Artificial intelligence-based pregnant and lying-in woman weight management method and system

Abstract

The invention relates to the technical field of health management, in particular to a pregnant and lying-in woman weight management method and system based on artificial intelligence, and the method comprises the steps: obtaining the weight data of a pregnant and lying-in woman, and generating a weight evaluation value; judging whether the weight of the pregnant and lying-in woman is abnormal or not according to the weight evaluation value; if the weight of the pregnant and lying-in woman is abnormal, obtaining diet data of the pregnant and lying-in Generating a diet nutrition balance value and a diet rule abnormal value according to the diet food type and diet time of the pregnant and lying-in woman; generating a diet influence value according to the diet nutrition balance value and the diet rule abnormal value; judging whether the pregnant and lying-in woman diet needs to be improved according to the diet influence value; by analyzing the weight state of the pregnant and lying-in woman, the abnormal weight state of the pregnant and lying-in woman can be reminded, meanwhile, by analyzing the diet state of the pregnant and lying-in woman, the diet of the pregnant and lying-in woman is adjusted in time according to the analysis result, and therefore the weight change of the pregnant and lying-in woman can be better controlled; the health of pregnant and lying-in women in the pregnant and lying-in period is ensured

Description

Technical Field

[0001] The present invention relates to the technical field of health management, and in particular to a method and system for managing the weight of pregnant women based on artificial intelligence. Background Art

[0002] Weight management of pregnant women is crucial to ensure the health of mothers and babies. During pregnancy, weight gain is usually affected by many factors, including but not limited to nutritional intake, physical activity, metabolic status, hormone levels, etc. Weight gain that is too fast or too slow may affect the health of pregnant women and fetuses. Therefore, scientific and accurate weight management during pregnancy has become a problem that needs to be solved urgently.

[0003] Current weight management methods mainly rely on manual recording and analysis, which are highly subjective and error-prone, and it is difficult to achieve personalized, dynamically adjusted diet and exercise recommendations. With the development of artificial intelligence technology, AI-based health management has become a new trend, which can monitor the weight gain of pregnant women in real time and intelligently, and provide personalized diet and lifestyle recommendations to help pregnant women better control their weight gain and ensure health during pregnancy and childbirth. Summary of the invention

[0004] The purpose of the present invention is to provide an artificial intelligence-based method for weight management of pregnant women to solve the above-mentioned problems.

[0005] The purpose of the present invention can be achieved through the following technical solutions: The artificial intelligence-based maternal weight management method includes the following steps: Set a detection cycle, set a time interval [t1, t2] for the detection cycle, obtain the weight value M1 of the pregnant woman at time point t1 and the weight value M2 of the pregnant woman at time point t2; According to the weight value M1 and the weight value M2, a weight change manifestation value and a detection cycle number abnormality degree value of the predicted weight change during the pregnancy stage are generated; Generate a weight assessment value MP based on the weight change manifestation value and the abnormality value of the number of test cycles predicted by the weight change during pregnancy; According to the weight assessment value MP, determine whether the weight of the pregnant woman is abnormal; If the maternal weight is abnormal, obtain the maternal diet data; the diet data includes food type and diet time; Generate dietary nutritional balance values ​​and dietary regularity abnormality values ​​based on the food types and eating times of pregnant women; Generate the dietary impact value SY according to the dietary nutritional balance value and dietary regularity abnormal value; According to the diet impact value SY, it is judged whether the diet of pregnant women needs to be improved.

[0006] As a further solution of the present invention: generating a weight change manifestation value and a detection cycle number abnormality degree value of a predicted weight change during pregnancy according to the weight value M1 and the weight value M2, specifically includes: Perform difference processing on the weight value M1 and the weight value M2 to generate a weight change value; Performing difference processing on the weight change value and the standard change value to generate a weight change difference value; The weight change difference is processed by ratio with the standard change value to generate the weight change value within the test period; The weight change values ​​of all detection cycles are added together to obtain the total weight change value; The total weight change value is subtracted from the total weight change value during pregnancy to generate the residual weight change value during pregnancy; The residual value of weight change during pregnancy is processed by ratio with the average value of weight change during the detection cycle to obtain the estimated number of weight change cycles during pregnancy; The estimated number of cycles of weight change during pregnancy and the remaining number of detection cycles during pregnancy are processed by difference, so as to generate an abnormal value of the number of detection cycles predicted by weight change during pregnancy; The abnormal value of the number of test cycles is processed by ratio with the total number of test cycles during the pregnancy stage to generate the abnormal degree value of the number of test cycles for predicting the weight change during the pregnancy stage.

[0007] As a further solution of the present invention: the weight assessment value MP is generated according to the weight change manifestation value and the abnormal degree value of the number of detection cycles predicted by the weight change during the pregnancy stage, specifically including: By formula , and obtain the weight assessment value MP; among them, Mb represents the value of weight change during the detection period, Mz represents the abnormal degree value of the number of detection cycles predicted by weight change during pregnancy, ab and ac are weight coefficients, and ab+ac=1.

[0008] As a further solution of the present invention: judging whether the weight of the pregnant woman is abnormal according to the weight assessment value MP specifically includes: Preset a weight assessment threshold, obtain a weight assessment value MP, and compare the weight assessment value MP with the weight assessment threshold; If the weight assessment value MP is less than or equal to the weight assessment threshold, it means that the smaller the weight assessment value MP of the pregnant woman is, the more normal the weight status of the pregnant woman is, and the weight of the pregnant woman will continue to be tested; If the weight assessment value MP is greater than the weight assessment threshold, it means that the larger the weight assessment value MP of the pregnant woman is, the more abnormal the weight status of the pregnant woman is, and the abnormal weight status of the pregnant woman needs to be dealt with in time.

[0009] As a further solution of the present invention: generating a diet impact value SY according to the diet nutritional balance value and the diet regularity abnormal value specifically includes: Establish a diet assessment model, substitute the diet nutritional balance value and diet regularity value into the diet assessment model, and generate the diet impact value SY; Among them, the expression of the diet assessment model is: ; In the expression, Yj represents the abnormal value of dietary nutrition, Yg represents the abnormal value of dietary regularity, Dx represents the basal metabolic evaluation value of pregnant women, and α, β, and γ are all proportional coefficients.

[0010] As a further solution of the present invention: the dietary nutritional balance value is generated in the following manner: Obtain the food types in the diet of pregnant women during the detection period, and perform ratio processing on the total amount of each food and the total diet to generate the food type ratio of the diet of pregnant women; The difference between the proportion of food types in the pregnant women's diet and the standard food proportion was processed to obtain the difference value of nutritional components; Add up all the nutritional difference values ​​to get the dietary nutritional balance abnormality value.

[0011] As a further solution of the present invention: the generation method of the dietary regularity abnormal value is: Obtain the eating time of the pregnant women during the testing period, perform difference processing on the eating time and the standard eating time, and obtain the eating time deviation value; Standard eating time refers to daily eating time, which is the normal eating time of human eating rules; Performing difference processing on the meal time deviation value and the meal time deviation error value to obtain a meal time deviation correction value; The error value of meal time deviation refers to the fluctuation of meal time caused by human activities; The correction value of the meal time deviation is compared with the error value of the meal time deviation to generate a meal regularity difference value.

[0012] As a further solution of the present invention: the method for obtaining the basal metabolic evaluation value of the pregnant woman is: Obtain the basal metabolic rate of pregnant women, perform difference processing on the basal metabolic rate of pregnant women and the standard basal metabolic rate, and generate a basal metabolic rate difference value; The basal metabolic rate difference value is compared with the standard basal metabolic rate to generate a basal metabolic evaluation value.

[0013] As a further solution of the present invention: judging whether the diet of pregnant women needs to be improved according to the diet impact value SY specifically includes: Preset a diet impact threshold, obtain a diet impact value SY, and compare the diet impact value SY with the diet impact threshold; If the diet impact value SY is less than or equal to the diet impact threshold, it means that the smaller the diet impact value SY is, the more normal the diet of the pregnant woman is, and it is necessary to analyze and process the cause of the abnormal weight of the pregnant woman; If the diet impact value SY is greater than the diet impact threshold, it means that the greater the diet impact value SY is, the more abnormal the diet state of the pregnant woman is, and the diet of the pregnant woman needs to be reasonably controlled; When it is necessary to control the diet of pregnant women, make corresponding adjustments based on the weight and dietary status of the pregnant women.

[0014] An artificial intelligence-based maternal weight management system, which is used to execute the above method, comprises: Weight data acquisition module: set the detection cycle, set the time interval [t1, t2] for the detection cycle, obtain the weight value M1 of the pregnant woman at time point t1 and the weight value M2 of the pregnant woman at time point t2; Weight status analysis module: generates weight change manifestation value and abnormal degree value of the number of detection cycles predicted by weight change during pregnancy according to weight value M1 and weight value M2; Weight assessment value generation module: generates a weight assessment value MP based on the weight change manifestation value and the abnormal degree value of the number of detection cycles predicted by the weight change during pregnancy; Maternal weight status judgment module: judge whether the maternal weight is abnormal based on the weight assessment value MP; Maternal diet data acquisition module: if the maternal weight is abnormal, the maternal diet data is acquired; the diet data includes food type and diet time; Maternal diet status analysis module: Generates dietary nutritional balance values ​​and dietary regularity abnormality values ​​based on the food types and dietary time of pregnant women; Diet impact value generation module: Generates the diet impact value SY according to the diet nutritional balance value and the diet regularity abnormal value; Diet improvement demand judgment module: Based on the diet impact value SY, determine whether the diet of pregnant women needs to be improved.

[0015] The present invention can analyze the weight status of pregnant women and remind them of abnormal weight status. At the same time, by analyzing the dietary status of pregnant women, the diet of pregnant women can be adjusted in time according to the analysis results, so as to better control the weight changes of pregnant women and ensure the health of pregnant women during pregnancy and delivery. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present invention will be further described below in conjunction with the accompanying drawings.

[0017] Figure 1 It is a flowchart of the method for weight management of pregnant women based on artificial intelligence provided by the present invention; Figure 2 This is a module block diagram of the artificial intelligence-based maternal weight management system provided by the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of 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.

[0019] See also Figure 1 As shown, the present invention is a method for managing maternal weight based on artificial intelligence, comprising the following steps: Step 1: Obtain the BMI data and weight data of the pregnant woman before pregnancy, and generate the weight assessment value of the pregnant woman; wherein, BMI data refers to the BMI value, and weight data refers to the weight value; In some embodiments, a detection cycle is set, a time interval [t1, t2] is set for the detection cycle, and a weight value M1 of the pregnant woman at time point t1 and a weight value M2 of the pregnant woman at time point t2 are obtained; Perform difference processing on the weight value M1 and the weight value M2 to generate a weight change value; Performing difference processing on the weight change value and the standard change value to generate a weight change difference value; The weight change difference is processed by ratio with the standard change value to generate the weight change value within the test period; The standard change value is the standard change value within the test period obtained by converting the standard corresponding to the pregnant woman's pre-pregnancy BIM, and its algorithm is equation conversion; the standard change value refers to the middle value of the standard weight change range; It should be explained that the standard weight change range of pregnant women during pregnancy is obtained based on the body mass index (BMI) of pregnant women 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 standards are 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 1 When the BMI is between 6kg and 18.5, the weight gain during pregnancy can be more, controlled between 12.5 and 18kg. When the BMI before pregnancy is ≥25, the weight gain should be strictly controlled, controlled between 7 and 11.5kg. In addition, the weight change of pregnant women is not uniform, and the amount of change varies according to the different stages of pregnancy. For example, weight gain in the early stage of pregnancy is usually slow, only increasing by 1 to 2kg, and weight gain in the second and third trimesters will accelerate, increasing by about 0.35 to 0.5kg per week. Further, the weight change values ​​of all detection cycles are added together to obtain a total weight change value; The total weight change value is subtracted from the total weight change value during pregnancy to generate the residual weight change value during pregnancy; The residual value of weight change during pregnancy is processed by ratio with the average value of weight change during the detection cycle to obtain the estimated number of weight change cycles during pregnancy; The estimated number of cycles of weight change during pregnancy and the remaining number of detection cycles during pregnancy are processed by difference, so as to generate an abnormal value of the number of detection cycles predicted by weight change during pregnancy; The abnormal value of the number of test cycles is processed by ratio with the total number of test cycles during the pregnancy stage, so as to generate the abnormal degree value of the number of test cycles for predicting the weight change during the pregnancy stage; By formula , and obtain the weight assessment value MP; where Mb represents the weight change value during the test period, Mz represents the abnormality value of the number of test periods predicted by the weight change during pregnancy, ab and ac are both weight coefficients, and ab+ac=1; It should be explained that the values ​​of ab and ac are set by relevant personnel in this field.

[0020] Step 2: Determine whether the weight of the pregnant woman is abnormal based on the weight assessment value; In some embodiments, a weight assessment threshold is preset, a weight assessment value MP is obtained, and the weight assessment value MP is compared with the weight assessment threshold; If the weight assessment value MP is less than or equal to the weight assessment threshold, it means that the smaller the weight assessment value MP of the pregnant woman is, the more normal the weight status of the pregnant woman is, and the weight of the pregnant woman will continue to be tested; If the weight assessment value MP is greater than the weight assessment threshold, it means that the larger the weight assessment value MP of the pregnant woman is, the more abnormal the weight status of the pregnant woman is, and the abnormal weight status of the pregnant woman needs to be dealt with in time.

[0021] Step 3: If the maternal weight is abnormal, obtain the maternal diet data and generate a diet impact value; the diet data includes food type and diet time; In some embodiments, if the pregnant woman's weight is abnormal, obtaining the type of food consumed by the pregnant woman; Generate dietary nutritional balance values ​​and dietary regularity values ​​based on the food types of pregnant women’s diet; Establish a diet assessment model, substitute the diet nutritional balance value and diet regularity value into the diet assessment model, and generate the diet impact value SY; Among them, the expression of the diet assessment model is: ; In the expression, Yj represents the abnormal value of dietary nutrition, Yg represents the abnormal value of dietary regularity, Dx represents the basic metabolic evaluation value of pregnant women, and α, β, and γ are all proportional coefficients; The dietary nutritional balance value is obtained in the following manner: Obtain the food types of the pregnant women's diet during the detection period, and perform ratio processing on the total amount of each food and the total diet to generate the food type ratio of the pregnant women's diet; The difference between the proportion of food types in the pregnant women's diet and the standard food proportion was processed to obtain the difference value of nutritional components; It should be explained that different foods correspond to different nutrients, and pregnant women have different needs for different nutrients during pregnancy. There are corresponding nutrient standards, so that standard food proportions can be obtained. In addition, the proportion of the required nutrients can be used to obtain the corresponding proportion of food types, that is, the standard food proportion. Add up all the nutritional difference values ​​to get the dietary nutritional balance abnormality value.

[0022] The method for obtaining the abnormal value of the dietary pattern is as follows: Obtain the eating time of the pregnant women during the testing period, perform difference processing on the eating time and the standard eating time, and obtain the eating time deviation value; Standard eating time refers to daily eating time, which is the normal eating time of human eating rules; Performing difference processing on the meal time deviation value and the meal time deviation error value to obtain a meal time deviation correction value; The error value of meal time deviation refers to the fluctuation of meal time caused by human activities, which is within a certain range. For example, if the meal time is advanced or postponed by one hour due to some unexpected circumstances, the meal time is within the normal deviation range, that is, the error value of meal time deviation. The correction value of the meal time deviation is compared with the error value of the meal time deviation to generate a meal regularity difference value; The method for obtaining the basal metabolic evaluation value of the pregnant woman is as follows: Obtain the basal metabolic rate of pregnant women, perform difference processing on the basal metabolic rate of pregnant women and the standard basal metabolic rate, and generate a basal metabolic rate difference value; The basal metabolic rate of pregnant women can be measured by indirect calorimetry, dual-energy X-ray absorptiometry, Harris-Benedict equation or Mifflin-St. Joel equation, bioelectrical impedance analysis, etc. The above methods are existing technologies and will not be described in detail here. The basal metabolic rate difference value is compared with the standard basal metabolic rate to generate a basal metabolic evaluation value.

[0023] Step 4: Determine whether the diet of pregnant women needs to be improved based on the dietary impact value; In some embodiments, a diet impact threshold is preset, a diet impact value SY is obtained, and the diet impact value SY is compared with the diet impact threshold; It should be noted that the method for obtaining the diet impact threshold is the same as the method for obtaining the diet impact value SY, which will not be described in detail here, and its value is set by relevant personnel in this field; If the diet impact value SY is less than or equal to the diet impact threshold, it means that the smaller the diet impact value SY is, the more normal the diet of the pregnant woman is, and it is necessary to analyze and process the cause of the abnormal weight of the pregnant woman; If the diet impact value SY is greater than the diet impact threshold, it means that the greater the diet impact value SY is, the more abnormal the diet state of the pregnant woman is, and the diet of the pregnant woman needs to be reasonably controlled; When it is necessary to control the diet of pregnant women, corresponding adjustments should be made according to the weight and dietary status of the pregnant women; for example, if the weight of the pregnant women increases too quickly or exceeds the normal weight for the corresponding stage, it is necessary to make reasonable adjustments to the amount of food and the food combination of the pregnant women to ensure that the weight of the pregnant women is within a reasonable range.

[0024] See also Figure 2 As shown, the present invention also provides a maternal weight management system based on artificial intelligence, which is used to execute the above method, and the system includes: Weight data acquisition module: set the detection cycle, set the time interval [t1, t2] for the detection cycle, obtain the weight value M1 of the pregnant woman at time point t1 and the weight value M2 of the pregnant woman at time point t2; Weight status analysis module: generates weight change manifestation value and abnormal degree value of the number of detection cycles predicted by weight change during pregnancy according to weight value M1 and weight value M2; Weight assessment value generation module: generates a weight assessment value MP based on the weight change manifestation value and the abnormal degree value of the number of detection cycles predicted by the weight change during pregnancy; Maternal weight status judgment module: judge whether the maternal weight is abnormal based on the weight assessment value MP; Maternal diet data acquisition module: if the maternal weight is abnormal, the maternal diet data is acquired; the diet data includes food type and diet time; Maternal diet status analysis module: Generates dietary nutritional balance values ​​and dietary regularity abnormality values ​​based on the food types and dietary time of pregnant women; Diet impact value generation module: Generates the diet impact value SY according to the diet nutritional balance value and the diet regularity abnormal value; Diet improvement demand judgment module: Based on the diet impact value SY, determine whether the diet of pregnant women needs to be improved.

[0025] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A maternal weight management method based on artificial intelligence, characterized in that: The following steps are involved: Set a detection cycle, set a time interval [t1, t2] for the detection cycle, obtain the weight value M1 of the pregnant woman at time point t1 and the weight value M2 of the pregnant woman at time point t2; According to the weight value M1 and the weight value M2, a weight change manifestation value and a detection cycle number abnormality degree value of the predicted weight change during the pregnancy stage are generated; Generate a weight assessment value MP based on the weight change manifestation value and the abnormality value of the number of test cycles predicted by the weight change during pregnancy; According to the weight assessment value MP, determine whether the weight of the pregnant woman is abnormal; If the maternal weight is abnormal, obtain the maternal diet data; the diet data includes food type and diet time; Generate dietary nutritional balance values ​​and dietary regularity abnormality values ​​based on the food types and eating times of pregnant women; Generate the dietary impact value SY according to the dietary nutritional balance value and dietary regularity abnormal value; According to the diet impact value SY, it is judged whether the diet of pregnant women needs to be improved.

2. The method for weight management of pregnant women based on artificial intelligence according to claim 1, characterized in that: The method of generating a weight change manifestation value and a detection cycle number abnormality degree value of a predicted weight change during pregnancy according to the weight value M1 and the weight value M2 specifically includes: Perform difference processing on the weight value M1 and the weight value M2 to generate a weight change value; Performing difference processing on the weight change value and the standard change value to generate a weight change difference value; The weight change difference is processed by ratio with the standard change value to generate the weight change value within the test period; The weight change values ​​of all detection cycles are added together to obtain the total weight change value; The total weight change value is subtracted from the total weight change value during pregnancy to generate the residual weight change value during pregnancy; The residual value of weight change during pregnancy is processed by ratio with the average value of weight change during the detection cycle to obtain the estimated number of weight change cycles during pregnancy; The estimated number of cycles of weight change during pregnancy and the remaining number of detection cycles during pregnancy are processed by difference, so as to generate an abnormal value of the number of detection cycles predicted by weight change during pregnancy; The abnormal value of the number of test cycles is processed by ratio with the total number of test cycles during the pregnancy stage to generate the abnormal degree value of the number of test cycles for predicting the weight change during the pregnancy stage.

3. The method for weight management of pregnant women based on artificial intelligence according to claim 1, characterized in that: The weight assessment value MP is generated according to the weight change manifestation value and the abnormal degree value of the number of detection cycles predicted by the weight change during the pregnancy stage, specifically including: By formula , and obtain the weight assessment value MP; among them, Mb represents the value of weight change during the detection period, Mz represents the abnormal degree value of the number of detection cycles predicted by weight change during pregnancy, ab and ac are weight coefficients, and ab+ac=1.

4. The method for weight management of pregnant women based on artificial intelligence according to claim 3, characterized in that: The method of judging whether the weight of the pregnant woman is abnormal based on the weight assessment value MP specifically includes: Preset a weight assessment threshold, obtain a weight assessment value MP, and compare the weight assessment value MP with the weight assessment threshold; If the weight assessment value MP is less than or equal to the weight assessment threshold, it means that the smaller the weight assessment value MP of the pregnant woman is, the more normal the weight status of the pregnant woman is, and the weight of the pregnant woman will continue to be tested; If the weight assessment value MP is greater than the weight assessment threshold, it means that the larger the weight assessment value MP of the pregnant woman is, the more abnormal the weight status of the pregnant woman is, and the abnormal weight status of the pregnant woman needs to be dealt with in time.

5. The method for weight management of pregnant women based on artificial intelligence according to claim 1, characterized in that: The generation of the diet impact value SY according to the diet nutritional balance value and the diet regularity abnormal value specifically includes: Establish a diet assessment model, substitute the diet nutritional balance value and diet regularity value into the diet assessment model, and generate the diet impact value SY; Among them, the expression of the diet assessment model is: ； In the expression, Yj represents the abnormal value of dietary nutrition, Yg represents the abnormal value of dietary regularity, Dx represents the basal metabolic evaluation value of pregnant women, and α, β, and γ are all proportional coefficients.

6. The method for weight management of pregnant women based on artificial intelligence according to claim 5, characterized in that: The dietary nutritional balance value is generated in the following manner: Obtain the food types of the pregnant women's diet during the detection period, and perform ratio processing on the total amount of each food and the total diet to generate the food type ratio of the pregnant women's diet; The difference between the proportion of food types in the pregnant women's diet and the standard food proportion was processed to obtain the difference value of nutritional components; Add up all the nutritional difference values ​​to get the dietary nutritional balance abnormality value.

7. The method for weight management of pregnant women based on artificial intelligence according to claim 5, characterized in that: The dietary regularity abnormal value is generated in the following manner: Obtain the eating time of the pregnant women during the testing period, perform difference processing on the eating time and the standard eating time, and obtain the eating time deviation value; Standard eating time refers to daily eating time, which is the normal eating time of human eating rules; Performing difference processing on the meal time deviation value and the meal time deviation error value to obtain a meal time deviation correction value; The error value of meal time deviation refers to the fluctuation of meal time caused by human activities; The correction value of the meal time deviation is compared with the error value of the meal time deviation to generate a meal regularity difference value.

8. The method for weight management of pregnant women based on artificial intelligence according to claim 5, characterized in that: The method for obtaining the basal metabolic evaluation value of the pregnant woman is as follows: Obtain the basal metabolic rate of pregnant women, perform difference processing on the basal metabolic rate of pregnant women and the standard basal metabolic rate, and generate a basal metabolic rate difference value; The basal metabolic rate difference value is compared with the standard basal metabolic rate to generate a basal metabolic evaluation value.

9. The method for weight management of pregnant women based on artificial intelligence according to claim 5, characterized in that: The determination of whether the diet of pregnant women needs to be improved according to the diet impact value SY specifically includes: Preset a diet impact threshold, obtain a diet impact value SY, and compare the diet impact value SY with the diet impact threshold; If the diet impact value SY is less than or equal to the diet impact threshold, it means that the smaller the diet impact value SY is, the more normal the diet of the pregnant woman is, and it is necessary to analyze and process the cause of the abnormal weight of the pregnant woman; If the diet impact value SY is greater than the diet impact threshold, it means that the greater the diet impact value SY is, the more abnormal the diet state of the pregnant woman is, and the diet of the pregnant woman needs to be reasonably controlled; When it is necessary to control the diet of pregnant women, make corresponding adjustments based on the weight and dietary status of the pregnant women.

10. The maternal weight management system based on artificial intelligence is characterized by: The system is used to execute the method described in any one of claims 1 to 9, and the system comprises: Weight data acquisition module: set the detection cycle, set the time interval [t1, t2] for the detection cycle, obtain the weight value M1 of the pregnant woman at time point t1 and the weight value M2 of the pregnant woman at time point t2; Weight status analysis module: generates weight change manifestation value and abnormal degree value of the number of detection cycles predicted by weight change during pregnancy according to weight value M1 and weight value M2; Weight assessment value generation module: generates a weight assessment value MP based on the weight change manifestation value and the abnormal degree value of the number of detection cycles predicted by the weight change during pregnancy; Maternal weight status judgment module: judge whether the maternal weight is abnormal based on the weight assessment value MP; Maternal diet data acquisition module: if the maternal weight is abnormal, the maternal diet data is acquired; the diet data includes food type and diet time; Maternal diet status analysis module: Generates dietary nutritional balance values ​​and dietary regularity abnormality values ​​based on the food types and dietary time of pregnant women; Diet impact value generation module: Generates the diet impact value SY according to the diet nutritional balance value and the diet regularity abnormal value; Diet improvement demand judgment module: Based on the diet impact value SY, determine whether the diet of pregnant women needs to be improved.

Images