Pregnant and lying-in woman health monitoring system based on artificial intelligence

Abstract

The invention is suitable for the technical field of medical health and information, and provides a pregnant and lying-in woman health monitoring system based on artificial intelligence, comprising a psychological health analysis unit for obtaining a pregnant and lying-in woman psychological health influence index according to a fetal state influence index, a vomiting influence index and a family accompanying index; the psychological health judgment module is used for generating psychological health change trend signals according to the psychological health influence indexes of the pregnant and lying-in women; the pregnant and lying-in woman comprehensive state analysis unit is used for generating a comprehensive health assessment index according to the pregnant and lying-in woman mental health influence index, the weight assessment index, the physical quality index and the daily work and rest standard degree index; the health state judgment module is used for generating a health state signal according to the pregnant and lying-in woman comprehensive health assessment index; according to the system, the mental health and the body health of the pregnant and lying-in woman can be analyzed, evaluated and early warned, so that the risk of the pregnant and lying-in woman during delivery is reduced, the health behavior of the pregnant and lying-in woman can be promoted through the health state signal, and the self-health-care consciousness of the pregnant and lying-in woman is enhanced.

Description

Technical Field

[0001] The present invention belongs to the field of medical health and information technology, and in particular to an artificial intelligence-based maternal health monitoring system. Background Art

[0002] The health status of pregnant women is directly related to the life safety and long-term health of both mother and baby. However, traditional health monitoring methods mostly rely on regular prenatal examinations and face-to-face psychological counseling, which makes it difficult to achieve all-weather and all-round health monitoring of pregnant women.

[0003] With the development of artificial intelligence technology, its application in the field of medical health is becoming more and more extensive, providing new solutions for maternal and child health management.

[0004] However, most existing AI-based health management systems focus on monitoring physiological parameters, ignoring the important dimension of mental health. Therefore, it is particularly important to develop a system that can comprehensively assess the physical and mental health of pregnant women and provide warnings. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide an artificial intelligence-based maternal health monitoring system, aiming to solve the problems existing in the above-mentioned background technology.

[0006] The embodiment of the present invention is implemented as follows: a maternal and child health monitoring system based on artificial intelligence includes: A mental health analysis unit is used to analyze the mental health of pregnant women according to the fetal status impact index, the frequency of morning sickness of pregnant women and the family accompanying index to obtain the mental health impact index of pregnant women; The mental health judgment module is used to judge the changing trend of the mental health of pregnant women according to the maternal mental health impact index and generate a mental health changing trend signal; The maternal comprehensive status analysis unit is used to generate a comprehensive health assessment index based on the maternal mental health impact index, weight assessment index, physical fitness index and standard degree index of living and working schedule; The health status judgment module is used to judge the health status of pregnant women according to the comprehensive health assessment index of pregnant women and generate health status signals; The mental health analysis unit specifically includes: A fetal status analysis module, used to generate a fetal status impact index according to the fetal heart rate; The maternal morning sickness analysis module is used to generate the frequency of maternal morning sickness based on the analysis of the number of maternal morning sickness; The maternal mental health assessment module is used to generate the maternal mental health impact index by substituting the fetal status impact index, maternal morning sickness frequency and relative care index into the mental health assessment model; The maternal comprehensive status analysis unit specifically includes: The weight analysis module is used to generate a weight assessment index based on the weight change value of pregnant women; Physical fitness analysis module, used to generate physical fitness index based on the blood sugar and blood pressure of pregnant women; The daily routine analysis module is used to generate a daily routine standard index based on the daily routine of pregnant women; The comprehensive health assessment module is used to substitute the maternal and child mental health impact index, weight assessment index, physical fitness index and lifestyle standard index into the comprehensive health assessment model to generate a comprehensive health assessment index.

[0007] Preferably, the fetal status analysis module specifically includes: Set a monitoring cycle, divide the monitoring cycle into several monitoring periods, and obtain the heart rate value of the fetus during the monitoring period; The heart rate values ​​in all monitoring periods are averaged to obtain the average heart rate; The average heart rate is processed with the middle value of the standard heart rate range to obtain the heart rate difference; Calculate the ratio of the heart rate difference to the standard heart rate to obtain the heart rate difference degree value; Compare the heart rate value during the monitoring period with the standard heart rate range. If the heart rate value is within the standard heart rate range, it means that the fetal heart rate is normal, and the monitoring period is marked as a normal heart rate period. If the heart rate value is outside the standard heart rate range, it means that the fetus' heart rate is abnormal, and the monitoring period is marked as an abnormal heart rate period; Obtain the number of abnormal heart rate periods, calculate the ratio of the number of abnormal heart rate periods to the total number of monitoring periods, and obtain the abnormal heart rate frequency; The abnormal heart rate frequency and the heart rate difference degree values ​​are weighted and summed to obtain the fetal status impact index.

[0008] Preferably, the maternal mental health assessment module specifically includes: Obtain the morning sickness impact index and family care index of pregnant women during the monitoring period, substitute the fetal status impact index, morning sickness impact index and family care index into the mental health assessment model to generate the maternal mental health impact index XL; Among them, the expression of the mental health assessment model is: ; In the expression, TR represents the fetal status impact index, YT represents the morning sickness impact index, JR represents the relative care index, ac, bc, dc are all weight coefficients, and ac+bc+dc=1.

[0009] The method for obtaining the relative accompaniment index specifically includes: Obtain the duration of family care during the monitoring period, calculate the ratio of the duration of family care during the monitoring period to the duration of the monitoring period, and obtain the proportion of the duration of family care during the monitoring period; The proportion of family care time during all monitoring periods is averaged to obtain the family care index.

[0010] Preferably, the method for obtaining the morning sickness impact index specifically includes: Obtain the number of morning sickness events during the monitoring period, calculate the ratio of the number of morning sickness events during the monitoring period to the duration of the monitoring period, and obtain the frequency of morning sickness events during the monitoring period; The frequency of morning sickness in all monitoring periods was averaged to obtain the morning sickness impact index.

[0011] Preferably, the maternal mental health assessment module specifically includes: The mental health impact threshold of the maternal mental health impact index is preset, and the maternal mental health impact index XL is compared with the maternal mental health impact threshold. If the maternal mental health impact index XL is less than or equal to the maternal mental health impact threshold, it means that the lower the maternal mental health impact index is, the more the maternal mental health tends to be normal, and a normal trend signal of maternal mental health change is generated; If the maternal mental health impact index XL is greater than the maternal mental health impact threshold, it means that the higher the maternal mental health impact index is, the more the maternal mental health tends to be abnormal, and an abnormal trend signal of maternal mental health changes is generated; when an abnormal trend signal of maternal mental health changes is received, it is necessary to provide timely psychological counseling for the pregnant woman.

[0012] Preferably, the comprehensive health assessment module specifically includes: Substitute the maternal mental health impact index, weight assessment index, physical fitness index and lifestyle standard index into the comprehensive health assessment model to generate the comprehensive health assessment index ZH; Among them, the expression of the comprehensive health assessment model is: ; In the expression, TZ represents the weight assessment index, ST represents the physical fitness index, ZX represents the standard of living index, α, β, γ, and δ are all weight coefficients, and α+β+γ+δ=1.

[0013] Preferably, the process of obtaining the weight assessment index is: Obtain the weight value within the monitoring period, perform difference processing on adjacent weight values, and obtain the weight change value; The weight change value is compared with the standard weight change range. If the weight change value is within the standard weight change range, the monitoring period is marked as a normal weight change period. If the weight change value is outside the standard weight change range, the monitoring period is marked as an abnormal weight change period; Obtain the number of periods with abnormal weight changes during the monitoring period, calculate the ratio of the number of periods with abnormal weight changes to the total number of monitoring periods, and obtain the proportion of periods with abnormal weight changes; The absolute difference between the weight change value and the middle value of the standard weight change range is calculated to obtain the weight change difference; The weight change difference is calculated by ratio calculation with the middle value of the standard weight change range to obtain the weight change difference degree value; The weight assessment index is obtained by taking a weighted sum of the difference in weight change degree and the proportion of abnormal weight change periods.

[0014] Preferably, the process of obtaining the physical fitness index is: Obtain the blood pressure values ​​of pregnant women during the monitoring period, average all the blood pressure values, and obtain the average blood pressure value; The average blood pressure value is calculated by comparing it with the middle value of the blood pressure standard range to obtain the blood pressure assessment value within the monitoring period; Obtain the blood sugar value of the pregnant woman during the monitoring period, average all the blood sugar values, and obtain the average blood sugar value; The average blood sugar value is calculated by ratio with the middle value of the blood sugar standard range to obtain the blood sugar assessment value within the monitoring period; The blood pressure assessment value and the blood sugar assessment value are weightedly summed to obtain the physical fitness index of the pregnant woman during the monitoring period.

[0015] Preferably, the process of obtaining the standard index of living routine is as follows: Analyze the daily sleep time periods of pregnant women and the sleep time periods in standard daily routines to obtain the overlap rate of sleep time periods; The analysis process specifically includes: comparing the time points corresponding to the daily sleep time period of the pregnant women with the time points corresponding to the sleep time period in the standard daily routine, and averaging all the ratios in the monitoring period according to the ratio between the number of identical time points and the number of time points corresponding to the sleep time period in the standard daily routine, so as to obtain the sleep time period overlap rate; By formula , the similarity rate XS of the sleep duration of pregnant women is calculated; where SA represents the average daily sleep duration of pregnant women during the monitoring period, and BA represents the sleep duration in a standard daily routine; The weighted sum of the overlap rate of sleep time periods and the similarity rate of sleep duration is taken to obtain the standard degree index of pregnant women’s daily routine.

[0016] Preferably, the health status judgment module specifically includes: Preset the comprehensive health assessment index range, and compare the comprehensive health assessment index ZH with the comprehensive health assessment index range; The lowest value of the comprehensive health assessment index range is marked as the first threshold, and the highest value of the comprehensive health assessment index range is marked as the second threshold. If the comprehensive health assessment index ZH is less than or equal to the first threshold, it means that the lower the comprehensive health assessment index ZH is, the better the health status of the pregnant woman is, and a green health status signal is generated; If the comprehensive health assessment index ZH is greater than the first threshold and less than the second threshold, it means that the higher the comprehensive health assessment index ZH is, the more abnormal the health status of the pregnant woman is, and a yellow health status warning signal is generated; If the comprehensive health assessment index ZH is greater than or equal to the second threshold, it means that the higher the comprehensive health assessment index ZH is, the worse the health status of the pregnant woman is, and a red health status signal is generated; When a green health status signal is received, it means that the health status of the pregnant woman is good and the health status of the pregnant woman will continue to be monitored; When a yellow health status signal is received, it means that the health status of the pregnant woman is abnormal and she needs to continue to pay attention to her health status and seek medical treatment in a timely manner if necessary; When a red health status signal is received, it means that the health status of the pregnant woman is poor and she needs to seek medical attention in time.

[0017] The artificial intelligence-based maternal health monitoring system provided by the present invention can analyze and evaluate the mental health and physical health of pregnant women, and issue early warnings on the health status of pregnant women based on the evaluation results. According to the early warning results, the health problems of pregnant women can be discovered in time, so that pregnant women can seek medical treatment in time and reduce the risks during delivery. It can also promote the healthy behavior of pregnant women through health status signals and enhance the self-care awareness of pregnant women. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A system block diagram of an artificial intelligence-based maternal health monitoring system provided in an embodiment of the present invention; Figure 2 A module block diagram of a mental health analysis unit provided in an embodiment of the present invention; Figure 3 A module block diagram of a maternal comprehensive status analysis unit provided in an embodiment of the present invention; Figure 4 A flowchart of a fetal status analysis module provided by an embodiment of the present invention; Figure 5 A flowchart of a weight analysis module provided in an embodiment of the present invention; Figure 6 This is a flow chart of the physical fitness analysis module provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0020] The specific implementation of the present invention is described in detail below in conjunction with specific embodiments.

[0021] like Figure 1 As shown, a maternal and child health monitoring system based on artificial intelligence is provided as an embodiment of the present invention, comprising: A mental health analysis unit is used to analyze the mental health of pregnant women according to the fetal status impact index, the frequency of morning sickness of pregnant women and the family accompanying index to obtain the mental health impact index of pregnant women; The mental health judgment module is used to judge the changing trend of the mental health of pregnant women according to the maternal mental health impact index and generate a mental health changing trend signal; The maternal comprehensive status analysis unit is used to generate a comprehensive health assessment index based on the maternal mental health impact index, weight assessment index, physical fitness index and standard degree index of living and working schedule; The health status judgment module is used to judge the health status of pregnant women based on the comprehensive health assessment index of pregnant women and generate a health status signal.

[0022] like Figure 2 As shown, as a preferred embodiment of the present invention, the mental health analysis unit specifically includes: A fetal status analysis module, used to generate a fetal status impact index according to the fetal heart rate; The maternal morning sickness analysis module is used to generate the frequency of maternal morning sickness based on the analysis of the number of maternal morning sickness; The maternal and child mental health assessment module is used to substitute the fetal status impact index, maternal morning sickness frequency and relative care index into the mental health assessment model to generate the maternal and child mental health impact index.

[0023] like Figure 3 As shown, as a preferred embodiment of the present invention, the pregnant woman comprehensive state analysis unit specifically includes: The weight analysis module is used to generate a weight assessment index based on the weight change value of pregnant women; Physical fitness analysis module, used to generate physical fitness index based on the blood sugar and blood pressure of pregnant women; The daily routine analysis module is used to generate a daily routine standard index based on the daily routine of pregnant women; The comprehensive health assessment module is used to substitute the maternal and child mental health impact index, weight assessment index, physical fitness index and lifestyle standard index into the comprehensive health assessment model to generate a comprehensive health assessment index.

[0024] like Figure 4 As shown, as a preferred embodiment of the present invention, the fetal status analysis module specifically includes: Set a monitoring cycle, divide the monitoring cycle into several monitoring periods, and obtain the heart rate value of the fetus during the monitoring period; The heart rate values ​​in all monitoring periods are averaged to obtain the average heart rate; The average heart rate is processed with the middle value of the standard heart rate range to obtain the heart rate difference; Calculate the ratio of the heart rate difference to the standard heart rate to obtain the heart rate difference degree value; Further, the heart rate value during the monitoring period is compared with the standard heart rate range. If the heart rate value is within the standard heart rate range, it means that the heart rate of the fetus is normal, and the monitoring period is marked as a normal heart rate period. If the heart rate value is outside the standard heart rate range, it means that the fetus' heart rate is abnormal, and the monitoring period is marked as an abnormal heart rate period; Obtain the number of abnormal heart rate periods, calculate the ratio of the number of abnormal heart rate periods to the total number of monitoring periods, and obtain the abnormal heart rate frequency; The abnormal heart rate frequency and the heart rate difference degree values ​​are weighted and summed to obtain the fetal status impact index; It needs to be explained that when the fetus in the pregnant woman's womb is in a healthy state, the pregnant woman usually feels at ease and satisfied. This positive mental state helps them better cope with the various challenges of pregnancy. On the contrary, if the fetus in the pregnant woman's womb is in an abnormal state, it will aggravate the pregnant woman's anxiety and worry, and have a certain impact on her mental health.

[0025] As a preferred embodiment of the present invention, the maternal mental health assessment module specifically includes: Obtain the morning sickness impact index and family care index of pregnant women during the monitoring period, substitute the fetal status impact index, morning sickness impact index and family care index into the mental health assessment model to generate the maternal mental health impact index XL; Among them, the expression of the mental health assessment model is: ; In the expression, TR represents the fetal status impact index, YT represents the morning sickness impact index, JR represents the relative care index, ac, bc, dc are all weight coefficients, and ac+bc+dc=1.

[0026] As a preferred embodiment of the present invention, the method for obtaining the morning sickness impact index specifically includes: Obtain the number of morning sickness events during the monitoring period, calculate the ratio of the number of morning sickness events during the monitoring period to the duration of the monitoring period, and obtain the frequency of morning sickness events during the monitoring period; The morning sickness impact index was obtained by averaging the frequency of morning sickness in all monitoring periods; It needs to be explained that the more frequent the morning sickness of pregnant women, the more likely they are to feel extremely uncomfortable, making them prone to negative emotions such as anxiety, irritability, and depression.

[0027] As a preferred embodiment of the present invention, the method for obtaining the relative companionship index specifically includes: Obtain the duration of family care during the monitoring period, calculate the ratio of the duration of family care during the monitoring period to the duration of the monitoring period, and obtain the proportion of the duration of family care during the monitoring period; The proportion of family care time during all monitoring periods was averaged to obtain the family care index; It needs to be explained that long-term care by family members can provide continuous emotional support for pregnant women, help them relieve anxiety, fear and loneliness during pregnancy and delivery, and reduce the psychological pressure of pregnant women.

[0028] As a preferred embodiment of the present invention, the maternal mental health assessment module specifically includes: The mental health impact threshold of the maternal mental health impact index is preset, and the maternal mental health impact index XL is compared with the maternal mental health impact threshold. If the maternal mental health impact index XL is less than or equal to the maternal mental health impact threshold, it means that the lower the maternal mental health impact index is, the more the maternal mental health tends to be normal, and a normal trend signal of maternal mental health change is generated; If the maternal mental health impact index XL is greater than the maternal mental health impact threshold, it means that the higher the maternal mental health impact index is, the more the maternal mental health tends to be abnormal, and a signal of abnormal trend of maternal mental health change is generated; when a signal of abnormal trend of maternal mental health change is received, it is necessary to provide timely psychological counseling for the maternal psychology, and the counseling methods include but are not limited to psychological counseling by family members, psychological treatment by psychologists, etc.; It needs to be explained that the maternal and child's mental health impact threshold is a preset value, and its acquisition method is consistent with the maternal and child's mental health impact index XL. The specific acquisition method is to calculate by setting the values ​​of the fetal status impact index, the frequency of maternal morning sickness and the family care index; in addition, the values ​​of the fetal status impact index, the frequency of maternal morning sickness and the family care index are set by relevant personnel in this field.

[0029] like Figure 5 As shown, as a preferred embodiment of the present invention, the weight analysis module specifically includes: Obtain the weight value within the monitoring period, perform difference processing on adjacent weight values, and obtain the weight change value; The weight change value is compared with the standard weight change range. If the weight change value is within the standard weight change range, the monitoring period is marked as a normal weight change period. If the weight change value is outside the standard weight change range, the monitoring period is marked as an abnormal weight change period; It should be explained that the standard weight change range is the weight change standard for pregnant women generated based on their body mass index (BMI) before pregnancy. For example, BMI < 18.5 is underweight, BMI between 18.5 and 24.9 is normal weight, BMI between 25 and 29.9 is overweight, and BMI ≥ 30 is obese. Depending on the BIM, the corresponding weight change standard is also different. For example, if the pre-pregnancy BMI is between 18.5 and 24.9, the weight change during pregnancy should be controlled between 11.5 and 16 kg. When BMI < 18.5, the weight gain during pregnancy is It can be more, controlled between 12.5~18kg. When the pre-pregnancy BMI is ≥25, the weight gain should be strictly controlled to be between 7~11.5kg. In addition, the weight change of pregnant women is not uniform. The amount of change varies according to the different stages of pregnancy. For example, the weight gain in the early pregnancy is usually slow, only increasing by 1~2kg. The weight gain in the second and third trimesters will accelerate, increasing by about 0.35~0.5kg per week. The standard weight change range here is obtained by conversion based on the standard corresponding to the pre-pregnancy BIM of pregnant women, and the algorithm is equation conversion. Obtain the number of periods with abnormal weight changes during the monitoring period, calculate the ratio of the number of periods with abnormal weight changes to the total number of monitoring periods, and obtain the proportion of periods with abnormal weight changes; Further, the absolute difference between the weight change value and the middle value of the standard weight change range is calculated to obtain the weight change difference; The weight change difference is calculated by ratio calculation with the middle value of the standard weight change range to obtain the weight change difference degree value; The weight assessment index is obtained by taking a weighted sum of the difference in weight change degree and the proportion of abnormal weight change periods.

[0030] like Figure 6 As shown, as a preferred embodiment of the present invention, the physical fitness analysis module specifically includes: Obtain the blood pressure values ​​of pregnant women during the monitoring period, average all the blood pressure values, and obtain the average blood pressure value; The average blood pressure value is calculated by comparing it with the middle value of the blood pressure standard range to obtain the blood pressure assessment value within the monitoring period; Furthermore, the blood sugar values ​​of pregnant women during the monitoring period are obtained, and all blood sugar values ​​are averaged to obtain an average blood sugar value; The average blood sugar value is calculated by ratio with the middle value of the blood sugar standard range to obtain the blood sugar assessment value within the monitoring period; The blood pressure assessment value and the blood sugar assessment value are weightedly summed to obtain the physical fitness index of the pregnant woman during the monitoring period.

[0031] As a preferred embodiment of the present invention, the daily routine analysis module specifically includes: Analyze the daily sleep time periods of pregnant women and the sleep time periods in standard daily routines to obtain the overlap rate of sleep time periods; It should be explained that the time points corresponding to the daily sleep time period of pregnant women are compared with the time points corresponding to the sleep time period in the standard daily routine. According to the ratio between the number of identical time points and the number of time points corresponding to the sleep time period in the standard daily routine, all ratios in the monitoring period are averaged to obtain the sleep time period overlap rate. By formula , the similarity rate XS of the sleep duration of pregnant women is calculated; where SA represents the average daily sleep duration of pregnant women during the monitoring period, and BA represents the sleep duration in a standard daily routine; The weighted sum of the overlap rate of sleep time periods and the similarity rate of sleep duration is taken to obtain the standard degree index of pregnant women’s daily routine.

[0032] As a preferred embodiment of the present invention, the comprehensive health assessment module specifically includes: Substitute the maternal mental health impact index, weight assessment index, physical fitness index and lifestyle standard index into the comprehensive health assessment model to generate the comprehensive health assessment index ZH; Among them, the expression of the comprehensive health assessment model is: ; In the expression, TZ represents the weight assessment index, ST represents the physical fitness index, ZX represents the standard of living index, α, β, γ, and δ are all weight coefficients, and α+β+γ+δ=1.

[0033] As a preferred embodiment of the present invention, the health status judgment module specifically includes: Preset the comprehensive health assessment index range, and compare the comprehensive health assessment index ZH with the comprehensive health assessment index range; The lowest value of the comprehensive health assessment index range is marked as the first threshold, and the highest value of the comprehensive health assessment index range is marked as the second threshold. If the comprehensive health assessment index ZH is less than or equal to the first threshold, it means that the lower the comprehensive health assessment index ZH is, the better the health status of the pregnant woman is, and a green health status signal is generated; If the comprehensive health assessment index ZH is greater than the first threshold and less than the second threshold, it means that the higher the comprehensive health assessment index ZH is, the more abnormal the health status of the pregnant woman is, and a yellow health status warning signal is generated; If the comprehensive health assessment index ZH is greater than or equal to the second threshold, it means that the higher the comprehensive health assessment index ZH is, the worse the health status of the pregnant woman is, and a red health status signal is generated; When a green health status signal is received, it means that the health status of the pregnant woman is good and the health status of the pregnant woman will continue to be monitored; When a yellow health status signal is received, it means that the health status of the pregnant woman is abnormal and she needs to continue to pay attention to her health status and seek medical treatment in a timely manner if necessary; When a red health status signal is received, it means that the health status of the pregnant woman is poor and she needs to seek medical attention in time.

[0034] The above-mentioned embodiment of the present invention provides an artificial intelligence-based maternal health monitoring system, which analyzes and evaluates the mental health and physical health of pregnant women, and issues early warnings on the health status of pregnant women based on the evaluation results. According to the early warning results, the health problems of pregnant women can be discovered in time, so that pregnant women can seek medical treatment in time and reduce the risks during delivery. The health status signals can also be used to promote the healthy behavior of pregnant women and enhance their self-care awareness.

[0035] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. The maternal and infant health monitoring system based on artificial intelligence is characterized by: include: A mental health analysis unit is used to analyze the mental health of pregnant women according to the fetal status impact index, the frequency of morning sickness of pregnant women and the family accompanying index to obtain the mental health impact index of pregnant women; The mental health judgment module is used to judge the changing trend of the mental health of pregnant women according to the maternal mental health impact index and generate a mental health changing trend signal; The maternal comprehensive status analysis unit is used to generate a comprehensive health assessment index based on the maternal mental health impact index, weight assessment index, physical fitness index and standard degree index of living and working schedule; The health status judgment module is used to judge the health status of pregnant women according to the comprehensive health assessment index of pregnant women and generate health status signals; The mental health analysis unit specifically includes: A fetal status analysis module, used to generate a fetal status impact index according to the fetal heart rate; The maternal morning sickness analysis module is used to generate the frequency of maternal morning sickness based on the analysis of the number of maternal morning sickness; The maternal mental health assessment module is used to generate the maternal mental health impact index by substituting the fetal status impact index, maternal morning sickness frequency and relative care index into the mental health assessment model; The maternal comprehensive status analysis unit specifically includes: The weight analysis module is used to generate a weight assessment index based on the weight change value of pregnant women; Physical fitness analysis module, used to generate physical fitness index based on the blood sugar and blood pressure of pregnant women; The daily routine analysis module is used to generate a daily routine standard index based on the daily routine of pregnant women; The comprehensive health assessment module is used to substitute the maternal and child mental health impact index, weight assessment index, physical fitness index and lifestyle standard index into the comprehensive health assessment model to generate a comprehensive health assessment index.

2. The artificial intelligence-based maternal health monitoring system according to claim 1 is characterized in that: The fetal status analysis module specifically includes: Set a monitoring cycle, divide the monitoring cycle into several monitoring periods, and obtain the heart rate value of the fetus during the monitoring period; The heart rate values ​​in all monitoring periods are averaged to obtain the average heart rate; The average heart rate is processed with the middle value of the standard heart rate range to obtain the heart rate difference; Calculate the ratio of the heart rate difference to the standard heart rate to obtain the heart rate difference degree value; Compare the heart rate value during the monitoring period with the standard heart rate range. If the heart rate value is within the standard heart rate range, it means that the fetal heart rate is normal, and the monitoring period is marked as a normal heart rate period. If the heart rate value is outside the standard heart rate range, it means that the fetus' heart rate is abnormal, and the monitoring period is marked as an abnormal heart rate period; Obtain the number of abnormal heart rate periods, calculate the ratio of the number of abnormal heart rate periods to the total number of monitoring periods, and obtain the abnormal heart rate frequency; The abnormal heart rate frequency and the heart rate difference degree values ​​are weighted and summed to obtain the fetal status impact index.

3. The artificial intelligence-based maternal health monitoring system according to claim 1 is characterized in that: The maternal mental health assessment module specifically includes: Obtain the morning sickness impact index and family care index of pregnant women during the monitoring period, substitute the fetal status impact index, morning sickness impact index and family care index into the mental health assessment model to generate the maternal mental health impact index XL; Among them, the expression of the mental health assessment model is: ； In the expression, TR represents the fetal status impact index, YT represents the morning sickness impact index, JR represents the relative care index, ac, bc, dc are all weight coefficients, and ac+bc+dc=1; The method for obtaining the relative accompaniment index specifically includes: Obtain the duration of family care during the monitoring period, calculate the ratio of the duration of family care during the monitoring period to the duration of the monitoring period, and obtain the proportion of the duration of family care during the monitoring period; The proportion of family care time during all monitoring periods is averaged to obtain the family care index.

4. The artificial intelligence-based maternal health monitoring system according to claim 3 is characterized in that: The method for obtaining the morning sickness impact index specifically includes: Obtain the number of morning sickness events during the monitoring period, calculate the ratio of the number of morning sickness events during the monitoring period to the duration of the monitoring period, and obtain the frequency of morning sickness events during the monitoring period; The frequency of morning sickness in all monitoring periods was averaged to obtain the morning sickness impact index.

5. The artificial intelligence-based maternal health monitoring system according to claim 1, characterized in that: The maternal mental health assessment module specifically includes: The mental health impact threshold of the maternal mental health impact index is preset, and the maternal mental health impact index XL is compared with the maternal mental health impact threshold. If the maternal mental health impact index XL is less than or equal to the maternal mental health impact threshold, it means that the lower the maternal mental health impact index is, the more the maternal mental health tends to be normal, and a normal trend signal of maternal mental health change is generated; If the maternal mental health impact index XL is greater than the maternal mental health impact threshold, it means that the higher the maternal mental health impact index is, the more the maternal mental health tends to be abnormal, and an abnormal trend signal of maternal mental health changes is generated; when an abnormal trend signal of maternal mental health changes is received, it is necessary to provide timely psychological counseling for the pregnant woman.

6. The artificial intelligence-based maternal health monitoring system according to claim 1, characterized in that: The comprehensive health assessment module specifically includes: Substitute the maternal mental health impact index, weight assessment index, physical fitness index and lifestyle standard index into the comprehensive health assessment model to generate the comprehensive health assessment index ZH; Among them, the expression of the comprehensive health assessment model is: ； In the expression, TZ represents the weight assessment index, ST represents the physical fitness index, ZX represents the standard of living index, α, β, γ, and δ are all weight coefficients, and α+β+γ+δ=1.

7. The artificial intelligence-based maternal health monitoring system according to claim 6, characterized in that: The process of obtaining the weight assessment index is as follows: Obtain the weight value within the monitoring period, perform difference processing on adjacent weight values, and obtain the weight change value; The weight change value is compared with the standard weight change range. If the weight change value is within the standard weight change range, the monitoring period is marked as a normal weight change period. If the weight change value is outside the standard weight change range, the monitoring period is marked as an abnormal weight change period; Obtain the number of periods with abnormal weight changes during the monitoring period, calculate the ratio of the number of periods with abnormal weight changes to the total number of monitoring periods, and obtain the proportion of periods with abnormal weight changes; The absolute difference between the weight change value and the middle value of the standard weight change range is calculated to obtain the weight change difference; The weight change difference is calculated by ratio calculation with the middle value of the standard weight change range to obtain the weight change difference degree value; The weight assessment index is obtained by taking a weighted sum of the difference in weight change degree and the proportion of abnormal weight change periods.

8. The artificial intelligence-based maternal health monitoring system according to claim 6, characterized in that: The process of obtaining the physical fitness index is as follows: Obtain the blood pressure values ​​of pregnant women during the monitoring period, average all the blood pressure values, and obtain the average blood pressure value; The average blood pressure value is calculated by comparing it with the middle value of the blood pressure standard range to obtain the blood pressure assessment value within the monitoring period; Obtain the blood sugar value of the pregnant woman during the monitoring period, average all the blood sugar values, and obtain the average blood sugar value; The average blood sugar value is calculated by ratio with the middle value of the blood sugar standard range to obtain the blood sugar assessment value within the monitoring period; The blood pressure assessment value and the blood sugar assessment value are weightedly summed to obtain the physical fitness index of the pregnant woman during the monitoring period.

9. The artificial intelligence-based maternal health monitoring system according to claim 6, characterized in that: The process of obtaining the standard index of living routine is as follows: Analyze the daily sleep time periods of pregnant women and the sleep time periods in standard daily routines to obtain the overlap rate of sleep time periods; The analysis process specifically includes: comparing the time points corresponding to the daily sleep time period of the pregnant women with the time points corresponding to the sleep time period in the standard daily routine, and averaging all the ratios in the monitoring period according to the ratio between the number of identical time points and the number of time points corresponding to the sleep time period in the standard daily routine, so as to obtain the sleep time period overlap rate; By formula , the similarity rate XS of the sleep duration of pregnant women is calculated; where SA represents the average daily sleep duration of pregnant women during the monitoring period, and BA represents the sleep duration in a standard daily routine; The weighted sum of the overlap rate of sleep time periods and the similarity rate of sleep duration is taken to obtain the standard degree index of pregnant women’s daily routine.

10. The artificial intelligence-based maternal health monitoring system according to claim 1, characterized in that: The health status judgment module specifically includes: Preset the comprehensive health assessment index range, and compare the comprehensive health assessment index ZH with the comprehensive health assessment index range; The lowest value of the comprehensive health assessment index range is marked as the first threshold, and the highest value of the comprehensive health assessment index range is marked as the second threshold. If the comprehensive health assessment index ZH is less than or equal to the first threshold, it means that the lower the comprehensive health assessment index ZH is, the better the health status of the pregnant woman is, and a green health status signal is generated; If the comprehensive health assessment index ZH is greater than the first threshold and less than the second threshold, it means that the higher the comprehensive health assessment index ZH is, the more abnormal the health status of the pregnant woman is, and a yellow health status warning signal is generated; If the comprehensive health assessment index ZH is greater than or equal to the second threshold, it means that the higher the comprehensive health assessment index ZH is, the worse the health status of the pregnant woman is, and a red health status signal is generated; When a green health status signal is received, it means that the health status of the pregnant woman is good and the health status of the pregnant woman will continue to be monitored; When a yellow health status signal is received, it means that the health status of the pregnant woman is abnormal and she needs to continue to pay attention to her health status and seek medical treatment in a timely manner if necessary; When a red health status signal is received, it means that the health status of the pregnant woman is poor and she needs to seek medical attention in time.

Images