Intelligent medicine taking reminding system and method
Through the intelligent medication reminder system, the input module, data processing module, intelligent algorithm module and recording module are used to generate a personalized medication reminder plan, which solves the problem of patients forgetting to take medication, improves drug compliance and treatment effect, and reduces adverse reactions.
Patent Information
- Application Number
- CN202411151456.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-21
- Publication Date
- 2024-11-29
AI Technical Summary
Many patients forget or mistakenly take medication, resulting in poor treatment results or adverse reactions, and the prior art is difficult to effectively solve this problem.
An intelligent drug reminder system was designed, including drug information input module, data processing module, intelligent algorithm module, reminder module, recording module and communication module. It generates personalized products based on the patient's basic information, condition information, work and rest time and lifestyle habits. The medication reminder plan is used to remind patients through sound, light or vibration, record and analyze medication in real time, and dynamically adjust the reminder plan.
It improves the patient's drug compliance, ensures that the medication is taken on time and in doses, reduces adverse reactions, improves the treatment effect and patient satisfaction, reduces the management burden of medical staff, and adapts to the changes in patients' life and the advancement of medical technology.
Smart Images

Figure CN119033593A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to medical related fields, and in particular to an intelligent medication reminder system and method. Background Art
[0002] In modern society, with the advancement of medical technology, many patients need to take multiple medications at specific times. However, due to various reasons, many patients often forget to take medication on time or take medication incorrectly, resulting in poor treatment effects or even adverse reactions. Therefore, it is particularly important to design a system that can intelligently remind patients to take medication correctly and on time. Summary of the invention
[0003] The purpose of the present invention is to provide an intelligent medication reminder system and method to solve the problems raised in the above background technology.
[0004] To achieve the above object, the present invention provides the following technical solutions: an intelligent medication reminder system, comprising a medication information input module, a data processing module, an intelligent algorithm module, a reminder module, a recording module and a communication module, wherein the medication information input module is used to input the patient's basic information, condition information and medication information, and at the same time input the patient's work and rest time and living habits according to the patient's needs;
[0005] The specific input information of the medication information input module includes the following:
[0006] a. Basic information: Age: The patient's age, used to determine the appropriate drug dosage and frequency of medication; Gender: The patient's gender, drugs have different dosage recommendations based on gender; Weight: The patient's weight, used to calculate the drug dosage based on weight;
[0007] b. Medical information: Disease type: the type of disease the patient suffers from; Severity: fill in the severity of the disease according to the doctor's advice, which is used to determine the drug dosage and frequency of medication; Drug allergy history: which drugs the patient is allergic to;
[0008] c. Medication information: Drug name: the name of the drug to be taken; Dosage: the dosage of the drug taken each time; Medication time: the recommended medication time, provided by the doctor; Contraindications: contraindications that need to be paid attention to when using the drug.
[0009] The data processing module is connected to the medication information input module and is used to generate a personalized medication reminder plan according to the input information;
[0010] The intelligent algorithm module is embedded in the data processing module and is used to analyze the patient's basic information, condition information, medication information, and the patient's work and rest schedule and living habits in the data processing module to generate an optimal medication time and dosage reminder plan;
[0011] The reminder module is connected to the data processing module and is used to remind the patient to take the medicine on time through sound, light or vibration at the scheduled medication time;
[0012] The recording module is connected to the data processing module, and is used to record the patient's medication situation and store the recorded information in the database; the real-time update of the patient's medication record and providing a reference basis for doctors and patients are as follows: the recording module records the patient's medication situation in detail, including: medication time, actual medication timestamp, used to compare the planned medication time; medication information, specific medication name, dosage, medication method; patient feedback, the patient's subjective feelings after taking the medication; confirmation status, recording whether the patient confirms taking the medication;
[0013] The recording module stores the patient's medication status in a database to ensure data security and traceability. The database is used to store and manage the patient's medication records. The database table structure includes the following fields: patient ID, medication time, drug name, dosage, confirmation status, patient feedback, and record creation time;
[0014] The recording module supports basic data analysis and visualization functions to help doctors and patients understand medication status, specifically: medication compliance analysis, which evaluates patients' medication compliance by analyzing the deviation between the actual medication time and the planned time; adverse reaction statistics, which counts patient feedback in the records, analyzes common adverse reactions and generates reports; trend charts, which provide chart functions to display patients' medication status in a graphical manner;
[0015] The recording module supports a report generation function for users to export data for further analysis or sharing.
[0016] The communication module is used to transmit the patient's medication status to the remote monitoring terminal in real time, so that medical staff can understand the patient's medication status in time.
[0017] Preferably, the specific working steps of the data processing module are as follows:
[0018] Step S1, data reception and storage: receiving all patient information from the medication information input module, including basic information, condition information and medication information; storing the received data in a database;
[0019] Step S2, data preprocessing: remove duplicate data, process missing values and outliers from the data stored in the database to ensure the integrity and accuracy of the data; standardize all input data into a unified format, and integrate data from different sources into a complete data set;
[0020] Step S3, feature extraction: extract key features from the data preprocessed in step S2, specifically including the patient's age, weight, disease type, drug name and dosage. The extracted key feature data provides structured data for the intelligent algorithm module for model analysis and prediction;
[0021] Step S4, data analysis: perform basic statistical analysis on the data preprocessed in step S2, specifically including average age, distribution of common diseases, and commonly used drugs, and provide a data overview;
[0022] Step S5, generating a personalized reminder plan: Based on the analysis results of the intelligent algorithm module, a personalized medication reminder plan is generated for each patient, the plan content includes the specific medication time, the dosage for each dose, the drug name, and any special precautions;
[0023] Step S6, dynamic adjustment: dynamically adjust the reminder plan according to the patient's actual medication situation and feedback to ensure its continued effectiveness and handle the patient's temporary change request.
[0024] Preferably, the specific steps of dynamically adjusting the reminder plan according to the patient's actual medication situation and feedback in step S6 are as follows:
[0025] Step S61, data collection and analysis: collect the patient's actual medication situation and feedback information, obtain the patient's medication record from the recording module, including medication time, drug information, confirmation status and patient feedback, and obtain the real-time transmitted medication data from the communication module; then analyze the patient's medication compliance, calculate the deviation between the actual medication time and the planned time, analyze the adverse reactions in the patient's feedback and the physical condition after taking the medication, and identify possible problems;
[0026] Step S62, dynamic adjustment mechanism: according to the analysis results, automatically or manually adjust the reminder plan, specifically automatic adjustment: if the patient fails to take the medicine on time for many times, the system automatically adjusts the reminder time, such as advancing or delaying the reminder, to ensure that the reminder is more in line with the patient's daily routine, automatically adjusts the drug dosage reminder according to the patient's feedback and the doctor's advice, and adjusts the reminder frequency of the reminder module according to the patient's medication situation, and increases the number of reminders; manual adjustment: medical staff or patients manually adjust the reminder plan through the remote monitoring terminal or patient equipment according to the actual situation;
[0027] Step S63, processing temporary change requests: patients submit temporary change requests through the communication module, including temporarily changing the medication time or suspending reminders. At the same time, medical staff can submit change requests through the remote monitoring terminal, including adjusting the patient's medication plan or reminder settings; for handling emergency situations, when patients report serious adverse reactions, reminders are immediately adjusted or suspended, and medical staff are notified to intervene.
[0028] Preferably, the specific working steps of the intelligent algorithm module are as follows:
[0029] Step 1, data collection: receiving the extracted key feature data from the data processing module and the patient's work and rest time and living habit data from the medication information input module;
[0030] Step 2: Personalized model training: A prediction model is established by using the K-means clustering algorithm, and the key feature data collected in step S1 are used to train a personalized model adapted to different types of patients. At the same time, the model parameters are optimized using the cross-validation method to improve the prediction accuracy of the model.
[0031] Step 3. Analysis of work and rest schedule and habits: Calculate the best time to take medication based on the input work and rest schedule, including working hours, sleeping hours, and eating hours. Combined with the patient's living habit data, i.e., daily activity patterns, ensure that the medication time does not conflict with the patient's important activities;
[0032] Step 4, generate reminder plan: drug interaction detection: use expert system and drug database to detect the interaction between drugs used by patients to avoid drug conflicts; optimization algorithm: use genetic algorithm to optimize medication time and dosage to ensure efficiency and safety; generate plan: generate detailed medication reminder plan, including specific medication time, dosage, and drug name.
[0033] Preferably, the specific steps of establishing a prediction model by using a K-means clustering algorithm in step 2, and using the key feature data collected in step S1 to train a personalized model adapted to different types of patients are as follows:
[0034] Step 21. Data preparation: Before training the model, you first need to prepare the data, including the key feature data collected from step S1. These data should include the following features:
[0035] The patient's basic information, including age, gender, and weight;
[0036] The patient's medical condition information, including disease type and severity;
[0037] Patient medication information, including drug type, dosage, and frequency of medication;
[0038] Step 22, data matrix: Represent the feature data prepared in step 21 as a data matrix X, where each row represents a patient and each column represents a feature: X = [x1, x2, ..., x n ], where x iis the feature vector of the ith patient; in the K-means algorithm, we must first determine the k clusters to be divided into, and randomly select k initial cluster centers, the formula is: Initial cluster center: C = [c1, c2, ..., c k ], where c j is the coordinate vector of the jth cluster center;
[0039] Step 23: Calculate distance and assign clusters: For each patient x n , calculate its relationship with each cluster center c k The distance between them is calculated and the patient is assigned to the cluster corresponding to the nearest cluster center, where the distance formula is:
[0040]
[0041] Among them, x im Is patient x i The value of the mth feature, c jm is the cluster center c j The value of the mth feature;
[0042] Allocation formula: assign patient x i Assign to cluster j such that: j = argmin j d(x i ,c j );
[0043] Step 24, update cluster centers: After all patients are assigned to the nearest cluster, update each cluster center to the mean of all patient characteristics in the cluster. The update formula is:
[0044]
[0045] Among them, S j is the set of patients in the jth cluster, |S j | is the number of patients in the cluster;
[0046] Step 25: Repeat steps 23 and 24 until the cluster center no longer changes significantly or the predetermined number of iterations is reached. The convergence condition is: when the change between the new cluster center and the previous cluster center is less than a certain threshold ∈, stop the iteration:
[0047]
[0048] Step 26, Personalized model generation: Clustering is completed, and each cluster represents a class of patients with similar characteristics. For each cluster, analyze the characteristics of the patients it represents and generate a personalized medication reminder plan suitable for this type of patients, that is, calculate the characteristics and statistics in each cluster, and customize a personalized medication plan for the patients in this cluster based on the statistical information;
[0049] Step 27, parameter adjustment and optimization: adjust the k value and model parameters through cross-validation to optimize the prediction accuracy of the model; cross-validation steps:
[0050] Divide the data in step 21 into a training set and a validation set;
[0051] Perform K-means clustering on different k values to train personalized models;
[0052] Use the validation set to evaluate model performance, specifically using the SSE and Silhouette Score indicators;
[0053] Select the k value and model parameters that optimize the performance of the validation set;
[0054] in,
[0055] Si lhouette Score:
[0056] Among them, a(i) is the average distance from patient i to other patients in the same cluster, and b(i) is the average distance from patient i to the nearest other cluster.
[0057] Preferably, the content of the work and rest time and habit analysis in step 3 is as follows:
[0058] Calculate the best time to take medicine: Calculate the best time to take medicine based on the nature and requirements of the medicine and the patient's work and rest schedule. Specifically: Drug absorption time: Consider whether the medicine needs to be taken before or after meals. Formula: Best time to take medicine = meal time ± absorption time; Medication interval time: If the medicine needs to be taken multiple times a day, the medication interval time needs to be evenly distributed. Formula: Medication interval time = 24 hours / number of medications; Avoid peak activity time: Avoid taking medicine during work or other important activities;
[0059] Lifestyle matching: Avoid conflicts with the patient's daily activity schedule. Specifically, create a time period set: List all the patient's activity time periods in a day and create a time period set T. The formula is: T = {t1, t2, ..., t n}, where t i Indicates the time period for each activity; Calculate the available time period: Calculate the time period available for medication based on the patient's schedule and activity arrangements. The formula is: Medication time matching: Match the time period required for medication with the available time period, formula:
[0060] Preferably, the detailed steps of using genetic algorithm to optimize medication time and dosage and generate reminder plan in step 4 are as follows:
[0061] Step 41, initialize the population: First, initialize a population containing multiple individuals, each individual represents a possible medication plan, and the individual is composed of a set of genes, where the genes include medication time and dosage. The specific formula is:
[0062] Individual representation: I = [t1, t2, ..., t n ,d1,d2,…,d n ], where t i represents the time of taking the i-th medication, d i represents the dosage of the i-th medication;
[0063] Step 42: Define a fitness function to evaluate the pros and cons of each individual. The fitness function is based on the following aspects: drug interaction detection: ensure that there is no conflict between drugs; reasonable medication time: medication time should avoid important activity time as much as possible and conform to work and rest rules; reasonable dosage: dosage should be within a safe range. The specific formula is:
[0064] Fitness function: F(I) = w1·InteractionPenalty(I) + w2·TimePenalty(I) + w3·DosePenalty(I);
[0065] Where w1, w2, w3 are weight coefficients;
[0066] Step 43, selection operation: select excellent individuals as parents according to the fitness function, specifically, calculate the fitness value of each individual, and select individuals according to the fitness value, wherein roulette selection is used, and the formula is:
[0067] Roulette wheel selection probabilities:
[0068] Among them, F(I i ) is individual I i The fitness value of , N is the population size;
[0069] Step 44, crossover operation: Generate new individuals by exchanging some genes of the parent individuals. Specifically, two individuals are selected from the parent generation, the crossover point is randomly selected, and the gene fragments are exchanged. The formula is: Assuming a single-point crossover is selected, the crossover point is:
[0070] Offspring 1:
[0071] Offspring 2:
[0072] Step 45, mutation operation: By randomly changing some genes of individuals, the diversity of the population is increased to avoid falling into the local optimal solution. Specifically, individuals and gene positions are randomly selected, and the gene values of the selected positions are randomly changed. The formula is: Assuming that the selected mutation position is v:
[0073] Before mutation: I = [t1, t2, …, t v ,…,t n ,d1,d2,…,d v ,…,d n ];
[0074] After mutation: I′=[t1,t2,…,t′ v ,…,t n ,d1,d2,…,d′ v ,…,d n ];
[0075] where t′ v and d′ v is the new gene value after mutation;
[0076] Step 46, generating the next generation: generating a new generation of population through selection, crossover and mutation operations, and repeating the iteration until the termination condition is met, and the termination condition includes the convergence of a predetermined number of generations or fitness value;
[0077] Step 47, generate a detailed medication reminder plan: After the algorithm converges, select the individual with the highest fitness value as the final medication reminder plan, and generate detailed plan content, including specific medication time, dosage, and drug name. The formula is:
[0078] The best individual: I * = argmax I∈Population F(I);
[0079] Generate a reminder schedule:
[0080] in and is the optimal individual I * The gene value of .
[0081] Preferably, a smart medication reminder method comprises the following steps:
[0082] Step A: The patient or his / her guardian inputs the patient's basic information, condition information, work and rest schedule, living habits and medication information through the medication information input module;
[0083] Step B: the data processing module generates a personalized medication reminder plan based on the input information;
[0084] Step C: The intelligent algorithm module analyzes the patient's basic information, condition information, work and rest schedule, and living habits, and optimizes and generates the optimal medication time and dosage reminder plan;
[0085] Step D: The reminder module reminds the patient to take the medicine on time through sound, light or vibration at the scheduled medication time;
[0086] Step E: After taking the medicine, the patient confirms the medication status through the medication information input module, and the recording module records and stores the patient's medication status;
[0087] Step F: The communication module transmits the patient's medication status to the remote monitoring terminal in real time, and the medical staff conducts necessary tracking and adjustments based on the transmitted information.
[0088] Preferably, an electronic device comprises: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;
[0089] The processor calls the computer program stored in the memory to execute and implement an intelligent medication reminder system.
[0090] Preferably, a computer program product stored on a computer-readable medium includes a computer-readable program, which, when executed on an electronic device, provides a user input interface to implement an intelligent medication reminder system.
[0091] Compared with the prior art, the present invention has the following beneficial effects:
[0092] Improve patient compliance: By analyzing the patient's actual medication situation and feedback, the reminder plan can be automatically or manually adjusted to make the reminder time and frequency more in line with the patient's daily living habits and actual needs. This function effectively improves the patient's medication compliance, ensuring that the patient can take the medication on time and in the right amount, thereby improving the treatment effect.
[0093] Personalized reminder service: It can provide personalized medication reminder service based on the patient's personal health status, lifestyle and real-time feedback. Through dynamic adjustment, the system can gradually learn and adapt to the patient's behavior pattern, provide more accurate reminder service, and improve patient satisfaction and treatment experience.
[0094] Responding to emergencies: The system supports patients or medical staff to submit temporary change requests, and can flexibly respond to patients' temporary changes in needs, such as temporarily adjusting medication time or suspending reminders. This flexibility ensures that the system can adapt to patients' life changes and emergencies, and provide continuous and effective support.
[0095] Reduce adverse reactions: By analyzing adverse reactions in patient feedback, the dynamic adjustment and feedback module can adjust drug reminders and dosage recommendations, helping medical staff to promptly detect and adjust inappropriate medication regimens, reduce the occurrence of adverse reactions, and improve patient safety.
[0096] Improve the work efficiency of medical staff: The system automatically analyzes data and adjusts reminder plans, reducing the burden of medical staff on managing patients' daily medication, especially in remote monitoring scenarios. Medical staff can focus on dealing with more complex medical problems based on the system's adjustment suggestions and improve work efficiency.
[0097] Continuous optimization and improvement: The system continuously collects and analyzes patients’ medication data and feedback to continuously optimize reminder plans and medication recommendations. This continuous improvement mechanism ensures that the system can maintain high efficiency in the long term and continue to evolve as patients’ needs change and medical technology advances.
[0098] Enhance patient autonomy: The state adjustment and feedback module allows patients to make reminder adjustments and feedback according to their own needs, which enhances the autonomy of patients, enables them to more actively participate in their own health management, and cultivate good medication habits.
[0099] In summary, the dynamic adjustment and feedback module significantly improves the overall effect of the medication management system by improving patient compliance, providing personalized services, responding to emergencies, reducing adverse reactions, improving medical care efficiency, continuously optimizing the system, and enhancing patient autonomy, and has a positive effect on patients' health management and treatment process. BRIEF DESCRIPTION OF THE DRAWINGS
[0100] Figure 1 It is a schematic diagram of the system structure of the present invention;
[0101] Figure 2 It is a schematic diagram of the working process of the data processing module of the present invention;
[0102] Figure 3 It is a schematic diagram of the intelligent algorithm workflow of the present invention;
[0103] Figure 4 It is a structural schematic diagram of the present invention;
[0104] Figure 5 The figure is a schematic diagram of the structure of an electronic device. DETAILED DESCRIPTION
[0105] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0106] Example 1
[0107] See also Figure 1-3 The present invention provides a technical solution: an intelligent medication reminder system, including a medication information input module, a data processing module, an intelligent algorithm module, a reminder module, a recording module and a communication module. The medication information input module is used to input the patient's basic information, condition information and medication information, and input the patient's work and rest time and living habits according to the patient's needs; the specific input information of the medication information input module includes the following:
[0108] a. Basic information: Age: The patient's age, used to determine the appropriate drug dosage and frequency of medication; Gender: The patient's gender, drugs have different dosage recommendations based on gender; Weight: The patient's weight, used to calculate the drug dosage based on weight;
[0109] b. Medical information: Disease type: the type of disease the patient suffers from; Severity: fill in the severity of the disease according to the doctor's advice, which is used to determine the drug dosage and frequency of medication; Drug allergy history: which drugs the patient is allergic to;
[0110] c. Medication information: Drug name: the name of the drug to be taken; Dosage: the dosage of the drug taken each time; Medication time: the recommended medication time, provided by the doctor; Contraindications: contraindications that need to be paid attention to when using the drug.
[0111] Through the above detailed steps and precautions, the medication information input module ensures that the basic information, condition information and medication information entered by the patient are accurate and complete, providing reliable data for generating a personalized medication reminder plan.
[0112] The data processing module is connected to the medication information input module and is used to generate a personalized medication reminder plan based on the input information;
[0113] The specific working steps of the data processing module are as follows:
[0114] Step S1, data reception and storage: receiving all patient information from the medication information input module, including basic information, condition information and medication information; storing the received data in a database;
[0115] Step S2, data preprocessing: remove duplicate data, process missing values and outliers from the data stored in the database to ensure the integrity and accuracy of the data; standardize all input data into a unified format, and integrate data from different sources into a complete data set;
[0116] Step S3, feature extraction: extract key features from the data preprocessed in step S2, specifically including the patient's age, weight, disease type, drug name and dosage. The extracted key feature data provides structured data for the intelligent algorithm module for model analysis and prediction;
[0117] Step S4, data analysis: perform basic statistical analysis on the data preprocessed in step S2, specifically including average age, distribution of common diseases, and commonly used drugs, and provide a data overview;
[0118] Step S5, generating a personalized reminder plan: Based on the analysis results of the intelligent algorithm module, a personalized medication reminder plan is generated for each patient, the plan content includes the specific medication time, the dosage for each dose, the drug name, and any special precautions;
[0119] Step S6, dynamic adjustment: dynamically adjust the reminder plan according to the patient's actual medication situation and feedback to ensure its continued effectiveness and handle the patient's temporary change request.
[0120] Through the above detailed description, the data processing module can effectively process the input patient information, generate a personalized medication reminder plan, and dynamically adjust it according to the actual situation to ensure that the patient takes the medicine correctly and on time.
[0121] In step S6, the specific steps of dynamically adjusting the reminder plan according to the patient's actual medication situation and feedback are as follows:
[0122] Step S61, data collection and analysis: collect the patient's actual medication situation and feedback information, obtain the patient's medication record from the recording module, including medication time, drug information, confirmation status and patient feedback, and obtain the real-time transmitted medication data from the communication module; then analyze the patient's medication compliance, calculate the deviation between the actual medication time and the planned time, analyze the adverse reactions in the patient's feedback and the physical condition after taking the medication, and identify possible problems;
[0123] Step S62, dynamic adjustment mechanism: according to the analysis results, automatically or manually adjust the reminder plan, specifically automatic adjustment: if the patient fails to take the medicine on time for many times, the system automatically adjusts the reminder time, such as advancing or delaying the reminder, to ensure that the reminder is more in line with the patient's daily routine, automatically adjusts the drug dosage reminder according to the patient's feedback and the doctor's advice, and adjusts the reminder frequency of the reminder module according to the patient's medication situation, and increases the number of reminders; manual adjustment: medical staff or patients manually adjust the reminder plan through the remote monitoring terminal or patient equipment according to the actual situation;
[0124] Step S63, processing temporary change requests: patients submit temporary change requests through the communication module, including temporarily changing the medication time or suspending reminders. At the same time, medical staff can submit change requests through the remote monitoring terminal, including adjusting the patient's medication plan or reminder settings; for handling emergency situations, when patients report serious adverse reactions, reminders are immediately adjusted or suspended, and medical staff are notified to intervene.
[0125] The intelligent algorithm module is embedded in the data processing module and is used to analyze the patient's basic information, condition information, medication information, and the patient's work and rest schedule and living habits in the data processing module to generate the optimal medication time and dosage reminder plan;
[0126] The specific working steps of the intelligent algorithm module are as follows:
[0127] Step 1, data collection: receiving the extracted key feature data from the data processing module and the patient's work and rest time and living habit data from the medication information input module;
[0128] Step 2: Personalized model training: A prediction model is established by using the K-means clustering algorithm, and the key feature data collected in step S1 are used to train a personalized model adapted to different types of patients. At the same time, the model parameters are optimized using the cross-validation method to improve the prediction accuracy of the model.
[0129] In step 2, the prediction model is established by the K-means clustering algorithm, and the specific steps of using the key feature data collected in step S1 to train a personalized model adapted to different types of patients are as follows:
[0130] Step 21. Data preparation: Before training the model, you first need to prepare the data, including the key feature data collected from step S1. These data should include the following features:
[0131] The patient's basic information, including age, gender, and weight;
[0132] The patient's medical condition information, including disease type and severity;
[0133] Patient medication information, including drug type, dosage, and frequency of medication;
[0134] Step 22, data matrix: Represent the feature data prepared in step 21 as a data matrix X, where each row represents a patient and each column represents a feature: X = [x1, x2, ..., x n ], where x i is the feature vector of the ith patient; in the K-means algorithm, we must first determine the k clusters to be divided into, and randomly select k initial cluster centers, the formula is: Initial cluster center: C = [c1, c2, ..., c k ], where c j is the coordinate vector of the jth cluster center;
[0135] Step 23: Calculate distance and assign clusters: For each patient x n , calculate its relationship with each cluster center c k The distance between them is calculated and the patient is assigned to the cluster corresponding to the nearest cluster center, where the distance formula is:
[0136]
[0137] Among them, x im Is patient x i The value of the mth feature, c jm is the cluster center c j The value of the mth feature;
[0138] Allocation formula: assign patient x i Assign to cluster j such that: j = argmin j d(x i ,c j );
[0139] Step 24, update cluster centers: After all patients are assigned to the nearest cluster, update each cluster center to the mean of all patient characteristics in the cluster. The update formula is:
[0140]
[0141] Among them, S j is the set of patients in the jth cluster, |S j | is the number of patients in the cluster;
[0142] Step 25: Repeat steps 23 and 24 until the cluster center no longer changes significantly or the predetermined number of iterations is reached. The convergence condition is: when the change between the new cluster center and the previous cluster center is less than a certain threshold ∈, stop the iteration:
[0143]
[0144] Step 26, Personalized model generation: Clustering is completed, and each cluster represents a class of patients with similar characteristics. For each cluster, analyze the characteristics of the patients it represents and generate a personalized medication reminder plan suitable for this type of patients, that is, calculate the characteristics and statistics in each cluster, and customize a personalized medication plan for the patients in this cluster based on the statistical information;
[0145] Step 27, parameter adjustment and optimization: adjust the k value and model parameters through cross-validation to optimize the prediction accuracy of the model; cross-validation steps:
[0146] Divide the data in step 21 into a training set and a validation set;
[0147] Perform K-means clustering on different k values to train personalized models;
[0148] Use the validation set to evaluate model performance, specifically using the SSE and Silhouette Score indicators;
[0149] Select the k value and model parameters that optimize the performance of the validation set;
[0150] in,
[0151] Si lhouette Score:
[0152] Among them, a(i) is the average distance from patient i to other patients in the same cluster, and b(i) is the average distance from patient i to the nearest other cluster.
[0153] Through the above steps, the K-means clustering algorithm can effectively group patients and identify different types of patient groups, thereby generating a more accurate personalized medication reminder plan.
[0154] Step 3. Analysis of work and rest schedule and habits: Calculate the best time to take medication based on the input work and rest schedule, including working hours, sleeping hours, and eating hours. Combined with the patient's living habit data, i.e., daily activity patterns, ensure that the medication time does not conflict with the patient's important activities;
[0155] Step 3: The content of the analysis of work and rest schedule and habits is as follows:
[0156] Calculate the best time to take medicine: Calculate the best time to take medicine based on the nature and requirements of the medicine and the patient's work and rest schedule. Specifically: Drug absorption time: Consider whether the medicine needs to be taken before or after meals. Formula: Best time to take medicine = meal time ± absorption time; Medication interval time: If the medicine needs to be taken multiple times a day, the medication interval time needs to be evenly distributed. Formula: Medication interval time = 24 hours / number of medications; Avoid peak activity time: Avoid taking medicine during work or other important activities;
[0157] Lifestyle matching: Avoid conflicts with the patient's daily activity schedule. Specifically, create a time period set: List all the patient's activity time periods in a day and create a time period set T. The formula is: T = {t1, t2, ..., t n}, where t i Indicates the time period for each activity; Calculate the available time period: Calculate the time period available for medication based on the patient's schedule and activity arrangements. The formula is: Medication time matching: Match the time period required for medication with the available time period, formula:
[0158] Through the above steps, combined with mathematical algorithms and practical applications, the best time to take medication can be scientifically determined, and the medication time can be adjusted according to the patient's living habits to ensure that the patient can take medication conveniently and on time, thereby improving medication compliance and treatment effects.
[0159] Step 4, generate reminder plan: drug interaction detection: use expert system and drug database to detect the interaction between drugs used by patients to avoid drug conflicts; optimization algorithm: use genetic algorithm to optimize medication time and dosage to ensure efficiency and safety; generate plan: generate detailed medication reminder plan, including specific medication time, dosage, and drug name.
[0160] The detailed steps of using genetic algorithm to optimize medication time and dosage and generate reminder plan in step 4 are as follows:
[0161] Step 41, initialize the population: First, initialize a population containing multiple individuals, each individual represents a possible medication plan, and the individual is composed of a set of genes, where the genes include medication time and dosage. The specific formula is:
[0162] Individual representation: I = [t1, t2, ..., t n ,d1,d2,…,d n ], where t i represents the time of taking the i-th medication, d i represents the dosage of the i-th medication;
[0163] Step 42: Define a fitness function to evaluate the pros and cons of each individual. The fitness function is based on the following aspects: drug interaction detection: ensure that there is no conflict between drugs; reasonable medication time: medication time should avoid important activity time as much as possible and conform to work and rest rules; reasonable dosage: dosage should be within a safe range. The specific formula is:
[0164] Fitness function: F(I) = w1·InteractionPenalty(I) + w2·TimePenalty(I) + w3·DosePenalty(I);
[0165] Where w1, w2, w3 are weight coefficients;
[0166] Step 43, selection operation: select excellent individuals as parents according to the fitness function, specifically, calculate the fitness value of each individual, and select individuals according to the fitness value, wherein roulette selection is used, and the formula is:
[0167] Roulette wheel selection probabilities:
[0168] Among them, F(I i ) is individual I i The fitness value of , N is the population size;
[0169] Step 44, crossover operation: Generate new individuals by exchanging some genes of the parent individuals. Specifically, two individuals are selected from the parent generation, the crossover point is randomly selected, and the gene fragments are exchanged. The formula is: Assuming a single-point crossover is selected, the crossover point is:
[0170] Offspring 1:
[0171] Offspring 2:
[0172] Step 45, mutation operation: By randomly changing some genes of individuals, the diversity of the population is increased to avoid falling into the local optimal solution. Specifically, individuals and gene positions are randomly selected, and the gene values of the selected positions are randomly changed. The formula is: Assuming that the selected mutation position is v:
[0173] Before mutation: I = [t1, t2, …, t v ,…,t n ,d1,d2,…,d v ,…,d n ];
[0174] After mutation: I′=[t1,t2,…,t′ v ,…,t n ,d1,d2,…,d′ v ,…,d n ];
[0175] where t′ v and d′ v is the new gene value after mutation;
[0176] Step 46, generating the next generation: generating a new generation of population through selection, crossover and mutation operations, and repeating the iteration until the termination condition is met, and the termination condition includes the convergence of a predetermined number of generations or fitness value;
[0177] Step 47, generate a detailed medication reminder plan: After the algorithm converges, select the individual with the highest fitness value as the final medication reminder plan, and generate detailed plan content, including specific medication time, dosage, and drug name. The formula is:
[0178] The best individual: I * = argmax I∈Population F(I);
[0179] Generate a reminder schedule:
[0180] in and is the optimal individual I * The gene value of .
[0181] Genetic algorithms can effectively optimize medication time and dosage, generate personalized medication reminder plans, and ensure the efficiency and safety of medication; and through the above steps, the intelligent algorithm module can analyze the patient's basic information, medical information and living habits, and develop the most suitable personalized medication reminder plan for the patient.
[0182] The reminder module is connected to the data processing module and is used to remind the patient to take the medicine on time through sound, light or vibration at the scheduled medication time;
[0183] The recording module is connected to the data processing module, and is used to record the patient's medication situation, and will update the patient's medication record in real time, and provide a reference basis for doctors and patients. Specifically, the recording module records the patient's medication situation in detail, including: medication time, actual medication timestamp, used to compare the planned medication time; medication information, specific medication name, dosage, medication method; patient feedback, the patient's subjective feelings after taking the medication; confirmation status, recording whether the patient confirms taking the medication;
[0184] The record module stores the patient's medication status in the database to ensure data security and traceability. The database is used to store and manage the patient's medication records. The database table structure includes the following fields: patient ID, medication time, drug name, dosage, confirmation status, patient feedback, and record creation time;
[0185] The record module supports basic data analysis and visualization functions to help doctors and patients understand medication status, including: medication compliance analysis, which evaluates patients' medication compliance by analyzing the deviation between the actual medication time and the planned time; adverse reaction statistics, which counts patient feedback in the records, analyzes common adverse reactions and generates reports; trend charts, which provide chart functions to display patients' medication status in a graphical manner;
[0186] The recording module supports the report generation function, which allows users to export data for further analysis or sharing.
[0187] The communication module is used to transmit the patient's medication status to the remote monitoring terminal in real time, so that medical staff can understand the patient's medication status in a timely manner.
[0188] Example 2
[0189] like Figure 5 , an intelligent medication reminder method, comprising the following steps:
[0190] Step A: The patient or his / her guardian inputs the patient's basic information, condition information, work and rest schedule, living habits and medication information through the medication information input module;
[0191] Step B: the data processing module generates a personalized medication reminder plan based on the input information;
[0192] Step C: The intelligent algorithm module analyzes the patient's basic information, condition information, work and rest schedule, and living habits, and optimizes and generates the optimal medication time and dosage reminder plan;
[0193] Step D: The reminder module reminds the patient to take the medicine on time through sound, light or vibration at the scheduled medication time;
[0194] Step E: After taking the medicine, the patient confirms the medication status through the medication information input module, and the recording module records and stores the patient's medication status;
[0195] Step F: The communication module transmits the patient's medication status to the remote monitoring terminal in real time, and the medical staff conducts necessary tracking and adjustments based on the transmitted information.
[0196] Example 3
[0197] An electronic device according to an exemplary embodiment includes: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;
[0198] The processor executes the above-mentioned intelligent medication reminder system by calling the computer program stored in the memory.
[0199] Figure 4It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor to implement a highly immersive human-computer interactive virtual driving vehicle testing system provided in the above-mentioned various method embodiments.
[0200] The electronic device may also include other components for realizing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input / output interface for input and output. The embodiments of the present application will not be described in detail here.
[0201] This embodiment also provides a computer program product stored on a computer-readable medium, including a computer-readable program, which, when executed on an electronic device, provides a user input interface to implement the intelligent medication reminder system.
[0202] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0203] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.
[0204] The present invention provides an intelligent medication reminder system and method based on an intelligent algorithm. Through the mutual cooperation of a medication information input module, a data processing module, an intelligent algorithm module, a reminder module, a recording module and a communication module, a personalized medication reminder plan can be generated according to the individual characteristics, work and rest time and living habits of different patients, so as to remind patients to take their medications on time and correctly, and transmit the patients' medication status to medical staff in real time, which is helpful to improve the treatment effect and reduce adverse reactions.
[0205] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. An intelligent medication reminder system, comprising a medication information input module, a data processing module, an intelligent algorithm module, a reminder module, a recording module and a communication module, characterized in that: The medication information input module is used to input the patient's basic information, condition information and medication information, and input the patient's work and rest time and living habits according to the patient's needs; the specific input information of the medication information input module includes the following: a. Basic information: Age: The patient's age, used to determine the appropriate drug dosage and frequency of medication; Gender: The patient's gender, drugs have different dosage recommendations based on gender; Weight: The patient's weight, used to calculate the drug dosage based on weight; b. Medical information: Disease type: the type of disease the patient suffers from; Severity: fill in the severity of the disease according to the doctor's advice, which is used to determine the drug dosage and frequency of medication; Drug allergy history: which drugs the patient is allergic to; c. Medication information: Drug name: the name of the drug to be taken; Dosage: the dosage of the drug to be taken each time; Medication time: the recommended medication time, provided by the doctor; Contraindications: contraindications that need to be noted when using the drug; The data processing module is connected to the medication information input module and is used to generate a personalized medication reminder plan according to the input information; The intelligent algorithm module is embedded in the data processing module and is used to analyze the patient's basic information, condition information, medication information, and the patient's work and rest schedule and living habits in the data processing module to generate an optimal medication time and dosage reminder plan; The reminder module is connected to the data processing module and is used to remind the patient to take the medicine on time through sound, light or vibration at the scheduled medication time; The recording module is connected to the data processing module, and is used to record the patient's medication situation and store the recorded information in the database; the real-time update of the patient's medication record and providing a reference basis for doctors and patients are as follows: the recording module records the patient's medication situation in detail, including: medication time, actual medication timestamp, used to compare the planned medication time; medication information, specific medication name, dosage, medication method; patient feedback, the patient's subjective feelings after taking the medication; confirmation status, recording whether the patient confirms taking the medication; The recording module stores the patient's medication status in a database to ensure data security and traceability. The database is used to store and manage the patient's medication records. The database table structure includes the following fields: patient ID, medication time, drug name, dosage, confirmation status, patient feedback, and record creation time; The recording module supports basic data analysis and visualization functions to help doctors and patients understand medication status, specifically: medication compliance analysis, which evaluates patients' medication compliance by analyzing the deviation between the actual medication time and the planned time; adverse reaction statistics, which counts patient feedback in the records, analyzes common adverse reactions and generates reports; trend charts, which provide chart functions to display patients' medication status in a graphical manner; The recording module supports the report generation function, which allows users to export data for further analysis or sharing. The communication module is used to transmit the patient's medication status to the remote monitoring terminal in real time, so that medical staff can understand the patient's medication status in time.
2. The intelligent medication reminder system according to claim 1, characterized in that: The specific working steps of the data processing module are as follows: Step S1, data reception and storage: receiving all patient information from the medication information input module, including basic information, condition information and medication information; storing the received data in a database; Step S2, data preprocessing: remove duplicate data, process missing values and outliers from the data stored in the database to ensure the integrity and accuracy of the data; at the same time, standardize all input data into a unified format and integrate data from different sources into a complete data set; Step S3, feature extraction: extract key features from the data preprocessed in step S2, specifically including the patient's age, weight, disease type, drug name and dosage. The extracted key feature data provides structured data for the intelligent algorithm module for model analysis and prediction; Step S4, data analysis: perform basic statistical analysis on the data preprocessed in step S2, specifically including average age, distribution of common diseases, and commonly used drugs, and provide a data overview; Step S5, generating a personalized reminder plan: Based on the analysis results of the intelligent algorithm module, a personalized medication reminder plan is generated for each patient, the plan content includes the specific medication time, the dosage for each dose, the name of the drug, and any special precautions; Step S6, dynamic adjustment: dynamically adjust the reminder plan according to the patient's actual medication situation and feedback to ensure its continued effectiveness and handle the patient's temporary change request.
3. The intelligent medication reminder system according to claim 2, characterized in that: The specific steps of dynamically adjusting the reminder plan according to the patient's actual medication situation and feedback in step S6 are as follows: Step S61, data collection and analysis: collect the patient's actual medication situation and feedback information, obtain the patient's medication record from the recording module, including medication time, drug information, confirmation status and patient feedback, and obtain the real-time transmitted medication data from the communication module; then analyze the patient's medication compliance, calculate the deviation between the actual medication time and the planned time, analyze the adverse reactions in the patient's feedback and the physical condition after taking the medication, and identify possible problems; Step S62, dynamic adjustment mechanism: according to the analysis results, automatically or manually adjust the reminder plan, specifically automatic adjustment: if the patient fails to take the medicine on time for many times, the system automatically adjusts the reminder time, such as advancing or delaying the reminder, to ensure that the reminder is more in line with the patient's daily routine, automatically adjusts the drug dosage reminder according to the patient's feedback and the doctor's advice, and adjusts the reminder frequency of the reminder module according to the patient's medication situation, and increases the number of reminders; manual adjustment: medical staff or patients manually adjust the reminder plan through the remote monitoring terminal or patient equipment according to the actual situation; Step S63, processing temporary change requests: patients submit temporary change requests through the communication module, including temporarily changing the medication time or suspending reminders. At the same time, medical staff can submit change requests through the remote monitoring terminal, including adjusting the patient's medication plan or reminder settings; for handling emergency situations, when patients report serious adverse reactions, reminders are immediately adjusted or suspended, and medical staff are notified to intervene.
4. The intelligent medication reminder system according to claim 1, characterized in that: The specific working steps of the intelligent algorithm module are as follows: Step 1, data collection: receiving the extracted key feature data from the data processing module and the patient's work and rest time and living habit data from the medication information input module; Step 2: Personalized model training: A prediction model is established by using the K-means clustering algorithm, and the key feature data collected in step S1 are used to train a personalized model adapted to different types of patients. At the same time, the model parameters are optimized using the cross-validation method to improve the prediction accuracy of the model. Step 3. Analysis of work and rest schedule and habits: Calculate the best time to take medication based on the input work and rest schedule, including working hours, sleeping hours, and eating hours. Combined with the patient's living habit data, i.e., daily activity patterns, ensure that the medication time does not conflict with the patient's important activities; Step 4. Generate a reminder plan: Drug interaction detection: Use expert systems and drug databases to detect interactions between patients' drugs and avoid drug conflicts; Optimization algorithm: Genetic algorithm is used to optimize medication time and dosage to ensure efficiency and safety; Generate plan: Generate a detailed medication reminder plan, including specific medication time, dosage, and drug name.
5. The intelligent medication reminder system according to claim 4, characterized in that: The specific steps of establishing a prediction model by using the K-means clustering algorithm in step 2 and training a personalized model adapted to different types of patients using the key feature data collected in step S1 are as follows: Step 21. Data preparation: Before training the model, you first need to prepare the data, including the key feature data collected from step S1. These data should include the following features: The patient's basic information, including age, gender, and weight; The patient's medical condition information, including disease type and severity; Patient medication information, including drug type, dosage, and frequency of medication; Step 22, data matrix: Represent the feature data prepared in step 21 as a data matrix X, where each row represents a patient and each column represents a feature: X = [x1, x2, ..., x n ], where x i is the feature vector of the ith patient; in the K-means algorithm, we must first determine the k clusters to be divided into, and randomly select k initial cluster centers, the formula is: Initial cluster center: C = [c1, c2, ..., c k ], where c j is the coordinate vector of the jth cluster center; Step 23: Calculate distance and assign clusters: For each patient x n , calculate its relationship with each cluster center c k The distance between them is calculated and the patient is assigned to the cluster corresponding to the nearest cluster center, where the distance formula is: Among them, x im Is patient x i The value of the mth feature, c jm is the cluster center c j The value of the mth feature; Allocation formula: assign patient x i Assign to cluster j such that: j = argmin j d(x i , c j ); Step 24, update cluster centers: After all patients are assigned to the nearest cluster, update each cluster center to the mean of all patient characteristics in the cluster. The update formula is: Among them, S j is the set of patients in the jth cluster, |S j | is the number of patients in the cluster; Step 25: Repeat steps 23 and 24 until the cluster center no longer changes significantly or the predetermined number of iterations is reached. The convergence condition is: when the change between the new cluster center and the previous cluster center is less than a certain threshold ∈, stop the iteration: Step 26, Personalized model generation: Clustering is completed, and each cluster represents a class of patients with similar characteristics. For each cluster, analyze the characteristics of the patients it represents and generate a personalized medication reminder plan suitable for this type of patients, that is, calculate the characteristics and statistics in each cluster, and customize a personalized medication plan for the patients in this cluster based on the statistical information; Step 27, parameter adjustment and optimization: adjust the k value and model parameters through cross-validation to optimize the prediction accuracy of the model; cross-validation steps: Divide the data in step 21 into a training set and a validation set; Perform K-means clustering on different k values to train personalized models; Use the validation set to evaluate model performance, specifically using the SSE and Silhouette Score indicators; Select the k value and model parameters that optimize the performance of the validation set; in, Silhouette Score: Among them, a(i) is the average distance from patient i to other patients in the same cluster, and b(i) is the average distance from patient i to the nearest other cluster.
6. The intelligent medication reminder system according to claim 4, characterized in that: The content of step 3 work and rest time and habit analysis is as follows: Calculate the best time to take medicine: Calculate the best time to take medicine based on the nature and requirements of the medicine and the patient's work and rest schedule. Specifically: Drug absorption time: Consider whether the medicine needs to be taken before or after meals. Formula: Best time to take medicine = meal time ± absorption time; Medication interval time: If the medicine needs to be taken multiple times a day, the interval time between medicines needs to be evenly distributed. Formula: Medication interval time = 24 hours / number of times to take medicine; Avoid peak activity time: Avoid taking medicine during work or other important activities; Lifestyle matching: Avoid conflicts with the patient's daily activity schedule. Specifically, create a time period set: List all the patient's activity time periods in a day and create a time period set T. The formula is: T = {t1, t2, ..., t n }, where t i Indicates the time period for each activity; Calculate the available time period: Calculate the time period available for medication based on the patient's schedule and activity arrangements. The formula is: Medication time matching: Match the time period required for medication with the available time period, formula:
7. The intelligent medication reminder system according to claim 4, characterized in that: The detailed steps of using genetic algorithm to optimize medication time and dosage and generate reminder plan in step 4 are as follows: Step 41, initialize the population: First, initialize a population containing multiple individuals, each individual represents a possible medication plan, and the individual is composed of a set of genes, where the genes include medication time and dosage. The specific formula is: Individual representation: I = [t1, t2, ..., t n ,d1,d2,…,d n ], where t i represents the time of taking the i-th medication, d i represents the dosage of the i-th medication; Step 42: Define a fitness function to evaluate the pros and cons of each individual. The fitness function is based on the following aspects: drug interaction detection: ensure that there is no conflict between drugs; reasonable medication time: medication time should avoid important activity time as much as possible and conform to work and rest rules; reasonable dosage: dosage should be within a safe range. The specific formula is: Fitness function: F(I) = w1·InteractionPenalty(I) + w2·TimePenalty(I) + w3·DosePenalty(I); Among them w1, w2, w3 are weight coefficients; Step 43, selection operation: select excellent individuals as parents according to the fitness function, specifically, calculate the fitness value of each individual, and select individuals according to the fitness value, wherein roulette selection is used, and the formula is: Roulette wheel selection probabilities: Among them, F(I i ) is individual I i The fitness value of , N is the population size; Step 44, crossover operation: Generate new individuals by exchanging some genes of the parent individuals. Specifically, two individuals are selected from the parent generation, the crossover point is randomly selected, and the gene fragments are exchanged. The formula is: Assuming a single-point crossover is selected, the crossover point is: Offspring 1: Offspring 2: Step 45, mutation operation: By randomly changing some genes of individuals, the diversity of the population is increased to avoid falling into the local optimal solution. Specifically, individuals and gene positions are randomly selected, and the gene values of the selected positions are randomly changed. The formula is: Assuming that the selected mutation position is v: Before mutation: I = [t1, t2, …, t v ,…,t n ,d1,d2,…,d v ,…,d n ]; After mutation: I′=[t1,t2,…,t′ v ,…,t n ,d1,d2,…,d′ v ,…,d n ]; where t ′ v and d ′ v is the new gene value after mutation; Step 46, generating the next generation: generating a new generation of population through selection, crossover and mutation operations, and repeating the iteration until the termination condition is met, and the termination condition includes the convergence of a predetermined number of generations or fitness value; Step 47, generate a detailed medication reminder plan: After the algorithm converges, select the individual with the highest fitness value as the final medication reminder plan, and generate detailed plan content, including specific medication time, dosage, and drug name. The formula is: The best individual: I * = argmax I∈Population F(I); Generate a reminder schedule: in and is the optimal individual I * The gene value of .
8. An intelligent medication reminder method according to any one of claims 1 to 7, characterized in that: The following steps are involved: Step A: The patient or his / her guardian inputs the patient's basic information, condition information, work and rest schedule, living habits and medication information through the medication information input module; Step B: the data processing module generates a personalized medication reminder plan based on the input information; Step C: The intelligent algorithm module analyzes the patient's basic information, condition information, work and rest schedule, and living habits, and optimizes and generates the optimal medication time and dosage reminder plan; Step D: The reminder module reminds the patient to take the medicine on time through sound, light or vibration at the scheduled medication time; Step E: After taking the medicine, the patient confirms the medication status through the medication information input module, and the recording module records and stores the patient's medication status; Step F: The communication module transmits the patient's medication status to the remote monitoring terminal in real time, and the medical staff conducts necessary tracking and adjustments based on the transmitted information.
9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor calls the computer program stored in the memory to execute and implement the intelligent medication reminder system as described in any one of claims 1-7.
10. A computer program product stored on a computer readable medium, characterized in that: It comprises a computer-readable program, which, when executed on an electronic device, provides a user input interface to implement an intelligent medication reminder system as described in any one of claims 1-7.
Citation Information
Cited By
Management system for oral medicine of stroke patient based on AI smart bracelet
CN119889569A
Automatic reminding system and reminding method for medicine bottle
CN120356612A
Eye medicine application management system with intelligent reminding function
CN120853993A
