the absolute value of the difference between the value of each item of circadian rhythm data and the corresponding ideal value, and perform normalization processing as the ideal difference coefficient;

[0012] Take the mean of the ideal difference coefficients of all items of circadian rhythm data as the circadian rhythm characteristic index of each measurement.

[0013] Further, according to the fluctuations of the characteristic sequences of different users in the same time period, the initial user groups with similar circadian rhythm characteristic fluctuations are determined, including:

[0014] Based on the dynamic time warping algorithm, calculate the DTW value of the characteristic sequences of any two users in the same time period, and normalize the negative value of the DTW value as the sequence similarity;

[0015] Perform clustering based on the sequence similarity to obtain different clusters as the initial user groups.

[0016] Further, perform clustering on the circadian rhythm characteristic indexes of all users in the same measurement to determine the target user groups with similar circadian rhythm characteristic indexes, including:

[0017] Perform DBSCAN density clustering on the circadian rhythm characteristic indexes of all users in the same measurement to obtain the target user groups.

[0018] Further, based on the numerical changes of the circadian rhythm characteristic indexes of the same user in adjacent measurements, determine the rhythm change value of each measurement, including:

[0019] Take any measurement of any user as the target measurement; take the other two measurements that are closest in time sequence to the target measurement as the adjacent measurements;

[0020] Based on the least squares method, perform linear fitting on the values of the circadian rhythm characteristic indexes corresponding to the target measurement and the adjacent measurements, and take the slope of the fitting line as the fluctuation trend coefficient of the target measurement;

[0021] The mean of the absolute values of the differences in the circadian rhythm characteristic indicators between the target measurement and each adjacent measurement is used as the target characteristic difference coefficient;

[0022] The product of the fluctuation trend coefficient and the standard characteristic difference coefficient is normalized to obtain the rhythm change value of the target measurement.

[0023] Further, according to the distribution of the rhythm change values of adjacent measurements among users, the nursing effect coefficient of the user at the corresponding measurement is determined. The corresponding calculation formula is:

[0024] ;

[0025] In the formula, represents the nursing effect coefficient of the th user at the th measurement; represents the rhythm change value of the th user at the th measurement; represents the mean of the rhythm change values of all users in the same target user group at the th measurement of the th user; represents the mean of the rhythm change values of all users in the same target user group at the th measurement of the th user. exp represents the exponential function with the natural constant as the base, and sigmoid represents the sigmoid function.

[0026] Further, according to the nursing effect coefficients of the same measurement in the same initial user group, the initial intervention value of each user is determined, including:

[0027] The mean of the nursing effect coefficients of the same measurement in the same initial user group is used as the nursing mean coefficient for the corresponding measurement;

[0028] The absolute value of the difference between the nursing effect coefficient of any user at any measurement and the corresponding nursing mean coefficient is normalized to obtain the mean difference factor;

[0029] The normalized value of the opposite number of the nursing effect coefficient of any user at any measurement is calculated as the effect intervention factor;

[0030] The product of the effect intervention factor and the mean difference factor is normalized as the initial intervention value.

[0031] Further, by combining the changes in the initial intervention values of each user in all measurements, intervention updates are performed to obtain the nursing intervention value, including:

[0032] Take the absolute value of the difference between the initial intervention values of each user in two adjacent measurements as the intervention difference coefficient;

[0033] Calculate the mean value of all intervention differences from the initial moment to the current moment, and linearly map it to the preset adjustment range as the intervention adjustment coefficient, where the initial moment is the moment of the last nursing intervention;

[0034] Take the product of the intervention adjustment coefficient and the initial intervention value as the nursing intervention value.

[0035] Further, the preset adjustment range is [0.5, 1.5].

[0036] Further, determine whether to adjust the nursing plan according to the nursing intervention value, including:

[0037] When the nursing intervention value is greater than the preset intervention threshold, determine to adjust the nursing plan; otherwise, do not adjust the nursing plan.

[0038] The present invention has the following beneficial effects:

[0039] In the embodiment of the present invention, by analyzing the numerical fluctuations of the circadian rhythm data of different users, the circadian rhythm characteristic indexes are determined, and then the initial user groups are obtained by grouping. The initial user groups represent the user groups with similar fluctuations, realizing the characteristic analysis of various types of circadian rhythm data. Then, according to the changes of the circadian rhythm characteristic indexes of different users in time series, the nursing effect is analyzed to obtain the nursing effect coefficient. After that, combining the values of the nursing effect coefficients within the initial user groups, the intervention analysis is carried out to obtain the nursing intervention value, and the nursing plan is adjusted according to the nursing intervention value. This application mainly conducts nursing intervention analysis through the single-user numerical feature dimension, the multi-user numerical feature dimension, the single-user numerical change dimension, and the multi-user numerical change dimension, so that the obtained nursing intervention value can combine the individual state changes and the overall characteristic differences, and is dynamically updated over time, so as to effectively analyze the individual differences of users, make intervention adjustments according to the individual differences and collective changes, and continuously optimize the grouping criteria and the update rules of the nursing plan, thereby realizing the refined nursing of users. In summary, this application can effectively improve the reliability of nursing, improve the accuracy and pertinence of the update of the nursing plan, and enhance the nursing effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0041] Figure 1 The structural diagram of an information management system based on circadian rhythm refined nursing provided by an embodiment of the present invention;

[0042] Figure 2 The schematic diagram of the body temperature fluctuation of a user provided by an embodiment of the present invention. Specific embodiments

[0043] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following combines the drawings and preferred embodiments to specifically describe the specific embodiments, structures, features and effects of an information management system based on circadian rhythm refined nursing proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0044] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0045] The following specifically describes the specific solution of an information management system based on circadian rhythm refined nursing provided by the present invention with reference to the drawings.

[0046] Please refer to Figure 1 , which shows the structural diagram of an information management system based on circadian rhythm refined nursing provided by an embodiment of the present invention, including: an acquisition module 101, a feature analysis module 102, a nursing effect analysis module 103, and an adjustment module 104. The following specifically describes each module:

[0047] The acquisition module 101 is used to acquire circadian rhythm data measured by different users at different times, where the circadian rhythm data at least includes sleep, body temperature, and heart rate.

[0048] Among them, the circadian rhythm refers to the natural change pattern of the physiological and behavioral activities of an organism within a circadian cycle (generally 24 hours), which is regulated by the external environment and the internal biological clock. The circadian rhythm data corresponding to each user will be different due to individual differences. In the embodiments of the present invention, wearable devices (such as smart bracelets and watches) or professional monitoring devices can be used to collect data related to the circadian rhythm. Specifically, the relevant data information of sleep, body temperature, and heart rate can be measured every half hour and integrated into the daily circadian rhythm data, including sleep data, body temperature fluctuations, and heart rate changes, etc.

[0049] In some other embodiments of the present invention, the collected circadian rhythm data can also be preprocessed: cleaning noise, eliminating data deviations caused by equipment errors, and performing standardization processing to unify data from different sources and different scales into comparable standardized indicators, without limitation thereto.

[0050] The feature analysis module 102 is configured to determine the circadian rhythm feature index for each measurement according to the difference between the value of each circadian rhythm data and the ideal value under the same measurement, and form a feature sequence according to the time sequence; determine the initial user group with similar fluctuations in circadian rhythm features according to the fluctuations of the feature sequences of different users within the same time period.

[0051] It can be understood that for users who need care, when there are problems with their health status, it may interfere with the users' circadian rhythm, manifested as abnormal circadian rhythm data, and each data index may deviate from the normal reference value or the ideal range. Refer to Figure 2 , Figure 2 FIG.

[0052] In the embodiments of the present invention, the ideal value is a known preset value, and the ideal values corresponding to different types of circadian rhythm data are different. For example, the ideal value of body temperature data is 36.5 degrees Celsius. Among them, due to differences between different individuals, the ideal value of each individual will also change. For example, the standard sleep time of a 70-year-old user is somewhat different from that of a 30-year-old user. Therefore, for each user for each item of circadian rhythm data, there can be corresponding ideal values. This solution is only used for standardized difference analysis, and no further limitation and elaboration are made thereto.

[0053] Further, in some embodiments of the present invention, determining the circadian rhythm feature index for each measurement according to the difference between the value of each circadian rhythm data and the ideal value includes: calculating the absolute value of the difference between the value of each circadian rhythm data and the corresponding ideal value, and performing normalization processing as the ideal difference coefficient; taking the mean value of the ideal difference coefficients of all items of circadian rhythm data as the circadian rhythm feature index for each measurement, and the corresponding calculation formula can be specifically, for example:

[0054] ;

[0055] In the formula, represents the circadian rhythm feature index in the th measurement of the th user; represents the number of types of circadian rhythm data; Indicates the th user's th measurement of the value of the circadian rhythm data item; Indicates the ideal value (known standard data) of the circadian rhythm data item, Indicates the maximum - minimum normalization process, Indicates taking the absolute value.

[0056] Indicates the th user's th measurement of the gap between the actual measured values and the ideal values of all circadian rhythm data, representing the characteristics of the abnormality of the index value reflected in the circadian rhythm.

[0057] As can be seen from the above formula, Indicates the ideal difference coefficient. The larger the value of the ideal difference coefficient, the greater the difference between the measured value of the current circadian rhythm data and the standard situation, that is, the more obvious the abnormal characteristics. Therefore, the average value of the ideal difference coefficients of all types of circadian rhythm data is used as the circadian rhythm characteristic index for the corresponding measurement.

[0058] Usually, circadian rhythm data is stored in a medical information management system. The medical information management system needs to achieve classified storage, fast retrieval, and sharing of circadian rhythm data information. By grouping and summarizing the care plans of users with similar circadian rhythms, the utilization rate of nursing resources is improved. Circadian rhythm data is dynamically changing, showing a regular or disordered dynamic change process over time. By the consistency of the dynamic change trend of circadian rhythm data, it helps to discover the common patterns of circadian rhythm (such as rhythm changes under specific abnormal states), classify users with similar dynamic changes, and facilitate the unified design of care plans. Through the dynamic change situation of circadian rhythm data, the consistency of the circadian rhythm change patterns of different users is obtained.

[0059] In the embodiments of the present invention, an initial user group is used as a group of users representing similar circadian rhythm fluctuation characteristics. Therefore, it is necessary to determine the initial user group with similar rhythm characteristic fluctuations according to the fluctuations of the characteristic sequences of different users within the same time period.

[0060] Furthermore, in some embodiments of the present invention, based on the dynamic time warping algorithm, the sequence similarity between the characteristic sequences of any two users within the same time period is calculated; clustering is performed based on the sequence similarity to obtain different clusters as the initial user groups.

[0061] Among them, the dynamic time warping algorithm is an algorithm well-known to those skilled in the relevant art. Based on the dynamic time warping algorithm, the DTW value of two time series can be calculated. The smaller the value of the DTW value, the higher the similarity between the two time series. Based on this, sequence similarity analysis is performed, and the negative value of the DTW value is normalized as the sequence similarity.

[0062] In the embodiments of the present invention, the value of the sequence similarity can be limited between [0, 1]. When the sequence similarity is greater than a preset similarity threshold (for example, 0.8), the corresponding two users can be regarded as a cluster. By analyzing all users, cluster division can be achieved, and each cluster is used as an initial user group.

[0063] For users in the same initial user group, the change patterns of their circadian rhythm data are relatively similar and can be analyzed as a type. For example, they are all users with weak constitutions, or all users with insomnia, etc., and classification can be carried out according to the actual situation.

[0064] After determining the initial user group, it is necessary to analyze the nursing effect of each user. For specific details, please refer to the subsequent embodiments.

[0065] The nursing effect analysis module 103 is used to cluster the circadian rhythm characteristic indicators measured by all users at the same time, determine the target user group with similar circadian rhythm characteristic indicators; based on the numerical changes of the circadian rhythm characteristic indicators of the same user in adjacent measurements, determine the rhythm change value of each measurement; in the same target user group, according to the distribution of the rhythm change values between adjacent measurements of users, determine the nursing effect coefficient of users under the corresponding measurement.

[0066] It should be noted that diseases (such as insomnia, diabetes, cardiovascular diseases, etc.) will significantly interfere with the circadian rhythm of users. At the same time, treatment plans (such as drugs, rehabilitation training, etc.) may also regulate or interfere with the circadian rhythm of users. To achieve refined nursing of users and optimize the nursing plan, it is necessary to clarify the impact of diseases on the circadian rhythm, analyze the change trend of rhythm characteristics, and evaluate the impact of nursing on the physiological rhythm of users, so as to analyze and obtain the nursing effect.

[0067] During the process of nursing users, the change rhythm of the circadian rhythm reflects the quality of the current nursing effect. Since the change of the circadian rhythm is dynamic, in different nursing stages, the nursing plans of some users may not be applicable, and their circadian rhythm change rhythm may slow down or stagnate. To more accurately match nursing plans for users, it is necessary to consider the dynamic nursing effect of the circadian rhythm with the change of the nursing plan. Therefore, the circadian rhythm characteristic indicators of all users in each circadian rhythm measurement are clustered.

[0068] Further, in some embodiments of the present invention, the circadian rhythm characteristic indexes measured for all users at the same time are clustered to determine a target user group with similar circadian rhythm characteristic indexes, including: performing DBSCAN density clustering on the circadian rhythm characteristic indexes measured for all users at the same time to obtain the target user group.

[0069] Among them, the target user group represents a clustering group corresponding to the circadian rhythm characteristic indexes obtained based on the same measurement, indicating the similar characteristics under one measurement. DBSCAN density clustering is a clustering algorithm well-known to those skilled in the relevant art, and based on this, the density of numerical values can be clustered, and users with similar circadian rhythm characteristic indexes are grouped into a target user group.

[0070] Based on the numerical change of the circadian rhythm characteristic indexes of the same user in adjacent measurements, the rhythm change value of each measurement is determined, including: taking any measurement of any user as the target measurement; taking the other two measurements that are closest in time sequence to the target measurement as adjacent measurements; performing linear fitting on the values of the circadian rhythm characteristic indexes corresponding to the target measurement and the adjacent measurements based on the least squares method, and taking the slope of the fitting line as the fluctuation trend coefficient of the target measurement; taking the mean value of the absolute value of the difference between the target measurement and each adjacent measurement in the circadian rhythm characteristic indexes as the target characteristic difference coefficient; calculating the product of the fluctuation trend coefficient and the target characteristic difference coefficient and performing normalization processing as the rhythm change value of the target measurement. The calculation formula of the rhythm change value can be, for example:

[0071] ;

[0072] represents the rhythm change value of the circadian rhythm of the th user in the th measurement; represents the fluctuation trend coefficient of the th measurement of the th user, that is, the slope of the fitting line for the circadian rhythm characteristics in the neighborhood of this measurement, representing the change trend of the circadian rhythm characteristics of this measurement; represents the circadian rhythm characteristic index of the th measurement of the th user; represents the circadian rhythm characteristic index of the th measurement in the neighborhood (including the two adjacent measurements, determined according to the distance of the measurement interval time) of the

[0073] In the formula, Indicates User No. The target characteristic difference coefficient of the measurement indicates the degree of circadian rhythm disorder of the measurement results in the neighborhood. The larger the target characteristic difference coefficient, the more disordered the circadian rhythm change. Similarly, the larger the value of the fluctuation trend coefficient, the larger the corresponding fluctuation trend slope value, that is, the more drastic the overall circadian rhythm characteristic change, and the more disordered the circadian rhythm change. Therefore, the product of the fluctuation trend coefficient and the target characteristic difference coefficient is directly calculated, and the product value is normalized as the rhythm change value of the target measurement.

[0074] Due to individual differences among users, for example, in the care process of the elderly, when the initial circadian rhythm characteristics are similar and the same care plan is adopted, different users may have different care effects on the same care plan (such as exercise time or food planning, etc.), resulting in different speeds of recovery of circadian rhythms such as blood sugar.

[0075] If a user belongs to different target user groups in two adjacent circadian rhythm feature clusters, it means that the user may have different nursing effects on the nursing plan. In the clusters of the same circadian rhythm feature, the greater the difference between the user's circadian rhythm change rhythm and the cluster average change rhythm, and the greater the difference between the average circadian rhythm change rhythm of two adjacent cluster results, it means that the nursing effect of the user is abnormal. Based on this, a specific nursing effect analysis is conducted.

[0076] According to the distribution of rhythm change values ​​of adjacent measurements between users, the nursing effect coefficient of the user under the corresponding measurements is determined. The corresponding calculation formula is:

[0077] ;

[0078] In the formula, Indicates User No. The nursing effect coefficient of the secondary measurement; Indicates User No. The rhythm change value of the measurement; Indicates User No. The average of the rhythm change values ​​of all users in the same target user group is measured; Indicates User No. The average of the rhythm change values ​​of all users in the same target user group is measured. exp represents an exponential function with a natural constant as the base. Represents the sigmoid function.

[0079] From the above formula, we can see that Indicating the rhythm change value of the circadian rhythm change of the user's th measurement and the difference between the rhythm change values of the circadian rhythm changes of other users in the same cluster. The larger the value of , the greater the rhythm change compared to other users in the same target user group, and the more likely the corresponding nursing effect is abnormal. That is, when there are significant differences in the rhythm change values of the circadian rhythm characteristics of the same target user group in this measurement, it indicates that the nursing effect may be abnormal.

[0080] Similarly, indicates the rhythm change value of the th measurement of the

[0081] user and the difference from the average rhythm change value of the target user group to which the previous adjacent measurement belongs. The larger this value, the more obvious the rhythm fluctuation becomes from the target user group with a lower value to the target user group with a higher value in the adjacent two measurements, and the worse the nursing effect.

[0082] Adjustment module 104 is used to determine the initial intervention value of each user according to the nursing effect coefficients of the same measurement in the same initial user group, and perform intervention update in combination with the changes in the initial intervention values of each user in all measurements to obtain the nursing intervention value, and determine whether to adjust the nursing plan according to the nursing intervention value.

[0083] Among them, the nursing intervention mainly involves adjusting the nursing plan, such as means of exercise adjustment, diet adjustment, etc. Individual differences among users may lead to differences in the treatment effects of similar nursing plans, so the nursing plan for this user can be intervened according to the nursing effect coefficient.

[0084] Furthermore, in some embodiments of the present invention, determining the initial intervention value of each user according to the nursing effect coefficients of the same measurement in the same initial user group includes: taking the mean of the nursing effect coefficients of the same measurement in the same initial user group as the corresponding nursing mean coefficient; normalizing the absolute value of the difference between the nursing effect coefficient of any user in any measurement and the corresponding nursing mean coefficient as the mean difference factor; calculating the normalized value of the opposite number of the nursing effect coefficient of any user in any measurement as the effect intervention factor; calculating the product of the effect intervention factor and the mean difference factor and normalizing it as the initial intervention value. The corresponding calculation formula can be specifically, for example:

[0085] ;

[0086] In the formula, represents the initial intervention value of the th user's th measurement of the circadian rhythm; represents the nursing effect coefficient of the circadian rhythm in the th user's th measurement; represents the average value of the nursing effect coefficient of the circadian rhythm in the initial clustering result corresponding to the th user's th measurement, represents taking the absolute value, represents the sigmoid function, and norm represents normalization of the maximum and minimum values.

[0087] As can be seen from the above formula, the average nursing effect in the initial user group obtained according to the changing trend of the circadian rhythm characteristics is compared with the nursing effect of the current user to obtain the mean difference factor . The larger the value of the mean difference factor, the greater the difference between the nursing effect of the current user and the average nursing effect in the same initial user group. Taking the average nursing effect in the same initial user group as the normal effect, the larger the value of the mean difference factor at this time indicates a greater difference from the normal nursing effect. Whether the user's state after nursing gradually improves or deteriorates, a large difference requires nursing intervention. Therefore, the analysis of the mean difference factor is achieved by the way of the absolute value of the difference.

[0088] Among them, the nursing effect coefficient characterizes the quality of the nursing effect. The larger its value, the better the nursing effect. Therefore, it can be used as a variable for analysis. Calculate the normalized value of the opposite number of the nursing effect coefficient of any user's any measurement as the effect intervention factor . The larger the value of the effect intervention factor, the smaller the value of the nursing effect coefficient itself, that is, the worse the nursing effect. Calculate the product of the effect intervention factor and the mean difference factor and normalize it as the initial intervention value.

[0089] It should be noted that the overall nursing process also has a superimposed characteristic. If the circadian rhythm characteristics after a single nursing are not sufficient to reflect the effect of the nursing plan and the obtained nursing intervention value is small, but as the nursing process progresses, due to the role of individual differences of users, the nursing effect of its nursing plan will become worse and worse, that is, the corresponding effect is superimposed, and this superimposed state needs to be analyzed.

[0090] Further, in some embodiments of the present invention, by combining the changes in the initial intervention values measured for each user in all measurements, intervention updates are performed to obtain nursing intervention values, including: taking the absolute value of the difference between the initial intervention values of each user in two adjacent measurements as the intervention difference coefficient; calculating the mean of all intervention differences from the initial moment to the current moment and linearly mapping it to a preset adjustment range as the intervention adjustment coefficient; and taking the product of the intervention adjustment coefficient and the initial intervention value as the nursing intervention value.

[0091] In the embodiments of the present invention, the preset adjustment range represents the predetermined intervention adjustment range index, and this value can be set according to individual differences and the sensitivity of individual nursing adjustments. Optionally, in the embodiments of the present invention, the preset adjustment range can be specifically, for example, [0.5, 1.5]. Of course, when more sensitive nursing adjustments are required for individual users, it can also be set to [0.8, 1.8] and adjusted according to individual circumstances.

[0092] Among them, the intervention difference coefficient not only represents the numerical change in the initial intervention values of two adjacent measurements, that is, the intervention superposition effect generated by two adjacent measurements. Therefore, calculating the mean of all intervention differences from the initial moment to the current moment and linearly mapping it to a preset adjustment range as the intervention adjustment coefficient, the intervention adjustment coefficient represents the intervention superposition from the initial moment to the current moment. It should be noted that the initial moment in the embodiments of the present invention is the moment when the previous nursing intervention was performed, that is, after the nursing intervention is performed, a new superposition analysis is carried out to avoid the influence of previous nursing on the current nursing.

[0093] Among them, the nursing intervention value is the index data for performing nursing interventions, and the intervention adjustment coefficient is the weight value for performing intervention adjustments. Taking the product of the intervention adjustment coefficient and the initial intervention value as the nursing intervention value means that when the value of the intervention adjustment coefficient is larger, the corresponding value of the nursing intervention value will also become larger, and more nursing interventions are required.

[0094] Therefore, in the embodiments of the present invention, determining whether to adjust the nursing plan according to the nursing intervention value includes: when the nursing intervention value is greater than the preset intervention threshold, determining to adjust the nursing plan; otherwise, not adjusting the nursing plan.

[0095] Among them, the preset intervention threshold is the threshold value of the nursing intervention value. Since the larger the value of the nursing intervention value, the more nursing interventions are required. At this time, a general preset intervention threshold can be set for specific analysis of nursing plan interventions. Optionally, the preset intervention threshold can be specifically, for example, 0.75, that is, when the nursing intervention value is greater than 0.75, determining to adjust the nursing plan; otherwise, not adjusting the nursing plan.

[0096] The circadian rhythm is dynamic, and an individual's physiological state may change over time. As the circadian rhythm data changes during the user's care process, the care intervention value is dynamically updated. If the current circadian rhythm care intervention value of the user exceeds the threshold of 0.75, it indicates that the current matching care plan has a poor care effect on this user, and the care plan needs to be adjusted separately to ensure that the care plan can adapt to the changes in the user's physiological state in a timely manner.

[0097] In the embodiments of the present invention, by analyzing the numerical fluctuations of the circadian rhythm data of different users, the circadian rhythm characteristic indexes are determined, and then the initial user groups are obtained through grouping. The initial user groups represent user groups with similar fluctuations, realizing the characteristic analysis of various types of circadian rhythm data. Then, according to the changes in the circadian rhythm characteristic indexes of different users in time series, the care effect is analyzed to obtain the care effect coefficient. After that, combining the values of the care effect coefficients within the initial user groups, intervention analysis is carried out to obtain the care intervention value, and the care plan is adjusted according to the care intervention value. This application mainly conducts care intervention analysis through the single-user numerical feature dimension, the multi-user numerical feature dimension, the single-user numerical change dimension, and the multi-user numerical change dimension, so that the obtained care intervention value can combine the individual state changes and the overall characteristic differences, and is dynamically updated as time progresses, thereby effectively analyzing the individual differences of users. According to the individual differences and collective changes, intervention adjustments are made, and the grouping criteria and the update rules of the care plan are continuously optimized, so as to achieve the refined care of users. In summary, this application can effectively improve the reliability of care, enhance the accuracy and pertinence of the update of the care plan, and enhance the care effect.

[0098] It should be noted that the above sequence of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0099] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments.

Claims

1. An information management system based on circadian rhythm refined care, characterized in that: include: An acquisition module, used to acquire circadian rhythm data measured at different times by different users, wherein the circadian rhythm data at least includes sleep, body temperature, and heart rate; The feature analysis module is used to determine the circadian rhythm feature index of each measurement based on the difference between the value of each circadian rhythm data under the same measurement and the ideal value, and to form a feature sequence according to the time sequence; according to the fluctuation of the feature sequence of different users in the same time period, determine the initial user group with similar rhythm feature fluctuations; The nursing effect analysis module is used to cluster the circadian rhythm characteristic indicators of all users measured at the same time, and determine the target user group with similar circadian rhythm characteristic indicators; determine the rhythm change value of each measurement based on the numerical changes of the circadian rhythm characteristic indicators of the same user in adjacent measurements; in the same target user group, determine the nursing effect coefficient of the user under the corresponding measurement according to the distribution of the rhythm change values ​​of adjacent measurements between users; An adjustment module is used to determine the initial intervention value of each user according to the nursing effect coefficient of the same measurement in the same initial user group, and to update the intervention according to the change of the initial intervention value of each user in all measurements to obtain the nursing intervention value, and to determine whether to adjust the nursing plan according to the nursing intervention value; Among them, the initial intervention value of each user is determined according to the nursing effect coefficient measured at the same time in the same initial user group, including: The mean of the nursing effect coefficients of the same measurements in the same initial user group is taken as the nursing mean coefficient of the corresponding measurements; The absolute value of the difference between the nursing effect coefficient measured by any user at any time and the corresponding nursing mean coefficient is normalized and used as the mean difference factor; Calculate the normalized value of the inverse of the nursing effect coefficient measured by any user at any time as the effect intervention factor; The product of the effect intervention factor and the mean difference factor was calculated and normalized as the initial intervention value; According to the fluctuation of feature sequences of different users in the same time period, the initial user group with similar rhythm feature fluctuations is determined, including: Based on the dynamic time warping algorithm, the DTW values ​​of the feature sequences of any two users in the same time period are calculated, and the opposite number of the DTW value is normalized as the sequence similarity; Clustering is performed based on sequence similarity to obtain different clusters as initial user groups; Cluster the circadian rhythm characteristic indicators of all users measured at the same time to determine the target user group with similar circadian rhythm characteristic indicators, including: The circadian rhythm characteristic indicators of all users measured at the same time are clustered by DBSCAN density to obtain the target user group.

2. An information management system based on circadian rhythm refined care as claimed in claim 1, characterized in that: The ideal value is a known preset value, and the ideal value corresponding to different circadian rhythm data types is different; According to the difference between the value of each circadian rhythm data under the same measurement and the ideal value, the circadian rhythm characteristic index of each measurement is determined, including: The absolute value of the difference between the value of each circadian rhythm data and the corresponding ideal value was calculated and normalized as the ideal difference coefficient; The mean of the ideal difference coefficients of all circadian rhythm data was used as the circadian rhythm characteristic index for each measurement.

3. The information management system based on circadian rhythm refined care as claimed in claim 1, characterized in that: Based on the numerical changes of the circadian rhythm characteristic indicators of the same user in adjacent measurements, the rhythm change value of each measurement is determined, including: Any measurement of any user is regarded as the target measurement; the other two measurements that are closest to the target measurement in time sequence are regarded as adjacent measurements; Based on the least squares method, a straight line fitting is performed on the values ​​of the circadian rhythm characteristic indexes corresponding to the target measurement and the adjacent measurements, and the slope of the fitting line is used as the fluctuation trend coefficient of the target measurement; The mean of the absolute values ​​of the differences between the target measurement and each adjacent measurement in the circadian rhythm characteristic index was taken as the target characteristic difference coefficient; The product of the fluctuation trend coefficient and the standard feature difference coefficient was calculated and normalized as the rhythm change value of the target measurement.

4. The information management system based on circadian rhythm refined care as claimed in claim 1, characterized in that: According to the distribution of rhythm change values ​​of adjacent measurements between users, the nursing effect coefficient of the user under the corresponding measurements is determined. The corresponding calculation formula is: ; In the formula, Indicates User No. The nursing effect coefficient of the secondary measurement; Indicates User No. The rhythm change value of the measurement; Indicates User No. The average of the rhythm change values ​​of all users in the same target user group is measured; Indicates User No. The mean of the rhythm change values ​​of all users in the same target user group is measured for the second time. exp represents an exponential function with a natural constant as the base, and sigmoid represents a sigmoid function.

5. The information management system based on circadian rhythm refined care as claimed in claim 1, characterized in that: Combined with the changes in the initial intervention values ​​of each user in all measurements, the intervention is updated to obtain the nursing intervention value, including: The absolute value of the difference between the initial intervention values ​​of each user in two consecutive measurements is taken as the intervention difference coefficient; Calculate the mean of all intervention differences from the initial moment to the current moment, and linearly map them to the preset adjustment range as the intervention adjustment coefficient, where the initial moment is the moment of the last nursing intervention; The product of the intervention adjustment coefficient and the initial intervention value is taken as the nursing intervention value.

6. An information management system based on circadian rhythm refined care as claimed in claim 5, characterized in that: The default adjustment range is [0.5,1.5].

7. The information management system based on circadian rhythm refined care as claimed in claim 1, characterized in that: Determine whether to adjust the nursing plan based on the nursing intervention value, including: When the nursing intervention value is greater than the preset intervention threshold, it is determined to adjust the nursing plan, otherwise, the nursing plan is not adjusted.

Images