Ear-nose-throat nursing scheme intelligent recommendation system based on cloud computing

Abstract

The invention discloses an ear-nose-throat nursing scheme intelligent recommendation system based on cloud computing, and relates to the technical field of big data analysis. The intelligent recommendation platform is in communication connection with a data acquisition and preprocessing module, a knowledge graph construction module, a patient portrait construction module, a nursing scheme recommendation module, an evaluation and adjustment module and a user interaction and feedback module. According to the intelligent recommendation system for the ear-nose-throat nursing scheme based on cloud computing, deep analysis and mining are carried out on real-time physiological data, ear-nose-throat related symptoms, wound healing conditions and function recovery progress of patients by utilizing the powerful data processing capability of a cloud computing platform, individual differences and rehabilitation requirements of the patients are accurately recognized, and the intelligent recommendation system for the ear-nose-throat nursing scheme based on cloud computing is provided for the patients. And personalized nursing schemes are customized for the patients, so that the pertinence and effectiveness of nursing are improved, and the prolonged rehabilitation time and the discomfort of the patients caused by the improper schemes are greatly reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis, and in particular to an intelligent recommendation system for ear, nose and throat care solutions based on cloud computing. Background Art

[0002] ENT diseases are common health problems, including snoring, apnea, rhinitis, pharyngitis, etc. These diseases not only affect the quality of life of patients, but may also cause other complications. Therefore, the demand for ENT disease care is growing. The symptoms, causes and pathogenesis of ENT diseases in different patients may vary. Therefore, formulating personalized care plans is crucial to improving treatment effects and patient satisfaction. Cloud computing, as an Internet-based computing resource allocation and provision method, has the characteristics of ultra-large scale, virtualization, high reliability, versatility, and high scalability. It can flexibly adjust resources according to actual needs, provide large-scale, highly available data storage and processing capabilities, and support the integration of multiple devices and platforms. These characteristics provide strong technical support for the construction of intelligent nursing systems.

[0003] In the existing technology, ENT care often recommends and formulates care plans based on the patient's physiological state and wound condition. However, different patients have different physical conditions and different rehabilitation conditions, which will interfere with the recommendation of care plans to a certain extent. Therefore, how to comprehensively consider the patient's rehabilitation condition (wound healing condition, functional recovery condition) and physiological data, evaluate the effectiveness of the care plan, and then recommend care plans as needed is the problem we need to solve. To this end, this paper proposes an ENT care plan intelligent recommendation system based on cloud computing. Summary of the invention

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent recommendation system for ear, nose and throat nursing solutions based on cloud computing, including an intelligent recommendation platform, wherein the intelligent recommendation platform is communicatively connected with a data acquisition and preprocessing module, a knowledge graph construction module, a patient portrait construction module, a nursing solution recommendation module, an evaluation and adjustment module and a user interaction and feedback module, wherein the modules are connected by electrical signals;

[0005] The data acquisition and preprocessing module is used to acquire the patient's physiological data and rehabilitation data, and preprocess the acquired data;

[0006] The knowledge graph construction module uses natural language processing technology to identify key medical entities from the nursing knowledge base, including disease names, symptoms, drugs, and nursing measures, and organizes the relationships between medical entities in the form of a graph to form a nursing knowledge graph, providing a structured framework for representing and processing complex medical relationships;

[0007] The patient portrait building module builds a patient portrait based on the patient's physiological data, rehabilitation data and personal information, and deeply understands the patient's health status and rehabilitation needs, providing a basis for personalized recommendations;

[0008] The nursing plan recommendation module combines patient portraits, nursing knowledge base and nursing knowledge graph, builds a nursing plan recommendation model based on machine learning algorithms, generates personalized ENT nursing plan recommendations, and can provide accurate and effective nursing suggestions based on the patient's actual situation and rehabilitation needs;

[0009] The evaluation and adjustment module is used to monitor and evaluate the patient's rehabilitation progress in real time, evaluate the effectiveness of the recommended nursing plan, and dynamically adjust the nursing plan based on the evaluation results, so as to ensure the effectiveness and adaptability of the nursing plan and improve the patient's rehabilitation speed and satisfaction;

[0010] The user interaction and feedback module provides a user interface for collecting user feedback, including feedback from patients and medical staff on nursing plans, making it convenient for medical staff and patients to view recommended nursing plans, rehabilitation progress and data analysis results, thereby improving the system's usability and user experience and promoting effective communication between doctors and patients.

[0011] Preferably, in the data collection and preprocessing module, the process of collecting the patient's physiological data and rehabilitation status data includes:

[0012] The patient's body temperature, blood pressure, and heart rate physiological data are collected through various medical devices. The patient's body temperature data is collected through a smart thermometer, the patient's blood pressure value is measured using an electronic sphygmomanometer, and the patient's heart rate information is obtained through a heart rate monitoring device;

[0013] Collect rehabilitation data on wound healing and functional recovery through medical records, nursing staff observations, and medical equipment. Wound healing progress is assessed through visual inspection, photographic records, and wound scanners, and functional recovery is assessed through medical staff assessments and the use of rehabilitation scales.

[0014] Preprocessing the collected physiological data and rehabilitation data, including data cleaning and format conversion steps;

[0015] The preprocessed data is marked, encrypted and access controlled, and then stored in the data warehouse for subsequent access and analysis.

[0016] Preferably, in the knowledge graph construction module, the construction process of the nursing knowledge graph includes:

[0017] Medical text big data is collected through different channels to form a nursing knowledge base, which includes medical literature, case reports, and nursing guidelines. The data is preprocessed by denoising, word segmentation, and part-of-speech tagging to facilitate subsequent entity recognition and relationship extraction. Medical literature is obtained from medical databases such as PubMed, Cochrane Library, and Web of Science, and case reports are obtained from academic databases. Nursing guidelines are obtained from institutions such as the International Nursing Association and the National Health Commission.

[0018] Using named entity recognition technology, key medical entities, including disease names, symptoms, drugs, and nursing measures, are identified from preprocessed data;

[0019] Each identified medical entity is labeled with a unique identifier, and the relationship between entities is determined using relationship extraction technology, including the relationship between disease and symptoms, the relationship between drugs and diseases, and the relationship between nursing measures and diseases. The results of relationship extraction are used as edges in the knowledge graph.

[0020] The identified entities and extracted relationships are organized in the form of a graph through entity linking technology to form a nursing knowledge graph, which is then stored in a graph database for subsequent query and analysis.

[0021] Preferably, in the patient portrait construction module, the process of constructing the patient portrait includes:

[0022] Extract the patient's physiological data and rehabilitation data, and collect the patient's personal information in a targeted manner. Physiological data includes the patient's vital signs, examination results, and imaging data, which can reflect the patient's current health status and potential health problems. Rehabilitation data includes wound healing and functional recovery, which helps to understand the patient's rehabilitation needs and rehabilitation effects, and provides a basis for formulating personalized rehabilitation plans. Personal information includes the patient's basic identity information, medical history records, and medical history, which helps to have a more comprehensive understanding of the patient and provide support for formulating scientific and reasonable diagnosis and treatment plans;

[0023] The collected data were analyzed using the K-means clustering algorithm. Patients were divided into different groups based on similar physiological characteristics, rehabilitation needs, and health conditions. The relevant laws between patients' health conditions and rehabilitation needs were discovered, providing a basis for developing personalized rehabilitation plans.

[0024] Based on the results of data analysis, a patient portrait model is constructed to reflect the patient's physiological condition, wound healing, functional recovery, and potential health risk information. The physiological condition displays the patient's overall physiological state through the summary of vital signs and examination results. The wound healing condition records the wound healing process in detail, including the healing speed and quality. The functional recovery condition evaluates the patient's functional recovery, including limb mobility and muscle strength. Based on the patient's medical history, examination results, and rehabilitation status, the health risks that the patient may face are predicted to provide a basis for formulating preventive measures.

[0025] Based on the physiological condition, wound healing and functional recovery in the patient portrait, a personalized rehabilitation plan is developed, and the health risk information in the patient portrait is used to optimize the diagnosis and treatment plan.

[0026] Preferably, in the nursing plan recommendation module, the construction process of the nursing plan recommendation model includes:

[0027] Combined with patient portraits (including physiological data, rehabilitation data and personal information), nursing knowledge base and nursing knowledge graph, features related to ENT care are extracted, including symptom severity, patient age, wound healing and functional recovery. The severity of ENT-related nasal congestion, runny nose, tinnitus and sore throat symptoms is extracted from patient portraits and expressed in scores. The healing speed and quality of surgical incisions and ulcer surface wounds, as well as whether infectious complications occur, are extracted from rehabilitation data. The recovery of ENT-related hearing, smell, swallowing and pronunciation functions, including recovery speed and degree, is extracted from rehabilitation data.

[0028] Extract historical nursing cases from the nursing knowledge base, including patient characteristics, nursing plans and nursing effect information, use machine learning algorithms to train the data in the nursing knowledge base, and obtain a nursing plan recommendation model that predicts the best nursing plan through training. The nursing plan recommendation model is built based on a neural network model.

[0029] Match the patient's symptom severity, age, wound healing, and functional recovery characteristics with the nursing plan recommendation model, use the nursing plan recommendation model to predict patient characteristics, and obtain a series of nursing plans that meet the patient's needs;

[0030] According to the actual situation and rehabilitation needs of the patient, the predicted nursing plans are screened and sorted, and plans that do not meet the patient's needs are excluded. The screened nursing plans are quantitatively analyzed, the nursing plan recommendation index of each plan is calculated, and the matching degree between the nursing plan and the patient's needs is analyzed;

[0031] Based on the matching analysis results, the best care plan is selected and recommended to patients and medical staff.

[0032] Preferably, the calculation process of the nursing plan recommendation index is:

[0033] Extract the patient's physiological data, rehabilitation data and personal information, obtain the patient's symptom severity score, age, wound healing score and functional recovery score, determine the symptom severity baseline score, age baseline score, wound healing baseline score and functional recovery baseline score, and determine the maximum symptom severity score, maximum age and maximum wound healing score;

[0034] Based on the symptom severity score of the patient's symptom severity, the symptom severity baseline score value and the symptom severity maximum score value, a standardized value of symptom severity is calculated, and the square of the standardized value is exponentially calculated to further calculate the Sigmoid function value of the symptom severity;

[0035] The standardized value of age was calculated based on the patient's age, the baseline age value, and the maximum age, and the reciprocal value of the age score was calculated by squaring the standardized value;

[0036] Calculate the standardized value of wound healing based on the patient's wound healing score, the baseline score value of wound healing and the maximum score value of wound healing, and calculate the square root of the standardized value;

[0037] Based on the ratio of the patient's functional recovery score to the functional recovery baseline score, the standardized value of functional recovery is calculated, and the standardized value of functional recovery is indexed, using the minimum value formula to make the index value not exceed 1;

[0038] The standardized results of the comprehensive symptom severity score, age, wound healing score, and functional recovery score were multiplied to obtain the nursing plan recommendation index.

[0039] Preferably, the calculation formula of the nursing plan recommendation index is:

[0040] ;

[0041] in, Recommended index for nursing program, Rate the severity of the patient's symptoms. is the baseline score for symptom severity, is the maximum score of symptom severity, is the patient's age, is the age reference value, is the maximum age, Scoring of wound healing. The baseline score for wound healing. is the maximum score of wound healing. To score the patient's functional recovery, is the baseline score for functional recovery. The closer the value is to 1, the higher the matching degree is.

[0042] Preferably, in the evaluation and adjustment module, the process of evaluating the effectiveness of the recommended nursing plan includes:

[0043] Real-time collection of patients' physiological data, changes in ENT-related symptoms, real-time progress of wound healing, and real-time monitoring data of functional recovery to evaluate the patient's rehabilitation progress. Evaluation indicators include the degree of symptom relief, wound healing speed, and degree of improvement in functional recovery;

[0044] Compare the data of patients before and after rehabilitation care, use the nursing activity evaluation scale to quantify the actual effect of the nursing plan, evaluate the actual effect of the nursing plan, analyze the improvement of patients' symptoms, wound healing quality and functional recovery, and calculate the effect evaluation coefficient;

[0045] Conduct trend analysis on the patient's rehabilitation progress and the effect of the nursing plan based on the effect evaluation coefficient, analyze the changing trend of rehabilitation progress and effect over time, and in the trend analysis, promptly discover the significant decline in the effect of the nursing plan on the patient's rehabilitation progress;

[0046] Based on the results of real-time monitoring and evaluation, effect evaluation and coefficient calculation, and effect trend analysis, the nursing plan is dynamically adjusted, including changes in nursing measures, adjustments in drug use, and modifications to rehabilitation plans. The adjusted nursing plan is sent to medical staff and patients. Medical staff provide care for patients according to the new plan, and patients rehabilitate according to the new plan.

[0047] Preferably, the calculation formula of the effect evaluation coefficient is:

[0048] ;

[0049] in, is the effect evaluation coefficient, Score the degree of symptom relief. is the baseline score for symptom relief. The maximum improvement score for symptom relief. Scoring the speed of wound healing, is the baseline score for wound healing speed. To score the degree of improvement in functional recovery, It is the baseline score value of the improvement of functional recovery. It is the maximum score of the improvement of functional recovery.

[0050] Preferably, in the user interaction and feedback module, the process of collecting user feedback includes:

[0051] Provide a user interface to display the recommended nursing plan, the patient's rehabilitation progress and data analysis results. The recommended nursing plan includes treatment plan, drug management, and rehabilitation activities. The patient's rehabilitation progress includes symptom changes, wound healing, and functional recovery. The data analysis results include effect evaluation coefficients and trend analysis results.

[0052] Provide a feedback mechanism to collect feedback from patients and medical staff on the nursing plan, including the applicability, effectiveness, and satisfaction of the plan, and classify, organize, and analyze the collected feedback to identify problems and improvements;

[0053] Data is displayed in the form of charts and reports, and patients and medical staff are provided with the function of viewing recommended care plans, rehabilitation progress and data analysis results, so that users can intuitively understand the rehabilitation progress and effects;

[0054] Incorporate user feedback into a continuous system improvement cycle, optimize recommendation algorithms and user interfaces, and regularly update the system to reflect the latest medical knowledge and user needs.

[0055] The present invention provides an intelligent recommendation system for ear, nose and throat care solutions based on cloud computing. It has the following beneficial effects:

[0056] 1. This cloud computing-based intelligent recommendation system for ENT care plans uses the powerful data processing capabilities of the cloud computing platform to conduct in-depth analysis and mining of patients' real-time physiological data, ENT-related symptoms, wound healing status, and functional recovery progress, accurately identify patients' individual differences and rehabilitation needs, and tailor personalized care plans for patients. This not only improves the pertinence and effectiveness of care, but also greatly reduces the extension of rehabilitation time and patient discomfort caused by inappropriate plans.

[0057] 2. The cloud computing-based intelligent recommendation system for ENT care plans uses data analysis technology to quantitatively evaluate the patient's rehabilitation effect and calculate the effect evaluation coefficient, thereby intuitively displaying the patient's rehabilitation results. Real-time monitoring and effect evaluation can not only help medical staff understand the patient's rehabilitation status in a timely manner, but also provide patients with intuitive rehabilitation progress reports, thereby improving the intelligence level of rehabilitation care. At the same time, it can dynamically adjust the care plan according to the patient's rehabilitation progress and feedback to ensure that the patient is always in the best rehabilitation state. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1This is a module structure diagram of an intelligent recommendation system for ear, nose and throat care solutions based on cloud computing of the present invention;

[0059] Figure 2 A flowchart for constructing a nursing plan recommendation model of the present invention;

[0060] Figure 3 Flowchart for evaluating the effectiveness of recommended care regimens for the present invention. DETAILED DESCRIPTION

[0061] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present invention are provided for the purpose of illustration and description, and are not intended to be exhaustive or to limit the present invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention, and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses.

[0062] The first embodiment, as Figure 1 , Figure 2 As shown, the present invention provides a technical solution: an intelligent recommendation system for ear, nose and throat nursing solutions based on cloud computing, including an intelligent recommendation platform, the intelligent recommendation platform is communicatively connected with a data acquisition and preprocessing module, a knowledge graph construction module, a patient portrait construction module, a nursing solution recommendation module, an evaluation and adjustment module and a user interaction and feedback module, wherein the modules are connected by electrical signals;

[0063] The data collection and preprocessing module is used to collect the patient's physiological data and rehabilitation data, and preprocess the collected data. The patient's body temperature, blood pressure, and heart rate physiological data are collected through various medical devices. Among them, the patient's body temperature data is collected through an intelligent thermometer, and the patient's blood pressure is measured using an electronic sphygmomanometer. The patient's heart rate information is obtained through a heart rate monitoring device. The wound healing and functional recovery data are collected through medical records, nursing staff observations, and medical equipment. The progress of wound healing is evaluated through visual inspections, photographic records, and wound scanners. The patient's functional recovery is evaluated by medical staff assessments and the use of rehabilitation scales. The collected physiological data and rehabilitation status The data is preprocessed, which includes data cleaning and format conversion steps. Data cleaning is used to remove invalid or abnormal data caused by equipment failure, data transmission error, etc., and to verify the legitimacy of the data, check whether the range, format and logic of the data are reasonable, such as heart rate should be within the normal range, blood pressure values ​​should be divided into systolic and diastolic pressure, etc., delete fields that are irrelevant to subsequent analysis or have too many missing values, convert data from different sources and formats into a unified format through format conversion, so as to facilitate subsequent analysis and processing, standardize the data, mark the preprocessed data, implement data encryption and access control measures, and store them in the data warehouse for subsequent access and analysis;

[0064] The knowledge graph construction module uses natural language processing technology to identify key medical entities from the nursing knowledge base, including disease names, symptoms, drugs, and nursing measures, and organizes the relationships between medical entities in the form of a graph to form a nursing knowledge graph, providing a structured framework for representing and processing complex medical relationships. Medical text big data is collected through different channels to form a nursing knowledge base, which contains medical literature, case reports, and nursing guidelines. The data is pre-processed by denoising, word segmentation, and part-of-speech tagging to facilitate subsequent entity recognition and relationship extraction. Obtain medical literature from medical databases such as Science, collect case reports from the websites of major hospitals and medical institutions, or obtain nursing guidelines from institutions such as the International Nursing Association and the National Health Commission. Use named entity recognition technology to identify key medical entities from preprocessed data, including disease names, symptoms, drugs, and nursing measures. Use unique identifiers to label each identified medical entity. Use relationship extraction technology to determine the relationship between entities, including the relationship between disease and symptoms, the relationship between drugs and disease, and the relationship between nursing measures and disease. Use the results of relationship extraction as edges in the knowledge graph. Use entity linking technology to organize the identified entities and extracted relationships in the form of a graph to form a nursing knowledge graph. Use a graph database to store the nursing knowledge graph for subsequent query and analysis.

[0065] The patient portrait construction module constructs a patient portrait based on the patient's physiological data, rehabilitation data and personal information, deeply understands the patient's health status and rehabilitation needs, and provides a basis for personalized recommendations. It extracts the patient's physiological data and rehabilitation data, and collects the patient's personal information in a targeted manner. Among them, physiological data includes the patient's vital signs, examination results and imaging data, which can reflect the patient's current health status and potential health problems. Rehabilitation status data includes wound healing and functional recovery, which helps to understand the patient's rehabilitation needs and rehabilitation effects, and provides a basis for formulating personalized rehabilitation plans. Personal information includes the patient's basic identity information, medical history records, and medical history, which helps to have a more comprehensive understanding of the patient and provide support for the formulation of scientific and reasonable diagnosis and treatment plans. The collected data is analyzed using the K-means clustering algorithm. Patients are divided into different groups based on similar physiological characteristics, rehabilitation needs and health conditions, and the patient's health status and The relevant laws of rehabilitation needs provide a basis for the formulation of personalized rehabilitation plans. Based on the results of data analysis, a patient portrait model is constructed to reflect the patient's physiological condition, wound healing, functional recovery and potential health risk information. Among them, the physiological condition shows the patient's overall physiological state through the summary of vital signs and examination results. The wound healing condition records the wound healing process in detail, including the healing speed and healing quality. The functional recovery condition evaluates the patient's functional recovery, including limb mobility and muscle strength. Based on the patient's medical history, examination results and rehabilitation status, the health risks that the patient may face are predicted to provide a basis for the formulation of preventive measures. According to the physiological condition, wound healing and functional recovery in the patient portrait, a personalized rehabilitation plan is formulated, and the health risk information in the patient portrait is used to optimize the diagnosis and treatment plan and improve the treatment effect. The information in the patient portrait is used to communicate more effectively with the patient to improve the patient's understanding and compliance with the treatment plan.

[0066] The nursing plan recommendation module combines patient portraits, nursing knowledge bases and nursing knowledge graphs, builds a nursing plan recommendation model based on machine learning algorithms, and generates personalized ENT nursing plan recommendations. It can provide accurate and effective nursing suggestions based on the patient's actual situation and rehabilitation needs. It combines patient portraits (including physiological data, rehabilitation data and personal information), nursing knowledge bases and nursing knowledge graphs to extract features related to ENT care, including symptom severity, patient age, wound healing and functional recovery. Among them, the severity of ENT-related nasal congestion, runny nose, tinnitus, and sore throat symptoms is extracted from patient portraits and expressed in scores. The healing speed and quality of surgical incisions and ulcer surface wounds, as well as whether infectious complications occur, are extracted from the rehabilitation data. The recovery of ENT-related hearing, smell, swallowing, and pronunciation functions, including recovery speed and degree, is extracted from the rehabilitation data. Extract historical nursing cases from the nursing knowledge base, including patient characteristics, nursing plans and nursing effect information, use machine learning algorithms to train the data in the nursing knowledge base, and obtain a nursing plan recommendation model that predicts the best nursing plan through training. The nursing plan recommendation model is built based on a neural network model, and the patient's symptom severity, patient age, wound healing status and functional recovery status characteristics are matched with the nursing plan recommendation model. The nursing plan recommendation model is used to predict patient characteristics to obtain a series of nursing plans that meet the patient's needs. According to the patient's actual situation and rehabilitation needs, the predicted nursing plans are screened and sorted, and plans that do not meet the patient's needs are excluded. The screened nursing plans are quantitatively analyzed, the nursing plan recommendation index of each plan is calculated, and the matching degree of the nursing plan with the patient's needs is analyzed. According to the matching analysis results, the best nursing plan is selected and recommended to patients and medical staff;

[0067] Furthermore, the calculation process of the nursing plan recommendation index is:

[0068] Extract the patient's physiological data, rehabilitation data and personal information, obtain the patient's symptom severity score, age, wound healing score and functional recovery score related data, determine the symptom severity baseline score value, age baseline value, wound healing baseline score value and functional recovery baseline score value, and determine the maximum symptom severity score value, maximum age value, and maximum wound healing score value. Based on the patient's symptom severity score, symptom severity baseline score value and maximum symptom severity score value, calculate the standardized value of symptom severity, square the standardized value for exponential calculation, and then calculate the Sigmoid function value of symptom severity. The standardized value of age is calculated by age, age baseline value and maximum age, and the reciprocal value of age score is calculated by squaring the standardized value. The standardized value of wound healing is calculated based on the patient's wound healing score, wound healing baseline score and wound healing maximum score, and the square root of the standardized value is calculated. The standardized value of functional recovery is calculated based on the ratio of the patient's functional recovery score and the functional recovery baseline score, and the standardized value of functional recovery is indexed. The minimum value formula is used to make the indexed value not exceed 1. The standardized results of the comprehensive symptom severity score, age, wound healing score and functional recovery score are multiplied to obtain the nursing plan recommendation index.

[0069] Furthermore, the calculation formula of the nursing plan recommendation index is:

[0070] ;

[0071] in, Recommended index for nursing program, Rate the severity of the patient's symptoms. is the baseline score for symptom severity, is the maximum score of symptom severity, is the patient's age, is the age reference value, is the maximum age, Scoring of wound healing. The baseline score for wound healing. is the maximum score of wound healing. To score the patient's functional recovery, is the baseline score for functional recovery. is a Sigmoid function used to score the severity of symptoms Normalized to between 0 and 1, when near When , this term is close to 0.5, when keep away When , the term is close to 0 or 1, To standardize the age of patients , is a square root function used to normalize wound healing scores , this item follows near And increase, is an exponential function used to standardize the functional recovery score , this item follows Increases as symptoms increase, but never exceeds 1. Close to the benchmark value hour, Increases when the patient's age Close to the benchmark value hour, Increased, when wound healing score When increasing, Increase, when functional recovery score When increasing, Increase, The closer the value is to 1, the higher the matching degree is;

[0072] The evaluation and adjustment module is used to monitor and evaluate the patient's rehabilitation progress in real time, evaluate the effectiveness of the recommended nursing plan, and dynamically adjust the nursing plan based on the evaluation results, which can ensure the effectiveness and adaptability of the nursing plan and improve the patient's recovery speed and satisfaction;

[0073] The user interaction and feedback module provides a user interface for collecting user feedback, including feedback from patients and medical staff on care plans, making it easier for medical staff and patients to view recommended care plans, rehabilitation progress, and data analysis results. This can improve the system's usability and user experience, and promote effective communication between doctors and patients.

[0074] The second embodiment is based on the first embodiment. Figure 3 As shown in the evaluation and adjustment module, the process of evaluating the effectiveness of the recommended care plan includes:

[0075] Collect the patient's physiological data, changes in ENT-related symptoms, real-time progress of wound healing, and real-time monitoring data of functional recovery in real time, evaluate the patient's rehabilitation progress, and the evaluation indicators include the degree of symptom relief, wound healing speed, and degree of improvement in functional recovery. Compare the data before and after the patient's rehabilitation care, use the nursing activity evaluation scale to quantify the actual effect of the nursing plan, evaluate the actual effect of the nursing plan, analyze the improvement of the patient's symptoms, wound healing quality, and functional recovery, calculate the effect evaluation coefficient, and conduct trend analysis on the patient's rehabilitation progress and the effect of the nursing plan based on the effect evaluation coefficient. Analyze the changing trend of rehabilitation progress and effect over time, and in the trend analysis, promptly discover the significant decline in the effect of the nursing plan on the patient's rehabilitation progress. According to the results of real-time monitoring and evaluation, effect evaluation and coefficient calculation, and effect trend analysis, dynamically adjust the nursing plan, including changes in nursing measures, adjustments in drug use, and modifications to the rehabilitation plan. Send the adjusted nursing plan to medical staff and patients, and the medical staff will care for the patients according to the new plan, and the patients will rehabilitate according to the new plan;

[0076] Furthermore, the calculation formula of the effect evaluation coefficient is:

[0077] ;

[0078] in, is the effect evaluation coefficient, Score the degree of symptom relief. is the baseline score for symptom relief. The maximum improvement score for symptom relief. Scoring the speed of wound healing, is the baseline score for wound healing speed. To score the degree of improvement in functional recovery, It is the baseline score value of the improvement of functional recovery. is the maximum score value of the improvement in functional recovery. Indicates the exponential change in the degree of symptom relief. When the degree of symptom relief exceeds the baseline value, the exponential growth The function limits the maximum value to 1, ensuring The value of does not exceed 1. It represents the radical change of wound healing speed. As the wound healing speed increases, the radical increases, reflecting the contribution of the healing speed to the effect evaluation coefficient. It represents the square change of the degree of functional recovery. When the degree of functional recovery is close to the maximum value, this item is close to 0, reflecting the influence of the degree of functional recovery on the effect evaluation coefficient. When increasing, Increases wound healing speed When increasing, Increase, when the degree of functional recovery Increase but not exceed hour, increase; exceed back, reduce;

[0079] In the user interaction and feedback module, the process of collecting user feedback includes:

[0080] Provide a user interface to display recommended care plans, patients' rehabilitation progress and data analysis results, among which the recommended care plans include treatment plans, drug management, and rehabilitation activities. The patient's rehabilitation progress includes symptom changes, wound healing, and functional recovery. The data analysis results include effect evaluation coefficients and trend analysis results. Provide a feedback mechanism to collect feedback from patients and medical staff on the care plans, including the applicability, effectiveness, and satisfaction of the plans. Classify, organize and analyze the collected feedback to identify problems and improvements. Display data in the form of charts and reports, and provide patients and medical staff with the function of viewing recommended care plans, rehabilitation progress, and data analysis results, so that users can intuitively understand the rehabilitation progress and effects. Incorporate user feedback into the system's continuous improvement cycle, optimize the recommendation algorithm and user interface, and update the system regularly to reflect the latest medical knowledge and user needs.

[0081] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field and related fields without creative work should fall within the scope of protection of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention are implemented according to the conventional means in the field unless otherwise specified and limited.

Claims

1. A cloud computing-based intelligent recommendation system for ear, nose and throat care solutions, including an intelligent recommendation platform, characterized in that: The intelligent recommendation platform is communicatively connected with a data acquisition and preprocessing module, a knowledge graph construction module, a patient portrait construction module, a nursing plan recommendation module, an evaluation and adjustment module, and a user interaction and feedback module, wherein the modules are connected by electrical signals; The data acquisition and preprocessing module is used to acquire the patient's physiological data and rehabilitation data, and preprocess the acquired data; The knowledge graph construction module uses natural language processing technology to identify key medical entities from the nursing knowledge base and organize the relationships between the medical entities in the form of a graph to form a nursing knowledge graph; The patient portrait building module builds a patient portrait based on the patient's physiological data, rehabilitation data and personal information; The nursing plan recommendation module combines patient portraits, nursing knowledge base and nursing knowledge graph, builds a nursing plan recommendation model based on machine learning algorithms, and generates personalized ENT nursing plan recommendations; The evaluation and adjustment module is used to monitor and evaluate the patient's rehabilitation progress in real time, evaluate the effectiveness of the recommended nursing plan, and dynamically adjust the nursing plan based on the evaluation results; The user interaction and feedback module provides a user interface and collects user feedback, including feedback from patients and medical staff on the nursing plan.

2. The cloud computing-based ENT care program intelligent recommendation system according to claim 1, characterized in that: In the data collection and preprocessing module, the process of collecting the patient's physiological data and rehabilitation status data includes: The patient's body temperature, blood pressure, and heart rate physiological data are collected through various medical devices. The patient's body temperature data is collected through a smart thermometer, the patient's blood pressure value is measured using an electronic sphygmomanometer, and the patient's heart rate information is obtained through a heart rate monitoring device; Collect rehabilitation data on wound healing and functional recovery through medical records, nursing staff observations, and medical equipment. Wound healing progress is assessed through visual inspection, photographic records, and wound scanners, and functional recovery is assessed through medical staff assessments and the use of rehabilitation scales. Preprocessing the collected physiological data and rehabilitation data, including data cleaning and format conversion steps; The pre-processed data is marked, encrypted and access controlled, and then stored in the data warehouse.

3. The cloud computing-based ENT care program intelligent recommendation system according to claim 2, characterized in that: In the knowledge graph construction module, the construction process of the nursing knowledge graph includes: Medical text big data is collected through different channels to form a nursing knowledge base, which includes medical literature, case reports, and nursing guidelines. The data is pre-processed by denoising, word segmentation, and part-of-speech tagging. Using named entity recognition technology, key medical entities, including disease names, symptoms, drugs, and nursing measures, are identified from preprocessed data; Each identified medical entity is labeled with a unique identifier, and the relationship between entities is determined using relationship extraction technology, including the relationship between disease and symptoms, the relationship between drugs and diseases, and the relationship between nursing measures and diseases. The results of relationship extraction are used as edges in the knowledge graph. The identified entities and extracted relationships are organized in the form of a graph through entity linking technology to form a nursing knowledge graph, and the nursing knowledge graph is stored in a graph database.

4. The cloud computing-based ENT care program intelligent recommendation system according to claim 3, characterized in that: In the patient portrait construction module, the patient portrait construction process includes: Extract the patient's physiological data and rehabilitation data, and collect the patient's personal information in a targeted manner. Physiological data includes the patient's vital signs, examination results, and imaging data; rehabilitation data includes wound healing and functional recovery; and personal information includes the patient's basic identity information, medical history, and medical history; The collected data were analyzed using the K-means clustering algorithm, and patients were divided into different groups based on similar physiological characteristics, rehabilitation needs, and health conditions, to discover the correlation between patients’ health conditions and rehabilitation needs; Based on the results of data analysis, a patient portrait model is constructed to reflect the patient's physiological condition, wound healing, functional recovery, and potential health risk information; Based on the physiological condition, wound healing and functional recovery in the patient portrait, a personalized rehabilitation plan is developed, and the health risk information in the patient portrait is used to optimize the diagnosis and treatment plan.

5. The cloud computing-based ENT care program intelligent recommendation system according to claim 4, characterized in that: In the nursing plan recommendation module, the construction process of the nursing plan recommendation model includes: Combined with patient portraits, nursing knowledge base and nursing knowledge graph, features related to ENT nursing are extracted, including symptom severity, patient age, wound healing and functional recovery. The severity of ENT-related nasal congestion, runny nose, tinnitus and sore throat symptoms is extracted from patient portraits and expressed in scores. The healing speed, healing quality and whether infectious complications of surgical incisions and ulcer surface wounds are extracted from rehabilitation data. The recovery of ENT-related hearing, smell, swallowing and pronunciation functions, including recovery speed and degree, is extracted from rehabilitation data. Extract historical nursing cases from the nursing knowledge base, including patient characteristics, nursing plans and nursing effect information, use machine learning algorithms to train the data in the nursing knowledge base, and obtain a nursing plan recommendation model that predicts the best nursing plan through training. The nursing plan recommendation model is built based on a neural network model. Match the patient's symptom severity, age, wound healing, and functional recovery characteristics with the nursing plan recommendation model, use the nursing plan recommendation model to predict patient characteristics, and obtain a series of nursing plans that meet the patient's needs; According to the actual situation and rehabilitation needs of the patient, the predicted nursing plans are screened and sorted, and plans that do not meet the patient's needs are excluded. The screened nursing plans are quantitatively analyzed, the nursing plan recommendation index of each plan is calculated, and the matching degree between the nursing plan and the patient's needs is analyzed; Based on the matching analysis results, the best care plan is selected and recommended to patients and medical staff.

6. The cloud computing-based ENT care program intelligent recommendation system according to claim 5, characterized in that: The calculation process of the nursing plan recommendation index is: Extract the patient's physiological data, rehabilitation data and personal information, obtain the patient's symptom severity score, age, wound healing score and functional recovery score, determine the symptom severity baseline score, age baseline score, wound healing baseline score and functional recovery baseline score, and determine the maximum symptom severity score, maximum age and maximum wound healing score; Based on the symptom severity score of the patient's symptom severity, the symptom severity baseline score value and the symptom severity maximum score value, a standardized value of symptom severity is calculated, and the square of the standardized value is exponentially calculated to further calculate the Sigmoid function value of the symptom severity; The standardized value of age was calculated based on the patient's age, the baseline age value, and the maximum age, and the reciprocal value of the age score was calculated by squaring the standardized value; Calculate the standardized value of wound healing based on the patient's wound healing score, the baseline score value of wound healing and the maximum score value of wound healing, and calculate the square root of the standardized value; Based on the ratio of the patient's functional recovery score to the functional recovery baseline score, the standardized value of functional recovery is calculated, and the standardized value of functional recovery is indexed, using the minimum value formula to make the index value not exceed 1; The standardized results of the comprehensive symptom severity score, age, wound healing score, and functional recovery score were multiplied to obtain the nursing plan recommendation index.

7. The cloud computing-based ENT care program intelligent recommendation system according to claim 6, characterized in that: The calculation formula of the nursing plan recommendation index is: ； in, Recommended index for nursing program, Rate the severity of the patient's symptoms. is the baseline score for symptom severity, is the maximum score of symptom severity, is the patient's age, is the age reference value, is the maximum age, Scoring of wound healing. The baseline score for wound healing. is the maximum score of wound healing. To score the patient's functional recovery, is the baseline score for functional recovery. The closer the value is to 1, the higher the matching degree is.

8. The cloud computing-based ENT care program intelligent recommendation system according to claim 7, characterized in that: In the evaluation and adjustment module, the process of evaluating the effectiveness of the recommended nursing plan includes: Real-time collection of patients' physiological data, changes in ENT-related symptoms, real-time progress of wound healing, and real-time monitoring data of functional recovery to evaluate the patient's rehabilitation progress. Evaluation indicators include the degree of symptom relief, wound healing speed, and degree of improvement in functional recovery; Compare the data of patients before and after rehabilitation care, use the nursing activity evaluation scale to quantify the actual effect of the nursing plan, evaluate the actual effect of the nursing plan, analyze the improvement of patients' symptoms, wound healing quality and functional recovery, and calculate the effect evaluation coefficient; Conduct trend analysis on the patient's rehabilitation progress and the effect of the nursing plan based on the effect evaluation coefficient, analyze the changing trend of rehabilitation progress and effect over time, and in the trend analysis, promptly discover the significant decline in the effect of the nursing plan on the patient's rehabilitation progress; Based on the results of real-time monitoring and evaluation, effect evaluation and coefficient calculation, and effect trend analysis, the nursing plan is dynamically adjusted, including changes in nursing measures, adjustments in drug use, and modifications to rehabilitation plans. The adjusted nursing plan is sent to medical staff and patients. Medical staff provide care for patients according to the new plan, and patients rehabilitate according to the new plan.

9. The cloud computing-based ENT care program intelligent recommendation system according to claim 8, characterized in that: The calculation formula of the effect evaluation coefficient is: ； in, is the effect evaluation coefficient, Score the degree of symptom relief. is the baseline score for symptom relief. The maximum improvement score for symptom relief. Scoring the speed of wound healing, is the baseline score for wound healing speed. To score the degree of improvement in functional recovery, It is the baseline score value of the improvement of functional recovery. It is the maximum score of the improvement of functional recovery.

10. The cloud computing-based ENT care program intelligent recommendation system according to claim 9, characterized in that: In the user interaction and feedback module, the process of collecting user feedback includes: Provide a user interface to display the recommended nursing plan, the patient's rehabilitation progress and data analysis results. The recommended nursing plan includes treatment plan, drug management, and rehabilitation activities. The patient's rehabilitation progress includes symptom changes, wound healing, and functional recovery. The data analysis results include effect evaluation coefficients and trend analysis results. Provide a feedback mechanism to collect feedback from patients and medical staff on the nursing plan, including the applicability, effectiveness, and satisfaction of the plan, and classify, organize, and analyze the collected feedback to identify problems and improvements; Display data in the form of charts and reports, and provide patients and medical staff with the ability to view recommended care plans, rehabilitation progress, and data analysis results; Incorporate user feedback into a continuous system improvement cycle, optimize recommendation algorithms and user interfaces, and regularly update the system to reflect the latest medical knowledge and user needs.

Images