Refined health care management and control method and management and control platform for pregnancy preparation people

Abstract

The invention discloses a refined health care management and control method and management and control platform for pregnancy preparation people, and relates to the technical field of health care, and the method comprises the steps: building a full-period pregnancy preparation health care system, and obtaining a plurality of health treatment and nursing nodes; constructing a pregnancy preparation health nursing patient education knowledge base, and obtaining a patient education nursing node partition knowledge base; obtaining a target health care risk parameter; and obtaining health care consultation knowledge, and performing refined health care management and control on the target user. The problems that existing pregnancy preparation health care lacks refined and personalized adjustment and risk assessment for individual health conditions, living habits and specific requirements, accurate, objective and comprehensive health care knowledge is difficult to obtain, consequently, tension and anxiety of a patient cannot be effectively relieved, the overall medical experience is poor, and the patient experience is poor are solved. The technical problems are solved, and the technical effects of improving the overall working efficiency, the medical experience and satisfaction of the patient and the treatment effect are achieved.

Description

Technical Field

[0001] The present application relates to the technical field related to health care, and specifically to a management and control method and a management and control platform for refined health care for people preparing for pregnancy. Background Art

[0002] With the increasing pressure of modern life and work and the increasing complexity of environmental factors, the incidence of infertility is gradually increasing worldwide. Although in vitro fertilization and embryo transfer (IVF-ET) technology is becoming more and more mature, as an assisted reproductive method for the treatment of infertility, it has brought fertility opportunities to more and more infertile patients, but about 10% of patients treated with IVF-ET still have repeated transplantation failures under the premise of having high-quality embryos. Patients with adverse pregnancies such as multiple transplantation failures, biochemical pregnancy or spontaneous abortion not only bear pressure from family and society, but also face high medical expenses and urgent expectations for pregnancy, causing them to show different degrees of anxiety and depression. The anxiety and depression of patients with repeated transplantation failures has become the focus of current nursing research. Up to now, major assisted reproductive centers across the country have not yet formed a complete management model. Combining various studies with basic clinical conditions, it is found that the main reason for patients' anxiety and depression is the lack of knowledge and vague understanding of the concept of new things. Therefore, it is very important to carry out refined nursing management throughout the whole cycle.

[0003] As the demand for health care among people preparing for pregnancy increases, and tends to be more refined and personalized, traditional health care methods for preparing for pregnancy often focus on basic physiological hygiene education and simple nutritional guidance, lacking careful consideration of individual health status and living habits, and are difficult to meet the comprehensive, in-depth, and personalized health care needs of modern people preparing for pregnancy. Traditional health care management for preparing for pregnancy usually includes a number of basic examinations, such as physical examinations, gynecological examinations, etc., to ensure that people preparing for pregnancy are physiologically qualified for conception. However, they often only focus on basic physiological indicators, lack in-depth analysis and evaluation of potential health risks or individualized health needs, and traditional methods are difficult to provide nutritional guidance based on individual nutritional needs, such as age, weight, physical condition and other factors. In addition, traditional health care management for preparing for pregnancy is also insufficient in the dissemination of health knowledge. People preparing for pregnancy usually obtain health knowledge through books, the Internet or doctor consultation, but these channels often provide relatively scattered information, lacking systematicity and authority.

[0004] Therefore, at the current stage, the technologies related to health care management lack refined and personalized adjustments and risk assessments based on individual health conditions, living habits and specific needs, and it is difficult to obtain accurate, objective and comprehensive health care knowledge, which in turn leads to technical problems such as the inability to effectively relieve patient tension and anxiety, poor overall medical experience, and poor treatment effects and patient satisfaction. Summary of the invention

[0005] This application solves the technical problems of the existing health care for pregnant women, such as the lack of refined and personalized adjustments and risk assessments for individual health conditions, living habits and specific needs, and the difficulty in obtaining accurate, objective and comprehensive health care knowledge, which leads to the inability to effectively relieve patients' tension and anxiety, poor overall medical experience, and poor treatment effects and patient satisfaction, by providing a management and control method and management platform for refined health care for people preparing for pregnancy. This achieves the technical effect of improving overall work efficiency, patient medical experience and satisfaction, and treatment effects.

[0006] The present application provides a method for controlling refined health care for people preparing for pregnancy, the method comprising: establishing a full-cycle health care system for preparing for pregnancy, extracting care nodes from the full-cycle health care system for preparing for pregnancy, and obtaining multiple health treatment care nodes; constructing a patient education knowledge base for preparing for pregnancy health care according to the full-cycle health care system for preparing for pregnancy, and associating and partitioning the patient education knowledge base for preparing for pregnancy health care and the multiple health treatment care nodes to obtain a patient education care node partition knowledge base; calling and obtaining the preparation for pregnancy treatment data and current treatment node of a target user, performing health risk analysis based on the preparation for pregnancy treatment data and the current treatment node, and obtaining a target health care risk parameter; performing knowledge matching on the target health care risk parameter and the current treatment node based on the patient education care node partition knowledge base to obtain a target health treatment care knowledge set; pushing the target health treatment care knowledge set to the target user for knowledge consultation to obtain health care consultation knowledge, and performing refined health care control on the target user based on the health care consultation knowledge.

[0007] In a possible implementation, the target health care risk parameters are obtained and the following processing is also performed: obtaining information on physiological influencing factors for pregnancy preparation, wherein the information on physiological influencing factors for pregnancy preparation includes age, gender, physical condition and living habits; collecting and obtaining a treatment data set of patients preparing for pregnancy, and based on the information on physiological influencing factors for pregnancy preparation and the multiple health treatment and care nodes, classifying, training and identifying the treatment data set of patients preparing for pregnancy, and constructing a health node analysis model library for pregnancy preparation treatment; classifying the physiological factors of the target user through the information on physiological influencing factors for pregnancy preparation to obtain target physiological factor parameters; based on the target physiological factor parameters and the current treatment node, obtaining a target pregnancy preparation treatment health analysis model from the pregnancy preparation treatment health node analysis model library; performing health analysis on the pregnancy preparation treatment data based on the target pregnancy preparation treatment health analysis model, and outputting the target health care risk parameters.

[0008] In a possible implementation, the construction of the pre-pregnancy treatment health node analysis model library also performs the following processing: classifying and identifying the pre-pregnancy patient treatment data set through the pre-pregnancy physiological influencing factor information to obtain the patient factor parameter classification treatment data set; performing deep learning training on the patient factor parameter classification treatment data set based on the multiple health treatment nursing nodes to obtain an initial treatment health node analysis model set; performing performance verification and model parameter optimization on the initial treatment health node analysis model set to obtain a pre-pregnancy treatment health node analysis model set; classifying and identifying the pre-pregnancy treatment health node analysis model set according to factor parameters and nursing nodes to construct the pre-pregnancy treatment health node analysis model library.

[0009] In a possible implementation, the obtaining of the initial treatment health node analysis model set also performs the following processing: extracting treatment features from the patient factor parameter classification treatment data set to obtain a classification factor parameter treatment feature set; performing association feature analysis on the classification factor parameter treatment feature set based on the multiple health treatment nursing nodes to obtain multiple node factor parameter association feature sets; performing data association mapping between the multiple node factor parameter association feature sets and the patient factor parameter classification treatment data set to obtain multiple node factor parameter treatment feature data sets; performing deep learning training based on the multiple node factor parameter treatment feature data sets to obtain the initial treatment health node analysis model set.

[0010] In a possible implementation, the target health treatment nursing knowledge set is obtained by further performing the following processing: matching and retrieving the patient education and nursing node partition knowledge base and the current treatment node of the target user to obtain a matching node patient education and nursing knowledge set; screening the patient education and nursing node partition knowledge base by the target health care risk parameter to obtain an applicable patient education and nursing knowledge set; taking the intersection of the applicable patient education and nursing knowledge set and the matching node patient education and nursing knowledge set as the applicable node patient education knowledge set; and determining the target health treatment nursing knowledge set based on the applicable node patient education knowledge set and the applicable patient education and nursing knowledge set.

[0011] In a possible implementation, the obtaining of health care consultation knowledge also performs the following processing: using natural language processing technology to convert the pre-pregnancy health care patient education knowledge base into text knowledge to obtain a patient education text vector knowledge base; selecting an LLM large language model to perform applicability question-answering training on the patient education text vector knowledge base to construct a patient education question-answering large language model; pushing the target health treatment care knowledge set to the target user to obtain health care questions to be consulted; performing knowledge retrieval question-answering on the health care questions to be consulted based on the patient education question-answering large language model, and outputting the health care consultation knowledge.

[0012] In a possible implementation, the method of obtaining the patient education text vector knowledge base also performs the following processing: using natural language processing technology to perform data preprocessing and text feature extraction on the pre-pregnancy health care patient education knowledge base to obtain a patient education knowledge text feature set; using a deep learning model to perform text vector training and model performance tuning on the patient education corpus to generate a text vector conversion model; based on the text vector conversion model, the patient education knowledge text feature set is subjected to text knowledge conversion to output the patient education text vector knowledge base.

[0013] The present application also provides a refined health care management and control platform for people preparing for pregnancy, including: a health treatment and nursing node acquisition module, which is used to establish a full-cycle health care system for preparing for pregnancy, extract nursing nodes from the full-cycle health care system for preparing for pregnancy, and obtain multiple health treatment and nursing nodes; a nursing patient education knowledge base construction module, which is used to construct a health care patient education knowledge base for preparing for pregnancy according to the full-cycle health care system for preparing for pregnancy, and associate and partition the health care patient education knowledge base for preparing for pregnancy with the multiple health treatment and nursing nodes to obtain a patient education and nursing node partition knowledge base; a health risk analysis module, which is used to call and obtain the preparation for pregnancy treatment data and current treatment node of the target user, perform health risk analysis based on the preparation for pregnancy treatment data and the current treatment node, and obtain a target health care risk parameter; a health treatment and nursing knowledge set acquisition module, which is used to perform knowledge matching on the target health care risk parameter and the current treatment node based on the patient education and nursing node partition knowledge base to obtain a target health treatment and nursing knowledge set; a health care management and control module, which is used to push the target health treatment and nursing knowledge set to the target user for knowledge consultation, obtain health care consultation knowledge, and perform refined health care management and control on the target user based on the health care consultation knowledge.

[0014] It is planned to establish a full-cycle health care system for pregnancy preparation through the management and control method and management platform for refined health care for people preparing for pregnancy proposed in this application, obtain multiple health treatment and care nodes; construct a patient education knowledge base for pregnancy preparation health care, obtain a patient education and care node partition knowledge base; obtain target health care risk parameters; obtain health care consulting knowledge, and conduct refined health care management and control for target users. It solves the problems existing in the existing pregnancy preparation health care, such as the lack of refined and personalized adjustments and risk assessments for individual health conditions, living habits and specific needs, and the difficulty in obtaining accurate, objective and comprehensive health care knowledge, which in turn leads to the inability to effectively relieve patients' tension and anxiety, poor overall medical experience, and poor treatment effects and patient satisfaction. The technical effect of improving overall work efficiency, patient medical experience and satisfaction, and treatment effects is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the drawings of the embodiment of the present disclosure are briefly introduced below. A flowchart is used in the present application to illustrate the operations performed by the control platform according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0016] Figure 1A schematic diagram of a method for controlling refined health care for pregnant women provided in an embodiment of the present application;

[0017] Figure 2 A schematic diagram of the structure of a management and control platform for refined health care for people preparing for pregnancy provided in an embodiment of the present application.

[0018] Explanation of the accompanying drawings: health treatment and nursing node acquisition module 10, nursing and patient education knowledge base construction module 20, health risk analysis module 30, health treatment and nursing knowledge set acquisition module 40, health care management and control module 50. DETAILED DESCRIPTION

[0019] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0020] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0021] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, management platform, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0022] The present application embodiment provides a method for controlling refined health care for pregnant women, such as Figure 1 As shown, the method includes:

[0023] Step S100, establishing a full-cycle pregnancy preparation health care system, extracting care nodes from the full-cycle pregnancy preparation health care system, and obtaining a plurality of health treatment care nodes.

[0024] Preferably, establishing a full-cycle health care system for pregnancy preparation refers to establishing a comprehensive and systematic health care model from pregnancy preparation to pregnancy tracking, aiming to ensure that the person preparing for pregnancy is in the best physical and mental state, thereby improving the success rate of pregnancy and the health level of the fetus, and extracting multiple health treatment and care nodes of the full-cycle health care system for pregnancy preparation, such as registration, basic examinations, ovulation induction treatment, surgery, embryo status, follow-up, etc. Specifically, registration and preliminary consultation are the starting points of the health care system for pregnancy preparation. At this stage, registration is made and preliminary consultation is conducted with a professional doctor to understand the precautions for pregnancy preparation, risk assessment and necessary examination items; basic examinations include a comprehensive assessment of physical health status, such as blood routine, urine routine, liver and kidney function, infectious disease screening, gynecological examination, sex hormone level detection, etc.; for some women, such as those with ovulation disorders In cases where assisted reproductive technology is needed, ovulation induction treatment may be required to increase the chance of conception; surgery refers to surgery that affects fertility, such as fallopian tube dredging, hysteroscopy, etc., or egg retrieval, embryo transfer and other surgeries in assisted reproductive technology; embryo monitoring refers to close monitoring of embryo development during assisted reproductive technology, including embryo quality assessment, implantation after transplantation, etc.; after successful conception, the pregnancy management stage begins, including regular prenatal examinations, nutritional guidance, psychological support, etc., to ensure the health of mother and baby; it may also include health education and lifestyle adjustments, such as providing guidance on healthy diet, moderate exercise, and avoiding exposure to harmful substances; pregnancy preparation and pregnancy may be accompanied by various psychological pressures and mood swings, and providing professional psychological support and counseling is essential to maintaining mental health. These health treatment and care nodes together constitute the core content of the full-cycle pregnancy preparation health care system, which aims to provide comprehensive and personalized health care services for women preparing for pregnancy.

[0025] Step S200, constructing a pre-pregnancy health care patient education knowledge base according to the full-cycle pre-pregnancy health care system, and associating and partitioning the pre-pregnancy health care patient education knowledge base and the multiple health treatment care nodes to obtain a patient education care node partition knowledge base.

[0026] Preferably, a patient education knowledge base for health care during pregnancy preparation is constructed based on the full-cycle health care system for pregnancy preparation. The patient education knowledge base for health care during pregnancy preparation is a systematic and structured knowledge storage system, which covers health care knowledge at each stage of the full cycle of pregnancy preparation, such as physical preparation, psychological preparation and nutritional guidance before pregnancy preparation; routine examinations, special examinations and their significance during pregnancy preparation; principles and precautions of assisted reproductive technologies such as ovulation induction therapy and surgery; key points and techniques for embryo monitoring and pregnancy management, as well as suggestions for postpartum care and recovery; this knowledge is presented in a variety of forms such as text, charts, videos, etc., aiming to help women preparing for pregnancy fully understand the health care knowledge of the full cycle of pregnancy preparation and improve their self-management capabilities.

[0027] Preferably, the patient education knowledge base for pre-pregnancy health care is associated with multiple health treatment and nursing nodes and partitioned, that is, the knowledge in the knowledge base is closely integrated with the actual treatment and nursing process. Specifically, each treatment and nursing node (such as registration and preliminary consultation, basic examination, ovulation induction treatment, etc.) is matched and corresponded with the corresponding patient education knowledge, and a patient education and nursing node partitioned knowledge base is obtained, which not only contains rich pre-pregnancy health care knowledge, but also is closely integrated with the actual treatment and nursing process, providing all-round and personalized health care guidance for couples preparing for pregnancy, including, week entry and monitoring, corresponding to the clinical assisted reproductive management system, such as return visit reminders, monitoring process and path, test tube process popular science materials, and self-management full-cycle medication records and medication guidance; HCG injection, corresponding to the HCG injection ranking table, for example, according to the HCG injection ranking table, the patient's arrival time and place are strongly reminded, HCG education (precautions before / after HCG injection); egg and sperm retrieval, corresponding to the egg retrieval ranking table surgical record system, such as egg retrieval education (precautions before / after egg retrieval and video interpretation of egg retrieval), sperm retrieval education (push sperm retrieval time, location and related precautions according to the sperm retrieval method obtained by the system), strong reminder of egg retrieval time and location (strong reminder at 8:00 pm the night before egg retrieval, fasting reminder for anesthetized patients the night before), data push (notification of number of eggs retrieved and fertilization method); embryo culture, corresponding to the laboratory management system, such as data push of (number of cysts, number of frozen embryos, number of transplants, reminder to sign informed consent); transplantation, corresponding to the transplantation ranking table surgical record system, such as transplantation education (precautions before / after transplantation, video interpretation of transplantation), transplantation time and location, and strong reminder at 8:00 pm the night before transplantation, luteal support medication records and medication guidance videos. The patient education and nursing node partition knowledge base can automatically obtain in-hospital data, and combined with the knowledge base, automatically push information matching their treatment nodes to patients. According to their actual situation and needs, they can conveniently obtain and check the corresponding patient education knowledge anytime and anywhere at different stages of treatment and nursing, clarify the process, to-do items and precautions of each node, so as to better understand the treatment and nursing process, improve self-management ability, reduce risks and promote health, improve the overall medical experience and compliance, and make medical treatment more relaxed and reassuring.

[0028] Step S300, calling to obtain the target user's pre-pregnancy treatment data and current treatment node, performing health risk analysis based on the pre-pregnancy treatment data and current treatment node, and obtaining target health care risk parameters.

[0029] Preferably, the target user's pre-pregnancy treatment data and current treatment node are called to obtain, and health risk analysis is performed based on these data, wherein the pre-pregnancy treatment data generally includes various treatment information received by the target user during the pre-pregnancy process, such as drug treatment, auxiliary treatment (such as acupuncture, nutritional counseling, etc.), completed examination items and their results (such as hormone level detection, reproductive system examination, etc.), and the current treatment node refers to the user's current treatment stage or status, such as the number of weeks of a specific course of treatment, whether a certain examination or treatment has been completed, etc. Specifically, the obtained pre-pregnancy treatment data and the current treatment node are integrated to form a comprehensive user health profile, and these data, including the user's treatment progress, treatment effects (such as hormone levels), and treatment status, are analyzed. The integrated data is then used to analyze the target user's health risks, including changes in pregnancy levels, symptom improvement, etc.), whether there are abnormalities or risk factors (such as side effects, complications, etc.), and then analyze the target user's health risks based on the integrated data, including evaluating the user's pregnancy success rate, risk of miscarriage, fetal health risks, complication risks, etc., while considering other factors such as the user's age, constitution, family medical history, living habits, etc., and finally obtain the target health care risk parameters, which are quantitative descriptions of the user's current health status and risk level, and may include but are not limited to predicted values ​​of pregnancy success rate, miscarriage risk coefficient, probability of occurrence of specific complications, etc., to guide doctors to develop more accurate treatment plans and care recommendations, and also help users better understand their own health status and risk levels.

[0030] Step S300 further includes step S310, obtaining information on physiological influencing factors for pregnancy preparation, wherein the information on physiological influencing factors for pregnancy preparation includes age, gender, physical condition and living habits; step S320, collecting and obtaining a treatment data set of patients preparing for pregnancy, and based on the information on physiological influencing factors for pregnancy preparation and the multiple health treatment and nursing nodes, classifying, training and identifying the treatment data set of patients preparing for pregnancy, and constructing a health node analysis model library for pregnancy preparation treatment; step S330, classifying the physiological factors of the target user through the information on physiological influencing factors for pregnancy preparation to obtain target physiological factor parameters; step S340, based on the target physiological factor parameters and the current treatment node, calling and obtaining a target pregnancy preparation treatment health analysis model from the pregnancy preparation treatment health node analysis model library; step S350, performing a health analysis on the pregnancy preparation treatment data based on the target pregnancy preparation treatment health analysis model, and outputting the target health care risk parameters.

[0031] Preferably, information on physiological factors that affect the success of pregnancy preparation is collected, mainly including age, gender, physical condition (such as the presence of chronic diseases, body mass index, etc.) and lifestyle habits (such as smoking, drinking, eating habits, exercise frequency, etc.), and then a treatment data set of patients preparing for pregnancy is collected, which may include medical records, test results, drug use, etc., to provide personalized pregnancy preparation advice and treatment plans. Then, based on the information on physiological factors affecting pregnancy preparation and multiple health treatment and care nodes (which may refer to different health indicators or treatment stages), the treatment data set of patients preparing for pregnancy is classified, trained and identified, and a library of analysis models containing multiple health nodes for pregnancy preparation treatment is constructed. These models can provide personalized health analysis and suggestions for patients preparing for pregnancy based on different physiological factors and treatment stages; the information on physiological factors affecting pregnancy preparation is used to perform pregnancy preparation on target users. The target physiological factor parameters are obtained by classifying physiological factors, which may include age range, gender, specific physical condition (such as whether a certain disease exists) and living habits, etc. Finally, according to the target physiological factor parameters and the current treatment node (which may refer to the current treatment stage or health status of the patient preparing for pregnancy), the most suitable target pregnancy preparation treatment health analysis model is called from the pregnancy preparation treatment health node analysis model library to perform health analysis on the target user's pregnancy preparation treatment data, and finally output target health care risk parameters, such as pregnancy preparation success rate, potential health risks (such as miscarriage risk, pregnancy complication risk, etc.), and recommended health care measures, etc., which are crucial for formulating personalized pregnancy preparation plans and health care plans, and can help target users better understand their health status and take appropriate measures to improve the success rate of pregnancy preparation.

[0032] Step S320 further includes step S321, classifying and identifying the treatment data set of the patient preparing for pregnancy through the information of the physiological influencing factors of preparing for pregnancy, and obtaining the patient factor parameter classification treatment data set; step S322, performing deep learning training on the patient factor parameter classification treatment data set based on the multiple health treatment nursing nodes, and obtaining an initial treatment health node analysis model set; step S323, performing performance verification and model parameter optimization on the initial treatment health node analysis model set, and obtaining a preparation for pregnancy treatment health node analysis model set; step S324, classifying and identifying the preparation for pregnancy treatment health node analysis model set according to factor parameters and nursing nodes, and constructing the preparation for pregnancy treatment health node analysis model library.

[0033] Preferably, known information on physiological factors affecting pregnancy preparation (such as age, gender, physical condition, living habits, etc.) is used to classify and identify the treatment data set of patients preparing for pregnancy, and patients with similar physiological factors are classified into the same category to obtain a patient factor parameter classification treatment data set, that is, a treatment data set of patients preparing for pregnancy classified according to different physiological factors. Then, a prediction model is constructed based on deep learning, and the patient factor parameter classification treatment data set is used for training. Multiple health treatment and nursing nodes may refer to different health indicators, treatment stages or nursing measures, etc. These nodes will serve as input features of the deep learning model. Through the prediction model training, the correlation between different physiological factors and treatment nodes is learned, so as to predict the patient's health status or treatment effect. After the training is completed, multiple initial treatment health node analysis models are obtained, and these models correspond to different physiological factors and treatment node combinations, respectively. ; Then, the performance of the initial treatment health node analysis model set is verified and the model parameters are optimized, that is, the performance of the initial treatment health node analysis model is evaluated, and necessary parameter optimization is performed, among which, performance verification may include using a verification data set to evaluate the accuracy, stability and other indicators of the model. According to the verification results, the parameters of the model can be adjusted and optimized to improve the performance of the model, and then the preparation for pregnancy treatment health node analysis model set is optimized; finally, the optimized preparation for pregnancy treatment health node analysis model set is classified and identified and integrated according to factor parameters and nursing nodes, so as to facilitate the subsequent selection of appropriate models for health analysis according to the patient's physiological factors and treatment needs. The integrated model set will constitute a preparation for pregnancy treatment health node analysis model library, which includes health analysis models under a variety of physiological factors and treatment node combinations, and is used to provide personalized health analysis and treatment recommendations for preparation for pregnancy patients.

[0034] Step S322 further includes step S3221, extracting treatment features from the patient factor parameter classification treatment data set to obtain a classification factor parameter treatment feature set; step S3222, performing association feature analysis on the classification factor parameter treatment feature set based on the multiple health treatment care nodes to obtain multiple node factor parameter association feature sets; step S3223, performing data association mapping with the multiple node factor parameter association feature sets and the patient factor parameter classification treatment data set to obtain multiple node factor parameter treatment feature data sets; step S3224, performing deep learning training based on the multiple node factor parameter treatment feature data sets to obtain the initial treatment health node analysis model set.

[0035] Preferably, treatment features related to health risk analysis are extracted, and then different nursing nodes are matched with treatment features and data mapped to train health analysis models for different nursing nodes and different physiological influencing factors, so as to improve the accuracy of model analysis and personalized applicability. Specifically, treatment-related features are extracted from the patient factor parameter classification treatment data set, which may include the patient's physiological indicators (such as blood pressure, blood sugar, weight, etc.), medical history information, drug use, living habits, etc., to obtain a classification factor parameter treatment feature set, that is, a treatment feature data set classified according to different physiological factors, and then the features in the classification factor parameter treatment feature set are subjected to association analysis. Multiple health treatment nursing nodes may refer to different health indicators, treatment stages, nursing measures or disease states, etc., and the correlation between different treatment features and health treatment nursing nodes is found. These relationships may be expressed as positive The method can obtain multiple node factor parameter association feature sets, i.e., feature association sets under different health treatment and nursing nodes, by using positive, negative or nonlinear relationships; then, the multiple node factor parameter association feature sets are associated and mapped with the patient factor parameter classification treatment data set, i.e., the information in the feature association set is mapped back to the original treatment data set, thereby obtaining multiple node factor parameter treatment feature data sets, i.e., treatment data sets containing feature association information; finally, the multiple node factor parameter treatment feature data sets are trained using deep learning technology to automatically learn the complex features and patterns in the data, thereby realizing the prediction and analysis of health treatment and nursing nodes. Through deep learning training, a set of initial treatment health node analysis models can be obtained. These models correspond to different physiological factors and treatment node combinations, which are used to provide personalized health analysis and treatment suggestions for pregnant patients, and help doctors develop more effective treatment plans.

[0036] Step S400: performing knowledge matching on the target health care risk parameter and the current treatment node based on the patient education and care node partition knowledge base to obtain a target health care knowledge set.

[0037] Preferably, the patient education and nursing node partition knowledge base is a database containing rich nursing knowledge and information, which is usually classified according to different nursing nodes or stages. Each stage contains corresponding nursing knowledge, risk assessment, preventive measures, treatment suggestions, etc. Specifically, according to the current treatment node of the target user, the corresponding stage or node in the patient education and nursing node partition knowledge base is determined. At the same time, considering the target health care risk parameters, the specific knowledge points or suggestions that need to be matched are determined, and knowledge matching is performed in the determined nodes or stages to find knowledge points or suggestions related to the target health care risk parameters, which may include preventive measures, treatment suggestions, lifestyle adjustments, psychological support, etc. According to the specific situation and needs of the target user, the most suitable knowledge points or suggestions are screened out, and the screened knowledge points or suggestions are evaluated. The target health treatment nursing knowledge set is a collection of personalized nursing knowledge and suggestions for the target user's current treatment nodes and risk parameters. For example, preventive measures are provided for the target user's current risk parameters, such as adjusting diet, increasing exercise, and improving living habits. According to the target user's current treatment nodes and risk parameters, treatment suggestions are provided, such as drug therapy, physical therapy, psychotherapy, etc. Suggestions are provided on how to adjust lifestyle to improve health status, such as improving sleep, reducing stress, and increasing social activities. Suggestions are provided on psychological support, such as seeking psychological counseling, participating in support groups, etc., to help target users cope with psychological stress and anxiety during treatment, thereby providing more accurate and effective nursing guidance for target users.

[0038] Step S400 further includes step S410, matching and retrieving the patient education and nursing node partition knowledge base with the current treatment node of the target user to obtain a matching node patient education and nursing knowledge set; step S420, screening the patient education and nursing node partition knowledge base through the target health care risk parameter to obtain an applicable patient education and nursing knowledge set; step S430, taking the intersection of the applicable patient education and nursing knowledge set and the matching node patient education and nursing knowledge set as the applicable node patient education knowledge set; step S440, determining the target health treatment nursing knowledge set based on the applicable node patient education knowledge set and the applicable patient education and nursing knowledge set.

[0039] Preferably, according to the current treatment node of the target user, a node matching with it is searched and retrieved in the patient education and nursing node partition knowledge base, so as to obtain the patient education and nursing knowledge set under the node, wherein the current treatment node of the target user refers to the current treatment stage or condition of the target user, and then the patient education and nursing node partition knowledge base is screened by the target health care risk parameter, that is, the target health care risk parameter (such as the health status, age, gender, previous medical history, etc. of the target user) is used as the screening condition, and the patient education and nursing knowledge applicable to the target user is screened from the patient education and nursing node partition knowledge base to form an applicable patient education and nursing knowledge set, and then the matching node patient education and nursing knowledge set and the applicable patient education and nursing knowledge set are intersected, that is, the patient education and nursing knowledge that satisfies both the current treatment node and the health care risk parameters is found, which is called the applicable node patient education knowledge set; finally, according to the applicable node patient education knowledge set and the applicable patient education and nursing knowledge set (which may also include other relevant information, such as the doctor's advice, the target user's preferences, etc.), a comprehensive health treatment and nursing knowledge set for the target user that meets both its current treatment node and its health care risks is comprehensively determined, which helps to improve the treatment effect and user satisfaction.

[0040] Step S500: Push the target health care knowledge set to the target user for knowledge consultation, obtain health care consultation knowledge, and perform refined health care management and control on the target user based on the health care consultation knowledge.

[0041] Preferably, the target health treatment and nursing knowledge set is pushed to the target user for knowledge consultation, so as to obtain health care consulting knowledge. For example, a full-cycle refined nursing management model is realized through modern electronic technologies such as Internet information systems and WeChat public accounts, forming a medical assistant that is convenient for the promotion and development of this model. Before diagnosis and during treatment, the medical assistant pushes the nursing knowledge set, that is, it conducts refined health care management and control of the target users based on health care consulting knowledge. Specifically, it guides patients by using appointment reminders at key nodes to prevent patients from missing the best time for medical treatment; during the diagnosis, the to-do items are clarified according to the push reminders to reduce the patient's helplessness caused by not understanding how to proceed next; and the relevant popular science knowledge and patient education content of the current treatment node are pushed regularly to help patients better understand their own disease The system provides patients with a comprehensive and personalized nursing management model, and provides them with a comprehensive and personalized nursing management model. ...

[0042] Step S500 further includes step S510, using natural language processing technology to convert the pre-pregnancy health care patient education knowledge base into text knowledge to obtain a patient education text vector knowledge base; step S520, selecting the LLM large language model to perform applicability question and answer training on the patient education text vector knowledge base, and constructing a patient education question and answer large language model; step S530, pushing the target health treatment and nursing knowledge set to the target user to obtain the health care questions to be consulted; step S540, performing knowledge retrieval question and answer on the health care questions to be consulted based on the patient education question and answer large language model, and outputting the health care consultation knowledge.

[0043] Preferably, natural language processing technology (NLP) is an artificial intelligence technology used to process and understand human language. Specifically, natural language processing technology is used to convert text information in a knowledge base into a format that can be understood and processed by a computer, such as a text vector, to obtain a patient education text vector knowledge base, in which the knowledge exists in the form of a text vector; the LLM large language model is a large language model based on deep learning, which can understand and generate natural language text, and the patient education text vector knowledge base is trained for applicability question answering based on the LLM large language model, that is, the patient education text vector knowledge base is used as training data to train the LLM model so that it can answer questions related to pre-pregnancy health care. The patient education question and answer large language model is obtained, which can provide accurate and useful answers to questions in the field of pre-pregnancy health care; the target health treatment and nursing knowledge set is pushed to the target user in some way (such as mobile phone application, email, text message, etc.). After reading the knowledge set, the user may have further questions or need more detailed answers. These questions will be collected as health care questions to be consulted. The patient education question and answer large language model is used to understand and analyze the questions raised by the user, and then the relevant information is retrieved in the knowledge base (which may be the original pre-pregnancy health care patient education knowledge base or the converted patient education text vector knowledge base). According to the retrieval results, the model will generate health care consultation knowledge and provide it to the user.

[0044] Step S510 further includes step S511, using natural language processing technology to perform data preprocessing and text feature extraction on the pre-pregnancy health care patient education knowledge base to obtain a patient education knowledge text feature set; step S512, using a deep learning model to perform text vector training and model performance tuning on the patient education corpus to generate a text vector conversion model; step S513, based on the text vector conversion model, performing text knowledge conversion on the patient education knowledge text feature set, and outputting the patient education text vector knowledge base.

[0045] Preferably, natural language processing technology (NLP) and deep learning models are used to process the pre-pregnancy health care patient education knowledge base and generate a patient education text vector knowledge base. Specifically, natural language processing technology is used to perform data preprocessing and text feature extraction on the pre-pregnancy health care patient education knowledge base. Data preprocessing generally includes steps such as removing irrelevant characters (such as punctuation marks, numbers, etc.) in the text, word segmentation, removing stop words, stemming or word form restoration, etc., to convert the original text into a format more suitable for subsequent processing, and then extract features that can represent its content from the text, such as vocabulary in a bag-of-words model, TF-IDF (term frequency-inverse document frequency) value, word embedding (such as Word2Vec, GloVe, etc.) or other more complex text representation methods. Each text in the pre-pregnancy health care patient education knowledge base will be converted into features to constitute a patient education knowledge text feature set.

[0046] Preferably, the patient education corpus is a database containing a large amount of pre-pregnancy health care related texts, which is used to train the deep learning model. The texts in the patient education corpus are trained using a deep learning model (such as a neural network, a recurrent neural network RNN, a long short-term memory network LSTM, a Transformer, etc.) to learn the mapping relationship from text to vectors, and the performance and accuracy of the model are improved by adjusting the model parameters (such as learning rate, batch size, network structure, etc.) and training strategies (such as early stopping method, learning rate decay, etc.); each feature vector in the patient education knowledge text feature set is converted using a text vector conversion model. The text vector conversion model is a deep learning model that has been trained and optimized, which can convert text into vector representations. Finally, each text in the patient education knowledge base of pregnancy preparation health care will be converted into a vector representation. These vector representations together constitute the patient education text vector knowledge base, which will be used in subsequent text classification, information retrieval, question-answering systems and other tasks, thereby facilitating the construction of more efficient and accurate knowledge retrieval and question-answering systems.

[0047] In the above, refer to Figure 1 The present invention describes in detail a method for controlling refined health care for pregnant women according to an embodiment of the present invention. Figure 2 A management and control platform for refined health care for people preparing for pregnancy according to an embodiment of the present invention is described.

[0048] The refined health care management and control platform for people preparing for pregnancy according to an embodiment of the present invention is used to solve the existing problems of health care for people preparing for pregnancy, such as lack of refined and personalized adjustment and risk assessment for individual health conditions, living habits and specific needs, and difficulty in obtaining accurate, objective and comprehensive health care knowledge, which leads to the inability to effectively relieve patients' nervousness and anxiety, poor overall medical experience, and poor treatment effect and patient satisfaction. The technical effect of improving overall work efficiency, patient medical experience and satisfaction, and treatment effect is achieved. The refined health care management and control platform for people preparing for pregnancy includes: a health treatment nursing node acquisition module 10, a nursing patient education knowledge base construction module 20, a health risk analysis module 30, a health treatment nursing knowledge set acquisition module 40, and a health care management and control module 50.

[0049] The health treatment and nursing node acquisition module 10 is used to establish a full-cycle health care system for pregnancy preparation, extract nursing nodes from the full-cycle health care system for pregnancy preparation, and obtain multiple health treatment and nursing nodes; the nursing patient education knowledge base construction module 20 is used to construct a health care patient education knowledge base for pregnancy preparation according to the full-cycle health care system for pregnancy preparation, and associate the health care patient education knowledge base for pregnancy preparation and the multiple health treatment and nursing nodes to obtain a patient education and nursing node partition knowledge base; the health risk analysis module 30 is used to call and obtain the pregnancy preparation treatment data and current treatment node of the target user, perform health risk analysis based on the pregnancy preparation treatment data and the current treatment node, and obtain the target health care risk parameter; the health treatment and nursing knowledge set acquisition module 40 is used to perform knowledge matching on the target health care risk parameter and the current treatment node based on the patient education and nursing node partition knowledge base to obtain the target health treatment and nursing knowledge set; the health care management and control module 50 is used to push the target health treatment and nursing knowledge set to the target user for knowledge consultation, obtain health care consultation knowledge, and perform refined health care management and control on the target user based on the health care consultation knowledge.

[0050] The specific configuration of the health risk analysis module 30 will be described in detail below. The health risk analysis module 30 may further include: obtaining information on physiological factors affecting pregnancy preparation, the information on physiological factors affecting pregnancy preparation including age, gender, physical condition and living habits; collecting and obtaining a treatment data set of patients preparing for pregnancy, and based on the information on physiological factors affecting pregnancy preparation and the multiple health treatment and nursing nodes, classifying and training the treatment data set of patients preparing for pregnancy, and constructing a health node analysis model library for treatment of pregnancy preparation; classifying the physiological factors of the target user through the information on physiological factors affecting pregnancy preparation, and obtaining target physiological factor parameters; according to the target physiological factor parameters and the current treatment node, calling and obtaining a target health analysis model for treatment of pregnancy preparation from the health node analysis model library for treatment of pregnancy preparation; performing health analysis on the treatment data for pregnancy preparation based on the target health analysis model for treatment of pregnancy preparation, and outputting the target health care risk parameters.

[0051] The specific configuration of the health risk analysis module 30 will be described in detail below. The health risk analysis module 30 may further include: classifying and identifying the treatment data set of the patient for pre-pregnancy through the information of the physiological influencing factors of the pre-pregnancy, and obtaining the patient factor parameter classification treatment data set; performing deep learning training on the patient factor parameter classification treatment data set based on the multiple health treatment nursing nodes, and obtaining an initial treatment health node analysis model set; performing performance verification and model parameter optimization on the initial treatment health node analysis model set, and obtaining a pre-pregnancy treatment health node analysis model set; classifying and identifying the pre-pregnancy treatment health node analysis model set according to the factor parameters and nursing nodes, and constructing the pre-pregnancy treatment health node analysis model library.

[0052] The specific configuration of the health risk analysis module 30 will be described in detail below. The health risk analysis module 30 may further include: extracting treatment features from the patient factor parameter classification treatment data set to obtain a classification factor parameter treatment feature set; performing association feature analysis on the classification factor parameter treatment feature set based on the multiple health treatment nursing nodes to obtain multiple node factor parameter association feature sets; performing data association mapping with the multiple node factor parameter association feature sets and the patient factor parameter classification treatment data set to obtain multiple node factor parameter treatment feature data sets; performing deep learning training based on the multiple node factor parameter treatment feature data sets to obtain the initial treatment health node analysis model set.

[0053] The specific configuration of the health treatment nursing knowledge set acquisition module 40 will be described in detail below. The health treatment nursing knowledge set acquisition module 40 may further include: performing a matching search based on the patient education nursing node partition knowledge base and the current treatment node of the target user to obtain a matching node patient education nursing knowledge set; screening the patient education nursing node partition knowledge base through the target health care risk parameter to obtain an applicable patient education nursing knowledge set; using the intersection of the applicable patient education nursing knowledge set and the matching node patient education nursing knowledge set as the applicable node patient education knowledge set; determining the target health treatment nursing knowledge set based on the applicable node patient education knowledge set and the applicable patient education nursing knowledge set.

[0054] The specific configuration of the health care management module 50 will be described in detail below. The health care management module 50 may further include: using natural language processing technology to convert the pre-pregnancy health care patient education knowledge base into text knowledge to obtain a patient education text vector knowledge base; selecting an LLM large language model to perform applicability question-answering training on the patient education text vector knowledge base to construct a patient education question-answering large language model; pushing the target health treatment nursing knowledge set to the target user to obtain health care questions to be consulted; performing knowledge retrieval question-answering on the health care questions to be consulted based on the patient education question-answering large language model, and outputting the health care consultation knowledge.

[0055] The specific configuration of the health care management module 50 will be described in detail below. The health care management module 50 may further include: using natural language processing technology to perform data preprocessing and text feature extraction on the pre-pregnancy health care patient education knowledge base to obtain a patient education knowledge text feature set; using a deep learning model to perform text vector training and model performance tuning on the patient education corpus to generate a text vector conversion model; based on the text vector conversion model, the patient education knowledge text feature set is converted into text knowledge, and the patient education text vector knowledge base is obtained as an output.

[0056] The management and control platform for refined health care for people preparing for pregnancy provided in an embodiment of the present invention can execute the management and control method for refined health care for people preparing for pregnancy provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0057] Although the present application makes various references to certain modules in the management and control platform according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0058] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for controlling refined health care for people preparing for pregnancy, characterized in that: The method comprises: Establishing a full-cycle pregnancy preparation health care system, extracting care nodes from the full-cycle pregnancy preparation health care system, and obtaining multiple health treatment care nodes; According to the full-cycle pre-pregnancy health care system, a pre-pregnancy health care patient education knowledge base is constructed, and the pre-pregnancy health care patient education knowledge base and the multiple health treatment nursing nodes are associated and partitioned to obtain a patient education nursing node partition knowledge base; Calling to obtain the target user's pregnancy preparation treatment data and current treatment node, performing health risk analysis based on the pregnancy preparation treatment data and current treatment node, and obtaining the target health care risk parameter; Based on the patient education and nursing node partition knowledge base, the target health care risk parameter and the current treatment node are matched to obtain a target health treatment and nursing knowledge set; The target health care knowledge set is pushed to the target user for knowledge consultation, health care consultation knowledge is obtained, and refined health care management and control of the target user is performed based on the health care consultation knowledge.

2. The method for controlling refined health care for pregnant women according to claim 1, characterized in that: The obtaining of target health care risk parameters includes: Acquire information on physiological factors affecting pregnancy preparation, wherein the information on physiological factors affecting pregnancy preparation includes age, gender, physical condition and living habits; Acquire a treatment data set of patients preparing for pregnancy, classify and train the treatment data set of patients preparing for pregnancy based on the information of physiological influencing factors of preparing for pregnancy and the multiple health treatment and nursing nodes, and build a health node analysis model library for preparing for pregnancy; Classify the target user's physiological factors according to the information of physiological factors affecting pregnancy preparation, and obtain target physiological factor parameters; According to the target physiological factor parameter and the current treatment node, a target pregnancy preparation treatment health analysis model is acquired from the pregnancy preparation treatment health node analysis model library; The preparation for pregnancy treatment data is subjected to health analysis based on the target preparation for pregnancy treatment health analysis model, and the target health care risk parameter is output.

3. The method for controlling refined health care for pregnant women according to claim 2, characterized in that: The construction of the pregnancy preparation treatment health node analysis model library includes: Classify and identify the treatment data set of patients preparing for pregnancy according to the information of physiological factors affecting preparation for pregnancy, and obtain a treatment data set classified by patient factor parameters; Based on the multiple health treatment nursing nodes, deep learning training is performed on the patient factor parameter classification treatment data set to obtain an initial treatment health node analysis model set; Performing performance verification and model parameter optimization on the initial treatment health node analysis model set to obtain a pregnancy preparation treatment health node analysis model set; The preparation for pregnancy treatment health node analysis model set is classified, identified and integrated according to factor parameters and nursing nodes to construct the preparation for pregnancy treatment health node analysis model library.

4. The method for controlling refined health care for pregnant women according to claim 3, characterized in that: The step of obtaining an initial treatment health node analysis model set includes: Extracting treatment features from the patient factor parameter classification treatment data set to obtain a classification factor parameter treatment feature set; Based on the multiple health treatment and nursing nodes, the classification factor parameter treatment feature set is respectively analyzed for correlation characteristics to obtain multiple node factor parameter correlation feature sets; Performing data association mapping on the multiple node factor parameter association feature sets and the patient factor parameter classification treatment data set to obtain multiple node factor parameter treatment feature data sets; Deep learning training is performed respectively based on the multiple node factor parameter treatment feature data sets to obtain the initial treatment health node analysis model set.

5. The method for controlling refined health care for pregnant women according to claim 1, characterized in that: The target health treatment nursing knowledge set is obtained, including: Perform matching retrieval based on the patient education and nursing node partition knowledge base and the current treatment node of the target user to obtain a matching node patient education and nursing knowledge set; The patient education and nursing node partition knowledge base is screened by the target health care risk parameter to obtain an applicable patient education and nursing knowledge set; The intersection of the applicable patient education and nursing knowledge set and the matching node patient education and nursing knowledge set is used as the applicable node patient education knowledge set; The target health treatment nursing knowledge set is determined according to the applicable node patient education knowledge set and the applicable patient education nursing knowledge set.

6. The method for controlling refined health care for pregnant women according to claim 1, characterized in that: The acquisition of health care consulting knowledge includes: Using natural language processing technology to convert the pre-pregnancy health care patient education knowledge base into text knowledge to obtain a patient education text vector knowledge base; Selecting the LLM large language model to perform applicability question-answering training on the patient education text vector knowledge base, and constructing a patient education question-answering large language model; Pushing the target health care knowledge set to the target user to obtain health care questions to be consulted; Based on the patient-teaching question-answering large language model, knowledge retrieval question-answering is performed on the health care question to be consulted, and the health care consultation knowledge is output.

7. The method for controlling refined health care for pregnant women according to claim 6, characterized in that: The step of obtaining a patient education text vector knowledge base includes: Using natural language processing technology to perform data preprocessing and text feature extraction on the pre-pregnancy health care patient education knowledge base to obtain a patient education knowledge text feature set; Use deep learning models to train text vectors and optimize model performance on the patient education corpus to generate a text vector conversion model; Based on the text vector conversion model, the patient education knowledge text feature set is converted into text knowledge, and the patient education text vector knowledge base is obtained as output.

8. A management and control platform for refined health care for people preparing for pregnancy, characterized by: The control platform is used to implement the control method for refined health care for pregnant people according to any one of claims 1 to 7, and the control platform includes: A health treatment and nursing node acquisition module is used to establish a full-cycle pregnancy preparation health care system, extract nursing nodes from the full-cycle pregnancy preparation health care system, and obtain multiple health treatment and nursing nodes; A nursing patient education knowledge base construction module is used to construct a pre-pregnancy health care patient education knowledge base according to the full-cycle pre-pregnancy health care system, and associate the pre-pregnancy health care patient education knowledge base with the multiple health treatment nursing nodes to obtain a patient education nursing node partition knowledge base; A health risk analysis module is used to call and obtain the target user's pre-pregnancy treatment data and current treatment node, perform health risk analysis based on the pre-pregnancy treatment data and current treatment node, and obtain target health care risk parameters; A health care knowledge set acquisition module, used for performing knowledge matching between the target health care risk parameter and the current treatment node based on the patient education and care node partition knowledge base to obtain a target health care knowledge set; The health care management and control module is used to push the target health care knowledge set to the target user for knowledge consultation, obtain health care consultation knowledge, and perform refined health care management and control on the target user based on the health care consultation knowledge.

Images