User self-management system embedded with a database of seasonal allergic rhinitis experts

Abstract

The present invention discloses a user self-management system embedded with an expert database for seasonal allergic rhinitis, belonging to the technical field of big data health management, including: an expert database construction module for constructing an expert database; a model supervision and training module for supervising and training an IMB intervention model; an engine connection establishment module for establishing an engine connection, wherein there is a corresponding relationship between role permissions and an index matrix; a data formatting module for receiving rhinitis data, identifying and performing semantic parsing, and converting and determining formatted data; a guidance information determination module for user guidance information; and a user self-management module for visually displaying the user guidance information on a terminal and performing user self-management. This application solves the problem of how to provide targeted guidance according to the user's status based on seasonal environmental variables and achieve effective self-management of users.

Description

Technical Field

[0001] The present invention relates to the technical field of big data health management, and particularly to a user self-management system embedded with an expert database for seasonal allergic rhinitis. Background Art

[0002] With the development of information technology, big data and artificial intelligence have been widely applied in the medical field, especially in disease management and the formulation of personalized treatment plans. The combination of data mining, machine learning, and intelligent intervention models enables medical health management to be more accurate and personalized, helping patients achieve better treatment effects and self-management.

[0003] Seasonal allergic rhinitis (AR), as a chronic allergic disease, patients are often affected by seasonal allergens and symptoms recur. Due to the strong environmental mobility and the variability of user states of seasonal allergic rhinitis, it is difficult for users to pay effective attention and respond daily, which exacerbates the user's reaction state. Therefore, how to provide targeted guidance according to seasonal environmental variables and user states to achieve effective self-management of users is a technical problem to be solved currently. Summary of the Invention

[0004] This application provides a user self-management system embedded with an expert database for seasonal allergic rhinitis, aiming to solve the problem of how to provide targeted guidance according to seasonal environmental variables and user states to achieve effective self-management of users.

[0005] In view of the above problems, this application provides a user self-management system embedded with an expert database for seasonal allergic rhinitis.

[0006] This application discloses a user self-management system embedded with an expert database for seasonal allergic rhinitis. The system includes retrieving big data and calling rhinitis data, performing data mining with seasonal environmental variables - first allergic characteristics - guidance information to construct an expert database; mining the second allergic correlation of information - motivation - behavior, supervising and training an IMB intervention model, wherein the IMB intervention model is embedded with the expert database; setting role permissions and an index matrix, allowing target users to access and allocate role permissions, establishing an engine connection, wherein there is a corresponding relationship between the role permissions and the index matrix, and the index matrix includes scanning engines in multiple ranges; receiving rhinitis data, identifying and performing semantic parsing, converting and determining formatted data; for the formatted data, performing database retrieval and intervention guidance decision under permission constraints based on the IMB intervention model to determine user guidance information; visually displaying the user guidance information on a terminal for user self-management.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] By adopting the technical solutions of embedding an expert database for seasonal allergic rhinitis, personalized intervention decision-making based on the IMB intervention model, data mining, and user self-management, the problem of how to provide targeted guidance according to seasonal environmental variables and user status to achieve effective self-management of users is solved, and the technical effects of improving the self-management ability of patients, optimizing the treatment effect, reducing the recurrence and exacerbation of rhinitis are achieved through precise intervention, real-time guidance, and personalized management.

[0009] The above description is only an overview of the technical solutions of this application. In order to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of this application more obvious and understandable, the specific embodiments of this application are hereinafter specifically exemplified. Brief Description of the Drawings

[0010] Figure 1 This is a schematic structural diagram of a user self-management system embedded with an expert database for seasonal allergic rhinitis provided by an embodiment of this application.

[0011] Figure 2 This is a schematic flowchart of constructing an expert database in a user self-management system embedded with an expert database for seasonal allergic rhinitis provided by an embodiment of this application.

[0012] Description of the reference numerals: Expert database construction module 11, model supervision and training module 12, engine connection establishment module 13, data formatting module 14, guidance information determination module 15, user self-management module 16. Detailed Embodiments

[0013] The general idea of the technical solution provided in this application is as follows:

[0014] An embodiment of this application provides a user self-management system embedded with an expert database for seasonal allergic rhinitis. By constructing a user self-management system based on an expert database for seasonal allergic rhinitis and combining big data retrieval, data mining, and the IMB intervention model, a personalized and comprehensive intervention plan is provided. The system analyzes rhinitis data, environmental variables, and user characteristics to determine guidance information, and provides dynamic and real-time management guidance through permission control and formatted data display to help users effectively manage the disease, optimize the treatment effect, and improve their self-management ability, reducing the risk of disease recurrence and exacerbation.

[0015] After introducing the basic principle of this application, the various non-limiting embodiments of this application will be specifically introduced below in conjunction with the drawings of the specification.

[0016] Embodiments, such as Figure 1 As shown, the embodiments of the present application provide a user self - management system embedded with an expert database for seasonal allergic rhinitis. The system includes:

[0017] An expert database construction module 11, which is used to perform big data retrieval and call rhinitis data, and conduct data mining with seasonal environmental variables - first allergic characteristics - guiding information to construct an expert database.

[0018] Specifically, rhinitis data refers to various types of data related to allergic rhinitis (AR), including patients' symptom data, treatment data, environmental factor data (such as seasonal changes, air quality, etc.), immune response data, etc. Seasonal environmental variables refer to environmental factors related to seasonal changes, such as temperature, humidity, the concentration of allergens in the air, etc. These factors will affect the attack frequency and severity of allergic rhinitis. The first allergic characteristic refers to the immune response characteristics that cause the onset of seasonal rhinitis, mainly including the immune response to specific allergens. The guiding information is personalized advice or treatment strategies for users generated based on the data mining results, which helps patients better manage the disease.

[0019] First, "big data retrieval" is carried out, that is, data related to seasonal allergic rhinitis is collected from major health databases, literature, and clinical data through data collection tools (such as API interfaces, crawler programs, etc.). These data include patients' symptom manifestations, environmental changes, immune responses, etc. For example, climate change data of a certain area can be obtained through environmental monitoring stations, and rhinitis symptom data recorded by patients through a health management APP.

[0020] Next, data mining techniques are used to process these data, and predictive seasonal environmental variables are extracted, such as the pollen concentration in spring and the humidity in autumn. Combining these environmental factors with the symptom manifestations of rhinitis patients, the first allergic characteristics are further analyzed, such as the intensity of allergic reactions in specific seasons.

[0021] Subsequently, machine learning algorithms (such as decision trees, support vector machines, etc.) are used for data mining to construct an expert database containing different seasonal environmental variables and allergic characteristics. This database contains information such as the influence mode of environmental changes on rhinitis and the change rules of rhinitis symptoms in different seasons.

[0022] Through big data retrieval and data mining, the system can identify the influence mode of seasonal environmental changes on rhinitis symptoms and construct an expert database. This database not only provides a scientific basis for doctors to help them make more accurate treatment decisions, but also provides personalized guiding information for patients.

[0023] The model supervision and training module 12 is used to mine the second allergic interrelationship of information-motivation-behavior, and supervise and train the IMB intervention model, where the expert database is embedded in the IMB intervention model.

[0024] Specifically, information-motivation-behavior (IMB) are the three core components of the model.

[0025] Among them, Information refers to the knowledge and information that an individual obtains about health problems, which helps them understand the severity of the problem and how to take actions. Motivation refers to the internal driving force for an individual to take actions, including the degree of personal attention to health and the willingness to adopt a certain behavior. Behavior refers to actual health behaviors, such as following treatment plans, changing lifestyles, etc. The second allergic interrelationship refers to the interaction between an individual's understanding of information and their motivation within the framework of the IMB model.

[0026] First, the application of the information-motivation-behavior (IMB) intervention model needs to be realized. This model works collaboratively through three dimensions (information, motivation, behavior) to help individuals change their health behaviors. Specifically, the information part is provided to patients through the medical knowledge and treatment suggestions stored in the expert database. This information involves knowledge of diseases, treatment methods, environmental control techniques, etc. The motivation part mainly stimulates the motivation of patients to participate in health management by analyzing their historical data, behavioral responses, and individualized health conditions.

[0027] Next, the mining of the second allergic interrelationship is carried out by analyzing the interaction between the personal motivation of patients and health information. For example, some patients still lack the motivation to change their living habits even though they know that spring pollen exacerbates rhinitis symptoms. Therefore, the system will dynamically adjust the intervention strategy according to the patient's acceptance of information, changes in the condition, and treatment feedback to optimize the motivation part.

[0028] In this process, the role of supervision and training becomes apparent. The system will monitor the patient's health behaviors in real life (such as medication compliance, implementation of environmental control, etc.) and give personalized feedback. This feedback is generated through the information and intervention strategies in the expert database.

[0029] By mining the second allergic interrelationship of information-motivation-behavior and combining with the supervision and training of the IMB intervention model, the system can more accurately identify and influence the behavior patterns of patients in rhinitis management. It helps patients better control seasonal rhinitis, relieve symptoms, and improve the quality of life.

[0030] The engine connection establishment module 13 is used to set role permissions and an index matrix, allow target users to access and allocate role permissions, and establish an engine connection. Among them, there is a corresponding relationship between the role permissions and the index matrix, and the index matrix includes scanning engines in multiple ranges.

[0031] Specifically, role-based permissions refer to different access permissions assigned to users according to their roles (such as administrators, doctors, patients, etc.). Each role has specific operation permissions to control which functions or data a user can access in the system. Role-based permissions are usually used to ensure the security of the system and the allocation of functions. An index matrix is a two-dimensional or multi-dimensional data structure used for indexing and quickly finding specific information. It classifies and arranges data so that users or systems can efficiently locate and access data. In this step, the index matrix is used to store and map the corresponding relationship between role permissions and related functions. A scanning engine is an automated tool used to quickly scan and identify data. It is usually used for operations such as data classification, searching, and verification. In this system, the scanning engine can be used to traverse and retrieve different databases or data tables to meet specific query requirements. An engine connection refers to the process of connecting each module or database in the system to a processing engine. Through the engine connection, the system can achieve fast data processing, analysis, and query.

[0032] First, it is necessary to set role permissions and establish an index matrix to ensure that different users can access corresponding data and functions according to their roles. Specifically, the system will first define different roles for different user groups (such as patients, doctors, administrators) and set different permissions based on these roles. For example, doctors can access medical record data and treatment plans, while patients can only view their own health data and guidance information.

[0033] Next, target users access and are allocated role permissions. After the system verifies the user's identity through user registration or login, it assigns corresponding role permissions according to the user's identity. For each role, the system has a set of preset permission lists that determine which operations the role can perform (such as querying rhinitis data, modifying health records, viewing intervention suggestions, etc.).

[0034] To efficiently manage and retrieve data, the system uses an index matrix to establish a mapping relationship between role permissions and system functions. The index matrix is a two-dimensional structure. The first dimension represents different roles, and the second dimension represents available function modules or data items in the system. Each element in the matrix indicates whether a certain role has access permission to a certain function. For example, the patient role can only access their own health data, while the doctor role has permission to access all patient data.

[0035] On this basis, the system establishes a scanning engine and assigns different scanning engine scopes to each role. The role of the scanning engine is to quickly scan the data source and retrieve specific data or functions. The scanning engine can quickly find the scope corresponding to the role permissions by accessing the index matrix, so as to efficiently extract the information required by the user.

[0036] Finally, establishing the engine connection is to efficiently connect these modules (role permissions, index matrix, scanning engine) so that the system can flexibly perform permission control and data access. When a user logs in, the system interacts with the corresponding scanning engine through the engine connection, quickly retrieves the user's permissions from the index matrix, and matches the permissions with the data access requests in the system to ensure that users can only access the content they are authorized to.

[0037] By setting the mapping relationship between role permissions and the index matrix and using the scanning engine for efficient data retrieval, the system can achieve precise permission control and fast data access. At the same time, the combination of the index matrix and the scanning engine greatly improves the efficiency of the system in processing a large amount of user data, reduces the query time and data processing burden, and improves the response speed and stability of the system.

[0038] The data formatting module 14 is used to receive rhinitis data, identify and perform semantic parsing, and convert and determine the formatted data.

[0039] Specifically, semantic parsing is a natural language processing technology used to understand the meaning and structure in text. Its goal is to convert natural language input into a semantic representation that can be understood by a computer, usually structured data or concepts. For example, converting the patient's description of "I feel itchy nose and sneeze" into entities of the two symptoms of "nasal itching" and "sneezing". Formatted Data: Formatted data refers to converting raw data into a data structure that conforms to specific rules or standards. The purpose of formatting is to enable data to be processed, analyzed, and stored in different systems.

[0040] First, receive rhinitis data from different sources. These data include the patient's self-reported symptoms, doctor's diagnosis, laboratory test results, etc. These data are usually stored in an unstructured form, such as free text, pictures, or PDF reports, and are difficult to directly use for subsequent processing and analysis.

[0041] Next, the system processes these data using semantic parsing technology. Specifically, the process of semantic parsing includes tasks such as text tokenization, entity recognition, relation extraction, and sentiment analysis. Through these technologies, the system can extract key information from the text and identify specific symptoms, causes, or treatment suggestions. For example, when parsing the patient's description "The symptoms of nasal congestion and runny nose are severe", the semantic parsing engine will identify "nasal congestion" and "runny nose" as symptom entities.

[0042] After that, the system formats the parsed information, that is, converts the information into structured data according to certain rules. These structured data are usually stored and represented based on standard data formats (such as JSON, XML, or database tables) for subsequent operations. For example, the system converts the patient's symptoms "nasal congestion" and "runny nose" into structured data records: "Symptom: Nasal congestion" "Symptom: Runny nose". These formatted data can not only be further processed by the system but also integrated with other data sources. Natural language processing (NLP) libraries (such as spaCy, NLTK, BERT, etc.) are usually used for semantic parsing, database management systems (such as MySQL, MongoDB, etc.) are used for data storage, and API interfaces are used for data interaction and format conversion.

[0043] Through the processing of semantic parsing and formatted data, the system can automatically extract and structure the originally scattered and unstructured rhinitis data. This process significantly improves the utilization efficiency of the data, facilitating subsequent analysis, model training, and personalized health management recommendations. The specific technical effects include: reducing manual intervention, improving the speed and accuracy of data processing; ensuring that the system can perform rapid retrieval and analysis based on structured data; providing accurate support for further intelligent intervention and personalized medicine.

[0044] The guidance information determination module 15 is used to perform database retrieval and intervention guidance decision-making under permission constraints based on the IMB intervention model for the formatted data, and determine user guidance information.

[0045] Specifically, the IMB intervention model, namely the Information-Motivation-Behavioral Skills model, is a psychological model aimed at changing an individual's behavior by providing information, motivating motivation, and cultivating behavioral skills. This model is used to guide individual behavior change and health management. Permission constraints refer to setting different data access scopes and operation permissions in the system according to user roles and permissions to ensure the security and compliance of information and operations. Database retrieval queries and extracts relevant data based on the formatted data provided by the user, and uses the information stored in the rhinitis expert database to support decision-making. Intervention guidance decision-making means that under the guidance of the IMB intervention model, the system provides personalized health management suggestions or intervention measures for users based on the queried data.

[0046] First, based on the received formatted data, information such as the user's rhinitis condition, medical history, and seasonal factors is analyzed. Next, the system, based on the IMB intervention model, guides the user's self-management behavior according to the three main elements in the model - information, motivation, and behavioral skills. For example, in the "information" section, the system provides information on seasonal triggers related to rhinitis, symptom management, etc.; in the "motivation" section, the system motivates the user to adhere to health management behaviors, such as enhancing motivation through goal setting and self-efficacy improvement; and in the "behavioral skills" section, the system provides specific behavioral guidance, such as daily nasal irrigation, medication use guidance, etc.

[0047] To ensure data security and compliance, the system adopts a permission constraint mechanism to assign different data access permissions to users with different roles. When performing database retrieval, the system compares the formatted data with the stored content in the expert database, queries the rhinitis data most relevant to the user's health condition, and generates corresponding guidance decisions. Finally, the system will provide specific guidance information for the user according to the IMB intervention model, and this information can include health advice, symptom management methods, drug recommendations, etc., to help the user effectively manage and relieve rhinitis symptoms.

[0048] Through this system based on the IMB intervention model, users can better manage their rhinitis symptoms under personalized health guidance, improve treatment compliance, and reduce the recurrence of the disease. At the same time, permission constraints ensure data security and the protection of user privacy.

[0049] The user self-management module 16 is used to visually display the user guidance information on the terminal for user self-management.

[0050] Specifically, terminal visual display refers to the display of user guidance information in various ways such as graphics, text, and video through terminal devices (such as smartphones, computers, tablets, etc.). Terminal visual display makes information easier to understand and use, helping users quickly obtain health management advice. User self-management refers to the active participation of users in the process of health management and adjustment and management according to their own conditions. Self-management includes taking medicine on time, recording symptoms, adjusting living habits, coping with health challenges, etc., aiming to improve health levels and quality of life.

[0051] First, based on the user's health data, historical records, and personalized analysis based on the IMB intervention model, guidance information is generated. The core goal of terminal visual display is to enable users to clearly and intuitively understand the actions to be taken through graphical, textual, or even vocal means. In this process, the system will use graphical interface design tools (such as Android Studio, Xcode, React Native, etc.) to develop terminal applications and utilize data visualization libraries (such as D3.js, Highcharts, etc.) to display health management information. Through these tools, the system can transform complex health data and management suggestions into easy-to-understand charts, flowcharts, and dynamic displays, helping users easily track and manage their health conditions.

[0052] Through terminal visual display, users can intuitively view the personalized guidance information generated by the system. This method not only helps users better understand and execute health management advice but also enhances the user's sense of participation and satisfaction. The visual interface makes complex health management data clearer and easier to operate, reducing the user's cognitive burden. At the same time, the real-time interactivity of terminal devices makes self-management more flexible and efficient, helping to improve user compliance and thus achieving better health management effects.

[0053] Furthermore, the expert database construction module 11 is also used to perform the following steps: combining the rhinitis data, determining seasonal rhinitis trigger nodes, determining the node time zones with initial and termination limits for each node, and determining multiple seasonal time zones; traversing the multiple seasonal time zones to determine the time zone environmental variables, where the time zone environmental variables are environmental factors affecting the rhinitis state; using the environmental variables as independent variables and the rhinitis characteristics as dependent variables to mine the first allergic characteristics.

[0054] Specifically, the seasonal rhinitis trigger node refers to the critical moment or time period that causes the aggravation or onset of seasonal allergic rhinitis symptoms. The node time zone refers to the time range of the trigger of rhinitis symptoms within a specific season or time period. For example, the spring pollen season is a "node time zone", which includes the specific time period from the rise in pollen concentration to the onset of allergic symptoms. The seasonal time zone refers to different time periods divided according to seasonal changes, which are related to specific environmental factors (such as temperature, humidity, pollen concentration, etc.) and can affect the occurrence and aggravation of rhinitis symptoms. The time zone environmental variable refers to the environmental factors within a specific season or time period, such as temperature, humidity, pollen concentration in the air, etc., which will have a direct impact on the onset and symptom changes of rhinitis. The environmental variable is the independent variable and the rhinitis characteristic is the dependent variable, which means that by taking seasonal environmental factors (such as pollen concentration, temperature, etc.) as the independent variable and rhinitis symptoms (such as nasal congestion, sneezing) as the dependent variable, the causal relationship between the two is analyzed using statistical methods or machine learning algorithms.

[0055] First, analyze the rhinitis data to identify the seasonal rhinitis trigger nodes. These trigger nodes are usually the critical time points when rhinitis symptoms are aggravated under specific seasons or specific environmental conditions. For example, the pollen season, the period with obvious humidity changes, and the time when the temperature fluctuates sharply are all seasonal trigger nodes. By statistically analyzing the historical data of the symptoms of a large number of patients, the system can identify these trigger nodes.

[0056] Next, the system determines the node time zones with initial and termination limits for each trigger node. For example, in the spring pollen season, the time zone of the trigger node starts from the time point when the pollen concentration begins to rise (such as early February) to the time point when the pollen concentration drops (such as mid-May). By determining these time zones, the system can more accurately divide each seasonal time zone and identify the relevant environmental variables for each time zone.

[0057] Then, by traversing multiple seasonal time zones, the system analyzes according to the environmental variables (such as temperature, humidity, concentration of allergens in the air, etc.) within each time zone. For example, in spring, a warm and humid environment promotes the release of certain pollens, while in autumn, it is a high-incidence period for molds and dust mites. By analyzing the environmental variables within these time zones, the system discovers their impact on rhinitis symptoms (such as nasal congestion, sneezing, etc.).

[0058] Finally, using statistical and machine learning methods (such as regression analysis, decision trees, or neural networks, etc.), taking the environmental variables as the independent variables and the rhinitis characteristics (such as symptoms like nasal congestion and runny nose) as the dependent variables, causal relationship modeling and data mining are carried out to extract the first allergic characteristics. For example, through analysis, it is found that when the pollen concentration in spring reaches a certain level, the incidence of nasal congestion symptoms increases significantly, and such a rule becomes part of the first allergic characteristics.

[0059] Through this step, the system can accurately identify the triggering nodes and time zone environmental variables of seasonal rhinitis, and analyze how environmental factors affect rhinitis symptoms. Using data mining techniques, the system can not only reveal the correlation between rhinitis symptoms and environmental factors, but also provide personalized treatment plans for patients.

[0060] Furthermore, as Figure 2 shown, the expert database construction module 11 is also used to perform the following steps: based on the seasonal rhinitis triggering nodes, perform primary data clustering integration to determine the first data group; based on multi-level permissions, perform secondary data clustering integration to determine the second data group; according to the first data group and the second data group, label the expert database.

[0061] Specifically, the seasonal rhinitis triggering nodes refer to the critical time points or periods when rhinitis symptoms occur during seasonal changes, and these periods are often closely related to changes in environmental factors (such as temperature, humidity, pollen concentration, etc.). For example, the arrival of the spring pollen season is a triggering node. Primary data clustering integration refers to the first round of clustering analysis of the initially collected rhinitis-related data, with the aim of dividing the data into several similar data groups. Usually, clustering is performed based on certain characteristics (such as season, environmental factors, patient type, etc.). The first data group refers to the preliminary grouping obtained from the primary data clustering integration. Multi-level permissions refer to setting different access permission levels in the database or system. Through these permissions, the system can perform different access control and management on the data according to different roles. Secondary data clustering integration refers to performing a more detailed clustering analysis on the basis of the primary data clustering integration to further refine the data grouping according to other characteristics (such as the severity of the patient's condition, treatment response, etc.). The second data group refers to the refined grouping obtained after the secondary clustering integration. These groupings can be defined according to factors such as the specific treatment needs of the patient and different stages of the disease. Labeling of the expert database refers to tagging and classifying each piece of data in the expert database to make it more convenient for subsequent retrieval, analysis, and use. Database labeling can be defined based on information such as the category, source, and treatment effect of the data.

[0062] First, the rhinitis data will be initially clustered based on the seasonal rhinitis triggering nodes (such as the spring pollen season, the autumn mold season, etc.). This process is called "primary data clustering integration". In this step, the data is assigned to different groups according to specific seasonal environmental factors or allergen types. For example, the data during the spring pollen season and the rhinitis data caused by summer humidity changes are divided into two independent groups. The purpose of this grouping is to integrate the rhinitis data in a roughly similar seasonal environment for subsequent in-depth analysis.

[0063] Next, based on multi-level permissions, the system will perform more refined "secondary clustering and integration of data". Multi-level permissions refer to the allocation of data access and management permissions to different users according to the roles of users or the importance of data. In the secondary clustering, data will be more carefully grouped according to the severity of the patient's condition, the intensity of allergic reactions, the effectiveness of treatment plans, etc. For example, data of patients with mild and severe seasonal rhinitis can be divided into different groups respectively, facilitating subsequent precise intervention.

[0064] Finally, based on the results of the first data grouping and the second data grouping, the system will perform expert database identification on this data, that is, label or mark each piece of data to facilitate future data retrieval and analysis.

[0065] Through this process, the system can not only accurately classify and identify relevant data of patients with seasonal allergic rhinitis, but also provide more personalized and targeted management plans for different patients according to the data grouping.

[0066] Furthermore, a normalized standard data format is set, and based on the standard data format, the index matrix is initialized.

[0067] Specifically, the normalized data format is to uniformly convert data from different sources and of different types into a standardized structure for easy processing and analysis in the system. The purpose of normalization is to eliminate the heterogeneity of data so that different data sources and formats can be seamlessly docked in the same system.

[0068] First, it is necessary to set a normalized standard data format. The key to this process is to uniformly convert rhinitis data from different sources (such as patients' chief complaints, medical test reports, environmental variables, allergen information, etc.) into a standardized data structure. Specifically, it includes mapping text-described symptoms to standard symptom codes and unifying different formats of laboratory results (such as IgE levels in blood tests) into standard data fields. The normalized standard data format uses formats such as JSON, XML, or the row-column representation in a database table.

[0069] Once the data is normalized, the next step is to initialize the index matrix based on the standard data format. The role of the index matrix is to quickly locate and query the stored data. For example, if we need to quickly find all patient records with nasal congestion symptoms in a certain season, the index matrix can use "seasonality" and "symptom type" as index conditions to help the system quickly find relevant entries in the vast amount of data. Usually, the design of the index matrix will set multiple dimensions according to actual needs, such as symptoms, time, environment, allergens, etc. The construction of the index matrix usually uses index technologies in database management systems (such as MySQL, MongoDB), or uses data processing frameworks (such as Pandas, NumPy) to create multi-dimensional matrices and arrays. Through the unified management of these standard data formats, the system can efficiently store, update, and retrieve data.

[0070] By setting the normalized standard data format and initializing the index matrix, the entire system can achieve efficient data storage, management, and retrieval. It significantly improves data consistency and operability, ensuring that the system can handle heterogeneous data from different sources and find case information related to the target in a short time. Especially in the case of a large amount of data, using the index matrix can greatly improve the speed and efficiency of data query.

[0071] Furthermore, the data formatting module 14 is also used to perform the following steps: constructing a large language model, where the large language model includes a semantic parsing unit and a format conversion unit; by receiving the rhinitis data, performing semantic recognition based on the semantic parsing unit to determine semantic elements; taking the standard data format as a benchmark, and combining with the format conversion unit, converting the semantic elements to determine the formatted data.

[0072] Specifically, large language models (such as GPT-4, BERT, etc.) are a class of natural language processing models based on deep learning, used to process and understand information such as grammar, semantics, and context in human language. Large language models can learn from large-scale text data through pre-training and generate text with strong reasoning and generation capabilities. The semantic parsing unit is a key component in the large language model, responsible for extracting meaningful content from natural language text. This includes identifying and extracting entities (such as symptoms, time, location, etc.), relationships (such as the relationship between allergic reactions and allergens), intentions (such as "the patient hopes to relieve nasal congestion"), etc. in the text. The format conversion unit is used to convert the information after semantic parsing into a standardized, computer-recognizable data format. This is a key step in converting unstructured natural language text into a format (such as JSON, XML, database tables, etc.) that can be used for storage, retrieval, and analysis.

[0073] First, a large language model needs to be constructed. Specifically, first, a large amount of text data is collected, ensuring that the data contains rich content related to rhinitis, such as medical literature, patient feedback, clinical records, etc. Then, the data is preprocessed, including removing noise, annotation, and tokenization, etc., to ensure the quality of the input data. Next, a suitable model architecture (such as Transformer, BERT, GPT, etc.) is selected using a deep learning framework (such as TensorFlow or PyTorch), and it is trained on a large-scale data, and the model parameters are optimized through backpropagation. During the training process, the model is tuned by adjusting hyperparameters (such as learning rate, batch size) to improve the model performance. After the training is completed, the accuracy and generalization ability of the model are verified, and fine-tuning is performed according to the requirements (for example, specific adjustments are made for the rhinitis field). Finally, the trained large language model is integrated into the system to be used for processing semantic parsing tasks related to rhinitis.

[0074] Once the large language model is trained, the next is the work of the semantic parsing unit. The semantic parsing unit processes the received rhinitis data. First, it extracts key information in the text through natural language processing techniques. After identifying these semantic elements, the next task is to convert them into a standard data format through the format conversion unit. The format conversion unit will structure the parsed semantic elements based on a predefined standard data format (such as JSON or database table structure).

[0075] This process greatly improves the processing efficiency and accuracy of the data. Through semantic parsing by the large language model, effective information can be automatically extracted from free text, avoiding the limitations of manual intervention and traditional rule matching. And the format conversion unit ensures that this information can be uniformly stored and managed, thus providing a standardized data basis for subsequent data mining, analysis, and decision-making.

[0076] Furthermore, the guidance information determination module 15 is further configured to perform the following steps: transmit the formatted data to the IMB intervention model, and determine the user motivation guided by the second allergic interrelationship; based on the user motivation, perform database retrieval and guidance decision-making to determine the user guidance information.

[0077] Specifically, user motivation refers to the driving force for users to change their behaviors when facing health problems. In the IMB intervention model, the enhancement of motivation is a key factor in promoting users to change their health behaviors.

[0078] First, the user health information obtained through the formatted data is transmitted into the IMB intervention model for subsequent analysis and intervention decision-making. First, the system analyzes the user motivation based on the rhinitis data input by the user through the second allergic interrelationship model.

[0079] After motivation recognition, the system conducts a database search based on the user's motivation. The purpose of the database search is to extract personalized health guidance information from the expert database for the user's specific symptoms and needs.

[0080] Finally, the system will combine the user's motivation, the suggestions from the expert database, and permission constraints (for example, patients can only view personal data, while doctors can access more clinical resources) to generate the final health management guidance information for the user. These guidance information can be displayed to the user through terminal devices (such as mobile phone apps or smart health devices) to help them with self-management.

[0081] Through this step, not only can the user's motivation be identified, but also personalized intervention decisions can be made in combination with the expert database. This method helps users manage their health problems more effectively, improve treatment compliance, reduce disease recurrence, and at the same time ensure data security and privacy protection.

[0082] Furthermore, the guidance information determination module 15 is also used to perform the following steps: introducing the user's historical guidance information, where the user's historical guidance information is called based on historical management records; initializing the second allergic interaction relationship based on the user's historical guidance information, where the second allergic interaction relationship is a universal relationship.

[0083] Specifically, the historical management record refers to the historical data of all the user's treatment and health management operations in the system, including the treatment methods the user has received, medication usage, symptom changes, etc. The universal relationship refers to a general health management model for most users, which can be applied to different users but still reflects personalization in specific applications.

[0084] First, introduce the user's historical guidance information, that is, understand the user's long-term health status by calling the user's historical management records (such as past rhinitis symptoms, treatment feedback, medication usage, etc.). For example, if the user has reported nasal congestion and runny nose multiple times during past spring allergy seasons and has used antihistamine drugs and nasal corticosteroid drugs to control the symptoms, the system will record this information as historical guidance information.

[0085] Next, the system initializes the second allergic interaction relationship based on this user's historical guidance information. This relationship is a universal pattern designed to help the system better provide treatment decisions for the user. The key to this step is that the system adjusts and optimizes the user's health management by inputting historical data and combining the universal relationship model (i.e., a general pattern that can adapt to most people). The system converts this data into applicable intervention decisions and makes corresponding adjustments according to each user's unique situation.

[0086] For example, assume that user Zhang San has seasonal allergic rhinitis. In the past three years, he has experienced nasal congestion, runny nose, and itchy eyes every spring. The system has recorded Zhang San's use of antihistamines and nasal corticosteroids every spring, as well as the measure of avoiding outdoor activities during the pollen peak period. Based on these historical records, the system has constructed a personalized "second allergic interrelationship" for Zhang San. This model believes that Zhang San's symptoms are related to the high pollen concentration in spring, and he responds well to antihistamine drugs. Through this model, the system can automatically provide Zhang San with new health advice, such as taking preventive measures in advance when the pollen concentration is high and using drugs rationally.

[0087] By introducing the user's historical health records and treatment feedback, the system can intelligently initialize and optimize the "second allergic interrelationship" to provide users with more accurate and personalized health management advice. It not only helps users to intervene immediately when symptoms occur but also provides a basis for long-term health management, which can significantly improve treatment compliance and patient satisfaction.

[0088] Furthermore, after the user completes self-management, including: setting a preset update cycle; based on periodic nodes, uploading new theoretical data to update the expert database, and calling the periodic management record to update and learn the IMB intervention model, where the periodic management record includes an output guidance record and an input feedback record.

[0089] Specifically, the preset update cycle refers to the time interval or frequency of regular updates preset in the system. The periodic node refers to a specific time point or event node within the update cycle used to trigger data updates in the system. The new theoretical data refers to newly added relevant theoretical research results, treatment methods, drug information, or case analyses in the expert database. The periodic management record refers to the periodic data recorded for the user's health management activities during the operation of the system.

[0090] After the user completes self-management, the system will set a preset update cycle to ensure that the expert database and the intervention model always maintain the latest data and academic achievements. For example, if the system is set to update once every quarter, the periodic node can be the end of each quarter. At this time, the system will trigger new data uploads and updates through the periodic node. The new theoretical data includes the latest medical research results, treatment methods, clinical case analyses, etc., used to supplement and improve the expert database.

[0091] Meanwhile, the system will upload periodic management records, which reflect the user's health management behaviors over a period of time, including output guidance records (such as the system's personalized health management suggestions for the user) and input feedback records (such as the user's feedback, reactions, and implementation of these suggestions). Through these records, the system can analyze the implementation of the user's health management and update the intervention strategy based on the user's feedback.

[0092] The IMB intervention model will be updated and learned based on these management records. By combining the output guidance records and input feedback records, the IMB model can optimize the user's health management intervention strategy. For example, if in a certain period, many users feedback that a certain treatment method has poor effects, the system will make adjustments in the next period and recommend other more suitable solutions to the users.

[0093] By setting preset update cycles and periodic nodes, the system can keep up with the latest medical research and practices, and optimize and update the expert database and intervention model in a timely manner. This regular update ensures that the system can flexibly adapt to changes in user needs and improve the accuracy and effectiveness of interventions.

[0094] In summary, the user self - management system embedded with the expert database for seasonal allergic rhinitis provided by the embodiments of the present application has the following technical effects:

[0095] 1. By constructing an expert database for seasonal allergic rhinitis, the present invention realizes personalized self - management for seasonal rhinitis patients. Through the embedding of the expert database, it can provide accurate intervention decisions and guidance, enhance the user's understanding of rhinitis, promote self - management behaviors, and thus improve rhinitis symptoms.

[0096] 2. By mining the first allergic characteristics of seasonal rhinitis and combining the analysis of environmental variables, it effectively identifies the inducements for rhinitis attacks. Through data mining and feature analysis, it can provide scientific prevention and intervention measures for patients, reducing the risk of symptom recurrence and aggravation.

[0097] 3. By introducing the user's historical guidance information and the general second allergic relationship, the present invention optimizes the personalization and universality of user health management. The invocation and analysis of historical data improve the accuracy and adaptability of the model, making the intervention plan more in line with the specific needs of each user.

[0098] Any step of the above - mentioned method can be stored as computer instructions or programs in an unrestricted computer memory and can be called and recognized by an unrestricted computer processor to implement any method in the embodiments of the present application, without further limitation here.

[0099] Further, the first or second as described above does not only represent an order relationship, but also represents a specific concept, and / or refers to the option of selecting some or all of multiple elements. Obviously, those skilled in the art can make various changes and modifications to this application without departing from the scope of this application. Thus, if these modifications and variations of this application fall within the scope of this application and its equivalent technologies, this application is intended to cover these modifications and variations.

Claims

1. A user self-management system embedded with a seasonal allergic rhinitis expert database, characterized in that, The system includes: An expert database construction module, which is used to perform big data retrieval and call rhinitis data, conduct data mining with seasonal environmental variables - first allergic characteristics - guiding information, and construct an expert database; A model supervision and training module, which is used to mine the second allergic interrelationship of information - motivation - behavior, supervise and train the IMB intervention model, wherein the IMB intervention model embeds the expert database; An engine connection establishment module, which is used to set role permissions and index matrices, enable target users to access and allocate role permissions, and establish an engine connection, wherein there is a corresponding relationship between the role permissions and the index matrix, and the index matrix includes scanning engines in multiple ranges; A data formatting module, which is used to receive rhinitis data, identify and perform semantic parsing, and convert and determine formatted data; A guiding information determination module, which is used to perform database retrieval and intervention guidance decision-making under permission constraints based on the IMB intervention model for the formatted data, and determine user guiding information; A user self-management module, which is used to visually display the user guiding information on the terminal and perform user self-management; Among them, mining the first allergic characteristic includes: Combining the rhinitis data, determining the seasonal rhinitis trigger nodes, determining the node time zones with initial and termination limits for each node, and determining multiple seasonal time zones; Traversing the multiple seasonal time zones to determine the time zone environmental variables, where the time zone environmental variables are environmental factors affecting the rhinitis state; Using the environmental variables as independent variables and the rhinitis characteristics as dependent variables to mine the first allergic characteristic.

2. The user self-management system embedded with a seasonal allergic rhinitis expert database according to claim 1, characterized in that, The construction of the expert database includes: Based on the seasonal rhinitis trigger nodes, performing primary data clustering and integration to determine the first data group; Based on multiple levels of permissions, performing secondary data clustering and integration to determine the second data group; Identifying the expert database according to the first data group and the second data group.

3. The user self-management system embedded with a seasonal allergic rhinitis expert database according to claim 1, wherein Setting a normalized standard data format, and initializing the index matrix based on the standard data format.

4. The user self-management system embedded with a seasonal allergic rhinitis expert database according to claim 3, wherein Receiving rhinitis data, identifying and performing semantic parsing, and converting and determining formatted data, including: Constructing a large language model, where the large language model includes a semantic parsing unit and a format conversion unit; By receiving the rhinitis data, performing semantic recognition based on the semantic parsing unit to determine semantic elements; Taking the standard data format as a benchmark, combining with the format conversion unit, converting the semantic elements to determine the formatted data.

5. The user self-management system embedded with a seasonal allergic rhinitis expert database according to claim 1, wherein Performing database retrieval and intervention guidance decision-making under permission constraints based on the IMB intervention model to determine user guiding information, including: Transmitting the formatted data to the IMB intervention model, and determining the user motivation with the second allergic interrelationship as a guide; Based on the user motivation, performing database retrieval and guidance decision-making to determine the user guiding information.

6. The user self-management system embedded with the seasonal allergic rhinitis expert database as claimed in claim 5, wherein Taking the second allergic interrelationship as a guide includes: Introducing the user's historical guiding information, where the user's historical guiding information is called based on historical management records; Initialize the second allergic correlation based on the user's historical guidance information, where the second allergic correlation is a universal relationship.

7. The user self-management system embedded with a seasonal allergic rhinitis expert database as claimed in claim 1, wherein After user self-management, it includes: Set a preset update period; Based on periodic nodes, upload new theoretical data to update the expert database, and call the periodic management record to update and learn the IMB intervention model, where the periodic management record includes an output guidance record and an input feedback record.

Images