31 results about "Contraindication" patented technology

The invention provides an intelligent inquiry method and system based on a large language model, and the method comprises the steps: carrying out ancient book transcription, semantic logic verification and multi-stage nested JSON formatting, constructing a data set to cover core modules of diseases, herbal medicines, prescriptions, incompatibility and the like, and marking the details of dosage, processing method and the like; the method comprises the following steps: carrying out logic chain analysis on traditional Chinese medicine classical literatures based on a large model, generating independent knowledge units by adopting a dynamic semantic partitioning strategy, fusing a traditional Chinese medicine term weight matrix and drug attribute constraint optimization into confusion distillation by improving a confusion distillation technology, carrying out efficient neighbor search by utilizing FAISS, and returning a Top-K related result; and based on the knowledge fine-tuning large model, combining the retrieved context to generate safety response content conforming to the theory of traditional Chinese medicine. Based on the technical scheme, the accuracy and semantic understanding ability of a retrieval model in the field of traditional Chinese medicine are remarkably improved; the professionality and the safety of the generated model are enhanced; the accuracy and the safety are improved; the knowledge retrieval integrity is optimized through dynamic semantic partitioning.

The invention belongs to the technical field of medical data processing, and particularly relates to an electronic medical record intelligent quality control method and system based on a medical knowledge graph, and the method comprises the steps: obtaining target medical record data, and constructing an initial logic drive vector; calculating the dynamic propagation impedance of each edge in the general medical knowledge graph according to the deviation degree between the measured value of the physiological index in the target medical record data and the physiological constraint condition of the edge attribute in the general medical knowledge graph; constructing a transition probability matrix by using the dynamic propagation impedance, and obtaining a steady-state correlation distribution vector of each node through iterative calculation; and calculating a dynamic judgment threshold according to the steady-state correlation distribution vector, and performing exception verification on an actual disposal instruction in the target medical record data. According to the method, the real-time physiological status of the individual patient can be dynamically mapped into the constraint condition of map reasoning, potential taboo caused by abnormal physiological indexes is effectively identified, and personalized quality control of the electronic medical record is realized.

The invention discloses a drug incompatibility detection method based on fusion of a map and a large language model. Comprising the following steps: standardizing drug names in a prescription, mapping the drug names into uniform national standard codes, and generating a drug pair set; and extracting a drug interaction triple in combination with a large language model in the medical field, and constructing a heterogeneous drug knowledge graph. Based on a graph neural network and a comparative learning mechanism, embedded representation learning is performed on the knowledge graph, and the discrimination capability of drug node features is improved. Path retrieval and risk scoring are carried out on the drug pairs with the explicit interaction paths; and for a drug pair without an explicit path, screening alternative drugs by using chemical component similarity, inputting a pre-trained large language model through structured prompt, predicting a potential interaction relationship and credibility, and supplementing implicit risk information. According to the method, the problems of insufficient coverage and limited reasoning ability of the traditional knowledge graph are effectively solved, and the comprehensiveness and reliability of detection are improved.

The invention relates to the technical field of oral implant, and discloses an intelligent oral implant planning recommendation method based on artificial intelligence. The method comprises the following steps: acquiring multi-modal oral data of a patient, and constructing a three-dimensional jaw bone model so as to comprehensively present the anatomical structure and physiological characteristics of the jaw bone of the patient; based on the multi-modal oral cavity data, generating initial implant type parameters and initial implant position parameters, and realizing preliminary intelligent recommendation of implant parameters; inputting the initial parameters into a parameter mapping layer for conversion, outputting geometric feature parameters and biomechanical weight parameters of the implant, and establishing correlation between the parameters and biomechanical properties; according to the three-dimensional jaw bone model, determining an implant region constraint condition, matching the implant region constraint condition with a preset implant taboo rule base, and when the conflict parameter exceeds a preset threshold value, generating an implant position adjusting instruction. According to the method, multi-modal data are integrated, full-process intelligentization of planting planning is realized, planning accuracy and safety are improved, and a clinical planting scheme making process is optimized.

The invention relates to the technical field of formula optimization, and discloses a Qi king liquid formula optimization method and system based on big data analysis, and the method comprises the steps: obtaining basic attribute data and compatibility relation data of traditional Chinese medicinal materials; constructing a medicine taste associated map, extracting a map embedding vector, splicing the vector with the medicine dosage information, and generating a state expression of the current formula; calculating a main efficiency reward item; when the medicinal material combination in the formula triggers the compatibility rule, calculating a compatibility constraint penalty term; calculating a reward signal; identifying monarch, minister, assistant and guide roles of the medicinal materials, generating role masks, limiting dosage adjustment ranges of the medicinal materials of different roles, and updating a task specific strategy according to an award signal; updating meta parameters of the meta learner based on the reward signals of the plurality of tasks; and repeating internal and external circulation until the convergence condition is met, and outputting the Qi liquid formula with the highest accumulated reward. According to the method, a comprehensive evaluation function capable of simultaneously evaluating the curative effect and accurately representing various incompatibility risks is constructed, so that the optimization result of the Qi king liquid formula is better.

The application relates to the technical field of diagnosis and treatment, in particular to an intelligent decision-making diagnosis and treatment method, system and equipment combining traditional Chinese medicine and western medicine. First, the symptoms of a patient are encoded into a feature vector, then vector matching is performed in a pre-constructed knowledge graph combining traditional Chinese medicine and western medicine, applicable diagnosis and treatment information is screened out by calculating the similarity and setting a threshold value, and a preliminary scheme is formed; then the individual information of the patient is read, and analysis is performed in combination with a medication contraindication rule library, so that personalized treatment parameters are obtained; finally, the preliminary scheme and the personalized parameters are optimized and adjusted, and the final diagnosis and treatment suggestion is generated; not only the deep integration of traditional Chinese medicine and western medicine knowledge is realized, but also the diagnosis and treatment scheme can be dynamically adjusted according to the individual characteristics of the patient, and the accuracy and effectiveness of the diagnosis and treatment are improved.

The invention belongs to the technical field of medicines. The invention relates to a plaster, in particular to a plaster containing anilinoprofen and a composition. The invention provides an externally applied medicine containing anilinoprofen or a composition containing anilinoprofen and iguratimod. Pharmacodynamic studies show that the aniline-ibuprofen single-prescription plaster can treat osteoarthritis (OA) and rheumatoid arthritis (RA), can effectively inhibit arthrocele and volume increase, remarkably reduces the level of proinflammatory factors, and improves the pathological score of joint tissue. After the anilinoprofen and the iguratimod are combined for use, the curative effect is further enhanced, multiple indexes are obviously superior to those of a single drug group, and an obvious synergistic interaction effect is shown. The iguratimod and anilinoprofen compound preparation disclosed by the invention is developed in an external form such as a gel plaster for the first time, an external compound system of anilinoprofen and iguratimod is innovatively constructed, a safe, effective and convenient novel local treatment choice is provided for OA / RA patients, especially people with oral taboo or needing long-term treatment, and the iguratimod and anilinoprofen compound preparation has good clinical transformation potential and application value.

The application relates to a zero-character full-symbol medication guidance system based on a fool-proof design, and belongs to the technical field of medical safety. The system comprises seven pure graphical symbol modules of medication frequency, medication time, medication dose, medication route, contraindication warning, adverse reaction treatment and missed medication treatment. The modules are visually distinguished by unified color, shape and line type, and are combined into a complete information chain in a fixed order of frequency, time, dose, route, contraindication, adverse reaction and missed medication, and are printed or displayed on a medicine box, a medication guidance sheet or a prescription carrier. The application migrates the picture priority and fool-proof and error-proof operation national standard system in the construction industry to a medical medication scene, fundamentally eliminates medication misreading risks caused by ambiguous characters, character ambiguity and cultural level differences, realizes the instinctive recognition and accurate execution of the whole population such as illiterates, the elderly with low vision and cognitive impairment, and has the remarkable technical effects of zero learning cost, full-process coverage and low cost and easy popularization.

The invention discloses an AI-assisted hospital taboo and conflict drug warning system, which relates to the technical field of medical equipment, and comprises a data layer, a data processing layer, an AI monitoring and early warning layer and an interaction layer, and is characterized in that the data layer provides basic data and transmits the basic data to the data processing layer; the data processing layer trains a drug classification model based on the basic data and performs drug classification; the AI monitoring and early warning layer monitors the medicine preparation condition of a doctor in real time, carries out early warning if medicine conflicts exist in a medicine classification result, and continuously optimizes a medicine classification model at the same time; and the interaction layer presents the early warning as a warning to a doctor, and stores a warning record at the same time. The invention provides an auxiliary decision-making system based on artificial intelligence, which is used for automatically identifying drug conflicts and taboo and improving the safety of clinical medication.

The invention discloses the technical field of medical treatment, relates to the technical field of medical record forms, and particularly relates to a physical treatment record sheet for a rehabilitation medicine department and a matched use process thereof, which are used for standardizing and efficiently recording physical treatment process information of a patient. In the physical treatment work of the rehabilitation medicine department, information such as treatment items, time and treatment effect of a patient needs to be recorded in detail, so that a doctor tracks the treatment progress, evaluates the effect and adjusts a scheme. A traditional recording mode has the problems that information is dispersed, key content (such as accurate identification of a treatment part and contraindication associated records) is easy to omit, a signature confirmation process is not clear and the like, medical work efficiency and quality are affected, and long-term management and tracing of medical data are not facilitated. Therefore, a record list which is more reasonable in design and more complete in function is needed to optimize the recording work of the physical therapy.

This application relates to a method, device, equipment, and storage medium for risk assessment of acupuncture needle placement. It involves three-dimensional modeling of the posture image of the target to be needled, constructing a three-dimensional posture model including predicted acupoints; conducting site contraindication risk assessment based on structured rules of virtual acupuncture location and site contraindications; conducting population contraindication risk assessment based on individual morphological parameters of the target to be needled and structured rules of population contraindications; simulating a current loop in the posture three-dimensional model based on the electrode connection scheme of an electroacupuncture device, and conducting operation contraindication risk assessment based on the current loop and structured rules of operation contraindications; integrating the obtained site contraindication risk assessment results, population contraindication risk assessment results, and operation contraindication risk assessment results to obtain a multimodal risk assessment result for acupuncture needle placement. Compared with existing technologies, the technical solution of this application achieves more accurate and comprehensive acupuncture needle placement risk assessment through the collaborative design of structured rules, three-dimensional modeling, and multi-dimensional integration.

The invention provides a thrombus prevention method and system based on digital clinical precise execution, and relates to the technical field of digital medical treatment, and the method comprises the steps: obtaining clinical data of a patient, and determining a thromboembolism risk level, a bleeding risk level and a mechanical prevention taboo state of the patient based on a preset rule; based on the combined state of the three evaluation results, generating a thrombus prevention measure scheme for the patient through a preset prevention strategy decision rule; monitoring clinical data changes in the hospitalization process of the patient in real time, when it is detected that the risk level or the taboo state is changed, comparing the consistency of a current execution scheme with a scheme regenerated based on the changed state, and if the current execution scheme is not consistent with the scheme regenerated based on the changed state, generating preventive measure adjustment reminding information; and pushing the scheme or the adjustment prompt to a clinical medical care terminal. According to the invention, intelligent decision and dynamic adjustment of thrombus prevention can be realized, the accuracy and timeliness of prevention measures are improved, and medical risks are reduced.

This invention provides a method and system for assessing the suitability of TCM-specific nursing operations based on syndrome credibility and operational contraindications, comprising the following steps: S1: acquiring patient multimodal state data; S2: generating patient multimodal syndrome credibility based on the multimodal state data; S3: recalling candidate operations related to patient multimodal syndrome credibility and nursing goals based on a TCM-specific nursing operation knowledge base; S4: determining absolute contraindications, relative contraindications, and parameter restrictions for candidate operations based on an operational contraindication constraint library; S5: generating and updating operation suitability weights, contraindication constraint rules, and parameter generation rules based on operation execution feedback; applying this technical solution enables automatic optimization of operation suitability rules, parameter generation rules, and risk restriction rules.

The invention discloses a mucous membrane healing evaluation method based on energy spectrum CT iodine quantification, and belongs to the field of medical image processing and clinical diagnose.The mucous membrane healing evaluation method comprises the following steps that an energy spectrum CT intestinal stage scanning image of a patient suffering from Crohn's disease is obtained, and a three-dimensional volume area of a diseased intestinal segment is delineated on an energy spectrum CT iodine substance decomposition graph; selecting a reference blood vessel area, and measuring an iodine concentration value; calculating a normalized iodine concentration value, wherein the normalized iodine concentration value is equal to a result obtained by dividing the iodine concentration value of the lesion intestinal segment by the iodine concentration value of the reference blood vessel region; and comparing the normalized iodine concentration value with a preset threshold value 0.44, if the normalized iodine concentration value is less than 0.44, determining that the mucous membrane is healed, otherwise, determining that the active inflammation is caused. According to the scheme, traditional invasive enteroscopy is replaced with energy spectrum CT image analysis, contraindications of endoscope operation, patient pain and examination blind areas are avoided, the acceptability and examination feasibility of patients are remarkably improved, and the method is particularly suitable for patients who cannot tolerate an endoscope or need frequent follow-up visit.

The application provides a medicine food recommendation method and related equipment based on ancient prescription tracing and safety classification, which comprises the following steps: in response to the medicine food conditioning requirements input by a user, at least one of the conditioning target, symptom keywords, eating method, special population information and contraindication information is obtained by analysis; candidate ancient prescriptions are searched in a pre-configured prescription knowledge base, and model input information is constructed according to the prescription name, source, composition, indication, original text evidence and medicinal material safety classification label of the candidate ancient prescriptions; candidate recommendation information is generated through a medicine food recommendation model; risk interception is performed based on the safety classification label to prevent high-risk medicinal materials from entering the medicine food recommendation; and consistency verification and residual risk verification are performed on the candidate recommendation information, and a medicine food recommendation result is output. The application can improve the traceability, safety and reliability of medicine food recommendation.

The application discloses an artificial intelligence-based all-medical order rational drug use auditing method and platform, which comprises the following steps: by integrating patient structured data and unstructured text, determining physiological safety range in time sequence, and constructing panoramic contraindication medical image; after deep information extraction and multi-source data fusion, forming a patient panoramic image, and comparing it with medical order drugs for contraindication, triggering hard blocking warning to avoid drug conflict; further establishing a digital twin model, setting the medical order compared by contraindication as a baseline scheme, simulating the dynamic change of physiological indicators within 72 hours, and assisting doctors in adjusting drug dosage combined with clinical experience; finally, according to the simulation curve, the individualized drug safety baseline is established, precise simulation, dynamic early warning and scientific decision are realized; the scheme significantly improves the treatment safety and precision, provides all-process intelligent drug use auditing support for complex patients, and has important clinical application value.

The invention discloses a wind-dispelling and pain-relieving plaster for treating wind-cold migraine and application thereof, and belongs to the technical field of traditional Chinese medicine, the wind-dispelling and pain-relieving plaster is prepared from the following medicinal raw materials in parts by mass: ligusticum wallichii, asarum, fructus evodiae, radix angelicae and borneol; the invention further discloses a preparation method and application of the traditional Chinese medicine composition. The wind-dispelling and pain-relieving patch has the beneficial effects that the wind-dispelling and pain-relieving patch provided by the invention avoids gastrointestinal tract injury caused by alimentary tract metabolism of medicines in a transdermal administration manner, avoids cardiovascular contraindications of triptan medicines, is particularly suitable for patients who are intolerant to western medicines or have contraindications, not only can quickly relieve pain, but also can reduce the recurrence frequency, and has a good application prospect. In addition, treatment is carried out by applying the Dazhui acupoint application, operation is easy and convenient, no wound is caused, patient compliance is high, and exertion of the curative effect is better facilitated, so that the anxiety emotion is relieved, and the life quality is improved.

The present application relates to medical care informatics, and discloses a kind of based on causal inference's chronic disease intervention effect evaluation and prediction method, comprising: obtaining long-period medical record to construct physiology and intervention sequence matrix, the conditional probability value of each time observation step intervention occurrence is calculated, the clinical contraindication threshold matrix corresponding to physiological state is determined, if physiological state falls into forbidden interval, the probability reciprocal calculation path is blocked, the intervention frequency deviation residual in historical stationary window is extracted to cover time-varying confounding adjustment weight, according to weight, sequence matrix is resampled to generate quasi-state equilibrium sequence, mapping output evolution track, the present application uses residual compensation mechanism to hedge the calculation divergence risk caused by the probability extreme value induced by guideline constraint, guarantee data time sequence integrity under critical condition, eliminate survivor bias.

The invention relates to selecting a patient treatment method. The method, implemented using a processor, includes the steps of: obtaining depersonalized patient medical data; extracting information about patients with a similar type of illness, the treatment method used, the treatment outcome and data about the clinic and the treating physician; determining from the information obtained criteria relating to the indications and contraindications of the treatment methods used, according to each clinic and treating physician, and generating a list of criteria for an algorithmic search according to medical approaches for curing the given type of illness; determining the type of medical care; generating a rating of the clinics and physicians and selecting a method for treatment with a radical treatment method or a palliative treatment method; sending to the patient the selected treatment method and a list of clinics and physicians in the patient's region, rated in descending order. The invention is intended to allow automated selection of a patient treatment method.

The application relates to the technical field of big data processing, and discloses a knowledge graph building method based on chronic disease management. The present application uses deduction logic based on biological steady-state game, introduces thermodynamic dissipation and entropy increase constraint, accurately quantifies the irreversible loss of living beings in the disease course, overcomes the defect that the existing algorithm cannot simulate physiological function decline, at the same time, the present application constructs a physical filter based on the principle of biological impedance mismatch, uses mass transport limitation to eliminate sensor high-frequency artifact noise, significantly reduces the false positive rate while ensuring the real lesion recall rate, further, the present application converts the medical contraindication rule into a rigid topological potential constraint through contact mechanics and gibbs free energy functional, forcibly corrects the data violating common sense, ensures the high unity of the output graph in the physical observation reality and the medical logic self-consistency, and greatly improves the clinical explainability and decision safety of the auxiliary diagnosis and treatment system.

The application relates to the technical field of treatment scheme optimization, and provides an emergency critical patient first-aid path optimization method and system based on big data, which comprises the following steps: constructing a standardized event sequence by extracting historical diagnosis and treatment data of a hospital information system, then analyzing the time sequence correlation between events by using a graph structure mining technology, identifying key diagnosis and treatment nodes and high and low frequency paths, and constructing a hierarchical first-aid path state transition network. When processing real-time patients, the system matches the electronic health records of the patients with the network core state, dynamically plans the subsequent standard transition path, and avoids low-frequency risk paths marked as contraindications, so that the first-aid path optimization scheme of risk avoidance and path dynamic optimization is realized, the treatment efficiency of emergency critical patients is improved, the treatment effect is improved, and the risk of adverse prognosis is reduced.

The invention relates to the technical field of drug taboo auditing, in particular to a drug taboo reverse recommendation auditing method based on multi-simulation-state AI reasoning, which comprises the following steps: collecting drug information of various drugs on the current market, acquiring a specification of each drug based on the drug information of the various drugs, and setting the specification of each drug as the specification; disease taboo key information of a specification of each medicine is manually extracted and uploaded to a medicine taboo database, a taboo rule of each medicine is set for the specification of each medicine and uploaded to the medicine taboo database, and an AI home medicine service platform is constructed based on the medicine taboo database. Therefore, the user can perform medication taboo auditing based on the AI home medication service platform, and the problem of inaccurate network prescription taboo auditing in the prior art is solved.

The application provides a kind of preventive inoculation information quick entry and check device, relating to medical information technology field, including information collection registration module, database storage module, central check processing module, interactive alarm module and inoculation execution confirmation module;The application obtains the identity of the recipient and vaccine information through multi-modal mode, and encapsulates into standardized data packet, avoids the problem of low efficiency of manual entry, then the central check processing module carries out real-time, multi-dimensional logical reasoning calculation based on dynamic rules, and the back-end operation and management indexes such as cold chain quality and inventory status are preposed as real-time check dimensions as important as medical contraindications and immunization programs, so that the use of invalid vaccine, inventory shortage misregistration and other difficult to prevent risks are actively intercepted before inoculation occurs, and further, the man-machine collaborative decision mechanism of alarm state is introduced, which ensures that the safety bottom line is not broken, and gives the final decision-making right to medical staff in complex situation.

The invention discloses a drug abortion success rate prediction system and method based on a random forest, particularly relates to the technical field of medical data analysis, and aims to solve the problem that clinical doctors depend on experience to judge the success rate of drug abortion and lack scientific and quantitative prediction tools. The method comprises the following steps: firstly, selecting a target population which requires drug abortion and has no contraindication, and collecting clinical data of the target population; making a binarization coding rule, coding the collected clinical data of the target population item by item, and constructing a feature vector of the target population; based on the feature vector of the target population, predicting whether the drug abortion of the patient succeeds or not through a random forest model; then collecting the drug abortion outcome of the target population; and finally, merging the drug abortion outcome and the clinical data-data model of the patient to obtain a predicted value of the drug abortion outcome of the patient. According to the invention, the evaluation system for the adaptive population of the drug-induced abortion is established, the adaptive population of the drug-induced abortion is defined, and the failure rate of the drug-induced abortion is reduced.

1. The name of the design product: prescription review drug contraindication data maintenance graphical user interface for electronic equipment. 2. The use of the design product: for electronic equipment. 3. The design points of the design product: the graphical user interface in the screen. 4. The picture or photo that best indicates the design points: front view. 5. The hardware product is a conventional design, and other views are omitted. 6. The use of the graphical user interface: for prescription review of drug contraindication data maintenance. 7. The area of the graphical user interface in the product: the interface in the screen. 8. The human-computer interaction mode of the graphical user interface: open the program through the computer to enter the main view, click gender in the main view to enter interface change state diagram 1, click age to enter interface change state diagram 2, click allergy, pregnant women to enter interface change state diagram 3, click lactation period, disease contraindication to enter interface change state diagram 4, and slide down the lactation period, disease contraindication interface to enter interface change state diagram 5.

The invention discloses a haemorrhoids treatment composition based on a sesame oil formula and an administration device. The haemorrhoids treatment composition is used for treating internal hemorrhoids, external hemorrhoids and mixed hemorrhoids. The composition takes sesame oil as a matrix, is compounded with various traditional Chinese medicine components, and is precisely administered to an anorectal focus through a sterile needle tube and a 12cm hose, so that local inflammation diminishing, hemostasis and hemorrhoid retraction promotion are realized. The medicine is taken once a day for 6 days continuously, and the dosage and taboo (such as fasting Chinese chives and forbidding by pregnant women) are strictly limited. And the matched device adopts an anti-injury design, so that the medication safety is ensured. Clinical verifications show that the traditional Chinese medicine composition can remarkably relieve hematochezia, pain and prolapse symptoms, transient abdominal pain is normal reaction after the traditional Chinese medicine composition is taken, and the transient abdominal pain can be recovered after the traditional Chinese medicine composition is stopped.

The invention, which belongs to the technical field of intelligent medication, discloses an intelligent medication scheme recommendation method based on big data, and the method specifically comprises the following steps: collecting daily activity characteristics and medical record data of a patient; according to the diagnosis information and the inspection result, screening drugs which are consistent in indications and have no taboo components to obtain a primarily screened drug set; determining life scene categories according to occupational types and work and rest laws of the patients, and calculating life scene interference values of the medicines based on a preset interference coefficient library; screening a reference group similar to the target patient, and calculating an expected curative effect score of each drug by analyzing a re-diagnosis record of the reference group; and normalizing the interference value and the curative effect score, weighting according to a preset weight to obtain a comprehensive adaptation degree, and selecting the drug with the highest adaptation degree to output. According to the invention, the daily life scene of the patient is fused into the medication decision, the fusion of clinical effectiveness and life feasibility is realized, and the medication compliance is improved.

The present application relates to the technical field of healthcare informatics, and discloses a personalized medical service recommendation method based on user portrait, comprising: dynamically constructing a chronic portrait layer and an acute context layer by calculating the occurrence frequency, survival duration and baseline sign statistical deviation of health data items, and getting rid of the dependence on static labels; checking the activation state of the acute context layer; when there are multiple activated acute items, making a clinical priority decision to select a dominant context; based on the dominant or unique acute context, preferentially recommending, and taking it as a temporary contraindication filter to review the silent conflict between chronic and secondary acute recommendations, the present application dynamically infers the clinical state and internally builds a priority decision, realizes the context awareness and dynamic suitability of the recommendation result, and avoids the clinical risks caused by state mismatch.

This invention belongs to the field of medical data processing technology, specifically relating to an intelligent quality control method and system for electronic medical records based on a medical knowledge graph. The method includes: acquiring target medical record data and constructing an initial logical driving vector; calculating the dynamic propagation impedance of each edge in the general medical knowledge graph based on the deviation between the measured values ​​of physiological indicators in the target medical record data and the physiological constraints of edge attributes in the general medical knowledge graph; constructing a transition probability matrix using the dynamic propagation impedance and obtaining the steady-state correlation distribution vector of each node through iterative calculation; calculating a dynamic judgment threshold based on the steady-state correlation distribution vector and performing anomaly verification on the actual treatment instructions in the target medical record data. This invention can dynamically map the real-time physiological state of an individual patient to the constraints of graph reasoning, effectively identifying potential contraindications caused by abnormal physiological indicators, and realizing personalized quality control of electronic medical records.

The embodiment of the invention provides a method and device for generating taboo information of drugs, and the method comprises the steps: determining a plurality of pharmacological mechanisms corresponding to a first drug through a pharmacological mechanism reasoning model based on the first drug information of the first drug; based on a plurality of pharmacological mechanisms, determining a plurality of first candidate taboo objects of the first drug through a pharmacological taboo reasoning model, and classifying the first candidate taboo objects into a candidate taboo object set of the first drug; the first medicine is combined with all objects in the candidate taboo object set to obtain all medicine object groups, and the medicine object groups comprise the first medicine object group; determining support evidence information and anti-evidence information corresponding to the first medicine object group from a specified evidence source, and performing confrontation verification on the first medicine object group by using the support evidence information and the anti-evidence information; and according to the confrontation verification result of each drug object group, determining each piece of taboo information corresponding to each drug object group so as to realize generation of the taboo information of the taboo object having the implicit taboo relationship with the drug.