Artificial intelligence auxiliary processing method and system for female climacteric medical data

Abstract

The invention discloses an artificial intelligence female climacteric medical data auxiliary processing method and system, and relates to the technical field of medical data auxiliary processing. The monitoring module is set, the monitoring module is a wearable intelligent device, physical sign information data and environment information data of a target patient are obtained based on the monitoring module, and feature information items and environment information items are obtained; the acquisition module is used for acquiring questionnaire score information of a target patient to obtain questionnaire information items; by setting the monitoring module of the wearable intelligent device, the typical hot tide phenomenon of female climacteric is accurately captured, body surface temperature and current change data are obtained through a micro heat-sensitive sensor and a micro current sensor, accurate feature information items are obtained through strict threshold judgment, meanwhile, environment information data such as noise and illumination can be obtained, and the intelligent female climacteric monitoring system is suitable for being used for monitoring female climacteric climacteric conditions. Interference of environmental factors on female endocrine and climacteric symptoms is comprehensively considered.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data auxiliary processing, and specifically to an artificial intelligence female menopausal medical data auxiliary processing method and system. Background Art

[0002] Medical data-assisted processing refers to the use of advanced technologies such as artificial intelligence and big data analysis to automatically or semi-automatically integrate, clean, analyze and apply massive, multi-source, heterogeneous data generated in the medical field, thereby improving medical decision-making efficiency, diagnosis and treatment accuracy, and management effectiveness. Female menopause refers to the natural physiological stage in which women transition from the reproductive period with strong reproductive function to the non-reproductive period. In essence, it is a process in which ovarian function gradually declines until failure. At this stage, medical data-assisted processing will help improve the quality of life of menopausal women and provide precise intervention measures based on the specific circumstances of different women.

[0003] Patent publication number CN119377899A is an artificial intelligence medical auxiliary data processing method and system. The dynamic weight model is based on the external attribute information of the multimodal medical data used in the medical data processing model, which is different from the same medical data set. The correlation between the auxiliary data and the reference auxiliary data based on the k-th modal medical data and the correlation relationship between the medical data of different dimensions are obtained from different dimensions. Since the input and output of the dynamic weight model are relatively simple, the dynamic weight model will reach a convergence state first and its training complexity is also low, so that relatively accurate dynamic weights can be obtained quickly, so that the dynamic weights of the medical data model can be quickly adjusted, thereby guiding the rapid descent iteration of the medical data processing model; thus, the rapid training of the medical data model can be completed with the support of less medical data, thereby improving the efficiency of medical data assistance.

[0004] In the process of assisting the processing of female menopausal medical data, the above-mentioned and similar technical solutions mostly focus on static physiological indicators, such as hormone levels and examination data. However, when faced with multi-source heterogeneous data such as vital sign monitoring and environmental noise, since vital sign monitoring, environmental noise and other data are dynamic data and are constantly changing, it is difficult to automatically extract complex correlation features, which can easily lead to information fragmentation and make it impossible to accurately assist in the processing of medical data. Summary of the Invention

[0005] The purpose of the present invention is to provide an artificial intelligence-assisted processing method and system for female menopausal medical data to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solutions: an artificial intelligence-assisted female menopausal medical data processing system, comprising:

[0007] Monitoring module: Setting the monitoring module, which is a wearable smart device, obtains the target patient's vital signs information data and environmental information data based on the monitoring module to obtain feature information items and environmental information items;

[0008] Acquisition module: obtains the questionnaire score information of the target patient, obtains the questionnaire information item, and simultaneously obtains the target patient's medical history information and hormone level data, obtains the medical history information item and hormone information;

[0009] Creation module: Based on the data acquisition method, obtain evaluation samples, the evaluation samples include at least two evaluation patients' evaluation data, obtain the evaluation data set, create a health assessment model based on the evaluation data set, and output the mapping data between the evaluation samples to obtain the basic mapping items;

[0010] Evaluation module: Based on the health assessment model, the health assessment coefficient of the target patient is obtained. The health assessment coefficient includes mapping data of physical sign data, questionnaire score information, past medical history information, and hormone level data to obtain the target mapping item;

[0011] Comparison module: compares the basic mapping items with the target mapping items, obtains the mapping differences of the target patients, obtains mapping difference items, and creates an environmental assessment model based on the mapping difference items and environmental information items. Based on the continuously obtained mapping difference items and environmental information items, the environmental assessment model is optimized to obtain the participation information of the environmental data.

[0012] Furthermore, the physical sign information data includes the number of hot flashes, and the method for obtaining the characteristic information item includes:

[0013] The monitoring module includes a micro-thermal sensor and a micro-current sensor, which obtains the real-time surface temperature changes and surface current changes of the target patient based on the monitoring module, and obtains the surface temperature item and the surface current item;

[0014] Setting an acquisition threshold, which is a time threshold, and acquiring change data of the body surface temperature item based on the acquisition threshold; setting a determination threshold and a first fluctuation threshold, which is a time threshold and a first fluctuation threshold, and obtaining a first determination data set when the temperature rises or falls within the determination threshold and exceeds the first fluctuation threshold based on the determination threshold;

[0015] Acquire change data of the body surface current item based on the acquisition threshold, set a second fluctuation threshold, the second fluctuation threshold is a numerical threshold, and obtain a second determination data set when the fluctuation of the body surface current item exceeds the second fluctuation threshold;

[0016] Obtain the time nodes of the first determination data set and the second determination data set, compare whether the time nodes are consistent, and when the time nodes are consistent, obtain a third determination data set, and use the third determination data set as the feature information item.

[0017] Furthermore, the environmental information data includes noise information and light exposure time information, and the method for obtaining the environmental information items includes:

[0018] The monitoring module also includes a built-in microphone module and a multi-spectral light sensor, and the multi-spectral light sensor includes an ambient light sensing module;

[0019] Acquire ambient sound wave data based on the built-in microphone module to obtain a sound wave information item, acquire light data based on the ambient light sensor module, divide the light data into natural light and artificial light, obtain natural light duration information, and obtain a light information item;

[0020] A determination period is set, where the determination period is a time period. Average information of the sound wave information item and the light information item is obtained based on the determination period to obtain a sound wave average item and a light average item. The sound wave average item and the light average item are combined to obtain an environment information item.

[0021] Furthermore, the questionnaire score information includes a menopausal symptom score, and the method for obtaining the questionnaire information item includes:

[0022] Obtain the menopausal symptom rating scale score results of the target user to obtain a first result set;

[0023] Obtaining the comparison time of the first result set to obtain a first time set;

[0024] Set a judgment threshold, which is a time threshold, obtain the time nodes in the first time set whose control time does not exceed the judgment threshold, obtain the first screening time set, obtain the corresponding items of the first screening time set and the first result set, obtain the average score of the corresponding items, and obtain the questionnaire information item.

[0025] Furthermore, the assessment data includes physical sign data, questionnaire score information, past medical history information, and hormone level data. The method for creating a health assessment model includes:

[0026] Setting and determining the minimum sample size, setting the first difference value, the second difference value, and the third difference value, so that the evaluation samples cover the first difference value, the second difference value, and the third difference value respectively, obtaining the physical sign data, questionnaire score information, past medical history information, and hormone level data of the evaluation samples, and obtaining the basic evaluation items;

[0027] Select the target model, split the evaluation basic items into first data and second data, use the first data as input, input the fully connected layer, use the second data as embedding, select the target algorithm for model training, and obtain the health assessment model.

[0028] Furthermore, the method for obtaining the basic mapping item includes:

[0029] Sequentially set one of the change data in the evaluation data as the first variable and the remaining change data as the first fixed quantity, obtain the change data of the variable, and obtain a first change data set;

[0030] Set the two changed data in the evaluation data as the second variable and the remaining changed data as the second fixed quantity in sequence, obtain the changed data of the second variable, and obtain the second changed data set. Repeat this step and increase the number of changed data in sequence to obtain the mapping relationship of the changed data in the evaluation data and obtain the basic mapping item.

[0031] Furthermore, the method for obtaining the target mapping item includes:

[0032] Taking physical sign information items, questionnaire information items, medical history information items and hormone information items as input, it interacts with the health assessment model and outputs the health assessment coefficient of the target patient, thereby obtaining the mapping data of physical sign data, questionnaire score information, past medical history information and hormone level data to obtain the target mapping item.

[0033] Furthermore, the method for creating the environmental assessment model includes:

[0034] Based on the mapping difference items, the mapping difference items include the matching differences between the physical sign data, questionnaire score information, past medical history information, and hormone level data in the basic mapping items and the physical sign data, questionnaire score information, past medical history information, and hormone level data in the target mapping items, thereby obtaining four difference control items;

[0035] Based on the difference control items and environmental information items as input, the target algorithm is selected for model training to obtain the environmental assessment model.

[0036] Furthermore, an artificial intelligence-assisted female menopause medical data processing method uses the artificial intelligence-assisted female menopause medical data processing system described above, including:

[0037] A monitoring module is set, where the monitoring module is a wearable smart device, and the vital signs information data and environmental information data of the target patient are obtained based on the monitoring module to obtain feature information items and environmental information items;

[0038] Obtaining questionnaire score information of the target patient to obtain questionnaire information items, and simultaneously obtaining medical history information and hormone level data of the target patient to obtain medical history information items and hormone information;

[0039] Based on the data acquisition method, an evaluation sample is obtained, where the evaluation sample includes evaluation data of at least two evaluation patients, to obtain an evaluation data set;

[0040] Create a health assessment model based on the assessment data set, and output the mapping data between the assessment samples to obtain the basic mapping items;

[0041] Based on the health assessment model, the health assessment coefficient of the target patient is obtained. The health assessment coefficient includes mapping data of physical sign data, questionnaire score information, past medical history information, and hormone level data to obtain the target mapping item;

[0042] The basic mapping items are compared with the target mapping items to obtain the mapping differences of the target patients and the mapping difference items. An environmental assessment model is created based on the mapping difference items and the environmental information items. The environmental assessment model is optimized based on the continuously obtained mapping difference items and environmental information items, and then the participation information of the environmental data is obtained. The environmental data is taken into consideration and intervention suggestions are assisted in generation based on the environmental assessment model.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] This artificial intelligence-assisted processing method and system for female menopausal medical data accurately captures the typical hot flashes of female menopause by setting a monitoring module for wearable smart devices. It obtains surface temperature and current change data through micro-thermistors and microcurrent sensors, and obtains accurate feature information items through strict threshold judgment. At the same time, it can also obtain environmental information data such as noise and light, and comprehensively consider the interference of environmental factors on female endocrine and menopausal symptoms. The acquisition module integrates multi-dimensional information such as questionnaire scores, past medical history and hormone levels to ensure the comprehensiveness of information. The evaluation module outputs the health assessment coefficient and target mapping item of the target patient based on the health assessment model. The comparison module compares the basic mapping item with the target mapping item, creates an environmental assessment model and continuously optimizes it, which can accurately obtain the participation information of environmental data and provide a comprehensive and accurate basis for clinical diagnosis and treatment.

[0045] At the same time, it greatly improves the scientificity and reliability of data processing. In the process of acquiring feature information items and environmental information items, strict judgment thresholds and cycles are set, such as acquisition thresholds, judgment thresholds, judgment cycles, etc., which effectively ensure the accuracy and representativeness of the data. In the acquisition of questionnaire information items, reliable response time nodes are screened out by setting judgment thresholds, avoiding inaccurate results caused by too long or too short response time. In terms of model creation, neural network models and XGBoost algorithms are used for training to ensure the scientificity and effectiveness of health assessment models and environmental assessment models. Taking into account various factors, the system can more accurately reflect the actual situation of women in menopause, provide strong support for doctors to formulate personalized treatment plans, and help improve the quality and effectiveness of medical services for women in menopause. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic diagram of the overall process of the present invention;

[0047] Figure 2 A schematic diagram of the process of obtaining environmental information items and characteristic information items of the present invention;

[0048] Figure 3 A schematic diagram of the process of obtaining questionnaire information items of the present invention;

[0049] Figure 4 A schematic diagram of first data and second data of the present invention;

[0050] Figure 5 Schematic diagram of the relationship between the first variable and the first fixed quantity of the present invention. DETAILED DESCRIPTION

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0052] In the field of medical data auxiliary processing of female menopause, existing methods generally focus on static physiological indicators, such as hormone levels, examination data, etc. At present, medical data auxiliary processing systems for female menopause are mostly based on laboratory test data and historical medical records for modeling and analysis. These data reflect the patient's physiological state at a specific time point and are highly stable and easy to process. For example, by analyzing changes in hormone levels, the stage and severity of menopause can be determined; by analyzing bone density data, the risk of osteoporosis can be assessed. However, these static data are difficult to fully reflect the health status of menopausal women, especially when dealing with complex and changeable symptoms. Sign monitoring data, such as heart rate, blood pressure, sleep quality, etc., as well as environmental noise data, as dynamic data, can reflect the patient's physiological and psychological state in real time. However, these dynamic data have the characteristics of high dimensionality and nonlinearity, and are difficult to directly apply to traditional static data analysis methods. Static data has time series characteristics, and features with time series relationships need to be extracted to effectively reflect its internal laws. However, in the face of sign monitoring and environmental noise data, the traditional static data analysis method can not only reflect the physiological and psychological state of patients, but also reflect the physiological and psychological state of patients. When dealing with multi-source heterogeneous data such as , due to its dynamic changing characteristics, existing methods face challenges in automatically extracting complex correlation features, resulting in information fragmentation, which in turn affects the accuracy of medical data auxiliary processing. The present application provides an artificial intelligence female menopause medical data auxiliary processing system. The monitoring module uses wearable smart devices to accurately capture the typical hot flashes of female menopause. Through micro-thermistors and micro-current sensors, the surface temperature and current change data are obtained. After strict threshold judgment, accurate feature information items are obtained. At the same time, environmental information data such as noise and light can be obtained. The interference of environmental factors on female endocrine and menopausal symptoms is comprehensively considered. The acquisition module integrates multi-dimensional information such as questionnaire scores, past medical history and hormone levels to ensure the comprehensiveness of information. The evaluation module outputs the health assessment coefficient and target mapping item of the target patient based on the health assessment model. The comparison module compares the basic mapping item with the target mapping item, creates an environmental assessment model and continuously optimizes it. It can accurately obtain the participation information of environmental data, provide a comprehensive and accurate basis for clinical diagnosis and treatment, and help to realize personalized intervention recommendations, such as Figure 1 As shown, it includes a monitoring module, an acquisition module, a creation module, an evaluation module and a comparison module.

[0053] Monitoring module: Set up the monitoring module, obtain the target patient's vital signs information data and environmental information data based on the monitoring module, and obtain characteristic information items and environmental information items.

[0054] It should be noted that if Figure 2As shown, the monitoring module is a wearable smart device, and the vital sign information data includes the number of hot flashes, which is one of the most typical physiological reactions of menopause. The fever is characterized by a sudden burning sensation in the chest, neck or face, redness of the skin, and an increase in the surface current. The method for obtaining the characteristic information item includes: the monitoring module includes a micro thermistor and a microcurrent sensor, and the real-time surface temperature change and surface current change of the target patient are obtained based on the monitoring module to obtain the surface temperature item and the surface current item; the acquisition threshold is set, the acquisition threshold is a time threshold, and the set acquisition threshold is 10 days. Based on the acquisition threshold, the change data of the surface temperature item is obtained, and the judgment threshold and the first fluctuation threshold are set. The judgment threshold is a time threshold, the judgment threshold is 3mim, and the first fluctuation threshold is a numerical threshold, which is 1°C. Based on the judgment threshold, when the temperature rises and falls within the judgment threshold and exceeds the first fluctuation threshold, the first judgment data set is obtained; based on the acquisition threshold, the change data of the surface current item is obtained, and the second fluctuation threshold is set. The second fluctuation threshold is a numerical threshold, and the second fluctuation threshold is 0.5μS. When the fluctuation of the surface current item exceeds the second fluctuation threshold, the second judgment data set is obtained; the time nodes of the first judgment data set and the second judgment data set are obtained, and the time nodes are compared to see if they are consistent. When the time nodes are consistent, the third judgment data set is obtained, and the third judgment data set is used as the feature information item.

[0055] In the specific implementation process, the wearable smart device is used to obtain the vital signs information data of a user A. According to the set acquisition threshold of 10 days, the surface temperature change data of user A is continuously obtained. The surface temperature change information of user A is shown in Table 1:

[0056] Table 1

[0057]

[0058] As shown in Table 1, user A experienced three temperature rise events on the first, second, fourth, seventh, and eighth days, and two temperature rise events on the remaining days. This results in a first judgment data set, and the user's body surface current change data is also obtained, as shown in Table 2:

[0059] Table 2

[0060]

[0061] As can be seen from Table 2, user A had three body surface current increase events on the first, second, fourth, and seventh days, one body surface current increase event on the tenth day, and two body surface current increase events on the remaining days. The second judgment data set is obtained, and the time nodes of the first judgment data set and the second judgment data set are obtained. The time nodes are compared to see whether they are consistent. When the time nodes are consistent, the third judgment data set is obtained. The third judgment data set is used as the feature information item. According to Tables 1 and 2, the time nodes at 24:00 on the eighth day and 22:00 on the tenth day are inconsistent, and the remaining time nodes are consistent. Thus, the third judgment data set is obtained, and the feature information item is obtained.

[0062] It should be noted that if Figure 2 As shown, the environmental information data includes noise information and light exposure time information. Noise and light exposure time will affect the female endocrine system, thereby interfering with menopausal symptoms. The method for obtaining environmental information items includes: the monitoring module also includes a built-in microphone module and a multispectral light sensor, and the multispectral light sensor includes an ambient light sensor module; based on the built-in microphone module, environmental sound wave data is obtained to obtain a sound wave information item, based on the ambient light sensor module, light data is obtained, and the light data is divided into natural light and artificial light source, and natural light duration information and natural light intensity information are obtained to obtain a light information item; a judgment period is set, and the judgment period is a time period, and the judgment period is 10 days. Based on the judgment period, the average information of the sound wave information item and the light information item is obtained to obtain a sound wave average item and a light average item. The sound wave average item and the light average item are combined to obtain the environmental information item.

[0063] In the specific implementation process, the environmental information data of a user A is obtained through a wearable smart device. According to the set judgment period of 10 days, the average information of the sound wave information item and the light information item is obtained based on the judgment period to obtain the sound wave average item and the light average item. The results of the sound wave information and light information obtained within the judgment period are shown in Table 3:

[0064] Table 3

[0065]

[0066] As shown in Table 3, the average sound wave item and the average light item are 60.3, 473.5, and 1.49, respectively. That is, the noise information of user A's environment is 60.3 dBA, the light intensity information is 473.5 lux, and the light duration information is 1.49 h, thus obtaining the environmental information item.

[0067] Acquisition module: obtains the questionnaire score information of the target patient, obtains the questionnaire information item, and simultaneously obtains the target patient's medical history information and hormone level data, obtains the medical history information item and hormone information.

[0068] It should be noted that if Figure 3 As shown, the questionnaire scoring information includes the menopausal symptom score, and the method for obtaining the questionnaire information item includes: obtaining the scoring results of the menopausal symptom scoring scale of the target user to obtain a first result set; obtaining the control time of the first result set to obtain a first time set; setting a judgment threshold, the judgment threshold is a time threshold, obtaining the time node in the first time set where the control time does not exceed the judgment threshold, obtaining the first screening time set, obtaining the corresponding items of the first screening time set and the first result set, obtaining the average score of the corresponding items, and obtaining the questionnaire information item.

[0069] Specifically, at different times, the time taken by users to answer the Menopause Symptom Rating Scale is inconsistent. When the response time is too long, it means that the user is hesitant in the process of answering, and the result of the response will be relatively inaccurate. When the response time is short, it means that the user may answer casually in the process of answering. At this time, a judgment threshold needs to be set. The judgment threshold is the standard time for answering the Menopause Symptom Rating Scale ±3min. The time node when the user answers the Menopause Symptom Rating Scale and the response time does not exceed the judgment threshold is obtained, and the response result corresponding to the time node is obtained, and the average score is obtained to obtain the questionnaire information item.

[0070] During the specific implementation process, user A responded to the menopausal symptom rating scale 5 times in total, with scores of 56, 65, 66, 68, and 83 respectively. When the score is between 0-60, the judgment result is mild, when the score is between 60-80, the judgment result is intermediate, and when the score is between 80-100, the judgment result is severe. The standard time for responding to the menopausal symptom rating scale is 15 minutes. The 5 response times of user A are 11 minutes, 13 minutes, 15 minutes, 17 minutes and 19 minutes respectively. According to the set judgment threshold, the judgment threshold is 15 minutes ± 3 minutes, that is, 12 minutes - 18 minutes. The first and fifth response times of user A are not within the judgment threshold. At this time, the time nodes where the response time does not exceed the judgment threshold are the second, third and fourth times. The response results corresponding to the time nodes are 65, 66, and 68 respectively, and the average score is obtained, that is, 66.33, to obtain the questionnaire information item.

[0071] Creation module: Based on the data acquisition method, obtain evaluation samples, the evaluation samples include at least two evaluation patients' evaluation data, obtain the evaluation data set, create a health assessment model based on the evaluation data set, and output the mapping data between the evaluation samples to obtain the basic mapping items.

[0072] It should be noted that if Figure 4As shown, the evaluation data includes physical sign data, questionnaire score information, past medical history information and hormone level data. The method for creating a health assessment model includes: setting a minimum sample size of 200, setting a first difference value, a second difference value and a third difference value, wherein the first difference value is age, the second difference value is age, and the third difference value is status, and the evaluation samples cover the first difference value, the second difference value and the third difference value respectively, obtaining the physical sign data, questionnaire score information, past medical history information and hormone level data of the evaluation samples to obtain the evaluation basic items; selecting a target model, the selected target model is a neural network model, splitting the evaluation basic items into first data and second data, wherein the first data is numerical data, which is physical sign data, questionnaire score information, and hormone level data, and the second data is categorical data, which is past medical history information. The first data is used as input to perform input into the fully connected layer, and the second data is used as the embedding layer. The time series data is encoded using LSTM, and the XGBoost algorithm is selected for model training to obtain a health assessment model.

[0073] It should be noted that the method for obtaining basic mapping items includes: sequentially setting one change data in the evaluation data as the first variable, and the remaining change data as the first fixed quantity, obtaining the change data of the variable, and obtaining the first change data set; sequentially setting two change data in the evaluation data as the second variable, and the remaining change data as the second fixed quantity, obtaining the change data of the second variable, and obtaining the second change data set, repeating this step, and sequentially increasing the number of change data, obtaining the mapping relationship of the change data in the evaluation data, and obtaining the basic mapping items.

[0074] Specifically, such as Figure 5As shown, since the evaluation data include physical sign data, questionnaire score information, past medical history information and hormone level data respectively, when obtaining the mapping data between the evaluation samples, one of the change data in the evaluation data is set as the first variable, and the remaining change data is set as the first fixed quantity, that is, first taking the physical sign data as the first variable, and the questionnaire score information, past medical history information and hormone level data as the first fixed quantity, the mapping data of the physical sign data in the health evaluation model is obtained, and then taking the questionnaire score information as the first variable, the physical sign data, past medical history information and hormone level data as the first fixed quantity, the mapping data of the questionnaire score information in the health evaluation model is obtained, and this step is repeated to obtain the first change data set, and then two change data in the evaluation data are set as the second variable, and the remaining change data are set as the second fixed quantity, that is, the physical sign data and the questionnaire score information are used as the second variable, and the past medical history information and hormone level data are used as the second fixed quantity, to obtain the mapping data of the physical sign data and the questionnaire score information in the health evaluation model, and this step is repeated again to obtain the second change data set, and then the number of change data is increased in sequence to obtain the mapping relationship of the change data in the evaluation data, and to obtain the basic mapping item.

[0075] Evaluation module: Based on the health assessment model, the health assessment coefficient of the target patient is obtained. The health assessment coefficient includes mapping data of physical sign data, questionnaire score information, past medical history information and hormone level data to obtain the target mapping item.

[0076] It should be noted that the method for obtaining the target mapping item includes: taking the physical sign information item, questionnaire information item, medical history information item and hormone information item as input, interacting with the health assessment model, outputting the health assessment coefficient of the target patient, and then obtaining the mapping data of the physical sign data, questionnaire score information, past medical history information and hormone level data to obtain the target mapping item.

[0077] Specifically, after creating the health assessment model, the acquired physical sign information items, questionnaire information items, medical history information items and hormone information items of the target patient are used as input items to interact with the health assessment model, and the mapping data of the target patient's physical sign data, questionnaire score information, past medical history information and hormone level data are output to obtain the target mapping items.

[0078] Comparison module: compares the basic mapping items with the target mapping items, obtains the mapping differences of the target patients, obtains mapping difference items, and creates an environmental assessment model based on the mapping difference items and environmental information items. Based on the continuously obtained mapping difference items and environmental information items, the environmental assessment model is optimized to obtain the participation information of the environmental data.

[0079] It should be noted that the method for creating the environmental assessment model includes: based on the mapping difference items, the mapping difference items include the matching differences between the physical sign data, questionnaire score information, past medical history information and hormone level data in the basic mapping items and the physical sign data, questionnaire score information, past medical history information and hormone level data in the target mapping items, and four difference control items are obtained; based on the difference control items and the environmental information items as input, the target algorithm is selected for model training to obtain the environmental assessment model.

[0080] Specifically, since the health assessment model is created based on the minimum sample size determined by the setting, the physical sign data, questionnaire score information, medical history information and hormone level data in the assessment sample are obtained as a sentence, and the physical sign information items, questionnaire information items, medical history information items and hormone information items of the target user are also affected by the environmental information items, there will be certain differences between the target mapping items and the basic mapping items in the health assessment model. This difference is caused by the influence of the environmental information items. Therefore, the difference obtained by comparison and the environmental information items are used as input to create an environmental assessment model, and then the participation information of the environmental data is obtained, so that the environmental data can be taken into consideration and intervention suggestions are assisted in generation based on the environmental assessment model.

[0081] An artificial intelligence-assisted female menopause medical data processing method uses the above-mentioned artificial intelligence-assisted female menopause medical data processing system, including: setting a monitoring module, the monitoring module is a wearable smart device, based on the monitoring module, obtaining the target patient's physical sign information data and environmental information data, obtaining feature information items and environmental information items; obtaining the target patient's questionnaire score information, obtaining the target patient's past medical history information and hormone level data, obtaining medical history information items and hormone information; based on the data acquisition method, obtaining an evaluation sample, the evaluation sample includes at least two evaluation patients' evaluation data, obtaining an evaluation data set; creating a health record based on the evaluation data set. Evaluation model, and output the mapping data between evaluation samples to obtain basic mapping items; based on the health assessment model, obtain the health assessment coefficient of the target patient, the health assessment coefficient includes the mapping data of physical sign data, questionnaire score information, past medical history information and hormone level data, and obtain the target mapping item; compare the basic mapping item with the target mapping item, obtain the mapping difference of the target patient, obtain the mapping difference item, and create an environmental assessment model based on the mapping difference item and the environmental information item, optimize the environmental assessment model based on the continuously obtained mapping difference item and environmental information item, and then obtain the participation information of the environmental data, take the environmental data into consideration, and assist in the generation of intervention suggestions based on the environmental assessment model.

[0082] Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is limited by the accompanying embodiments and their equivalents.

Claims

1. An artificial intelligence-assisted female menopause medical data processing system, comprising: Monitoring module: Setting the monitoring module, which is a wearable smart device, obtains the target patient's vital signs information data and environmental information data based on the monitoring module to obtain feature information items and environmental information items; Acquisition module: obtains the questionnaire score information of the target patient, obtains the questionnaire information item, and simultaneously obtains the target patient's medical history information and hormone level data, obtains the medical history information item and hormone information; Its characteristics are: Creation module: Based on the data acquisition method, obtain evaluation samples, the evaluation samples include at least two evaluation patients' evaluation data, obtain the evaluation data set, create a health assessment model based on the evaluation data set, and output the mapping data between the evaluation samples to obtain the basic mapping items; Evaluation module: Based on the health assessment model, the health assessment coefficient of the target patient is obtained. The health assessment coefficient includes mapping data of physical sign data, questionnaire score information, past medical history information, and hormone level data to obtain the target mapping item; Comparison module: compares the basic mapping items with the target mapping items, obtains the mapping differences of the target patients, obtains mapping difference items, and creates an environmental assessment model based on the mapping difference items and environmental information items. Based on the continuously obtained mapping difference items and environmental information items, the environmental assessment model is optimized to obtain the participation information of the environmental data.

2. The artificial intelligence female menopause medical data auxiliary processing system according to claim 1 is characterized by: The physical sign information data includes the number of hot flashes, and the method for obtaining the characteristic information item includes: The monitoring module includes a micro-thermal sensor and a micro-current sensor, which obtains the real-time surface temperature changes and surface current changes of the target patient based on the monitoring module, and obtains the surface temperature item and the surface current item; Setting an acquisition threshold, which is a time threshold, and acquiring change data of the body surface temperature item based on the acquisition threshold; setting a determination threshold and a first fluctuation threshold, which is a time threshold and a first fluctuation threshold, and obtaining a first determination data set when the temperature rises or falls within the determination threshold and exceeds the first fluctuation threshold based on the determination threshold; Acquire change data of the body surface current item based on the acquisition threshold, set a second fluctuation threshold, the second fluctuation threshold is a numerical threshold, and obtain a second determination data set when the fluctuation of the body surface current item exceeds the second fluctuation threshold; Obtain the time nodes of the first determination data set and the second determination data set, compare whether the time nodes are consistent, and when the time nodes are consistent, obtain a third determination data set, and use the third determination data set as the feature information item.

3. The artificial intelligence female menopause medical data auxiliary processing system according to claim 1 is characterized by: The environmental information data includes noise information and light exposure time information, and the method for obtaining the environmental information items includes: The monitoring module also includes a built-in microphone module and a multi-spectral light sensor, and the multi-spectral light sensor includes an ambient light sensing module; Acquire ambient sound wave data based on the built-in microphone module to obtain a sound wave information item, acquire light data based on the ambient light sensor module, divide the light data into natural light and artificial light, obtain natural light duration information, and obtain a light information item; A determination period is set, where the determination period is a time period. Average information of the sound wave information item and the light information item is obtained based on the determination period to obtain a sound wave average item and a light average item. The sound wave average item and the light average item are combined to obtain an environment information item.

4. The artificial intelligence female menopause medical data auxiliary processing system according to claim 1 is characterized by: The questionnaire score information includes a menopausal symptom score, and a method for obtaining the questionnaire information items includes: Obtain the menopausal symptom rating scale score results of the target user to obtain a first result set; Obtaining the comparison time of the first result set to obtain a first time set; Set a judgment threshold, which is a time threshold, obtain the time nodes in the first time set whose control time does not exceed the judgment threshold, obtain the first screening time set, obtain the corresponding items of the first screening time set and the first result set, obtain the average score of the corresponding items, and obtain the questionnaire information item.

5. The artificial intelligence female menopause medical data auxiliary processing system according to claim 1 is characterized by: The assessment data includes physical sign data, questionnaire score information, past medical history information, and hormone level data. The method for creating a health assessment model includes: Setting and determining the minimum sample size, setting the first difference value, the second difference value, and the third difference value, so that the evaluation samples cover the first difference value, the second difference value, and the third difference value respectively, obtaining the physical sign data, questionnaire score information, past medical history information, and hormone level data of the evaluation samples, and obtaining the basic evaluation items; Select the target model, split the evaluation basic items into first data and second data, use the first data as input, input the fully connected layer, use the second data as embedding, select the target algorithm for model training, and obtain the health assessment model.

6. The artificial intelligence female menopause medical data auxiliary processing system according to claim 5 is characterized by: The method for obtaining the basic mapping item includes: Sequentially set one of the change data in the evaluation data as the first variable and the remaining change data as the first fixed quantity, obtain the change data of the variable, and obtain a first change data set; Set the two changed data in the evaluation data as the second variable and the remaining changed data as the second fixed quantity in sequence, obtain the changed data of the second variable, and obtain the second changed data set. Repeat this step and increase the number of changed data in sequence to obtain the mapping relationship of the changed data in the evaluation data and obtain the basic mapping item.

7. The artificial intelligence female menopause medical data auxiliary processing system according to claim 6 is characterized by: The method for obtaining the target mapping item includes: Taking physical sign information items, questionnaire information items, medical history information items and hormone information items as input, it interacts with the health assessment model and outputs the health assessment coefficient of the target patient, thereby obtaining the mapping data of physical sign data, questionnaire score information, past medical history information and hormone level data to obtain the target mapping item.

8. The artificial intelligence female menopause medical data auxiliary processing system according to claim 7 is characterized by: The method for creating the environmental assessment model includes: Based on the mapping difference items, the mapping difference items include the matching differences between the physical sign data, questionnaire score information, past medical history information, and hormone level data in the basic mapping items and the physical sign data, questionnaire score information, past medical history information, and hormone level data in the target mapping items, thereby obtaining four difference control items; Based on the difference control items and environmental information items as input, the target algorithm is selected for model training to obtain the environmental assessment model.

9. An artificial intelligence-assisted method for processing medical data related to female menopause, characterized by: An artificial intelligence female menopause medical data auxiliary processing system according to any one of claims 1 to 8 is used, comprising: A monitoring module is set, where the monitoring module is a wearable smart device, and the vital signs information data and environmental information data of the target patient are obtained based on the monitoring module to obtain feature information items and environmental information items; Obtaining questionnaire score information of the target patient to obtain questionnaire information items, and simultaneously obtaining medical history information and hormone level data of the target patient to obtain medical history information items and hormone information; Based on the data acquisition method, an evaluation sample is obtained, where the evaluation sample includes evaluation data of at least two evaluation patients, to obtain an evaluation data set; Create a health assessment model based on the assessment data set, and output the mapping data between the assessment samples to obtain the basic mapping items; Based on the health assessment model, the health assessment coefficient of the target patient is obtained. The health assessment coefficient includes mapping data of physical sign data, questionnaire score information, past medical history information, and hormone level data to obtain the target mapping item; The basic mapping items are compared with the target mapping items to obtain the mapping differences of the target patients and the mapping difference items. An environmental assessment model is created based on the mapping difference items and the environmental information items. The environmental assessment model is optimized based on the continuously obtained mapping difference items and environmental information items, and then the participation information of the environmental data is obtained. The environmental data is taken into consideration and intervention suggestions are assisted in generation based on the environmental assessment model.

Images