Intelligent reminding method, system and equipment for patient medicine dispensing and storage medium

Abstract

The invention discloses an intelligent reminding method, system and device for patient medicine dispensing and a storage medium, and the method comprises the steps: obtaining an electronic medical record, historical medicine consumption data and health state data of a patient, and medicine data in an intelligent medicine box; analyzing the electronic medical record, the historical drug consumption data and the health state data, and establishing a drug consumption characteristic model; calculating a target consumption rate of the target medicine according to the medicine data, the health state data and a medicine consumption characteristic model; determining an acquisition difficulty feature of the target drug; determining the remaining drug consumption duration of the target drug based on the target consumption rate, the historical drug consumption data and the drug data; determining a supplement time threshold value of the target drug based on the target consumption rate and the acquisition difficulty feature; and when the remaining medicine consumption duration and the supplement time threshold meet the preset reminding requirement, generating reminding information, and sending the reminding information to a reminding information receiving end meeting the preset information receiving requirement. The accuracy of medicine supplement reminding can be improved.

Description

Technical Field

[0001] This application relates to the field of medical and health management, and particularly to an intelligent reminder method, system, device and storage medium for prescribing drugs to patients. Background Art

[0002] As an emerging health management tool, the intelligent medicine box plays an important role in the modern medical system. By integrating a variety of information technology means, it realizes the real-time monitoring and management of patients' medication conditions, greatly improves patients' medication compliance, and also provides more efficient auxiliary decision-making support for medical staff. With the aggravation of population aging and the increase in the prevalence of chronic diseases, the application of intelligent medicine boxes can not only effectively improve the quality of life of patients, but also significantly reduce the probability of risk events caused by wrong medication.

[0003] In the prior art, the reminder for refilling medicine in the intelligent medicine box usually sends a supplementary reminder to the patient automatically when the quantity of medicine is lower than a preset threshold by presetting the fixed dosage and taking time of each medicine in advance. However, only reminding based on a fixed threshold fails to fully consider the impact of the actual situation of the patient on the dosage of medicine. When the patient's condition worsens, the dosage of medicine may increase, and the reminder time of the fixed threshold may lag, so it is difficult to accurately grasp the best time for refilling medicine, and the accuracy of the refilling reminder is relatively low. Summary of the Invention

[0004] This application provides an intelligent reminder method for prescribing drugs to patients to improve the accuracy of the refilling reminder.

[0005] In the first aspect of this application, an intelligent reminder method for prescribing drugs to patients is provided, which is applied to an intelligent medicine box. The method includes: Obtaining the electronic medical record, historical drug consumption data, health status data of the patient and the drug data in the intelligent medicine box; analyzing the electronic medical record, historical drug consumption data and health status data to establish a drug consumption characteristic model; calculating the target consumption rate of the target drug in the intelligent medicine box according to the drug data, health status data and the drug consumption characteristic model, where the target drug is any drug in the intelligent medicine box; determining the acquisition difficulty characteristic of the target drug according to the drug data and the preset drug database; determining the remaining drug consumption duration of the target drug based on the target consumption rate, historical drug consumption data and drug data; determining the supplementary time threshold of the target drug based on the target consumption rate and the acquisition difficulty characteristic; when the remaining drug consumption duration and the supplementary time threshold meet the preset reminder requirements, generating a reminder message and sending the reminder message to a reminder message receiving end that meets the preset information receiving requirements, and the reminder message receiving end includes a patient end and a family member end.

[0006] Optionally, analyzing the electronic medical record, historical drug consumption data and health status data to establish a drug consumption characteristic model specifically includes: Analyze the electronic medical records to determine the standard medication data of the target drug. The standard medication data includes the standard single-dose quantity, standard dosing frequency, and standard dosing interval; based on the historical drug consumption data, determine the historical medication data of the target drug. The historical medication data includes the historical single-dose quantity, historical dosing frequency, and historical dosing interval; calculate the difference values between the historical medication data and the standard medication data for each preset historical time period to obtain the target consumption deviation set. The target consumption deviation set includes the single-dose deviation value, dosing frequency deviation value, and dosing interval deviation value; according to the preset health status assessment rules, analyze the target health status data for each preset historical time period to obtain the corresponding historical health status type for each preset historical time period; perform time matching between the target consumption deviation set and the historical health status type to obtain the consumption deviation characteristics of the target drug corresponding to each historical health status type; establish a drug consumption characteristic model based on the standard medication data and consumption deviation characteristics.

[0007] Optionally, calculate the target consumption rate of the target drug in the intelligent medicine box based on the drug data, health status data, and drug consumption characteristic model, specifically including: According to the preset health status assessment rules, determine the current health status type of the patient based on the health status data; obtain the consumption deviation characteristics of the target drug corresponding to the current health status type from the drug consumption characteristic model; based on the drug data, construct the consumption time series of the target drug, and use the sliding time window method to extract the consumption trend characteristics of the target drug; perform feature fusion on the consumption deviation characteristics and consumption trend characteristics to obtain the consumption prediction parameters of the target drug; determine the target consumption rate of the target drug according to the consumption prediction parameters.

[0008] Optionally, determine the remaining drug consumption duration of the target drug based on the target consumption rate, historical drug consumption data, and drug data, specifically including: Determine the remaining quantity of the target drug based on the drug data; according to the target consumption rate and the remaining quantity, construct the consumption time function of the target drug and calculate the target consumption duration of the target drug; based on the historical drug consumption data, calculate the coefficient of uncertainty of the patient's medication behavior; perform weighted calculation on the coefficient of uncertainty of the medication behavior and the target consumption duration to obtain the remaining drug consumption duration of the target drug.

[0009] Optionally, the replenishment time threshold includes a first replenishment time threshold and a second replenishment time threshold, and the first replenishment time threshold is greater than the second replenishment time threshold. Determine the replenishment time threshold of the target drug based on the target consumption rate and the acquisition difficulty characteristics, specifically including: Construct a drug availability evaluation model based on the drug acquisition priority, delivery timeliness, and the number of alternative channels in the acquisition difficulty characteristics, and calculate the acquisition risk compensation coefficient; calculate the first replenishment time threshold based on the remaining drug consumption duration and the acquisition risk compensation coefficient; calculate the emergency coefficient based on the emergency deployment difficulty in the acquisition difficulty characteristics, and determine the second replenishment time threshold based on the first replenishment time threshold and the emergency coefficient.

[0010] Optionally, when the remaining drug consumption duration and the replenishment time threshold meet the preset reminder requirements, generate a reminder message and send the reminder message to a reminder message receiving end that meets the preset information receiving requirements. Specifically, it includes: When the remaining drug consumption duration is less than the first replenishment time threshold and greater than the second replenishment time threshold, generate a first reminder message and send the first reminder message to the patient end; within a preset waiting time length after sending the first reminder message, determine the drug replenishment status of the smart medicine box according to the drug data, and the preset waiting time length is greater than zero and less than the difference between the first replenishment time threshold and the second replenishment time threshold; if the drug replenishment status, the remaining drug consumption duration, and the second replenishment time threshold meet the preset reminder requirements, generate a second reminder message and send the second reminder message to the patient end and the family member end.

[0011] Optionally, if the drug replenishment status, the remaining drug consumption duration, and the second replenishment time threshold meet the preset reminder requirements, generate a second reminder message. Specifically, it includes: When the drug replenishment status is not replenished and the remaining drug consumption duration is less than or equal to the second replenishment time threshold, generate a second reminder message.

[0012] In the second aspect of the present application, a patient prescribing intelligent reminder system is provided, including: An acquisition module, configured to acquire the electronic medical record, historical drug consumption data, health status data of the patient, and drug data in the smart medicine box; An analysis module, configured to analyze the electronic medical record, historical drug consumption data, and health status data to establish a drug consumption characteristic model; a calculation module, configured to calculate the target consumption rate of the target drug in the smart medicine box according to the drug data, health status data, and the drug consumption characteristic model, and the target drug is any drug in the smart medicine box; A first determination module, configured to determine the acquisition difficulty characteristics of the target drug according to the drug data and the preset drug database; A second determination module, configured to determine the remaining drug consumption duration of the target drug based on the target consumption rate, historical drug consumption data, and drug data; A third determination module, configured to determine the replenishment time threshold of the target drug based on the target consumption rate and the acquisition difficulty characteristics; A reminder module is used to generate a reminder message when the remaining medicine consumption duration and the replenishment time threshold meet the preset reminder requirements, and send the reminder message to a reminder message receiver that meets the preset message receiving requirements. The reminder message receiver includes a patient terminal and a family member terminal.

[0013] In a third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface, and a network interface. The memory is used to store instructions. Both the user interface and the network interface are used to communicate with other devices. The processor is used to execute the instructions stored in the memory so that the electronic device executes the method described in any one of the above.

[0014] In a fourth aspect of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores instructions that, when executed, execute the method described in any one of the above.

[0015] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. By obtaining multi-dimensional information such as the patient's electronic medical record, historical medicine consumption data, and health status data, a comprehensive basis for medicine use analysis is established; by establishing a medicine consumption characteristic model and combining real-time health status data to calculate the target consumption rate, accurate prediction of medicine use needs is achieved; at the same time, based on the medicine database, the acquisition difficulty characteristics are determined and the replenishment time threshold is dynamically adjusted, and an intelligent early warning mechanism for medicine replenishment is constructed; finally, through the intelligent comparison of the remaining medicine consumption duration and the replenishment time threshold, a hierarchical reminder strategy is formed, thus solving the technical problem that the traditional medicine-taking reminder method cannot be intelligently adjusted according to the actual medicine use situation and the medicine acquisition difficulty. This intelligent reminder mechanism based on multi-dimensional data analysis enables the system to dynamically evaluate according to the patient's actual medicine use rules and medicine characteristics, and improves the accuracy of medicine-taking reminders through accurate time prediction and multi-terminal collaborative reminders.

[0016] 2. By analyzing the electronic medical record to determine the standard medicine use data as a reference, a standardized medicine use evaluation standard is established; by extracting the difference value between the historical medicine use data and the standard medicine use data, a quantitative index system for medicine use deviation is constructed; on this basis, by analyzing the health status data of each historical time period and performing time matching with the medicine use deviation, the medicine use deviation characteristics under different health statuses are obtained, and a correlation model between the health status and the medicine use behavior is formed; finally, a medicine consumption characteristic model is established based on the standard medicine use data and the consumption deviation characteristics, thus solving the technical problem that the traditional medicine use model cannot be dynamically adjusted according to the patient's individual differences and health status changes. This medicine use modeling mechanism based on multi-dimensional data analysis enables the system to establish a personalized medicine use characteristic model through the comparative analysis of standard data and actual medicine use behavior, combined with health status changes, not only improving the accuracy of medicine use prediction.

[0017] 3. By evaluating the current health status type according to preset rules and obtaining the corresponding consumption deviation characteristics, a medication benchmark based on health status is established; by constructing a consumption time series and using the sliding time window method to extract consumption trend characteristics, dynamic monitoring of medication behavior is realized; on this basis, by fusing the consumption deviation characteristics with the consumption trend characteristics to obtain consumption prediction parameters, a prediction model that takes into account both health status and real-time medication trends is formed; finally, based on the prediction parameters, the target consumption rate is determined, thus solving the technical problem that traditional consumption prediction cannot simultaneously consider changes in health status and real-time medication trends. This consumption prediction mechanism based on multi-dimensional feature fusion enables the system to comprehensively analyze the changes in the patient's health status and the actual medication trend, not only improving the accuracy and real-time performance of medication consumption prediction, but also realizing the dynamic evaluation and intelligent prediction of the patient's medication needs.

[0018] 4. By constructing an availability evaluation model based on drug acquisition priority, delivery timeliness, and alternative channels to calculate the risk compensation coefficient, a two-threshold hierarchical early warning mechanism is established; by refining the threshold in combination with the emergency coefficient of the emergency deployment difficulty, a more accurate time early warning system is formed; at the same time, by setting a preset waiting time, a progressive early warning strategy for patient self-supplementation and family member collaborative reminder is realized, thus solving the technical problem that traditional reminder methods cannot perform hierarchical early warning according to the drug acquisition difficulty and urgency. This hierarchical reminder mechanism based on multi-dimensional risk assessment enables the system to perform dynamic early warning according to the drug availability characteristics, and through a multi-level reminder strategy of patient priority and family member collaboration, not only improves the timeliness of drug supplementation. Description of the Drawings

[0019] Figure 1 is a schematic flowchart of a method for intelligent reminder of prescribing drugs for patients in an embodiment of the present application; Figure 2 is a schematic structural diagram of an intelligent reminder system for prescribing drugs for patients in an embodiment of the present application; Figure 3 is a schematic structural diagram of an electronic device in an embodiment of the present application.

[0020] Description of the reference numerals: 201, acquisition module; 202, analysis module; 203, calculation module; 204, first determination module; 205, second determination module; 206, third determination module; 207, reminder module; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. Detailed Embodiment

[0021] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of the embodiments.

[0022] In the description of the embodiments of this application, words such as "for example" or "for illustration" are used to give examples, illustrations, or explanations. Any embodiment or design solution described as "for example" or "for illustration" in the embodiments of this application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "for example" or "for illustration" is intended to present relevant concepts in a specific manner.

[0023] In the description of the embodiments of this application, the meaning of the term "plural" refers to two or more. For example, a plurality of systems refers to two or more systems, and a plurality of screen terminals refers to two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "include", "comprise", "have" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0024] Figure 1 It is a schematic flowchart of an intelligent reminder method for prescribing medicine to patients in the embodiments of this application.

[0025] Please refer to Figure 1 , an intelligent reminder method for prescribing medicine to patients in the embodiments of this application, which is applied to an intelligent medicine box. The method includes: S101. Obtain the patient's electronic medical record, historical drug consumption data, health status data, and drug data in the smart medicine box. First, obtain the electronic medical record, historical drug consumption data, health status data, and drug data in the smart medicine box that the patient has authorized. Among them, the electronic medical record includes medical information such as the patient's basic information (such as age, gender, allergy history, etc.), diagnosis records, treatment plans, and medication orders. The historical drug consumption data includes the patient's drug use records within a specific past time period (such as the recent 3 months). The specific record content includes medication details such as the medication time, dosage, and frequency. For example, the record shows that the patient takes 1 tablet of nifedipine, an antihypertensive drug, at 8 am and 1 tablet of nifedipine at 8 pm every day. The health status data can be vital sign data (such as blood pressure, heart rate, blood sugar, etc.) collected through wearable devices, intelligent medical devices, and various clinical examination results. For example, the blood pressure monitoring record shows that the patient's systolic blood pressure is maintained within the range of 140 - 150 mmHg, and the diastolic blood pressure is maintained within the range of 90 - 95 mmHg. The drug data in the smart medicine box can be information such as the remaining quantity of the corresponding drug, the opening time of the box, and the medicine-taking record collected in real time through the sensors of the smart medicine box. Information such as the drug name, specification, and dosage form can be uploaded through the smart medicine box data system. For example, the smart medicine box shows that there are 15 tablets of nifedipine remaining and the interval between each box opening is about 12 hours. The electronic medical record, historical drug consumption data, health status data, and drug data in the smart medicine box can be obtained through various channels such as the hospital's information system, the data acquisition module of the smart medicine box, and the data transmission interface of the wearable device, and these data are transmitted to the data processing system of the smart medicine box through the data interface.

[0026] S102. Analyze the electronic medical record, historical drug consumption data, and health status data, and establish a drug consumption characteristic model. Specifically, analyze the electronic medical record to determine the standard medication data of the target drug. The standard medication data includes the standard single-dose medication quantity, standard medication frequency, and standard medication interval time. Based on the historical drug consumption data, determine the historical medication data of the target drug. The historical medication data includes the historical single-dose medication quantity, historical medication frequency, and historical medication interval time. Calculate the difference value between the historical medication data and the standard medication data within each preset historical time period to obtain the target consumption deviation set. The target consumption deviation set includes the single-dose medication deviation value, medication frequency deviation value, and medication interval time deviation value. According to the preset health status assessment rules, analyze the target health status data for each preset historical time period to obtain the historical health status type corresponding to each preset historical time period. Match the target consumption deviation set with the historical health status type in terms of time to obtain the consumption deviation characteristics of the target drug corresponding to each historical health status type. Establish a drug consumption characteristic model based on the standard medication data and consumption deviation characteristics.

[0027] In step S102, first, by analyzing the electronic medical record information, the target drug prescriptions and medication orders issued by doctors are extracted to determine the standard medication data. The standard medication data specifically includes: the standard single-dose quantity (for example, the doctor's order clearly states that each time 1 tablet / 10mg of nifedipine sustained-release tablets should be taken), the standard medication frequency (for example, the doctor's order stipulates that it should be taken 2 times a day), and the standard medication interval time (for example, the doctor requires it to be taken at 8 am and 8 pm every day, with an interval of 12 hours). These data serve as the standard reference benchmarks for evaluating the patient's actual medication behavior.

[0028] Subsequently, the system will systematically process and analyze the collected historical drug consumption data, extract the detailed medication records of the target drug during actual use, and obtain the historical medication data, which specifically includes: the historical single-dose quantity (for example, the intelligent medicine box records show that the actual quantity of each drug taken by the patient fluctuates between 0.5 and 1 tablet), the historical medication frequency (for example, the records show that the actual number of times the patient takes the medicine varies between 1 and 3 times a day), and the historical medication interval time (for example, the data shows that the actual time interval between the patient's medications ranges from 10 to 14 hours).

[0029] Next, the system will compare and calculate the historical medication data and the standard medication data according to a preset time period (for example, it can be selected in units of days, weeks, or months) to obtain the target consumption deviation set. The specific calculation process includes: calculating the deviation value of the single-dose quantity (for example, if the standard dose is 1 tablet and the actual dose is 0.5 tablet, the deviation value is -0.5 tablet), calculating the deviation value of the medication frequency (for example, if the standard frequency is 2 times a day and the actual frequency is 3 times, the deviation value is +1 time), and calculating the deviation value of the medication interval time (for example, if the standard interval is 12 hours and the actual interval is 14 hours, the deviation value is +2 hours). These deviation data can quantitatively describe the patient's medication compliance level.

[0030] Then, the system analyzes and classifies the patient's health status data according to the pre-set health status assessment rules. Taking hypertensive patients as an example, the assessment rules can divide the blood pressure status into different levels: normal (systolic blood pressure < 130 mmHg and diastolic blood pressure < 85 mmHg), slightly elevated (systolic blood pressure 130 - 139 mmHg or diastolic blood pressure 85 - 89 mmHg), moderately elevated (systolic blood pressure 140 - 159 mmHg or diastolic blood pressure 90 - 99 mmHg), etc. The system accordingly evaluates the health status data within each preset historical time period to obtain the specific health status type corresponding to that period.

[0031] The system performs precise matching and correlation analysis on the target consumption deviation set and the historical health status type in the time dimension. For example, it may be found that during the period when the blood pressure is in the "slightly high" state, the patient's medication behavior exhibits the following characteristics: the average deviation of the single-dose amount is +0.5 tablets (i.e., tending to increase the dose), the average deviation of the medication frequency is +1 time (i.e., tending to increase the number of doses), and the average deviation of the medication interval time is -2 hours (i.e., tending to shorten the medication interval). Through this matching analysis, the specific medication behavior characteristics of patients in different health states can be obtained.

[0032] Finally, based on the obtained standard medication data and the consumption deviation characteristics in various health states obtained from the foregoing analysis, the system constructs a drug consumption characteristic model. The drug consumption characteristic model may include: a benchmark medication parameter module (including standard medication data), a health state classification module (for judging the current health state type), a deviation prediction module (for predicting possible medication behavior deviations based on the health state), etc. In the specific implementation manner of the present invention, the construction process of the drug consumption characteristic model first needs to establish a benchmark medication parameter module including standard medication data, which module includes a standard single-dose medication parameter matrix (such as recording the standard single-dose of 10 mg, medication time point, etc.), a standard medication frequency parameter matrix (such as recording the number of daily doses of 2 times, dosing interval of 12 hours, etc.), and a standard cycle medication parameter matrix (such as recording special requirements such as whether intermittent administration is required); secondly, construct a health state classification module, which module includes a health index threshold matrix (such as setting blood pressure classification criteria), a state classification rule set (such as defining the determination method of the health state), and a state feature vector (such as classifying the blood pressure state into normal H1, slightly elevated H2, moderately elevated H3, etc.); then establish a time series deviation matrix and a health state-deviation mapping function, the time series deviation matrix D(t) = [d1(t), d2(t), d3(t)], where D(t) is the time series deviation matrix, d1(t) is the single-dose medication deviation at time t, d2(t) is the medication frequency deviation at time t, d3(t) is the dosing interval deviation at time t, and the health state-deviation mapping function is f: H → D(t), where f is the health state-deviation mapping function, H is the health state, and D(t) is the time series deviation matrix; then construct a drug consumption rate prediction function and a consumption characteristic correction coefficient matrix, the drug consumption rate prediction function C(t) = g(P, H, D(t)), where C(t) is the drug consumption rate prediction function, P is the set of benchmark parameters, g is the consumption characteristic modeling function, and the consumption characteristic correction coefficient matrix K = [k1, k2, k3], where k1, k2, k3 are consumption characteristic correction coefficients for correcting the prediction result); finally, establish a model evaluation system E including indicators such as prediction accuracy, time responsiveness, adaptability, etc., and design a model optimization algorithm A and a self-learning mechanism L, and finally form a drug consumption characteristic model M = {P, H, D(t), C(t), K, E, A, L}.

[0033] S103. Calculate the target consumption rate of the target drug in the intelligent medicine box according to the drug data, health state data and the drug consumption characteristic model, where the target drug is any drug in the intelligent medicine box; Based on the preset health status assessment rules, determine the current health status type of the patient based on the health status data; obtain the consumption deviation characteristics of the target drug corresponding to the current health status type from the drug consumption characteristic model; based on the drug data, construct the consumption time series of the target drug, and use the sliding time window method to extract the consumption trend characteristics of the target drug; fuse the consumption deviation characteristics and the consumption trend characteristics to obtain the consumption prediction parameters of the target drug; determine the target consumption rate of the target drug according to the consumption prediction parameters.

[0034] In step S103, the system first analyzes and evaluates the real-time collected patient health status data according to the preset health status assessment rules to determine the current health status type of the patient. Taking hypertensive patients as an example, the assessment rules include the following specific contents: The system will perform statistical analysis on the blood pressure monitoring data within the recent 24 hours, calculate the average value, fluctuation range, and excessive standard times of systolic blood pressure and diastolic blood pressure, and combine the blood pressure grading standards (such as normal blood pressure: systolic blood pressure < 130 mmHg and diastolic blood pressure < 85 mmHg; slightly elevated: systolic blood pressure 130 - 139 mmHg or diastolic blood pressure 85 - 89 mmHg; moderately elevated: systolic blood pressure 140 - 159 mmHg or diastolic blood pressure 90 - 99 mmHg). At the same time, considering multi-dimensional indicators such as heart rate changes (such as heart rate > 100 beats per minute may indicate poor blood pressure control) and the blood pressure change trend before and after the medication time point, the specific current health status type of the patient is determined through comprehensive evaluation.

[0035] After determining the current health status type, the system extracts the consumption deviation characteristics of the target drug corresponding to this health status type from the established drug consumption characteristic model. The specific extraction process includes: The system retrieves the historical medication behavior records under this health status type; calculates the statistical characteristics of the single-dose medication amount (such as in the moderately elevated blood pressure state, statistics show that the patient will increase the single-dose medication amount from the standard 1 tablet to 1.25 tablets on average, that is, an increase of 25%), the change characteristics of the medication frequency (such as the data shows that there is a 60% probability that the patient will increase the medication frequency by 1 time in this state), and the adjustment characteristics of the medication interval time (such as the analysis finds that the patient tends to shorten the standard 12-hour medication interval to 10 hours); the system will also combine the confidence levels (such as based on the sufficiency of historical data volume) and stability (such as the fluctuation range of deviation values) of these deviation characteristics to form a complete description of the consumption deviation characteristics.

[0036] Next, based on the real-time drug data collected from the intelligent medicine box, the system constructs the consumption time series of the target drug, and uses the sliding time window method to analyze this time series to extract the consumption trend characteristics of the target drug. The specific implementation method is as follows: First, construct a time series data set with time on the horizontal axis and drug consumption on the vertical axis; then set the sliding window parameters (for example, the window size is set to 7 days to fully consider periodic changes; the step size is set to 1 day to ensure the continuity of the analysis); perform feature extraction within each window, including calculating the daily average consumption and its change rate (for example, it is found that the daily average consumption within the recent 7 days has increased by 10% compared to the previous window), analyzing the distribution characteristics of the medication time points (for example, it is found that the evening medication time has gradually advanced from the original 20:00 to 19:00), and extracting the medication regularity index (for example, calculating the standard deviation of the medication time to evaluate the stability of the medication time); finally, through window sliding, obtain the change trend of these features over time, forming a complete set of consumption trend characteristics.

[0037] Then, the system uses the feature fusion algorithm to fuse the consumption deviation characteristics and the consumption trend characteristics to obtain the consumption prediction parameters of the target drug. The specific fusion process includes: First, standardize the two types of features to unify their numerical ranges; then determine the fusion weights based on the feature importance analysis (where the weight of the consumption deviation characteristics is set to 0.6 because the health status has a dominant impact on the medication behavior; the weight of the consumption trend characteristics is set to 0.4 to reflect the continuous impact of the medication habit); then use the weighted fusion algorithm to calculate the fusion feature values, considering the correlation between the features (for example, the increase in the medication amount caused by the health status may be related to the earlier medication time); finally, convert the fusion result into a parameter form that can be used for prediction, including the expected medication amount adjustment coefficient, the expected medication time adjustment coefficient, etc.

[0038] Finally, based on the consumption prediction parameters obtained by fusion, combined with the standard drug data, the system calculates the target consumption rate of the target drug through the prediction model. The specific calculation process is as follows: First, read the standard medication parameters (for example, the standard dose is 1 tablet / time, and the standard frequency is 2 times / day); then apply the prediction parameters for adjustment (for example, calculate the new medication parameters according to the predicted 20% increase in the medication amount and the 1-hour shortening of the time interval); then consider the influence of time factors (such as the differences in medication behavior between day and night) and other relevant factors (such as the requirements for taking medicine before or after meals); finally, through comprehensive calculation, obtain the expected drug consumption rate within the next 24 hours (for example, the expected consumption rate is 1.2 tablets / 11 hours).

[0039] S104. Determine the acquisition difficulty characteristics of the target drug according to the drug data and the preset drug database; The system receives drug data from the intelligent medicine box (including basic information such as drug name, specification, dosage form, medication cycle, daily dosage, etc.), and then queries the preset drug database to determine the acquisition difficulty characteristics of the target drug. These acquisition difficulty characteristics at least include the following three aspects: First is the drug acquisition priority, that is, grading drugs according to the purpose and importance of drug use, including first-aid drugs such as Suxiao Jiuxin Pills and Nitroglycerin that have a direct impact on vital signs, therapeutic drugs such as antihypertensive drugs and antidiabetic drugs used to maintain important physiological indicators, preventive drugs such as vitamins and calcium tablets for prevention and health care, and adjuvant drugs such as gastrointestinal motility drugs for improving symptoms; Second is the delivery time limit and the number of alternative channels, that is, the actual delivery time of the drug in each pharmacy. For example, the delivery time in the community hospital pharmacy is usually 2 hours due to its close distance and sufficient inventory, the chain pharmacy needs to transfer across stores and the delivery time is about 4 hours, and the hospital pharmacy may require 24 hours due to processes such as prescription review. At the same time, the number of all channels where the drug can be purchased should be counted; Third is the difficulty of emergency allocation, that is, the difficulty of obtaining the drug in an emergency, mainly examining factors such as whether the pharmacy has the ability to provide urgent delivery services (such as whether there are dedicated delivery personnel and 24-hour service), whether it supports cross-regional dispensing (such as drug dispensing between different stores or hospitals), and whether it supports remote issuance of electronic prescriptions (such as the convenience of online consultation and prescription issuance).

[0040] S105. Determine the remaining drug consumption duration of the target drug based on the target consumption rate, historical drug consumption data, and drug data; Determine the remaining quantity of the target drug based on the drug data; construct a consumption time function of the target drug according to the target consumption rate and the remaining quantity, and calculate the target consumption duration of the target drug; calculate the coefficient of uncertainty in the patient's medication behavior based on the historical drug consumption data; perform a weighted calculation on the coefficient of uncertainty in the medication behavior and the target consumption duration to obtain the remaining drug consumption duration of the target drug.

[0041] The system uses the sensors built into the intelligent medicine box to monitor the remaining situation of the drugs in real time, and obtains the actual remaining quantity of the target drug through the drug data. For example: Monitor the drug data in real time. A certain antihypertensive drug uses devices such as the weight sensor or infrared sensor of the intelligent medicine box to obtain that there are still 30 tablets remaining in the current medicine box.

[0042] Based on the target consumption rate and the accurate remaining quantity obtained from the previous calculations, the system constructs a drug consumption time function and calculates the target consumption duration. The specific implementation process is as follows: First, the system establishes a consumption time function T = Q / R, where T represents the theoretical consumption duration, Q is the remaining quantity, and R is the target consumption rate; then, substitute the actual parameters into the consumption time function for calculation; finally, consider the characteristics of the medication time distribution to correct the theoretical value. For example, for this hypertensive patient, it is known that there are 32 tablets of amlodipine besylate remaining, and the target consumption rate at the current stage is 2.4 tablets per day (considering a 20% increase in dosage due to high blood pressure). Substituting into the consumption time function, we get T = 32 ÷ 2.4 ≈ 13.3 days. At the same time, considering the patient's medication time distribution (7:00 ± 0.5 hours in the morning, 19:00 ± 0.8 hours in the evening) and the required medication interval (12 hours), the system determines that the target consumption duration is 13.3 days.

[0043] Since the patient's medication behavior is usually affected by various factors, such as changes in health status, fluctuations in medication habits, external environmental factors (such as forgetting or changes in daily routines), etc., relying solely on a fixed consumption rate to calculate the drug consumption duration may lead to deviations. To solve this problem, the system needs to calculate the coefficient of uncertainty of the patient's medication behavior (U). The calculation formula for the coefficient of uncertainty of the patient's medication behavior (U) is: U = ω t ·U t +ω d ·U d +ω c ·U c , where U is the coefficient of uncertainty of the patient's medication behavior; U t is the fluctuation of the medication interval, which measures the stability of the patient's medication time each time, where σ t is the standard deviation of the patient's medication intervals over a past period (such as 30 days) (unit: hours), is the average medication interval over a past period (such as 30 days) (unit: hours); U d is the change in the single-dose medication, which measures whether the patient often adjusts the medication dose, σ d is the standard deviation of the single-dose medication (unit: tablets), is the average single-dose medication over a past period (such as 30 days) (unit: tablets); U c is the medication compliance, which measures whether the patient has missed or taken the medication in advance. U c = 1 - C, where C is the medication compliance index, representing the proportion of the patient taking the medication on time. For example, if the patient has taken the medication on time 85% of the time in the past 30 days, then C = 0.85; ω t 、ω d, ω c They are the weights of the dosing interval volatility, single-dose change, and medication compliance respectively, indicating their influence on the overall uncertainty coefficient.

[0044] After obtaining the medication behavior uncertainty coefficient, the system uses a weighted correction method to combine the target consumption duration with the medication behavior uncertainty coefficient to calculate the remaining medication consumption duration. The calculation formula is as follows: Remaining medication consumption duration = Target consumption duration × (1 - Medication behavior uncertainty coefficient). Suppose a patient is taking antihypertensive drugs, and the smart medicine box detects that there are 30 tablets remaining. The system calculates based on the patient's health status and medication records: The target consumption rate is 1.2 tablets / 11 hours; the target consumption duration is 11.5 days; the medication behavior uncertainty coefficient is 0.1525; the calculated remaining medication consumption duration is 9.7 days.

[0045] S106. Determine the replenishment time threshold of the target drug based on the target consumption rate and acquisition difficulty characteristics; Specifically, construct a drug availability evaluation model based on the drug acquisition priority, delivery time, and number of alternative channels in the acquisition difficulty characteristics to calculate the acquisition risk compensation coefficient; calculate the first replenishment time threshold based on the remaining medication consumption duration and the acquisition risk compensation coefficient; calculate the emergency coefficient based on the emergency deployment difficulty in the acquisition difficulty characteristics, and determine the second replenishment time threshold based on the first replenishment time threshold and the emergency coefficient.

[0046] After determining the acquisition difficulty characteristics of the target drug, the system needs to construct a drug availability evaluation model to quantify the difficulty of the patient in obtaining the drug and calculate the acquisition risk compensation coefficient for dynamically adjusting the replenishment time threshold. This evaluation model scores based on the drug acquisition priority, delivery time, and number of alternative channels of the acquisition difficulty characteristics in step S104, and comprehensively evaluates the drug availability using a weighted calculation method. First, the drug acquisition priority reflects the importance and irreplaceability of the drug. Second, the delivery time is determined by analyzing historical drug purchase data and pharmacy delivery capabilities. For example, community hospital pharmacies can usually be delivered within 2 hours due to their close distance and sufficient inventory, while chain pharmacies may take 4 hours, and hospital pharmacies may take 24 hours or even longer due to the need for prescription review. The number of alternative channels measures whether there are multiple ways to purchase drugs. For example, if a certain drug can only be obtained in a specific hospital, the acquisition risk is high, while if it can be purchased through multiple channels such as online pharmacies, chain drugstores, and community hospitals, the acquisition risk is low. Finally, the system uses the following calculation formula to calculate the acquisition risk compensation coefficient: R 补偿 = α(1 - S 获取优先级 ) + β(1 - S 配送时效 ) + γ(1 - S 备选渠道 ), where R 补偿To obtain the risk compensation coefficient; S 获取优先级 To obtain the drug availability score for the priority dimension, which is used to measure the importance and irreplaceability of drugs. The lower the value, the more difficult it is to obtain the drug. For example, emergency drugs (such as nitroglycerin and quick-acting heart-saving pills) have a lower acquisition priority (0.1 - 0.3) due to their direct impact on vital signs; therapeutic drugs (such as antihypertensive drugs and antidiabetic drugs) come next (0.4 - 0.6); auxiliary and health care drugs (such as vitamins and calcium tablets) have a higher acquisition priority (0.7 - 1.0); S 配送时效 To obtain the drug availability score for the delivery timeliness dimension, which is used to measure the delivery speed of drugs. The higher the value, the shorter the delivery time and the easier it is to obtain. For example, the pharmacy in community hospitals has a short delivery time (score 0.8 - 1.0) due to sufficient inventory; chain pharmacies need to allocate drugs across stores and have a longer delivery time (score 0.5 - 0.7); hospital pharmacies have the longest delivery time (score 0.1 - 0.4) due to processes such as prescription review; S 备选渠道 To obtain the drug availability score for the number of alternative channels dimension, which is used to measure the number of alternative channels for patients to purchase drugs. The higher the value, the more choices for drug purchase and the easier it is to obtain. For example, if a certain drug can be purchased through multiple channels such as online pharmacies, offline drugstores, and hospitals, the score is relatively high (0.8 - 1.0); if it can only be purchased at a designated hospital, the score is relatively low (0.1 - 0.3).

[0047] After calculating the risk compensation coefficient, the system needs to combine the remaining drug consumption duration of the patient to calculate the first replenishment time threshold, that is, the time point when the system first reminds the patient to replenish the drug. The remaining drug consumption duration refers to the time that the patient's drug inventory can last according to the current target consumption rate. For example, if a patient takes 2 pills per day and the current inventory is 20 pills, the remaining drug consumption duration is 10 days. To ensure that the patient purchases drugs in time before the drugs are about to run out, the system needs to adjust the replenishment time in advance according to the risk compensation coefficient. The calculation formula is as follows: T1 = T 剩 -(T 剩 ×R 补偿 ), where T1 is the first replenishment time threshold and T 剩 is the remaining drug consumption duration. For example, if the remaining drug consumption duration of a certain drug is 10 days and the risk compensation coefficient is 0.4, the first replenishment time threshold for this drug is: T1 = 10 - (10 × 0.4) = 6 days, that is, the system will first remind the patient to replenish the drug when the patient's inventory is still 6 days left. If the acquisition difficulty of this drug is high (such as only available for purchase at a specific hospital) and the risk compensation coefficient is high, the first replenishment time threshold will be earlier to ensure that the patient has enough time to purchase drugs.

[0048] Considering that the patient may not purchase medicine in time after the first supplementary reminder, the system also needs to further calculate the second supplementary time threshold, that is, when the patient does not respond to the first reminder, the system issues a more urgent reminder to replenish medicine. The determination of this time threshold depends on the difficulty of emergency allocation, that is, the ease of obtaining the medicine in an emergency, including factors such as whether there is an express delivery service, whether cross-regional dispensing is supported, and whether remote electronic prescription issuance is supported. For example, if a certain medicine supports 24-hour express delivery and the emergency allocation difficulty is low, the emergency coefficient is small; if the medicine can only be obtained by prescribing at the hospital and the hospital does not provide online consultation or electronic prescription, the emergency allocation difficulty is high and the emergency coefficient is large. The calculation formula for the system emergency coefficient E is as follows: E = 1 - S 紧急调配难度 , where S 紧急调配难度 reflects the accessibility in an emergency, and the scoring range is 0 - 1. The lower the value, the more difficult it is to obtain in an emergency. Then, based on the first supplementary time threshold T1 and the emergency coefficient E, calculate the second supplementary time threshold T2: T2 = T1 - (T1 × E). For example, if the first supplementary time threshold for a certain medicine is 6 days and the emergency coefficient is 0.5, then: T2 = 6 - (6 × 0.5) = 3 days. That is, the system will issue a second supplementary reminder when there are still 3 days of medicine left in the patient's inventory. If the medicine is extremely difficult to obtain in an emergency (such as only being able to prescribe offline at the hospital and there is no express delivery service), the second supplementary time threshold will be earlier to ensure that the patient has enough time to cope with the delay in purchasing medicine.

[0049] S107. When the remaining medicine consumption duration and the supplementary time threshold meet the preset reminder requirements, generate a reminder message and send the reminder message to the reminder message receiving end that meets the preset information receiving requirements. The reminder message receiving end includes the patient end and the family member end.

[0050] When the remaining medicine consumption duration is less than the first supplementary time threshold and greater than the second supplementary time threshold, generate a first reminder message and send the first reminder message to the patient end; within the preset waiting time length after sending the first reminder message, determine the medicine replenishment status of the intelligent medicine box according to the medicine data. The preset waiting time length is greater than zero and less than the difference between the first supplementary time threshold and the second supplementary time threshold; if the medicine replenishment status, the remaining medicine consumption duration, and the second supplementary time threshold meet the preset reminder requirements, generate a second reminder message and send the second reminder message to the patient end and the family member end.

[0051] When the system detects that the remaining drug consumption duration is less than the first replenishment time threshold and greater than the second replenishment time threshold, it means that the patient's drug inventory is decreasing and approaching the critical point for the first drug replenishment. At this time, the system will generate a first reminder message to remind the patient to replenish the drugs as soon as possible and send this reminder message to the patient terminal. The reminder methods can include mobile push notifications, text messages, WeChat / Alipay notifications, smart speaker voice reminders, etc., to ensure that the patient can receive the drug purchase reminder in a timely manner. The reminder content usually includes the drug name, remaining days, drug purchase suggestions, recommended drug purchase channels, and provides an online drug purchase link or information about nearby pharmacies to improve the convenience of drug purchase. For example, assume that a patient takes 2 antihypertensive drugs per day, the current inventory is 8 tablets remaining, the first replenishment time threshold calculated by the system is 5 days, and the second replenishment time threshold is 2 days. Then when the inventory is left with 4 days (less than 5 days but greater than 2 days), the system generates the first reminder message, which can include the following content: [Drug Purchase Reminder] Dear [Patient Name], your [Drug Name] is expected to run out in [Remaining Drug Consumption Duration] days. To ensure your continuous medication, please replenish the drugs as soon as possible.

[0052] Suggested drug purchase methods: Online drug purchase: [Drug Purchase Platform Name]([Online Drug Purchase Link]), expected to be delivered in [Delivery Time Limit] days; Nearby pharmacy: [Recommended Pharmacy Name], Address: [Pharmacy Address], Phone: [Pharmacy Phone]; Hospital pharmacy: [Designated Hospital Name], please go to purchase drugs with a prescription.

[0053] After purchasing the drugs, please put the drugs into the smart medicine box, and the system will automatically update the inventory status.

[0054] If the patient does not put the newly purchased drugs into the smart medicine box, the system will continue to track the drug purchase situation within the preset waiting time and enter the next monitoring stage.

[0055] After sending the first reminder message, the system will enter the preset waiting time to monitor whether the patient has replenished the drugs and determine the drug replenishment status by obtaining drug data through the smart medicine box sensor. The drug replenishment status includes replenished, not replenished, and purchased but not replenished. The length of the preset waiting time should be greater than 0 and less than the difference between the first replenishment time threshold and the second replenishment time threshold to ensure that the patient has enough time to purchase drugs and avoid ineffective or overly frequent reminders. For example, if the first replenishment time threshold is 5 days and the second replenishment time threshold is 2 days, the preset waiting time can be set to 2 days. That is, within 2 days after the first reminder is sent, the system continuously detects the drug inventory in the medicine box to determine whether the patient has completed the drug replenishment.

[0056] During this period, the system will determine whether new drugs have been added to the smart medicine box through the weight sensor or the barcode scanning and recognition function of the smart medicine box. If an increase in the target drug quantity is detected, the drug replenishment status is "replenished", indicating that the patient has replenished the drugs. In this case, the system will not trigger further reminders and will push a confirmation message to the patient side, such as:

Drug Purchase Confirmation

[0057] If the system does not detect drug replenishment within the preset waiting time and the remaining drug consumption duration of the patient is approaching the second replenishment time threshold, the system will proceed to the next step and trigger a more urgent reminder mechanism.

[0058] Before the preset waiting time ends, if the drug replenishment status remains unchanged and the remaining drug consumption duration is approaching or below the second replenishment time threshold, the drug replenishment status is "not replenished", indicating that the patient has not replenished the drugs yet and there is a high risk of running out of drugs. The system will generate a second reminder message and send this reminder message to both the patient side and the family member side simultaneously to ensure that the patient can purchase drugs as soon as possible and involve the family members to assist in purchasing drugs or confirm the drug purchase situation. The reminder methods can include text messages, phone voice notifications, WeChat / text message reminders for family members, and voice broadcasts can be added (such as playing reminder messages through smart speakers or smart bracelets) to ensure that the patient will not ignore the drug purchase reminder. The reminder content should emphasize the urgency of drug purchase, provide the fastest drug purchase methods, and notify the family members to intervene. For example:

Emergency Drug Purchase Reminder

[0059] Optimal drug purchase methods: Emergency delivery: [Drug Purchase Platform Name]([Express Delivery Link]), expected to be delivered within [Delivery Time Limit] hours; Nearest pharmacy: [Recommended Pharmacy Name], Address: [Pharmacy Address], Phone: [Pharmacy Phone]; Drug purchase at the hospital: [Designated Hospital Name], please go to purchase drugs as soon as possible.

[0060] Family member notification: This reminder has been sent to [Family Member Name] (Contact Information: [Family Member Phone]) simultaneously. Please ensure the progress of drug purchase.

[0061] If you have purchased drugs, please put them into the smart medicine box in time, and the system will automatically update the inventory status.

[0062] After the first reminder message is sent, the system will continuously monitor the patient's medication purchase situation within a preset waiting time. If the system detects that the patient has purchased medicine online (such as detecting the purchase order data) or infers that the patient has purchased medicine at a physical pharmacy based on historical medication purchase behavior (such as the patient has purchased the same medicine at a certain pharmacy multiple times), but the medicine has not been detected as replenished in the smart medicine box, then the system determines that the medicine replenishment status is purchased but not replenished, indicating that the patient may have purchased the medicine but not put it into the medicine box. The system will send a reminder to the patient's terminal to remind the patient to put the newly purchased medicine into the smart medicine box and provide operation guidelines, such as scanning the code for entry, voice confirmation, or automatic detection by the smart medicine box, to ensure the accurate update of inventory information. The reminder message can be sent in various ways, such as mobile phone push, text message, or voice broadcast by a smart speaker, for example:

Medication Storage Reminder

[0063] If you have any questions, you can contact your family member or doctor, or use the [Online Medication Purchase Link] to purchase medicine.

[0064] If the patient still does not put the new medicine into the smart medicine box, the system can further send reminders, such as: Notification by family member: If the family member does not reply to the text message, an automatic dial reminder will be triggered to notify the family member to confirm the medication purchase situation. Notification by doctor: For high-risk patients (such as patients with chronic diseases), the system can choose to notify the patient's attending doctor or the health management platform to ensure that the patient receives timely medication purchase assistance.

[0065] Please refer to Figure 2 for the structural schematic diagram of an intelligent reminder system for prescribing medicine to patients provided in the embodiment of this application. An intelligent reminder system 200 for prescribing medicine to patients specifically includes: An acquisition module 201, configured to acquire the patient's electronic medical record, historical medicine consumption data, health status data, and medicine data in the smart medicine box; An analysis module 202, configured to analyze the electronic medical record, historical medicine consumption data, and health status data to establish a medicine consumption feature model; A calculation module 203, configured to calculate the target consumption rate of the target medicine in the smart medicine box according to the medicine data, health status data, and medicine consumption feature model, where the target medicine is any medicine in the smart medicine box; The first determination module 204 is configured to determine the acquisition difficulty characteristics of the target drug according to the drug data and the preset drug database. The second determination module 205 is configured to determine the remaining drug consumption duration of the target drug based on the target consumption rate, the historical drug consumption data, and the drug data. The third determination module 206 is configured to determine the replenishment time threshold of the target drug based on the target consumption rate and the acquisition difficulty characteristics; the reminder module 207 is configured to generate a reminder message when the remaining drug consumption duration and the replenishment time threshold meet the preset reminder requirements, and send the reminder message to a reminder message receiving end that meets the preset message receiving requirements, and the reminder message receiving end includes a patient end and a family member end.

[0066] Optionally, the analysis module 202 is specifically configured to: Analyze the electronic medical record to determine the standard drug usage data of the target drug, where the standard drug usage data includes the standard single drug usage quantity, the standard drug usage frequency, and the standard drug usage interval time; based on the historical drug consumption data, determine the historical drug usage data of the target drug, where the historical drug usage data includes the historical single drug usage quantity, the historical drug usage frequency, and the historical drug usage interval time; calculate the difference value between the historical drug usage data and the standard drug usage data in each preset historical time period to obtain a target consumption deviation set, and the target consumption deviation set includes a single drug usage quantity deviation value, a drug usage frequency deviation value, and a drug usage interval time deviation value; according to the preset health status evaluation rule, analyze the target health status data of each preset historical time period to obtain the historical health status type corresponding to each preset historical time period; perform time matching on the target consumption deviation set and the historical health status type to obtain the consumption deviation characteristics of the target drug corresponding to each historical health status type; establish a drug consumption characteristic model based on the standard drug usage data and the consumption deviation characteristics.

[0067] Optionally, the calculation module 203 is specifically configured to: Determine the current health status type of the patient based on the health status data according to the preset health status evaluation rule; obtain the consumption deviation characteristics of the target drug corresponding to the current health status type from the drug consumption characteristic model; construct a consumption time series of the target drug based on the drug data, and use the sliding time window method to extract the consumption trend characteristics of the target drug; perform feature fusion on the consumption deviation characteristics and the consumption trend characteristics to obtain the consumption prediction parameters of the target drug; determine the target consumption rate of the target drug according to the consumption prediction parameters.

[0068] Optionally, the second determination module 205 is specifically configured to: Determine the remaining quantity of the target drug based on drug data; construct a consumption time function of the target drug according to the target consumption rate and the remaining quantity, and calculate the target consumption duration of the target drug; calculate the medication behavior uncertainty coefficient of the patient based on historical drug consumption data; perform weighted calculation on the medication behavior uncertainty coefficient and the target consumption duration to obtain the remaining drug consumption duration of the target drug.

[0069] Optionally, the third determination module 206 is specifically configured to: Construct a drug availability evaluation model based on the drug acquisition priority, distribution timeliness, and the number of alternative channels in the acquisition difficulty characteristics, and calculate the acquisition risk compensation coefficient; calculate the first replenishment time threshold based on the remaining drug consumption duration and the acquisition risk compensation coefficient; calculate the emergency coefficient based on the emergency deployment difficulty in the acquisition difficulty characteristics, and determine the second replenishment time threshold based on the first replenishment time threshold and the emergency coefficient.

[0070] Optionally, the reminder module 207 is specifically configured to: When the remaining drug consumption duration is less than the first replenishment time threshold and greater than the second replenishment time threshold, generate a first reminder message and send the first reminder message to the patient terminal; within the preset waiting time length after sending the first reminder message, determine the drug replenishment status of the smart medicine box according to the drug data, and the preset waiting time length is greater than zero and less than the difference between the first replenishment time threshold and the second replenishment time threshold; if the drug replenishment status, the remaining drug consumption duration, and the second replenishment time threshold meet the preset reminder requirements, generate a second reminder message and send the second reminder message to the patient terminal and the family member terminal.

[0071] Optionally, the reminder module 207 is further specifically configured to: When the drug replenishment status is not replenished and the remaining drug consumption duration is less than or equal to the second replenishment time threshold, generate a second reminder message.

[0072] It should be noted that: when the device provided in the above embodiment realizes its functions, only the above-mentioned division of each functional module is used for illustration. In practical applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be seen in the method embodiment, which will not be elaborated here.

[0073] This embodiment also discloses an electronic device. Refer to Figure 3 , the electronic device may include: at least one processor 301, at least one communication bus 302, a user interface 303, a network interface 304, and at least one memory 305.

[0074] Among them, the communication bus 302 is used to realize the connection and communication between these components.

[0075] Among them, the user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may further include a standard wired interface and a wireless interface.

[0076] Among them, the network interface 304 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0077] Among them, the processor 301 may include one or more processing cores. The processor 301 connects various parts within the entire server by using various interfaces and circuits. By running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and by calling the data stored in the memory 305, it executes various functions of the server and processes data. Optionally, the processor 301 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 301 may integrate one or several combinations of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for the rendering and drawing of the content to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 301 and may be implemented separately by a single chip.

[0078] Among them, the memory 305 may include a Random Access Memory (RAM), or may also include a Read-Only Memory. Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above method embodiments, etc.; the data storage area can store the data involved in the above method embodiments. Optionally, the memory 305 may also be at least one storage device located far from the aforementioned processor 301. As Figure 3 shown, in the memory 305 as a computer storage medium, there may be included an operating system, a network communication module, a user interface module, and an application program of an intelligent reminder method for prescribing medicine for patients.

[0079] In Figure 3 the electronic device shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; while the processor 301 can be used to call the application program of an intelligent reminder method for prescribing medicine for patients stored in the memory 305. When executed by one or more processors 301, the electronic device executes the method of one or more of the above embodiments.

[0080] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0081] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0082] In several embodiments provided in this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling, direct coupling, or communication connection between each other can be through some service interfaces. The indirect coupling or communication connection of devices or units can be in electrical or other forms.

[0083] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0084] In addition, each functional unit in various embodiments of this application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0085] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory 305 and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of this application. And the aforementioned memory 305 includes: various media such as USB flash drives, mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0086] The above are only exemplary embodiments of the present disclosure and should not be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. Those skilled in the art will easily think of other implementation schemes of the present disclosure after considering the disclosure of the specification. This application aims to cover any variations, uses, or adaptive changes of the present disclosure, and these variations, uses, or adaptive changes follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. An intelligent reminder method for prescribing medicine to patients, characterized in that, Applied to an intelligent medicine box, the method includes: Obtaining the electronic medical record, historical medicine consumption data, health status data of a patient, and medicine data in the intelligent medicine box; Analyzing the electronic medical record, the historical medicine consumption data, and the health status data to establish a medicine consumption feature model; Calculating the target consumption rate of a target medicine in the intelligent medicine box according to the medicine data, the health status data, and the medicine consumption feature model, where the target medicine is any medicine in the intelligent medicine box; Determining the acquisition difficulty feature of the target medicine according to the medicine data and a preset medicine database; Determining the remaining medicine consumption duration of the target medicine based on the target consumption rate, the historical medicine consumption data, and the medicine data; Determining the replenishment time threshold of the target medicine based on the target consumption rate and the acquisition difficulty feature; When the remaining medicine consumption duration and the replenishment time threshold meet the preset reminder requirements, generating a reminder message and sending the reminder message to a reminder message receiving end that meets the preset information receiving requirements, where the reminder message receiving end includes a patient end and a family member end.

2. The method according to claim 1, wherein The analyzing the electronic medical record, the historical medicine consumption data, and the health status data to establish a medicine consumption feature model specifically includes: Analyzing the electronic medical record to determine the standard medicine usage data of the target medicine, where the standard medicine usage data includes the standard single-dose medicine quantity, the standard medicine usage frequency, and the standard medicine usage interval time; Based on the historical medicine consumption data, determining the historical medicine usage data of the target medicine, where the historical medicine usage data includes the historical single-dose medicine quantity, the historical medicine usage frequency, and the historical medicine usage interval time; Calculating the difference value between the historical medicine usage data and the standard medicine usage data in each preset historical time period to obtain a target consumption deviation set, where the target consumption deviation set includes a single-dose medicine quantity deviation value, a medicine usage frequency deviation value, and a medicine usage interval time deviation value; According to a preset health status evaluation rule, analyzing the target health status data of each preset historical time period to obtain a historical health status type corresponding to each preset historical time period; Performing time matching on the target consumption deviation set and the historical health status type to obtain the consumption deviation feature of the target medicine corresponding to each historical health status type; Establishing the medicine consumption feature model based on the standard medicine usage data and the consumption deviation feature.

3. The method according to claim 1, characterized in that, The calculating the target consumption rate of a target medicine in the intelligent medicine box according to the medicine data, the health status data, and the medicine consumption feature model specifically includes: Based on a preset health status evaluation rule, determining the current health status type of the patient according to the health status data; Obtaining the consumption deviation feature of the target medicine corresponding to the current health status type from the medicine consumption feature model; Based on the medicine data, constructing a consumption time series of the target medicine, and adopting a sliding time window method to extract the consumption trend feature of the target medicine; Performing feature fusion on the consumption deviation feature and the consumption trend feature to obtain the consumption prediction parameter of the target medicine; Determine the target consumption rate of the target drug according to the consumption prediction parameter.

4. The method according to claim 1, characterized in that, Determining the remaining drug consumption duration of the target drug based on the target consumption rate, historical drug consumption data, and the drug data specifically includes: Determine the remaining quantity of the target drug based on the drug data; Construct a consumption time function of the target drug according to the target consumption rate and the remaining quantity, and calculate the target consumption duration of the target drug; Calculate the medication behavior uncertainty coefficient of the patient based on the historical drug consumption data; Perform a weighted calculation on the medication behavior uncertainty coefficient and the target consumption duration to obtain the remaining drug consumption duration of the target drug.

5. The method according to claim 1, wherein The replenishment time threshold includes a first replenishment time threshold and a second replenishment time threshold, and the first replenishment time threshold is greater than the second replenishment time threshold. Determining the replenishment time threshold of the target drug based on the target consumption rate and the acquisition difficulty feature specifically includes: Construct a drug availability evaluation model based on the drug acquisition priority, delivery timeliness, and the number of alternative channels in the acquisition difficulty feature, and calculate the acquisition risk compensation coefficient; Calculate the first replenishment time threshold based on the remaining drug consumption duration and the acquisition risk compensation coefficient; Calculate the emergency coefficient based on the emergency deployment difficulty in the acquisition difficulty feature, and determine the second replenishment time threshold based on the first replenishment time threshold and the emergency coefficient.

6. The method according to claim 5, characterized in that When the remaining drug consumption duration and the replenishment time threshold meet the preset reminder requirements, generate a reminder message and send the reminder message to a reminder message receiving end that meets the preset information receiving requirements, specifically including: When the remaining drug consumption duration is less than the first replenishment time threshold and greater than the second replenishment time threshold, generate a first reminder message and send the first reminder message to the patient terminal; Within a preset waiting time length after sending the first reminder message, determine the drug replenishment status of the intelligent medicine box according to the drug data, and the preset waiting time length is greater than zero and less than the difference between the first replenishment time threshold and the second replenishment time threshold; If the drug replenishment status, the remaining drug consumption duration, and the second replenishment time threshold meet the preset reminder requirements, generate a second reminder message and send the second reminder message to the patient terminal and the family member terminal.

7. The method according to claim 6, wherein If the drug replenishment status, the remaining drug consumption duration, and the second replenishment time threshold meet the preset reminder requirements, then generate a second reminder message, specifically including: When the drug replenishment status is not replenished and the remaining drug consumption duration is less than or equal to the second replenishment time threshold, generate the second reminder message.

8. An intelligent reminder system for prescribing medicine to patients, characterized in that, Including: An acquisition module, configured to acquire the electronic medical record, historical drug consumption data, health status data of the patient, and drug data in the intelligent medicine box; An analysis module, configured to analyze the electronic medical record, the historical drug consumption data, and the health status data to establish a drug consumption feature model; A calculation module, configured to calculate a target consumption rate of a target drug in the intelligent medicine box according to the drug data, the health status data, and the drug consumption characteristic model, where the target drug is any drug in the intelligent medicine box; A first determination module, configured to determine an acquisition difficulty characteristic of the target drug according to the drug data and a preset drug database; A second determination module, configured to determine a remaining drug consumption duration of the target drug based on the target consumption rate, the historical drug consumption data, and the drug data; A third determination module, configured to determine a replenishment time threshold of the target drug based on the target consumption rate and the acquisition difficulty characteristic; A reminder module, configured to generate a reminder message when the remaining drug consumption duration and the replenishment time threshold meet a preset reminder requirement, and send the reminder message to a reminder message receiving end that meets the preset information receiving requirement, where the reminder message receiving end includes a patient end and a family member end.

9. An electronic device, characterized in that, including: One or more processors and a memory; The memory is coupled to the one or more processors, and the memory is configured to store computer program code, where the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the electronic device to execute the method according to any one of claims 1-7.

10. A computer-readable storage medium, comprising instructions, characterized in that, When the instructions run on the electronic device, the electronic device is caused to execute the method according to any one of claims 1-7.

Images