1015 results about "Medication use" patented technology

The invention discloses a chronic disease patient personalized diet and exercise guidance system and method, and relates to the technical field of medical health information, and the system comprises a data sensing module which continuously collects the dynamic physiological data, behavior data and environment variable data of a patient through an intelligent sensing device, the dynamic physiological data comprises a heart rate time sequence, a step number time sequence and a blood glucose concentration time sequence monitored by the wearable device, and the behavior data comprises a medication operation record with a timestamp and a patient's daily symptom self-grading number. According to the personalized diet and exercise guidance system and method for the chronic disease patient, the time synchronization precision of multi-source data is effectively improved, the accuracy of medication compliance monitoring and physiological index correlation analysis is ensured, and by establishing the dynamic correlation model of the environment temperature and the human body metabolic rate, the accuracy of medication compliance monitoring and physiological index correlation analysis is improved. The timeliness and safety of clinical intervention are improved, and powerful support is provided for health management of chronic disease patients.

The invention relates to the technical field of medical data processing and prediction, and discloses a chemotherapy adverse reaction prediction and intervention system based on big data. The system integrates an unstructured disease course text and structured inspection data of a patient, generates a time-series symptom event, and performs time window alignment and fusion on the time-series symptom event, a medication record and a physical sign monitoring stream to form a multi-dimensional time-series data block. The system is combined with an external medical knowledge base to construct a dynamic association network among symptoms, medicines and physiological indexes, and dynamically calculates the confidence coefficient of an adverse reaction mode according to real-time data. By using a predictive model of the timing attention mechanism, the system can output a continuous curve of patient risk over time. The system automatically matches and generates a personalized intervention instruction sequence containing specific measures and execution time windows according to key time points and modes when the risk curve exceeds a threshold value. According to the invention, dynamic and advanced early warning and accurate intervention of adverse reaction risks of chemotherapy are realized.

Systems and Methods are disclosed for detecting acute coronary syndrome (ACS) events, arrythmias, heart rate abnormalities, medication problems such as non-compliance or ineffective amount or type of medication, and demand / supply related cardiac ischemia. The system may have both implanted and external components that communicate with a Physicians's programmer, and smart-devices for monitoring and alerting to detected medically relevant events or states. At least one processor provides event detection using statistical threshold criteria calculated upon at least a portion of a patient's data / distributions and set for a patient or based upon what a doctor determines as abnormal for a patient. Cardiovascular condition is tracked using histogram, trend, and summary information related to heart rate and / or cardiac features such as S-T segment measures of heartbeats. Heartbeats with elevated rates, and below a “high” range, provide medically relevant detections including medication non-compliance. Novel methods of power management and patient monitoring are disclosed.

The invention relates to the technical field of chronic disease information management, in particular to a chronic disease information management method which comprises the following steps: S1, acquiring physiological index data, medication record data and behavioral habit data of a patient through a multi-source data acquisition module; s2, performing feature extraction on the multi-source data by using a data analysis module to generate multi-dimensional health assessment parameters; and S3, dynamically comparing the health assessment parameters with a preset assessment value through a risk early warning module, triggering hierarchical early warning when an abnormal parameter combination is detected, realizing multi-modal data deep mining by using an intelligent analysis module, performing association analysis on wearable device sensor data, an electronic medical record and a medication compliance record, and determining whether the health assessment parameters are abnormal or not. An individualized medication portrait of the chronic disease patient is constructed, parameters such as gene detection and metabolic indexes are combined, through medicine-disease conflict detection and dose self-adaptive calculation, an accurate medication adjustment strategy and a chronic disease patient health behavior guidance scheme are generated, and individual differences are fully reflected.

A system and method for generating patient care instructions based on real-time sensor and medical data. The method includes receiving time-stamped sensor data from a sensor network comprising motion, occupancy, and environmental sensors, and receiving medical data associated with a patient, including medical conditions, treatment history, medication data, and biometric data. The sensor data is enriched with room-specific information, and activity pattern data is generated in real time using a pattern recognition model. The activity pattern data includes mobility, sleep patterns, medication adherence, statistical measures, temporal patterns, and correlations with medical data. Anomalies indicating potential health risks are detected by comparing current activity patterns with baseline data. A prediction model, trained on historical patient data, assesses the patient's health and generates care instructions accordingly. The care instructions are securely delivered to patient devices, caregiver applications, or automated medication dispensing systems, enabling timely interventions and continuous patient monitoring.

The invention provides a medication guidance generation system, and relates to the technical field of medical informatization. Comprising a knowledge base construction module used for constructing a medication guidance knowledge base; the graph term construction module is used for constructing a knowledge graph and a standard term set according to the medication guidance knowledge base; the index construction module is used for splitting the medication guidance knowledge base and constructing a vector index and a full-text index; the personal information processing module is used for acquiring personal information of a patient and preprocessing the personal information to obtain preprocessed personal information; the mixed detection module is used for performing retrieval by utilizing a knowledge graph, a vector index and a full-text index according to the preprocessed personal information to obtain a retrieval result set and obtain an intersection result according to the retrieval result set; and the generation module is used for generating medication guidance corresponding to the target patient according to the intersection result. The problems that traditional medication guidance mainly depends on experience and professional knowledge of medical staff, and is low in efficiency, prone to errors and difficult to personalize are solved.

The invention discloses an automatic medicine vending machine based on AI inquiry. The automatic medicine vending machine comprises a machine body, an intelligent interaction system, an AI inquiry system, a medicine storage bin, a control system, a payment system and a printing device. A constant-temperature and constant-humidity system and a disinfection and air purification module are arranged in the machine body. The intelligent interaction system collects symptom information in a multi-mode mode, and the AI inquiry system achieves symptom analysis, intelligent triage and personalized medication recommendation based on a medical knowledge graph and a natural language processing technology. The medicine storage bin carries a three-dimensional matrix type medicine cabinet and an intelligent inventory system, and intelligent replenishment is carried out through an LSTM algorithm. And the control system adopts a controller and triple verification to realize high-precision medicine discharging operation. The payment system supports multiple settlement modes and block chain evidence storage data. And the printing device outputs the medication guide sheet and the anti-counterfeit label. According to the invention, AI and automation technologies are deeply integrated, the service of less than or equal to 3 minutes in the whole process of inquiry-payment-medicine dispensing is realized, and the safety and convenience of medicine use are improved.

The invention discloses an internal medicine drug curative effect evaluation method based on big data analysis of an electronic health record, and the method comprises the steps: extracting basic health data, diagnosis and treatment time sequence data and drug intervention data from the electronic health record, and carrying out the time-space alignment to generate a dynamic feature set; subgroups are obtained based on disease typing standard hierarchical clustering, and historical data and real world data are fused through transfer learning to construct a subgroup curative effect reference matrix; collecting data after medication in real time, and generating an evaluation vector containing short-term physiological response, middle-term symptom improvement and long-term prognosis risk through deep learning; dynamically matching the evaluation vector with the reference matrix, and introducing an individual weight coefficient to correct deviation; taking the deviation correction value as input, constructing a self-adaptive evaluation model through reinforcement learning, and performing iterative optimization; and generating an individualized report containing the curative effect level, the medication suggestion and the risk early warning, and quantifying the curative effect level through a fuzzy comprehensive evaluation method. According to the method, individual differences are accurately captured, full-cycle dynamic evaluation is realized, and the curative effect evaluation accuracy and the clinical decision-making efficiency are improved.

The invention relates to the field of medical health and artificial intelligence, and discloses a cancer patient low-molecular heparin individualized dose dynamic optimization method based on reinforcement learning, and the method comprises the steps: S1, collecting multi-dimensional clinical data of a cancer patient, carrying out the preprocessing, carrying out the enhancement of the preprocessed data, and generating time sequence synthesis data; s2, based on the multi-dimensional clinical data and the time sequence synthesis data, constructing a reinforcement learning environment, including defining a state space, an action space and a reward function; s3, constructing an environment adaptive deep reinforcement learning EA-DRL model as a dose optimization model; performing model training and optimization in the reinforcement learning environment until convergence and obtaining an optimal dose decision strategy; and S4, inputting real-time dynamic clinical data of a patient to be decided into the trained dosage optimization model, and outputting individualized low molecular heparin LMWH administration dosage recommendation. Individualized precise administration is realized, and the treatment effect and the clinical medication safety are improved.

The invention relates to the technical field of medical information, and discloses a dosage regulation and control data storage method and system based on multi-modal diagnosis and treatment data, and the method comprises the steps: obtaining historical diagnosis and treatment data and historical dosage data of a patient; matching the diagnosis result data with health diagnosis result data in the health diagnosis and treatment data, and matching the wearable device data with health wearable device data in the health diagnosis and treatment data; determining whether to adjust the historical dose data to obtain the current dose, and outputting a judgment result needing to be adjusted; and obtaining the adjusted dose data, and storing the diagnosis result data, the diagnosis result similarity, the wearable device data, the wearable data similarity, the historical dose data and the adjusted dose data into a dose adjustment unit in a patient database. According to the invention, multi-modal diagnosis and treatment data can be integrated and applied to dose regulation and control, and a complete medication decision data chain is constructed.

The invention belongs to the technical field of artificial intelligence and medical information, and discloses a multi-round inquiry method and system based on a large language model and session state tracking. According to the method, extraction and synonym normalization are carried out for key medical elements, and high-confidence filling and conflict resolution are continuously completed in multiple rounds of conversations; and fusing the red flag symptom rule and model prediction, and carrying out hierarchical scoring and security constraint generation on individual risks. The information gain maximization serves as a target, and the next round of clarification problem is generated in a self-adaptive mode under the risk constraint; and through cooperation of a large language model and a knowledge base / knowledge graph, sorting and gate type calibration are carried out on candidate diseases and matched departments, and doctor-seeing suggestions, examination suggestions and medication precautions are generated. Finally, efficient understanding and multi-round reasoning of the unstructured symptom information are realized through joint supervision of the session state, the slot confidence and the risk hierarchy.

The invention relates to the technical field of hepatitis diagnosis and treatment management, and discloses a block chain-based hepatitis patient full-period management method. The method comprises the following steps: creating a patient identity chain in a block chain network, and storing patient registration data and initial diagnosis information; full-cycle diagnosis and treatment data of a patient are obtained and divided into clinical examination, iconography, medication records and life sign monitoring data. Performing multi-dimensional cleaning on the clinical examination data to generate a standardized data set; inputting the iconography data into a pre-trained hepatitis feature extraction model, and outputting a liver injury feature set; verifying the integrity of the medication record, and generating a non-tampering medication time sequence chain; comparing the life sign monitoring data with preset health reference parameters to generate a sign deviation coefficient set; according to the method, data safety and traceability are guaranteed through the block chain, diagnosis and treatment data quality is improved through multi-dimensional data processing, patient privacy is protected, and reliable support is provided for full-period management of hepatitis patients.

The invention discloses a low-water-solubility medicine crystal as well as a preparation method and application thereof. The compound Z pamoate crystal form I has large characteristic diffraction peaks at one or more positions with diffraction angles 2 theta of 9.9 + / -0.2 degrees, 10.7 + / -0.2 degrees, 12.1 + / -0.2 degrees, 14.9 + / -0.2 degrees, 17.3 + / -0.2 degrees, 19.4 + / -0.2 degrees, 20.7 + / -0.2 degrees and 23.1 + / -0.2 degrees. Compared with an amorphous compound Z pamoate, the crystal provided by the invention has the advantages of good stability, no crystal transformation phenomenon, no obvious increase of related substances and low solubility; the production process is simple, only water is used as a solvent in the whole process, and no organic solvent is used; when the long-acting slow-release anti-Parkinson medicine composition is prepared from the compound Z pamoate crystal form I, the medicine encapsulation efficiency is high, the burst release is low, the composition continuously releases the medicine in vivo for more than 2 weeks, the administration frequency of a patient can be reduced, and the medication compliance is improved.

The invention discloses a postoperative block analgesia curative effect evaluation system based on multi-modal data analysis, particularly relates to the technical field of medical information processing, and is used for solving the problem of poor analgesia evaluation standardization. An evaluation path of analgesia deviation quantification, state time sequence judgment and strategy generation is realized by constructing a structured comparison mechanism of an analgesia observation frame and an individualized analgesia baseline trajectory, pain, medication and activity deviations are dynamically calculated by fusing an anesthesia record, an analgesia pump log and clinical monitoring data, and an analgesia result is obtained. Typical states such as insufficient retardation effect are identified in combination with a time sequence inference model, a curative effect level and an early warning mark are automatically output, additional retardation, parameter adjustment and medicine remedy suggestions are generated according to a credibility level, and a state, disposal and result chain is constructed by continuously learning historical case data, so that the treatment efficiency is improved. The adaptive optimization of the baseline trajectory, the state threshold and the adjustment strategy is realized, and the individual matching performance, the response timeliness and the risk control capability of the analgesia strategy are improved.

The invention discloses a chronic disease management system for hospitals, which relates to the technical field of chronic disease management systems and comprises a patient file module, a risk assessment module, an intervention scheme module, a follow-up management module, a monitoring and early warning module and a decision support module. The patient archive module is used for collecting and sorting personal information and medical history information of patients by adopting an automatic data integration method to obtain a complete patient health archive; the risk assessment module is used for analyzing the health information in the patient health record by adopting an intelligent assessment algorithm to obtain a chronic disease risk assessment result; the intervention scheme module is used for formulating a personalized health intervention scheme according to the risk assessment result, and the personalized health intervention scheme comprises diet, exercise and medication suggestions; and the follow-up management module is used for executing the follow-up plan in the intervention scheme through multiple communication modes, tracking the rehabilitation condition of the patient, recording and feeding back, and generating a follow-up report.

The invention discloses an artificial intelligence-based whole doctor's advice reasonable medication auditing method and platform, and the method comprises the steps: integrating the structured data and unstructured text of a patient, carrying out the preprocessing according to a time sequence, determining a physiological safety range, and constructing a panoramic taboo doctor-seeing portrait; after deep information extraction and multi-source data fusion, a panoramic image of a patient is formed and is subjected to taboo comparison with medicine advised by a doctor, and a hard interception warning is triggered to avoid medicine conflict; further establishing a digital twinborn model, setting medical advices subjected to taboo comparison as a baseline scheme, simulating dynamic changes of physiological indexes within 72 hours, and assisting doctors to adjust drug doses in combination with clinical experience; finally, an individualized medication safety baseline is determined according to the simulation curve, and accurate simulation, dynamic early warning and scientific decision making are achieved. According to the scheme, the treatment safety and accuracy are remarkably improved, full-process intelligent medication auditing support is provided for complex patients, and the scheme has important clinical application value.

The invention discloses a spray bottle medicine recommendation method and system based on image processing, and relates to the technical field of image processing. According to the spray bottle medicine recommendation method based on image processing, wound image data are obtained, a wound image structure distinguishing index is analyzed, and then whether the wound image structure distinguishing index is lower than a preset threshold value or not is judged; inputting the wound image data into a pre-trained image enhancement model for enhancement analysis if the wound image data is lower than the preset threshold value, generating wound enhanced image data, and analyzing a wound image confidence index of the wound enhanced image data; and then, based on a pre-trained wound surface identification model, performing wound response index analysis on the enhanced image data, and synthesizing the wound response index with a wound surface image confidence index to obtain a wound condition perception intensity index. Therefore, fusion evaluation of identification accuracy and image credibility is realized, and the reliability of injury identification results and the scientificity of drug recommendation are improved.

The invention discloses a hospital pharmacy inventory intelligent management system and method, and belongs to the technical field of data management. Medicine basic information and multiple batches of inventory records are acquired; an application risk grade R is extracted based on the medicine application label; combining the remaining validity period, the stability parameter and the risk factor to construct a batch ex-warehouse priority scoring model P; generating a sorting ex-warehouse list and executing allocation and ex-warehouse operation; when it is monitored that the medicine is in time or the inventory is abnormal, dynamically adjusting the score and updating the sorting result; according to the invention, fine control of the drug delivery sequence can be realized, clinical availability of high-risk-purpose drugs is guaranteed preferentially, and inventory use efficiency and medication safety are improved at the same time.

The present invention relates to a use of THBS1 as a novel combination drug target that can overcome drug resistance of a targeted anticancer agent. A THBS1 inhibitor according to the present invention inhibits the drug resistance of a target anticancer agent and thus increases an anticancer effect when administered in combination with a target anticancer agent. Accordingly, the present invention can overcome resistance to a targeted anticancer agent and increase a treatment success rate of anticancer drugs for cancer patients, thereby suggesting new possibilities for treatment strategies using targeted anticancer drugs and contributing to the realization of precision medicine.

The invention relates to the technical field of artificial intelligence, in particular to a machine learning-based double-J tube indwelling membranous fungus infection risk medication decision support method, and aims to solve the problems of inaccurate double-J tube indwelling membranous fungus infection risk assessment and medication decision experience. According to the method, the machine learning model for predicting infection risks, pathogenic bacteria and drug curative effects is constructed by collecting multi-dimensional data and performing feature engineering, and personalized medication suggestions and visual decision support are provided in combination with a knowledge base and a rule engine. By adopting the scheme, accurate risk prediction can be realized, drug curative effect evaluation can be optimized, drug use reasonability and safety can be ensured, and clinical decision-making efficiency can be improved.

The invention provides application of active decapeptide in preparation of a medicine for preventing or treating cerebral apoplexy, and belongs to the technical field of biological medicine, the active decapeptide with the amino acid sequence as shown in SEQ ID NO.1 is applied to prevention or treatment of cerebral apoplexy for the first time, the active decapeptide can effectively inhibit formation of cerebral thrombosis of zebra fish with ischemic cerebral apoplexy, and the active decapeptide can be used for preventing or treating cerebral apoplexy. The brain blood flow supply is recovered; meanwhile, the active decapeptide can significantly reduce the hemorrhagic area and hemorrhagic rate of the zebra fish brain with hemorrhagic stroke, repair brain vascular injury and inhibit the occurrence and development of hemorrhagic stroke. In addition, the active decapeptide has small toxic and side effects, and is of great significance for improving the clinical curative effect of cerebral apoplexy and reducing the medication risk when being used for research and development of novel drugs for resisting cerebral apoplexy.

The invention provides a medication monitoring device and a medication monitoring method, relates to the field of medical apparatuses and instruments, and solves the technical problem that whether a capsule rotates to release medicines or not is difficult to monitor in a capsule type dry powder inhalation used in a transversely placed inhaler. The medication monitoring device comprises a shell and a photoelectric sensor, the photoelectric sensor is arranged on the shell, and a light path of the photoelectric sensor is configured to penetrate through the air inlet of the inhaler and the medicine bin, so that the rotation state of the capsule in the medicine bin is judged by detecting the change of the light path; the photoelectric sensor and the air inlet of the inhaler are arranged in a spaced mode in space so as to allow the inlet air flow to pass through. The rotation state of the capsule in the medicine bin is judged by detecting the change of the light path, whether the capsule rotates or not can be directly monitored, the problems that in the prior art, whether the capsule rotates or not cannot be known, and medicine taking failure caused by improper posture of the capsule cannot be judged are solved, effectiveness of medicine taking monitoring is ensured, and medicine taking guidance is facilitated.

An automated dispensing apparatus for providing food and medication to pets, includes a base supporting a feed assembly with an auger chute and motor-driven auger, and a storage bin positioned above to supply food. A medication feed assembly features a holder and a dispensing plate, controlled by an actuator, to deliver medication to a food bowl located below the dispensing ends. The apparatus is managed by a control circuit equipped with a CPU, memory, and wireless communication capabilities, allowing remote programming and adjustment of feeding and medication schedules via a remote electronic device, such as a smart phone. Additionally, a camera and lighting system are integrated for monitoring the dispensing process. The apparatus can be powered by a rechargeable battery, AC adapter, or solar cells, ensuring continuous operation. This system provides a reliable and automated solution for feeding and medicating pets, suitable for both indoor and outdoor use.

The invention relates to the field of artificial intelligence and digital medical treatment, discloses a multi-mode intelligent inquiry method and device, computer equipment and a storage medium, and can be applied to inquiry processing of families, drugstores and medical institutions. The method comprises the following steps: receiving biological characteristic data sent by a user terminal to verify a user identity, and obtaining a historical medical record of a user according to the user identity; receiving chief complaint symptoms and multi-modal physiological data, uploaded by the user terminal, of the user; fusing the chief complaint symptoms, the multi-modal physiological data and historical medical records, and constructing a dynamic knowledge graph; and generating a medication suggestion based on the dynamic knowledge graph and feeding back the medication suggestion to the user terminal. According to the method, the chief complaint symptom and the multi-modal physiological data are collected through the user terminal, intelligent monitoring of the user symptom is achieved, the dynamic knowledge graph is constructed by fusing the chief complaint symptom, the multi-modal physiological data and the historical medical records, efficient diagnosis decision is achieved, and the progress of medical digitization is promoted.

The invention discloses a construction method of a rivaroxaban population pharmacokinetic model and application of the rivaroxaban population pharmacokinetic model in an individualized medication prediction model, and relates to the field of biological information. According to the invention, a high performance liquid chromatography-tandem mass spectrometry method is adopted to determine the blood concentration of a rivaroxaban taking person, and a DNA sequencing method is adopted to determine the gene polymorphism of related metabolic enzymes CYP3A4 and CYP3A5 and transporters ABCB1 and ABCG2 of the rivaroxaban taking person; collecting data to establish a rivaroxaban group pharmacokinetic model, performing internal verification, and evaluating the stability and prediction performance of the model; in the final PPK model, the influence of the creatinine clearance rate, the ABCB1rs1045642 and the health condition on the clearance rate is the greatest; the experimental verification result shows that the model has good predictability and is accurate and reliable; the method can be applied to an individualized medication prediction model.

The invention provides a liver function data detection method and system for liver cancer high-risk groups, and relates to the field of health management. Context snapshots based on user IDs are created and updated in real time in a high-speed memory cache region, and a user diagnosis type, a medication state and a medication timestamp are combined to detect the liver function data of the liver cancer high-risk groups. According to the method and the device, the liver function data is subjected to differential judgment on the basis of the preset logic tree, so that the problems of misinformation and missing report caused by lack of context information in the prior art are effectively solved, the liver function data can be subjected to differential judgment accurately in real time according to the diagnosis type and the medication state of the user, misinformation and missing report are effectively avoided, and the user experience is improved. And the accuracy and the reliability of the alarm system are improved.

According to the application of the medicine composition containing the anti-CD20 antibody medicine conjugate to preparation of the medicine for treating the non-Hodgkin lymphoma, the medicine composition comprises the anti-CD20 antibody medicine conjugate and at least one therapeutic agent, and compared with an existing clinical first-line standard therapy, the medicine composition combined therapy has the advantages that the curative effect is better, the number of medicine types is smaller, the infusion time is shorter, and the curative effect is better. The safety risk is lower; and the economic burdenability is better.

The invention relates to the technical field of medical health monitoring, and discloses a urine volume detection system based on a strain gauge type sensor, which comprises a urine collection container, a strain gauge type sensor, an electromagnetic valve, a main controller and an infrared human body sensor, the upper port of the urine collecting container is used for receiving urine, and the lower port of the urine collecting container is connected with the strain gauge type sensor; the strain gauge type sensor is used for detecting the weight change of the urine collection container, the urine volume detection system based on the strain gauge type sensor and the intelligent closestool overcome the defect that a traditional closestool cannot measure and record the urine volume, convenience is brought to patients who do not want to use a urinal or a pedestal pan and old people with poor eyesight, and the intelligent closestool is convenient to use. A user can know the urine volume when using the closestool or pouring urine into the urinal into the closestool, use is convenient and sanitary, accurate urine volume data helps a doctor to formulate a more accurate medication scheme for a patient, and the patient is prevented from seeing a doctor repeatedly and the health risk caused by medicine problems.

The invention provides a medication guidance system and method based on knowledge graph and vector retrieval fusion, and relates to the technical field of artificial intelligence, and the medication guidance system comprises an application access layer, a service interface layer and a mixed retrieval engine layer; the application access layer is used for receiving external demand information and transmitting the external demand information to the large model platform; the service interface layer is used for receiving a query instruction of a large model platform, transmitting the query instruction to the mixed retrieval engine layer and transmitting a retrieval result to the large model platform, so that the large model platform outputs the retrieval result; the mixed retrieval engine layer is used for generating a graph database query statement and a query semantic vector according to the query instruction, performing structured query on a graph database according to the graph database query statement, performing semantic similarity retrieval in a vector database based on the query semantic vector, and generating a graph retrieval result and a vector retrieval result to the large model platform. Through the medication guidance system, specialized medication guidance can be realized.

The invention discloses a medicine purchasing behavior data processing method and device, electronic equipment and a storage medium, and relates to the technical field of data management.The method comprises the steps that historical medicine purchasing behavior data of a user is collected; determining a drug use continuous state sequence of the user according to the historical drug purchase behavior data; the historical medicine purchasing behavior data, the context features and the user tags are coded through an attention model, and user behavior time sequence features are obtained; according to the medication continuous state sequence and the user behavior time sequence characteristics, hidden medication state information of the user is determined, and the hidden medication state information at least comprises probability distribution information of the user in various medication states. According to the method and the device, the technical problem that the prediction accuracy of the medication state of the user is low due to the fact that the medication state of the user is predicted mainly depending on physiological monitoring indexes or single behavior rules in the prior art, and the user cannot be accurately reminded to purchase or take medicines in time is solved.