Pregnant woman self-management ability evaluation and analysis management method

Abstract

The invention relates to the technical field of medical diagnosis, and particularly discloses a pregnant woman self-management ability evaluation and analysis management method, which comprises the following steps: providing a module of related knowledge points of gestational diabetes in pregnant woman terminal equipment or application, and enabling a pregnant woman to learn and test through the module to obtain the mastering condition of the pregnant woman on knowledge; real-time monitoring is carried out through a pregnant woman terminal device or application, and health data and daily management feedback of a pregnant woman are collected regularly; comprehensively calculating the self-management ability level of the pregnant woman according to the health data and the knowledge mastering condition by utilizing a machine learning algorithm, and outputting an evaluation result; the health data and daily management feedback of the pregnant woman are collected in real time, the health change of the pregnant woman can be continuously monitored, the self-management effect of the pregnant woman can be reflected in time, the knowledge mastering condition and the health data of the pregnant woman are comprehensively analyzed through a machine learning algorithm, the self-management ability of the pregnant woman is accurately evaluated, and the self-management efficiency of the pregnant woman is improved. Weak links in the management process are identified, and personalized optimization suggestions are provided.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical diagnosis, and particularly relates to a method for evaluating, analyzing and managing the self - management ability of pregnant women. Background Art

[0002] Gestational diabetes mellitus (GDM) refers to abnormal glucose metabolism that occurs or is first detected during pregnancy in pregnant women. At present, the current situation of GDM at home and abroad is not optimistic. According to the survey, the prevalence rate of GDM in China is 17.5%. Research has found that GDM will cause a series of short - term and long - term adverse effects on the mother and fetus, such as adverse obstetric outcomes such as premature birth, cesarean section, shoulder dystocia or birth injury, and increase the risk of the mother and fetus suffering from metabolic diseases and cardiovascular diseases.

[0003] Traditional pregnancy health management methods mainly rely on regular medical examinations and professional guidance from doctors. Pregnant women need to receive regular examinations in clinics or hospitals and rely on the health advice provided by doctors for management. However, due to the uneven self - management awareness and ability of pregnant women, especially in the complexity of diabetes management, many pregnant women lack sufficient knowledge and skills for effective health management. Secondly, the health status and self - management ability of pregnant women are dynamically changing, and traditional assessment methods cannot reflect the changes in the health of pregnant women and the management effect in real time. With the development of smart devices and mobile applications, many health management tools and applications have begun to be used for the health monitoring and management of pregnant women. However, existing technologies usually lack a comprehensive personalized assessment and dynamic optimization mechanism, cannot fully consider the health data, learning progress and personal needs of pregnant women, and are difficult to provide targeted self - management suggestions.

[0004] Therefore, it is necessary to propose a method for evaluating, analyzing and managing the self - management ability of pregnant women to solve the problems existing in the prior art, such as the inability to reflect the changes in the health of pregnant women and the management effect in real time, and the low degree of intelligence.

[0005] The above - disclosed information in this background art is only used to increase the understanding of the background art of the present invention. Therefore, it may include prior art that is not known to those of ordinary skill in the art. Summary of the Invention

[0006] The purpose of the present invention is to provide a method for evaluating, analyzing and managing the self - management ability of pregnant women to solve the problems raised in the above - mentioned background art.

[0007] To achieve the above purpose, the present invention provides the following technical solutions:

[0008] A method for evaluating, analyzing and managing the self - management ability of pregnant women, comprising:

[0009] Provide a knowledge point module related to gestational diabetes in the pregnant woman's device or application. The pregnant woman can learn and test through the module to obtain her mastery of the knowledge.

[0010] Conduct real-time monitoring through the pregnant woman's device or application, and regularly collect the pregnant woman's health data and daily management feedback.

[0011] Use machine learning algorithms to comprehensively calculate the pregnant woman's self-management ability level based on the health data and the knowledge mastery situation, and output an evaluation result.

[0012] Analyze the weak aspects of the pregnant woman in the self-management process according to the evaluation result, generate an evaluation report on the pregnant woman's self-management ability, and provide personalized optimization suggestions for the weak aspects.

[0013] Based on the changes in the daily management feedback and the health data, dynamically adjust the self-management ability evaluation report and provide new optimization suggestions.

[0014] An educational resource module is also provided in the pregnant woman's device or application to improve the pregnant woman's awareness of pregnancy self-management.

[0015] Preferably, introduce an evaluation scale for the self-management ability of pregnant women with gestational diabetes to preliminarily evaluate the self-management ability of pregnant women, and generate learning content for pregnant women based on the preliminary evaluation process.

[0016] Analyze the learning process of pregnant women through natural language processing technology to understand their learning behaviors, answer feedback, and learning progress.

[0017] Use a weighted scoring model to evaluate the learning progress and test results of pregnant women. The formula of the weighted scoring model is as follows:

[0018]

[0019] In the formula, S total is the total score, w i is the weight of each question, and S i is the score of each question.

[0020] Based on the pregnant woman's learning history, the test results, and actual operation performance, use a comprehensive scoring algorithm to evaluate the pregnant woman's mastery of the learned knowledge.

[0021] According to the knowledge mastery situation, use machine learning algorithms to dynamically adjust the learning path, and recommend learning content and test questions that match the pregnant woman's current mastery level.

[0022] Collect the pregnant woman's question feedback in real time, and adjust the learning content or provide additional help according to the question feedback.

[0023] Preferably, the health data of the pregnant woman is collected in real time through a smart device, and the pregnant woman can choose to manually input the health data, and the daily management feedback of the pregnant woman in the pregnant woman terminal device or application is collected;

[0024] The smart device is connected to the pregnant woman terminal device or application through an API interface or a communication protocol to achieve instant data transmission;

[0025] Based on the collected health data and the health data manually input by the pregnant woman, a health record of the pregnant woman is formed and stored in a database;

[0026] Based on the health record, the health status of the pregnant woman is dynamically evaluated, and the LSTM is used to predict the health trend of the pregnant woman in combination with historical data. The LSTM formula is as follows:

[0027] h t = σ(W h ·h t-1 + W γ ·γ t + b h )

[0028] In the formula, h t is the current hidden layer state, σ is the activation function, W h and W γ are weight matrices, γ t is the input, and b h is the bias term.

[0029] Preferably, the multi-layer perceptron is trained based on the health data and the knowledge mastery situation, and the classification label of the self-management ability is output;

[0030] Combined with the judgment criteria of the self-management ability evaluation scale for pregnant women with gestational diabetes, the final score of the self-management ability is given;

[0031] The classification label and the analysis are jointly used as the evaluation result of the self-management ability, and a data interface is built using Flask or FastAPI to provide the evaluation result to the pregnant woman in real time.

[0032] Preferably, through the analysis of the evaluation result, the weak aspects are quantified in combination with the real-time health data, and the severity of the weak area is measured using a differential score or weight;

[0033] The K-means clustering algorithm is used for data clustering, and pregnant women with similar weak areas are grouped together to find out the common characteristics of the weak areas;

[0034]

[0035] Wherein, β j is the jth cluster, u x is the data point, and μ j is the centroid of the cluster;

[0036] Based on the described weak areas of the pregnant woman, personalized optimization suggestions are generated based on data-driven analysis and expert knowledge, and the successful experiences or optimization methods of pregnant women with similar needs are recommended;

[0037] Integrate ChatGPT to integrate the evaluation results, the weak areas, and the optimization suggestions of the pregnant woman into the report, and automatically add data interpretation, trend prediction, and health analysis information.

[0038] Preferably, the collected latest health data is compared with the health record of the pregnant woman to find the changes in the health data;

[0039] Combined with the daily management feedback of the pregnant woman, the self-management ability is re-evaluated, and the latest evaluation results are output;

[0040] Based on the latest evaluation results, re-analysis is carried out, the content of the optimization suggestions is dynamically adjusted, or new optimization suggestions that meet the current health status of the pregnant woman are generated;

[0041] Based on the self-management ability evaluation report, the content of the evaluation results and the optimization suggestions part is automatically updated through ChatGPT;

[0042] Regularly collect the feedback information of the pregnant woman on the self-management ability evaluation report and the optimization suggestions, and adjust the generation rules of the optimization suggestions according to the feedback information.

[0043] Preferably, a collaborative filtering or content-based recommendation system is used to push personalized educational resources according to the health data and the daily management feedback;

[0044] Combined with current medical research and dynamic data, articles or tips related to pregnancy health management are automatically generated through natural language generation technology;

[0045] By providing interactive educational resources, the pregnant woman is involved in the learning process, and personalized feedback is provided according to the performance of the pregnant woman.

[0046] Compared with the prior art, the beneficial effects of the present invention are:

[0047] By collecting the health data of pregnant women and daily management feedback in real time, the present invention can continuously monitor the health changes of pregnant women and timely reflect the effects of their self-management, solving the problem that traditional methods cannot reflect the health changes of pregnant women in real time. At the same time, through machine learning algorithms, comprehensively analyze the knowledge mastery situation and health data of pregnant women, accurately evaluate the self-management ability of pregnant women, identify weak links in the management process, and provide personalized optimization suggestions, effectively improving the self-management ability of pregnant women. Introducing the educational resource module further enhances pregnant women's awareness of pregnancy self-management and promotes the health education and knowledge absorption of pregnant women. The method of the present invention not only improves the intelligent level of pregnant women's health management, but also can achieve continuous tracking and dynamic adjustment to ensure that pregnant women receive personalized and scientific health management support throughout the pregnancy. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a diagram of the method for evaluating and analyzing the self-management ability of pregnant women according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0050] Embodiment 1:

[0051] Please refer to Figure 1 As shown, a method for evaluating and analyzing the self-management ability of pregnant women includes:

[0052] Provide a module of relevant knowledge points about gestational diabetes in the pregnant women's terminal device or application. Pregnant women learn and test through the module to obtain the knowledge mastery situation of pregnant women;

[0053] Through the pregnant women's terminal device or application, conduct real-time monitoring and regularly collect the health data of pregnant women and daily management feedback;

[0054] Use machine learning algorithms to comprehensively calculate the self-management ability level of pregnant women based on the health data and knowledge mastery situation, and output the evaluation results;

[0055] According to the evaluation results, analyze the weak aspects of pregnant women in the self-management process, generate an evaluation report on the self-management ability of pregnant women, and provide personalized optimization suggestions for the weak aspects;

[0056] Based on the changes in daily management feedback and health data, dynamically adjust the evaluation report on self-management ability and provide new optimization suggestions;

[0057] An educational resource module is also provided in the pregnant woman's device or application to improve the pregnant woman's awareness of self-management during pregnancy.

[0058] Introduce the Self-Management Ability Evaluation Scale for Pregnant Women with Gestational Diabetes Mellitus to preliminarily evaluate the self-management ability of pregnant women, and generate the learning content of pregnant women based on the preliminary evaluation process;

[0059] The Self-Management Ability Evaluation Scale for Pregnant Women with Gestational Diabetes Mellitus includes 4 dimensions: self-management awareness (8 items), pregnancy management (7 items), blood glucose management (12 items), and resource utilization (5 items), with a total of 32 items. All items in this scale adopt the Likert 5-level scoring method, all items in the scale are scored positively, the sum of the scores of each item is the total score of the scale, and the self-management level of pregnant women is positively correlated with the scale score.

[0060] The grading of the measurement results uses standard score analysis, standard score = (actual score / highest possible score) × 100, and it is defined that the standard score < 60 indicates poor self-management ability, 60 - 80 indicates medium self-management ability, and > 80 indicates good self-management ability.

[0061] Analyze the learning process of pregnant women through natural language processing technology to understand their learning behaviors, answer feedback, and learning progress;

[0062] Knowledge points related to gestational diabetes mellitus include, but are not limited to, diagnostic criteria for gestational diabetes mellitus, diet control, exercise recommendations, blood glucose monitoring and adjustment methods, etc.;

[0063] Use a weighted scoring model to evaluate the learning progress and test results of pregnant women; among them, self-tests include multiple-choice questions, true or false questions, and short-answer questions, and pregnant women need to answer relevant questions according to the prompts to evaluate their mastery of knowledge;

[0064] Based on the learning history, test results, and actual operation performance of pregnant women, use a comprehensive scoring algorithm to evaluate the mastery of knowledge that pregnant women have learned;

[0065] According to the mastery of knowledge, use machine learning algorithms to dynamically adjust the learning path and recommend learning content and test questions that meet the current mastery level of pregnant women;

[0066] Collect the problem feedback of pregnant women in real time, and adjust the learning content or provide additional help according to the problem feedback.

[0067] By introducing natural language processing technology and a weighted scoring model to analyze the learning process of pregnant women and adjust the learning path in real time, it is ensured that pregnant women can learn at a pace suitable for themselves. This intelligent learning adjustment mechanism can greatly improve the pregnant women's mastery of pregnancy knowledge and enhance their self-management ability.

[0068] Collect the health data of pregnant women in real time through intelligent devices, and pregnant women can choose to manually input health data, and collect the daily management feedback of pregnant women in the pregnant woman's device or application;

[0069] The health data includes data in multiple dimensions such as blood glucose monitoring data, exercise volume, diet content, weight change, and the mental state of pregnant women;

[0070] The intelligent device is connected to the pregnant woman's device or application through an API interface or communication protocol to achieve instant data transmission;

[0071] Based on the collected and manually input health data by pregnant women, form a health record of pregnant women and store it in the database;

[0072] Dynamically evaluate the health status of pregnant women based on the health record, and use LSTM to predict the health trend of pregnant women in combination with historical data.

[0073] Use a multi-layer perceptron to train based on health data and knowledge mastery, and output classification labels of self-management ability;

[0074] Combined with the judgment criteria of the self-management ability evaluation scale for pregnant women with gestational diabetes, give the final score of self-management ability;

[0075] Use the classification label and analysis together as the evaluation result of self-management ability, and build a data interface using Flask or FastAPI to provide the evaluation result to pregnant women in real time.

[0076] The above combines the health data of pregnant women with knowledge mastery, and uses machine learning algorithms to calculate and output the evaluation result. This comprehensive evaluation method can dynamically and real-time reflect the actual performance of pregnant women in pregnancy health management, which is more accurate and efficient than the traditional method that only relies on regular examinations.

[0077] Through the analysis of the evaluation result, quantify the weak aspects in combination with real-time health data, and use differential scores or weights to measure the severity of the weak areas;

[0078] Use the K-means clustering algorithm for data clustering, and divide pregnant women with similar weak areas into a group to find out the common characteristics of the weak areas;

[0079] Based on the weak areas of pregnant women, generate personalized optimization suggestions based on data-driven analysis and expert knowledge, and recommend the successful experiences or optimization methods of pregnant women with similar needs;

[0080] The successful experiences include personalized health management plans such as diet plan adjustment, exercise program optimization, sleep quality management, and emotion regulation;

[0081] Integrate ChatGPT to incorporate the evaluation results, weak areas, and optimization suggestions for pregnant women into the report, and automatically add data interpretation, trend prediction, and health analysis information.

[0082] Through the analysis of the evaluation results, combined with the health data and learning progress of pregnant women, personalized optimization suggestions are generated and continuously updated based on dynamic changes. Moreover, during the generation of optimization suggestions, data-driven analysis and expert knowledge are combined, making the optimization suggestions not only scientifically accurate but also practically guiding. This personalized optimization mechanism can provide precise guidance for the specific needs of pregnant women and effectively improve their self-management ability.

[0083] Compare the newly collected health data with the health records of pregnant women to detect changes in the health data;

[0084] Combine the daily management feedback of pregnant women, re-evaluate the self-management ability, and output the latest evaluation results;

[0085] Re-analyze based on the latest evaluation results, dynamically adjust the content of the optimization suggestions, or generate new optimization suggestions that conform to the current health status of pregnant women;

[0086] Based on the self-management ability assessment report, automatically update the content of the evaluation results and optimization suggestions section through ChatGPT;

[0087] Regularly collect feedback information from pregnant women on the self-management ability assessment report and optimization suggestions, and adjust the optimization suggestion generation rules according to the feedback information.

[0088] Use a collaborative filtering or content-based recommendation system to push personalized educational resources based on health data and daily management feedback;

[0089] Combine current medical research and dynamic data, and automatically generate articles or tips related to pregnancy health management through natural language generation technology;

[0090] Provide interactive educational resources to enable pregnant women to participate in the learning process and provide personalized feedback based on their performance.

[0091] Provide an educational resource module in the pregnant women's device or application, which can push personalized educational resources while recommending self-management knowledge, and improve pregnant women's awareness of self-management through interactive learning. This design can enhance pregnant women's absorption ability of self-management knowledge and promote their better participation in the self-management process.

[0092] Example 2:

[0093] Apply the evaluation and analysis management method of pregnant women's self - management ability to the pregnancy management of pregnant women, especially in the scientific and precise self - management of gestational diabetes, improve the health status, and reduce the occurrence of pregnancy complications. The application process is as follows:

[0094] (1) Learning and evaluation stage

[0095] The pregnant woman downloads and logs in to the application. When initially using it, she conducts self - assessment through the self - management ability evaluation scale for gestational diabetes to obtain the preliminary score of her management ability.

[0096] The pregnant woman learns knowledge about gestational diabetes according to the learning content recommended by the module and takes tests within the application to evaluate her mastery of the knowledge.

[0097] Design and construct an entertainment game called "Eliminating Misunderstandings about Sugar Control". Combining the 4 dimensions of the self - management ability evaluation scale for gestational diabetes, the pregnant woman can switch the game mode so that the specific game content rotates among the health education content of the 4 dimensions. There are specific knowledge point classifications (9 correct and 9 wrong) and interaction designs (clicking to change color to judge the correct rate) in each dimension, and the score is automatically calculated according to the pregnant woman's answering situation to obtain the score of the pregnant woman's self - management level.

[0098] Examples of specific game content: "Fruits can be eaten freely", "The lower the blood sugar during pregnancy, the better", "Fasting blood sugar should be controlled at 3.3 - 3.5 mmol / L", "If there are symptoms such as dizziness, palpitation, tremors, hunger, etc., it is necessary to inform the nurse", "Exercise can be carried out immediately after meals", "Sugar - free foods do not raise blood sugar", etc.

[0099] According to the learning progress and test results, use weighted scoring models, machine learning algorithms, etc. to evaluate the self - management ability of pregnant women.

[0100] (2) Real - time health data collection and analysis stage

[0101] The pregnant woman measures key health data such as blood sugar, weight, blood pressure, etc. in real - time through intelligent devices and inputs daily feedback (such as diet, exercise, mood, etc.).

[0102] Based on the LSTM model, dynamically evaluate the health data of pregnant women, predict the health trend, and generate a health record.

[0103] Combining historical health data and current health status, output a health assessment report, including the evaluation of the pregnant woman's self - management ability and the prediction of the health trend.

[0104] (3) Personalized optimization suggestions and dynamic adjustment

[0105] Based on the evaluation results of pregnant women, automatically identify their weak areas in the management process (such as large blood sugar fluctuations, improper diet, etc.), and generate personalized optimization suggestions, such as adjusting the diet plan, increasing exercise, etc.

[0106] As the health data and the daily feedback of pregnant women are updated, through automated learning path adjustment and optimization suggestions, provide new guidance for pregnant women in real time and dynamically adjust the evaluation report.

[0107] (4) Feedback and optimization loop

[0108] Pregnant women can regularly provide feedback on the self-management ability evaluation report and optimization suggestions, and then adjust the learning content and management suggestions according to the feedback information.

[0109] Obtain the latest health data and combine the feedback content to continuously update the self-management evaluation report to ensure that the personalized optimization suggestions meet the current health needs of pregnant women.

[0110] Example output:

[0111] ① Pregnant women's self-management ability evaluation report:

[0112] Evaluation score: 85 points (good)

[0113] Advantages: Pregnant women have a good grasp of diet management knowledge and stable blood sugar control.

[0114] Weak areas: Lack of exercise, need to increase daily exercise.

[0115] Personalized optimization suggestions: According to the current health status, it is recommended to increase moderate-intensity exercise 3 times a week, each time lasting 30 minutes, and keep monitoring blood sugar regularly every day.

[0116] ② Health trend prediction:

[0117] It is predicted that there is a risk of slight blood sugar fluctuations in pregnant women within the next two weeks. It is recommended to adjust the sugar intake in the diet and increase low-intensity aerobic exercise.

[0118] ③ Recommended educational resources:

[0119] Push relevant articles: "How to Control Gestational Diabetes through Diet Management"

[0120] Provide learning modules: Exercise programs for gestational diabetes to help pregnant women with self-management.

[0121] Example 3:

[0122] An embodiment of the present invention further provides a computer-readable storage medium, on which a program for implementing the method for evaluating and analyzing the self-management ability of pregnant women as described in any one of the above is stored. When the program is executed by a processor, it implements each process of the above-described embodiment of the evaluation and analysis management method and can achieve the same technical effects. To avoid repetition, it will not be elaborated here. Among them, the computer-readable storage medium includes, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc, etc.

[0123] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0124] In the drawings of the disclosed embodiments of the present invention, only the structures related to the disclosed embodiments of the present invention are involved, and other structures can refer to the general design. Without conflict, the same embodiment and different embodiments of the present invention can be combined with each other.

[0125] The flowcharts shown in the drawings are only illustrative, and do not necessarily include all the contents and operations / steps, nor do they necessarily need to be executed in the described order. For example, some operations / steps can also be decomposed, combined, or partially merged, so the actual execution order may change according to the actual situation.

[0126] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for evaluating and analyzing the self-management ability of pregnant women, characterized in that, Including: Provide relevant knowledge modules for gestational diabetes in the pregnant women's device or application. Pregnant women can learn and test through the modules to obtain their mastery of knowledge. Conduct real-time monitoring through the pregnant women's device or application, and regularly collect pregnant women's health data and daily management feedback. Use machine learning algorithms to comprehensively calculate the self-management ability level of pregnant women based on the health data and the knowledge mastery situation, and output an evaluation result. Analyze the weak aspects of pregnant women in the self-management process according to the evaluation result, generate a self-management ability evaluation report for pregnant women, and provide personalized optimization suggestions for the weak aspects. Dynamically adjust the self-management ability evaluation report based on the changes in the daily management feedback and the health data, and provide new optimization suggestions. An educational resource module is also provided in the pregnant women's device or application to improve pregnant women's awareness of self-management during pregnancy.

2. The self - management ability evaluation and analysis management method for pregnant women according to claim 1, characterized in that: The pregnant women learn and test through the module to obtain their mastery of knowledge, including: Introduce an evaluation scale for the self-management ability of pregnant women with gestational diabetes to preliminarily evaluate the self-management ability of pregnant women, and generate learning content for pregnant women based on the preliminary evaluation process. Analyze the learning process of pregnant women through natural language processing technology to understand their learning behaviors, answer feedback, and learning progress. Use a weighted scoring model to evaluate the learning progress and test results of pregnant women. The formula of the weighted scoring model is as follows: Where, S total is the total score, w i is the weight of each question, and S i is the score of each question; Based on the learning history of pregnant women, the test results, and actual operation performance, use a comprehensive scoring algorithm to evaluate the mastery of knowledge that pregnant women have learned. Dynamically adjust the learning path according to the knowledge mastery situation using machine learning algorithms, and recommend learning content and test questions that match the current mastery level of pregnant women. Collect pregnant women's problem feedback in real time, and adjust the learning content or provide additional help according to the problem feedback.

3. The method for evaluating and analyzing the self-management ability of pregnant women according to claim 2, characterized in that: The real-time monitoring through the pregnant women's device or application, and regularly collecting pregnant women's health data and daily management feedback, including: Real-time collect the health data of pregnant women through intelligent devices, and pregnant women can choose to manually input the health data, and collect the daily management feedback of pregnant women in the pregnant women's device or application. The intelligent device is connected to the pregnant women's device or application through an API interface or communication protocol to achieve instant data transmission. Based on the collected and manually input health data of pregnant women, form a health record for pregnant women and store it in the database. Dynamically evaluate the health status of pregnant women based on the health record, and use LSTM to predict the health trend of pregnant women in combination with historical data. The LSTM formula is as follows: h t = σ(W h ·h t-1 + W γ ·γ t + b h ) where h t is the current hidden layer state, σ is the activation function, W h and W γ are weight matrices, γ t is the input, and b h is the bias term.

4. The self-management ability assessment and analysis management method for pregnant women according to claim 3, characterized in that: The use of machine learning algorithms to comprehensively calculate the self-management ability level of pregnant women based on the health data and the knowledge mastery situation, and output an evaluation result, including: Use a multi-layer perceptron to train based on the health data and the knowledge mastery situation, and output classification labels of self-management ability. Combined with the judgment criteria of the evaluation scale for the self-management ability of pregnant women with gestational diabetes, give the final score of self-management ability. Take the classification label and the analysis as the evaluation result of the self - management ability, and use Flask or FastAPI to build a data interface for providing the evaluation result to pregnant women in real time.

5. The self - management ability evaluation and analysis management method for pregnant women according to claim 4, characterized in that: Analyze the weak aspects of pregnant women in the self - management process according to the evaluation result, and generate an evaluation report on the self - management ability of pregnant women. Provide personalized optimization suggestions for the weak aspects, including: Through the analysis of the evaluation result, combine the real - time health data to quantify the weak aspects, and use differential scores or weights to measure the severity of the weak areas; Use the K - means clustering algorithm for data clustering, group pregnant women with similar weak areas into one group, so as to find out the common characteristics of the weak areas; where β j is the j-th cluster, u x is the data point, and μ j is the centroid of the cluster; According to the weak areas of pregnant women, generate personalized optimization suggestions based on data - driven analysis and expert knowledge, and recommend the successful experiences or optimization methods of pregnant women with similar needs; Integrate ChatGPT to integrate the evaluation result, the weak areas, and optimization suggestions of pregnant women into the report, and automatically add data interpretation, trend prediction, and health analysis information.

6. The self - management ability evaluation and analysis management method for pregnant women according to claim 5, characterized in that: Based on the daily management feedback and the changes in the health data, dynamically adjust the self - management ability evaluation report and provide new optimization suggestions, including: Compare the newly collected health data with the health records of pregnant women to find the changes in the health data; Combine the daily management feedback of pregnant women, re - evaluate the self - management ability, and output the latest evaluation result; Re - analyze according to the latest evaluation result, dynamically adjust the content of the optimization suggestions, or generate new optimization suggestions that meet the current health status of pregnant women; Based on the self - management ability evaluation report, automatically update the content of the evaluation result and the optimization suggestions part through ChatGPT; Regularly collect the feedback information of pregnant women on the self - management ability evaluation report and the optimization suggestions, and adjust the generation rules of the optimization suggestions according to the feedback information.

7. A method for evaluating and analyzing the self - management ability of pregnant women according to claim 6, characterized in that: An educational resource module is also provided in the pregnant women's device or application to improve pregnant women's awareness of pregnancy self - management, including: Use a collaborative - filtering - or content - based recommendation system to push personalized educational resources according to the health data and the daily management feedback; Combine current medical research and dynamic data, and use natural language generation technology to automatically generate articles or tips related to pregnancy health management; Provide interactive educational resources to let pregnant women participate in the learning process and provide personalized feedback according to the performance of pregnant women.

Images