Intelligent nursing system and method

Abstract

The invention relates to the technical field of medical data processing, in particular to an intelligent nursing system and method. Comprising the steps of collecting physiological data of a patient, preprocessing the physiological data of the patient to obtain preprocessed physiological data, analyzing the preprocessed physiological data by using a health risk assessment analysis algorithm based on physiological data adaptive dynamic fuzzy mapping to obtain an analysis result, and assessing the health risk of the patient according to the analysis result. Obtaining a health risk assessment result; and generating a personalized nursing scheme according to the health risk assessment result and the historical medical record and individual information of the patient, and optimizing the personalized nursing scheme based on a quantitative analysis result as feedback to obtain a self-adaptive personalized nursing scheme. The technical problems that in intelligent nursing, processing and analysis of physiological data of a patient are not accurate enough, and health assessment of the patient lacks flexibility are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and in particular to an intelligent nursing system and method. Background Art

[0002] In modern medicine and health management, health risk assessment has become an important tool for predicting diseases and preventing health problems. Traditional health risk assessment methods usually rely on fixed health standards and universal assessment models, aiming to predict potential health risks by analyzing patients' health indicators, such as blood pressure, blood sugar, weight, etc. However, these methods often have certain limitations, especially when assessing individualized risks. Because they ignore the physiological differences between individuals, the risk assessment results are not accurate enough or cannot reflect the actual health status.

[0003] With the advancement of medical technology, more and more researchers are trying to introduce more flexible and dynamic assessment methods into the health risk assessment system. In recent years, technologies such as machine learning, data mining, and fuzzy logic have been widely used in the field of health management. These technologies can handle large-scale, multi-dimensional, and complex health data and provide more accurate individualized assessments. In particular, fuzzy logic technology can handle the uncertainty and ambiguity in the data, thereby providing more accurate assessment results in a dynamic environment.

[0004] However, the existing intelligent nursing methods have the following technical problems: in intelligent nursing, the processing and analysis of patients' physiological data are not accurate enough and the assessment of patients' health lacks flexibility. Summary of the invention

[0005] The present invention provides an intelligent nursing system and method to solve the technical problems of inaccurate processing and analysis of patient physiological data and lack of flexibility in patient health assessment in intelligent nursing.

[0006] An intelligent nursing system and method of the present invention specifically include the following technical solutions:

[0007] An intelligent nursing method comprises the following steps:

[0008] S1. Collecting physiological data of the patient, and preprocessing the physiological data of the patient to obtain preprocessed physiological data, analyzing the preprocessed physiological data using a health risk assessment and analysis algorithm based on physiological data adaptive dynamic fuzzy mapping to obtain an analysis result, and assessing the health risk of the patient according to the analysis result to obtain a health risk assessment result;

[0009] S2. Generate a personalized care plan based on the health risk assessment results, the patient's historical medical records, and individual information, and optimize the personalized care plan based on the quantitative analysis results as feedback to obtain an adaptive personalized care plan.

[0010] Preferably, the S1 specifically includes:

[0011] In the implementation process of the health risk assessment analysis algorithm based on physiological data adaptive dynamic fuzzy mapping, use the fuzzy membership function to fuzzify the preprocessed physiological data and map the preprocessed physiological data to the fuzzy subset. The specific implementation formula is:

[0012]

[0013] Where, represents the fuzzy membership value of the i-th preprocessed physiological data X i (t) belonging to the fuzzy category m at time t, that is, the fuzzified physiological data; X i (t) is the value of the i-th preprocessed physiological data at time t; α m is the parameter that adjusts the sensitivity of the fuzzy membership function; β m is the offset parameter of the fuzzy mapping.

[0014] Preferably, the S1 specifically includes:

[0015] In the implementation process of the health risk assessment analysis algorithm based on physiological data adaptive dynamic fuzzy mapping, after obtaining the fuzzified physiological data, adaptively adjust the fuzzified physiological data based on the patient's individual characteristics, and dynamically adjust the health assessment factors by introducing an adaptive adjustment mechanism to obtain the adjusted health assessment factors.

[0016] Preferably, the S1 specifically includes:

[0017] In the implementation process of the health risk assessment analysis algorithm based on physiological data adaptive dynamic fuzzy mapping, after completing the adaptive adjustment, perform health risk assessment processing based on the adjusted health assessment factors to obtain a health risk index, and convert the health risk index into a health risk probability value, that is, the analysis result; according to the analysis result, obtain the health risk assessment result.

[0018] Preferably, the S2 specifically includes:

[0019] Perform preliminary care based on the personalized care plan, detect the patient during the care process, and when it is detected that the patient's health data is abnormal, use the weighted regression quantitative analysis algorithm to quantitatively analyze the abnormal data to obtain the quantitative analysis result.

[0020] Preferably, the S2 specifically includes:

[0021] In the implementation process of the weighted regression quantitative analysis algorithm, a weighted regression model is constructed to perform quantitative analysis on abnormal data. Based on the current abnormal data and the historical data of the current abnormal data, the abnormal severity score is obtained. The specific implementation formula is:

[0022]

[0023] Where S(t) represents the abnormality severity score at time point t; is the regression coefficient; X′ t is the abnormal data value at time point t; T(t) is the anomaly detection threshold at time point t; is the regression coefficient; is the weight coefficient; Indicates at a point in time Historical data of current abnormal data on; is the time window size of historical data.

[0024] Preferably, the S2 specifically includes:

[0025] In the implementation process of the weighted regression quantitative analysis algorithm, a dynamic feedback mechanism is introduced. When abnormal data is detected, the weighted regression model parameters are dynamically adjusted in combination with the feedback information to obtain the quantitative results of the abnormal degree of physiological data, that is, the quantitative analysis results, which are used as feedback.

[0026] Preferably, the S2 specifically includes:

[0027] By comparing the current personalized care plan with the quantitative analysis results, the current personalized care plan is evaluated; and based on the quantitative analysis results, the key parameters of the patient's care plan are optimized to obtain an adaptive personalized care plan.

[0028] An intelligent nursing system comprises the following parts:

[0029] Health data collection module, data preprocessing module, health data analysis module, personalized care plan generation module, intelligent care and feedback module;

[0030] The health data collection module collects the patient's physiological data in real time and sends the collected patient's physiological data to the data preprocessing module;

[0031] A data preprocessing module preprocesses the patient's physiological data to obtain preprocessed physiological data, and sends the preprocessed physiological data to the health data analysis module;

[0032] The health data analysis module uses a health risk assessment analysis algorithm based on physiological data adaptive dynamic fuzzy mapping to analyze the preprocessed physiological data to obtain analysis results, evaluates the patient's health risk based on the analysis results, obtains health risk assessment results, and sends the health risk assessment results to the personalized care plan generation module;

[0033] The personalized nursing plan generation module generates a personalized nursing plan based on the health risk assessment results, the patient's historical medical records and individual information, and sends the personalized nursing plan to the intelligent nursing and feedback module. At the same time, the personalized nursing plan is optimized in combination with the quantitative analysis results of the intelligent nursing and feedback module as feedback to obtain an adaptive personalized nursing plan, and the adaptive personalized nursing plan is sent to the intelligent nursing and feedback module for real-time monitoring and adjustment;

[0034] Intelligent care and feedback module, patients, family caregivers or doctors provide intelligent care based on personalized care plans, and test patients at the same time. When abnormalities are detected in the patient's health data, the abnormal data is quantitatively analyzed to obtain quantitative analysis results, which are sent as feedback to the personalized care plan generation module, and intelligent care is implemented based on the adaptive personalized care plan.

[0035] The beneficial effects of the technical solution of the present invention are:

[0036] 1. In order to effectively process and compare the physiological data of different patients, the intelligent nursing system performs fuzzy conversion on the preprocessed physiological data. Each preprocessed physiological data is mapped to multiple fuzzy subsets according to the fuzzy membership function, so as to perform a more detailed analysis of the preprocessed physiological data. This step ensures that each value in the preprocessed physiological data can be represented as multiple possible health states, thereby improving the accuracy of subsequent evaluations.

[0037] 2. Based on the individual characteristics of the patient (such as age, gender, medical history, etc.), the intelligent nursing system adaptively adjusts the physiological data after fuzzy processing. By dynamically adjusting the weight of the fuzzy classification, the health assessment of each patient is more personalized and accurately reflects their actual health status.

[0038] 3. By continuously tracking the patient's health status and using a weighted regression quantitative analysis algorithm to perform quantitative analysis on abnormal data, the patient's health status is always kept in sync with the care plan. The intelligent care system periodically evaluates and provides feedback on each health indicator to ensure that it is always in the best state. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a structural diagram of an intelligent nursing system according to the present invention;

[0040] Figure 2 The present invention is a flow chart of an intelligent nursing method. DETAILED DESCRIPTION

[0041] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] 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.

[0043] The specific scheme of an intelligent nursing system and method provided by the present invention is described in detail below with reference to the accompanying drawings.

[0044] Refer to the attached Figure 1 , which shows a structure diagram of an intelligent nursing system provided by an embodiment of the present invention, the system includes the following parts:

[0045] Health data collection module, data preprocessing module, health data analysis module, personalized care plan generation module, intelligent care and feedback module;

[0046] The health data collection module collects the patient's physiological data in real time through smart sensors such as smart bracelets, blood glucose meters, and blood pressure monitors, and sends the collected patient's physiological data to the data preprocessing module;

[0047] The patient’s physiological data includes heart rate, blood sugar, blood pressure, body temperature, respiratory rate, etc.;

[0048] The data preprocessing module performs preprocessing such as cleaning, denoising, and standardization on the patient's physiological data to ensure the consistency of the quality of the patient's physiological data, obtains the preprocessed physiological data, and sends the preprocessed physiological data to the health data analysis module for subsequent analysis and evaluation;

[0049] The health data analysis module uses a health risk assessment analysis algorithm based on physiological data adaptive dynamic fuzzy mapping to conduct an in-depth analysis of the pre-processed physiological data to obtain analysis results, evaluate the patient's health risks based on the analysis results, obtain health risk assessment results, and send the health risk assessment results to the personalized care plan generation module for formulating subsequent care plans;

[0050] The personalized nursing plan generation module generates a personalized nursing plan based on the health risk assessment results, the patient's historical medical history, and individual information (such as age, gender, living habits, past medical history, etc.), and sends the personalized nursing plan to the intelligent nursing and feedback module. At the same time, the personalized nursing plan is optimized in combination with the quantitative analysis results of the intelligent nursing and feedback module as feedback to obtain an adaptive personalized nursing plan, and the adaptive personalized nursing plan is sent to the intelligent nursing and feedback module to ensure that the patient can follow the nursing plan and conduct real-time monitoring and adjustment;

[0051] Intelligent nursing and feedback module, patients, family caregivers or doctors perform intelligent nursing based on personalized nursing plans, and test patients at the same time. When abnormalities are detected in the patient's health data, the abnormal data is quantitatively analyzed to obtain quantitative analysis results, which are sent as feedback to the personalized nursing plan generation module to optimize the personalized nursing plan, ensure the continuity and accuracy of the entire nursing process, and implement intelligent nursing based on adaptive personalized nursing plans.

[0052] See attached Figure 2 , which shows a flow chart of an intelligent nursing method provided by an embodiment of the present invention, the method comprising the following steps:

[0053] S1. Collecting physiological data of the patient, and preprocessing the physiological data of the patient to obtain preprocessed physiological data, analyzing the preprocessed physiological data using a health risk assessment and analysis algorithm based on physiological data adaptive dynamic fuzzy mapping to obtain an analysis result, and assessing the health risk of the patient according to the analysis result to obtain a health risk assessment result;

[0054] The patient's physiological data, including heart rate, blood sugar, blood pressure, body temperature, respiratory rate, etc., are collected in real time through smart sensors such as smart bracelets, blood glucose meters, and blood pressure monitors. The patient's physiological data is preprocessed such as cleaning, denoising, and standardization to ensure that the quality of the patient's physiological data remains consistent and obtain preprocessed physiological data. The above preprocessing process uses existing technical means and will not be elaborated here.

[0055] Furthermore, the preprocessed physiological data is deeply analyzed using a health risk assessment analysis algorithm based on physiological data adaptive dynamic fuzzy mapping to obtain analysis results; the specific implementation process is as follows:

[0056] First, in order to avoid the large volatility of the patient's physiological data and the different health status of different patients under the same physiological indicators, the pre-processed physiological data can be effectively processed and compared in the subsequent analysis, and the pre-processed physiological data is fuzzy processed. The core purpose of fuzzy processing is to map the pre-processed physiological data into multiple fuzzy subsets through fuzzy membership functions, and further analyze the pre-processed physiological data more flexibly and carefully. For example, blood sugar level may correspond to three fuzzy categories: "normal", "low" and "high"; for heart rate, it may correspond to three fuzzy categories: "normal", "low" and "high", and blood pressure will also be fuzzy processed in a similar way. Specifically, for each pre-processed physiological data X i (t), fuzzy conversion is performed using the fuzzy membership function, and the formula is as follows:

[0057]

[0058] in, represents the physiological data X after the i-th preprocessing i (t) the fuzzy membership value belonging to the fuzzy category m at time t, that is, the physiological data after fuzzification processing. The fuzzy membership value reflects the degree to which the pre-processed physiological data belongs to a certain fuzzy category; X i (t) is the value of the physiological data after the i-th preprocessing at time t; α m is the parameter for adjusting the sensitivity of the fuzzy membership function; β m It is the offset parameter of the fuzzy mapping, which determines the position of the preprocessed physiological data in the fuzzy membership function.

[0059] Through the above formula, each preprocessed physiological data can be mapped to multiple fuzzy categories, and the corresponding fuzzy membership value can be calculated for each preprocessed physiological data. The continuous preprocessed physiological data can be converted into multiple fuzzy subsets, thereby providing a more detailed hierarchical analysis for subsequent health assessment.

[0060] After obtaining the fuzzy processed physiological data, the fuzzy processed physiological data is adaptively adjusted based on the individual characteristics of the patient (such as age, gender, living habits, past medical history, etc.). The pre-processed physiological data of each patient has different interpretations and risks due to individual differences, so an adaptive adjustment mechanism is introduced to dynamically adjust the health assessment factor according to the specific situation of the patient. The specific formula is expressed as:

[0061]

[0062]

[0063] Among them, E i (t) is the initial evaluation value of the patient's health status at time t of the fuzzy processed physiological data corresponding to the i-th preprocessed physiological data; n is the number of fuzzy categories, indicating how many fuzzy categories each preprocessed physiological data is converted into; λ m is the weight coefficient of the fuzzy category, which indicates the weight coefficient of the fuzzy category m on the health assessment factor, reflecting the influence of the fuzzy category on the patient's health assessment; f(C i ) is the individual characteristic adjustment factor, which means the adjustment factor based on the individual characteristics of the patient, including age, gender, lifestyle, past medical history, etc.; C i is the set of individual features associated with the ith type of preprocessed physiological data; it is calculated by the following formula:

[0064]

[0065] in, is the first individual feature set associated with the ith preprocessed physiological data. individual characteristics; N is the number of individual characteristics; γ is a parameter for adjusting the sensitivity of individual characteristics, which determines the degree of influence of individual characteristic changes on health assessment factors. If γ is large, the difference in individual characteristics will have a more significant impact on health assessment factors; δ is an offset, which represents the adjustment value of the patient's individual characteristics at a certain baseline level. The above process dynamically adjusts the health assessment factor of each preprocessed physiological data according to the individual characteristics of the patient to ensure that the results of the health assessment are more accurate and personalized.

[0066] E adjusted (t) is the adjusted health assessment factor, which reflects the actual health status of the patient after adaptive adjustment; It is the treatment effect coefficient, which indicates the impact of the treatment process on health assessment, which changes over time. For example, when a patient undergoes a treatment (such as medication, surgery, etc.), the improvement or deterioration of his health status will be reflected in superior, and are the first treatment effect coefficient and the second treatment effect coefficient of the health assessment factor before and after treatment; k 1 and k 2 is the decay constant, which represents the change in the effect of treatment on health assessment over time; It is the coefficient of change in lifestyle habits, which indicates the impact of the patient’s lifestyle on health assessment. It is related to factors such as diet, exercise, and stress, and can reflect the impact of changes in the patient’s lifestyle on health assessment factors. is the baseline coefficient before the improvement of living habits; and is the adjustment factor for lifestyle changes, which is used to indicate the long-term impact of changes in patients’ lifestyle habits on health assessment; 0 It is the starting point for changes in lifestyle habits.

[0067] After the adaptive adjustment is completed, the health risk assessment is performed based on the adjusted health assessment factors. Each adjusted health assessment factor is weighted and summed to obtain the overall health risk index R of any patient. j (t), the formula is:

[0068]

[0069] Among them, R j (t) represents the health risk index of patient j at time t, which is a quantitative indicator of the patient's health risk; ω i is each adjusted health assessment factor The weight coefficient represents the influence of the adjusted health assessment factor on the overall health risk, which is determined according to the expert experience method; M is the number of pre-processed physiological data involved in the health assessment;

[0070] Furthermore, the health risk index is converted into the health risk probability value P j (t), using the following formula:

[0071]

[0072] Among them, P j (t) represents the health risk probability value of the patient at time t, that is, the analysis result, with a value range of [0, 1], which reflects the degree of health risk of the patient and provides a quantitative assessment of the patient's health status. This value can be used to judge the patient's health risk level; R is the sensitivity coefficient of the health risk conversion function; β R is a constant offset that determines the baseline level of health risk conversion.

[0073] Finally, according to the health risk probability value P as the analysis result j (t) Assess the patient's health risk and obtain the health risk assessment result, that is, classify the patient into different health risk levels according to the health risk probability value. For example:

[0074]

[0075] Among them, L j (t) is the health risk level of patient j at time t, i.e., the health risk assessment result; θ 1 ,θ 2It is the health probability threshold preset according to the expert experience method; 0 represents low risk level; 1 represents medium risk level; 2 represents high risk level;

[0076] S2. Generate a personalized care plan based on the health risk assessment results and the patient's historical medical history and individual information. At the same time, optimize the personalized care plan based on the quantitative analysis results as feedback to obtain an adaptive personalized care plan.

[0077] Based on the health risk assessment results and the patient's medical history and personal information, including: basic information such as age, gender, height, weight, etc.; past medical history, such as whether the patient has chronic diseases such as hypertension, diabetes, heart disease, etc.; medical history such as medication history, surgical history, etc.; genetic factors; lifestyle habits, such as diet, exercise, smoking, drinking, etc., generate personalized care plans, specifically: according to the health risk level L j (t), patients are divided into different health risk levels, such as low risk, medium risk, and high risk. Each health risk level corresponds to different nursing intensity and intervention measures. For example: if L j (t) belongs to the low risk level, indicating that the patient is in good health and the care plan focuses on prevention and regular check-ups; if L j (t) Medium risk level means that the patient has certain health risks, and the care plan may include more frequent examinations, medication, dietary adjustments, etc. j (t) Belongs to the high-risk level, which means that the patient's health condition is poor and the care plan needs to be more rigorous, which may involve hospitalization, emergency treatment, close monitoring, etc. Adjustment based on historical cases: If the patient has a history of hyperglycemia, measures to control blood sugar will be added to the care plan; if the patient has a history of heart disease, measures such as monitoring electrocardiograms and limiting high-salt diet will be added to the care plan; if the patient has a history of allergies, the care plan should avoid the use of drugs or treatments that may cause allergies. Individual care goal setting: According to the health risk level and the specific situation of the patient, set individualized care goals, such as lowering blood sugar, controlling blood pressure, increasing exercise, etc. Each care goal will have corresponding evaluation criteria and time nodes for achievement.

[0078] Based on the above evaluations and goals, the intelligent care system will automatically generate specific care measures, which may include: Medication treatment: Recommending the types, dosages, and usage methods of medications according to the patient's health condition; Lifestyle intervention: Such as reasonable diet suggestions, exercise plans, sleep regulation, etc.; Monitoring plan: Regularly monitoring the patient's physiological data, such as blood glucose, blood pressure, heart rate, etc., to ensure timely adjustment of the care plan when the patient's health status changes; At the same time, for certain patients, such as the elderly, pregnant women, critically ill patients, etc., when there are special needs, special care and adjustment measures should be added to the care plan, such as strengthening psychological counseling, regular physical examinations, emergency medical support, etc.

[0079] Furthermore, the patient, family caregiver, or doctor conducts preliminary care based on the personalized care plan and monitors the patient during the care process. When abnormal patient health data is detected, the weighted regression quantitative analysis algorithm is used to quantitatively analyze the abnormal data to obtain the quantitative analysis result. The specific implementation process is as follows:

[0080] First, a weighted regression model is constructed for quantitatively analyzing abnormal data. The abnormal severity score S(t) of the abnormal data in any type of physiological data is calculated based on the current abnormal data value X′ t and the historical data of the current abnormal data. The specific formula is as follows:

[0081]

[0082] where S(t) represents the abnormal severity score at time point t, reflecting the quantitative result of the abnormal degree of a certain type of physiological data of the patient; is the regression coefficient, used to control the relative importance of the current abnormal data X′ t and the abnormal detection threshold T(t), reflecting the contribution of the deviation between the current abnormal data and the abnormal detection threshold to the abnormal severity score; X′ t is the abnormal data value at time point t; T(t) is the abnormal detection threshold at time point t, which is calculated based on the weighted average of the current time point and the historical data of the current abnormal data, reflecting the reasonable range of the physiological data at the current moment; is the regression coefficient, used to control the influence degree of the historical data of the current abnormal data on the current abnormal severity score, that is, the weighted influence degree of the historical data on the current abnormal severity score; is the weight coefficient, used to weight the historical data of the current abnormal data 's contribution degree to the current abnormal severity score. The larger the weight, the greater the influence of the historical data on the current abnormal severity score; represents the historical data of the current abnormal data at time point t; It is the time window size of historical data, which indicates the number of historical data considered when performing weighted calculation.

[0083] The abnormal severity score S(t) not only reflects the deviation of the current normalized abnormal data from the abnormal detection threshold, but also takes into account the changes in the patient's health status over the past period of time. Therefore, this score can provide more comprehensive information for the diagnosis of abnormal data and the formulation of nursing plans.

[0084] In order to ensure the adaptability and robustness of the weighted regression model, a dynamic feedback mechanism is introduced. When abnormal data is detected, the model parameters are dynamically adjusted based on the feedback information. This feedback mechanism is based on the following formula:

[0085]

[0086] in, Represents the regression coefficient of the model The amount of adjustment; is the feedback coefficient, which is used to control the amplitude of feedback adjustment; is the mean of the normal values ​​of this type of physiological data. The function of this formula is to compare the historical data of the current abnormal data with the normal values ​​of this type of physiological data, and adjust the model parameters according to the deviation, so that the weighted regression model is continuously optimized in the continuous physiological data.

[0087] All types of abnormal data of physiological data are processed as above to obtain quantitative results of the abnormal degree of physiological data, that is, quantitative analysis results, which are used as feedback.

[0088] Based on the quantitative analysis results as feedback, the personalized care plan is optimized to obtain an adaptive personalized care plan and realize intelligent care. Specifically, it includes: evaluating the effectiveness of the current personalized care plan by comparing the current personalized care plan with the quantitative analysis results. For example, if the intelligent care system detects elevated blood sugar and gives a high blood sugar warning, it is necessary to check whether the current personalized care plan has covered blood sugar management measures. And based on the quantitative analysis results, the key parameters of the patient's care plan are optimized to obtain an adaptive personalized care plan. The specific adjustments include: Dietary management: Adjust the patient's dietary recommendations based on blood sugar, blood pressure and other data. For example, for patients with high blood sugar, a low GI diet is recommended to reduce carbohydrate intake. Exercise plan: If the patient's exercise ability or health status changes, optimize the intensity and frequency of the exercise plan. For example, if the intelligent care system detects that the heart rate is continuously high, the exercise plan may need to reduce the intensity of exercise or increase the rest time. Drug management: For patients receiving drug treatment, adjust the dosage or type of drugs according to changes in health status. For example, for patients with high blood sugar, if blood sugar is found to be continuously elevated, it may be necessary to adjust the insulin dosage or change the drug. Lifestyle recommendations: Based on the patient's sleep quality, activity level and other data, it is recommended to adjust lifestyle habits, for example, to improve sleep quality or increase daily activity.

[0089] Finally, intelligent care is achieved based on the adaptive personalized care plan.

[0090] In summary, an intelligent nursing system and method are completed.

[0091] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages 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.

[0092] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0093] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. An intelligent nursing method, characterized in that: The following steps are involved: S1. Collecting physiological data of the patient, and preprocessing the physiological data of the patient to obtain preprocessed physiological data, analyzing the preprocessed physiological data using a health risk assessment and analysis algorithm based on physiological data adaptive dynamic fuzzy mapping to obtain an analysis result, and assessing the health risk of the patient according to the analysis result to obtain a health risk assessment result; S2. Generate a personalized care plan based on the health risk assessment results and the patient's historical medical history and individual information. At the same time, optimize the personalized care plan based on the quantitative analysis results as feedback to obtain an adaptive personalized care plan.

2. An intelligent nursing method according to claim 1, characterized in that: The S1 specifically includes: In the process of implementing the health risk assessment and analysis algorithm based on physiological data adaptive dynamic fuzzy mapping, the fuzzy membership function is used to fuzzify the preprocessed physiological data and map the preprocessed physiological data into fuzzy subsets. The specific implementation formula is: in, represents the physiological data X after the i-th preprocessing i (t) the fuzzy membership value of fuzzy category m at time t, i.e., the physiological data after fuzzification; X i (t) is the value of the physiological data after the i-th preprocessing at time t; α m is the parameter for adjusting the sensitivity of the fuzzy membership function; β m is the offset parameter of the fuzzy mapping.

3. An intelligent nursing method according to claim 2, characterized in that: The S1 specifically includes: In the process of implementing the health risk assessment analysis algorithm based on adaptive dynamic fuzzy mapping of physiological data, after obtaining the fuzzy-processed physiological data, the fuzzy-processed physiological data is adaptively adjusted based on the individual characteristics of the patient, and the health assessment factor is dynamically adjusted by introducing an adaptive adjustment mechanism to obtain the adjusted health assessment factor.

4. An intelligent nursing method according to claim 3, characterized in that: The S1 specifically includes: In the process of implementing the health risk assessment analysis algorithm based on adaptive dynamic fuzzy mapping of physiological data, after completing the adaptive adjustment, the health risk assessment is processed based on the adjusted health assessment factor to obtain a health risk index, and the health risk index is converted into a health risk probability value, that is, the analysis result; based on the analysis result, the health risk assessment result is obtained.

5. The intelligent nursing method according to claim 1, characterized in that: The S2 specifically includes: Initial care is provided based on personalized care plans, and patients are tested during the care process. When abnormalities are detected in the patient's health data, the abnormal data is quantitatively analyzed using a weighted regression quantitative analysis algorithm to obtain quantitative analysis results.

6. An intelligent nursing method according to claim 5, characterized in that: The S2 specifically includes: In the implementation process of the weighted regression quantitative analysis algorithm, a weighted regression model is constructed to perform quantitative analysis on abnormal data. Based on the current abnormal data and the historical data of the current abnormal data, the abnormal severity score is obtained. The specific implementation formula is: Where S(t) represents the abnormality severity score at time point t; is the regression coefficient; X′ t is the abnormal data value at time point t; T(t) is the anomaly detection threshold at time point t; is the regression coefficient; is the weight coefficient; Indicates at a point in time Historical data of current abnormal data on; is the time window size of historical data.

7. An intelligent nursing method according to claim 6, characterized in that: The S2 specifically includes: In the implementation process of the weighted regression quantitative analysis algorithm, a dynamic feedback mechanism is introduced. When abnormal data is detected, the weighted regression model parameters are dynamically adjusted in combination with the feedback information to obtain the quantitative results of the abnormal degree of physiological data, that is, the quantitative analysis results, which are used as feedback.

8. An intelligent nursing method according to claim 7, characterized in that: The S2 specifically includes: By comparing the current personalized care plan with the quantitative analysis results, the current personalized care plan is evaluated; and based on the quantitative analysis results, the key parameters of the patient's care plan are optimized to obtain an adaptive personalized care plan.

9. An intelligent nursing system, applied to the intelligent nursing method according to claim 1, characterized in that: Includes the following sections: Health data collection module, data preprocessing module, health data analysis module, personalized care plan generation module, intelligent care and feedback module; The health data collection module collects the patient's physiological data in real time and sends the collected patient's physiological data to the data preprocessing module; A data preprocessing module preprocesses the patient's physiological data to obtain preprocessed physiological data, and sends the preprocessed physiological data to the health data analysis module; The health data analysis module uses a health risk assessment analysis algorithm based on physiological data adaptive dynamic fuzzy mapping to analyze the preprocessed physiological data to obtain analysis results, evaluates the patient's health risk based on the analysis results, obtains health risk assessment results, and sends the health risk assessment results to the personalized care plan generation module; The personalized nursing plan generation module generates a personalized nursing plan based on the health risk assessment results, the patient's historical medical records and individual information, and sends the personalized nursing plan to the intelligent nursing and feedback module. At the same time, the personalized nursing plan is optimized in combination with the quantitative analysis results of the intelligent nursing and feedback module as feedback to obtain an adaptive personalized nursing plan, and the adaptive personalized nursing plan is sent to the intelligent nursing and feedback module for real-time monitoring and adjustment; Intelligent care and feedback module, patients, family caregivers or doctors provide intelligent care based on personalized care plans, and test patients at the same time. When abnormalities are detected in the patient's health data, the abnormal data is quantitatively analyzed to obtain quantitative analysis results, which are sent as feedback to the personalized care plan generation module, and intelligent care is implemented based on the adaptive personalized care plan.

Images