Intelligent hemp essence medicine management system and method

Abstract

The invention belongs to the technical field of intelligent management of hemp essence medicines, and discloses an intelligent hemp essence medicine management system and method, and the method comprises the steps: processing an operation context parameter, and calculating a risk score; secondly, a white-box rule engine is used for checking medicament metering specifications, and clinical pathway compliance and medicament interaction are analyzed; then, in combination with biological characteristics and geographical location information, evaluating risks in real time and taking multi-level intervention measures; then, generating a detailed visual auditing report according to the collected data; and finally, optimizing the system performance based on a feedback dynamic adjustment strategy. The safety and the accuracy of medical operation are improved, the intelligent level and the response efficiency of the system are remarkably improved, and a highly-safe operation verification process and an accurate prescription data verification capability are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent management of narcotic and psychotropic drugs. More specifically, the present invention relates to an intelligent management system and method for narcotic and psychotropic drugs. Background Art

[0002] Due to their special pharmacological effects, narcotic and psychotropic drugs play an important role in the medical process, but there is also a high risk of abuse. Therefore, the management of narcotic and psychotropic drugs needs to be particularly cautious to ensure that their use meets clinical needs while avoiding abuse. Traditional management systems for narcotic and psychotropic drugs usually rely on manual review, paper records, etc. These methods are not only inefficient but also prone to human errors or malicious tampering.

[0003] The operation verification methods of existing systems usually rely on a single authentication means, such as passwords or simple biometrics (e.g., fingerprints). This method is ineffective in the face of complex operating environments and changing behavior patterns. Due to the lack of a comprehensive assessment of operation context parameters, including time granularity, geographical location, device information, etc., it is impossible to accurately assess operation risks. In addition, existing prescription data verification technologies often ignore the complex interactions between drugs and the personalized health conditions of patients (such as liver and kidney functions), which is likely to cause potential medication risks. At the same time, these systems fail to make full use of the large amount of data generated during the operation process for subsequent analysis and decision support, limiting the intelligence level and response speed of the system. Summary of the Invention

[0004] To overcome the above defects of the prior art and to achieve the above object, the present invention provides the following technical solution: An intelligent management system for narcotic and psychotropic drugs, comprising: Operator Identity Verification and Dynamic Generation Verification Unit: The operator is verified based on operation context parameters to obtain an operation risk score, and then a knowledge-driven decision rule library is constructed to dynamically generate the operator's verification strategy, and the operator's multi-modal biometric identifier set is verified through multi-node collaboration to obtain a verification result and a biometric hash; Prescription Data Verification and Early Warning Conflict Strength Calculation Unit: Based on the verification result, the patient's full-department medication data is captured, and the dosage specification of the medicine and the compliance with the clinical pathway are verified step by step through a white-box rule engine, and high-risk combinations are identified through a pharmacokinetic interaction matrix to obtain the early warning conflict strength; Real-time Risk Assessment and Multi-level Intervention Blocking Unit: Based on the operator's geographical location, combined with encrypted biometric hashes, operation risk scores, prescription data, and warning conflict intensities, construct a spatio-temporal - biological joint map, and then obtain a real-time risk score. Combine the real-time risk score and warning conflict intensity to generate a comprehensive risk assessment value. According to the comprehensive risk assessment value, generate an interception instruction to execute multi-level intervention blocking measures on high-risk behaviors, and obtain an encrypted evidence chain package; Visualization Report Generation Unit: Generate a drug management trajectory file based on the operation risk score, warning conflict intensity, and encrypted evidence chain package, construct a visualization audit map, and generate an audit report and a heat map of drug flow; Dynamic Adjustment and Optimization Unit: Dynamically adjust the operation risk threshold range according to the audit report and the heat map of drug flow, and update the knowledge-driven decision rule base and the verification strategy configuration plan.

[0005] Furthermore, the construction method of the knowledge-driven decision rule base includes: Operation context parameters include time granularity, pharmaceutical pedigree and corresponding drug control levels, historical behavior reputation values, geographical locations, and device information; Use the weighted average method to calculate all influencing factors within the operation context parameters to obtain an operation risk score, and set an operation risk threshold range to divide the operation risk score into different operation risk levels; Set a geographical fence and a maximum deviation distance. If the actual path distance between the geographical location and the geographical fence range is greater than the maximum deviation distance, mark it as a location anomaly; If the actual path distance between the geographical location and the geographical fence range is less than or equal to the maximum deviation distance, mark it as a normal location; Consider the normal location and the location anomaly as the location status of the geographical location; Combine different time granularities, location statuses, drug control levels, and operation risk levels as an operation scenario; Randomly select one or more verification strategies from the verification strategy set, and randomly select one verification occurrence method from the edge and cloud center verifications. Combine the selected verification strategies and verification occurrence methods to form a verification strategy combination; Among them, the verification strategy set includes vein recognition, fingerprint recognition, iris recognition, and dynamic passwords. The edge and cloud center verifications include local node verification and cloud node verification. The local node is the local server, and the cloud node is the remote data center; For each operation scenario, randomly select a verification strategies from all strategy combinations as the initial verification strategy set for the operation scenario; Integrate all operation scenarios and their corresponding initial verification strategy sets to construct an initial operation scenario - verification strategy mapping table; Update the initial operation scenario - verification policy mapping table, and use an expert rule engine to generate a knowledge - driven decision rule base according to the updated operation scenario - verification policy mapping table.

[0006] Furthermore, the method for updating the initial operation scenario - verification policy mapping table includes: According to the initial operation scenario - verification policy mapping table, randomly assign a verification policy combination to each operation scenario to obtain an initial operation scenario - verification policy combination, and then integrate all initial operation scenario - verification policy combinations to obtain a complete set of verification policy configuration schemes; repeat the assignment operation b times to obtain b different verification policy configuration schemes, and then form an initial policy configuration pool; Based on the initial policy configuration pool, calculate the effective value of each initial operation scenario - verification policy combination in each verification policy configuration scheme, and take the average value to obtain the average effective value of each verification policy configuration scheme; For each operation scenario, extract the verification policy combination with the highest effective value from the c verification policy configuration schemes with the highest average effective value to obtain a new operation scenario - verification policy combination, and then integrate it into a new verification policy configuration scheme; Use the new verification policy configuration scheme to replace the verification policy configuration scheme with the lowest average effective value in the initial policy configuration pool, and repeat the iterative operations of effective value calculation, extraction, and replacement until the maximum number of iterations is reached or the effective values of all operation scenario - verification policy combinations no longer increase, and then stop to obtain the best verification policy combination for all operation scenarios; Use the best verification policy combination to update the operation scenario - verification policy mapping table to obtain the updated operation scenario - verification policy mapping table.

[0007] Furthermore, the method for obtaining the verification result and biometric hash includes: According to the knowledge - driven decision rule base, match a verification policy combination for the operator. According to the matched verification policy combination, obtain the multi - modal biometric identifiers of the operator through the device used by the operator for the current operation, and integrate them into a biometric identifier set; Among them, the multi - modal biometric identifiers include vein biometric identifiers, fingerprint biometric identifiers, iris biometric identifiers, and dynamic password biometric identifiers; Perform preliminary processing on the operator's biometric identifier set, including image pre - processing, biometric identifier extraction, and multi - modal biometric identifier fusion; If the matched verification policy is for local node verification, send the preliminarily processed multi - modal biometric identifier set to the local node; If the matched verification policy is for cloud node verification, send the preliminarily processed multi - modal biometric identifier set to the local node and d cloud nodes, where d > 1; For the device currently being operated by the operator and each node participating in the verification, the received set of biometric identifiers is independently compared for features using its own database to obtain corresponding verification results, including whether there is a match and the corresponding confidence score; Based on all the verification results, calculate the difference value between all the verification results. If the difference value is less than the preset difference value threshold, it is determined that the verification results are correct, which are used as the final verification results, and corresponding verification result signals are generated. The types of verification result signals include verification success signals and verification failure signals; If the difference value is greater than or equal to the preset difference value threshold, it is determined that there is an abnormal behavior in the current verification, the locking mechanism is triggered and a verification failure signal is generated, and at the same time, feedback is given to the operator; Based on the verification success signal, convert the set of biometric identifiers into a biometric hash value and encrypt it to obtain the encrypted biometric hash.

[0008] Furthermore, the methods for the early warning conflict intensity include: Based on the encrypted final verification results, obtain the patient's prescription data, and then obtain the corresponding prescription dose; Grab and parse the prescription medication data of the patient's entire department through the hospital HIS system, and calculate the cumulative dose of the same type of drugs within 24 hours; Use a white-box rule engine to retrieve the corresponding drug instructions in the hospital HIS system and extract the maximum single dose and the 24-hour cumulative dose threshold; Adjust the 24-hour cumulative dose threshold according to the patient's liver and kidney function status to obtain the corrected cumulative dose threshold; Based on the cumulative dose of the same type of drugs and the corrected cumulative dose threshold, if the cumulative dose is less than or equal to the cumulative dose threshold, it is determined that the drug dose complies with the specification; If the cumulative dose is greater than the cumulative dose threshold, it is determined that the drug dose does not comply with the specification, and a drug dose early warning is generated; Obtain the patient's diseases, allergy history, liver and kidney function indicators, and treatment plan, and then construct an association rule library of drugs - diseases - test indicators - treatment plans, and use the association rule library to construct a clinical pathway knowledge graph; Use the clinical pathway knowledge graph to perform a subgraph matching operation on the current prescription data to calculate the clinical pathway compliance; If the clinical pathway compliance is greater than or equal to the preset clinical pathway compliance threshold, it is determined that the clinical pathway compliance complies with the specification; If the clinical pathway compliance is less than the preset clinical pathway compliance threshold, it indicates deviation from the standard path, and it is determined that the clinical pathway compliance does not comply with the specification, and a clinical pathway compliance early warning is generated; Apply a pharmacokinetic interaction matrix to detect high-risk interaction combinations in the prescription medication data of the entire department; If a high-risk interaction combination is detected, it is determined that the prescription has a high-risk interaction combination, and a high-risk warning is generated; if no high-risk combination is detected, it is determined that the prescription does not have a high-risk interaction combination; According to the pharmaceutical dosage specification, the clinical pathway compliance, and the determination result of the high-risk interaction combination, the warning conflict intensity is obtained.

[0009] Furthermore, the method for obtaining the corrected cumulative dose threshold includes: Obtain the liver function index and kidney function index of the patient through the hospital HIS system, and use the Cockcroft-Gault formula to calculate the kidney function correction factor through the kidney function index; Use the Child-Pugh scoring system to evaluate and obtain the liver function correction factor; Combine the kidney function correction factor and the liver function correction factor to construct a multi-organ function adjustment model based on the minimum value rule, and output the correction coefficient of the cumulative dose threshold; Take the product of the correction coefficient and the 24-hour cumulative dose threshold to obtain the corrected cumulative dose threshold.

[0010] Furthermore, the method for constructing the pharmacokinetic interaction matrix includes: Collect data on all narcotic and psychotropic drugs and all other drugs with known interactions with narcotic and psychotropic drugs, and integrate them into a drug category set, including the name, main ingredient, common dosage range, administration route, known interactions and their mechanisms between different drugs, and the main pharmacokinetic parameters of each drug; According to the known interactions of the drugs, classify the drugs into different categories according to the mechanism, and assign an interaction intensity to each pair of drugs with interactions according to the classified drugs; Construct a two-dimensional matrix with one drug as the row and another drug as the column, and each cell in the matrix represents the interaction between a pair of drugs; For each pair of drug combinations, fill in the corresponding interaction information in the corresponding cell in the matrix to obtain the constructed pharmacokinetic interaction matrix.

[0011] Furthermore, the method for obtaining the encrypted evidence chain package includes: Take the operator's own identifier as the personal node, the operator's geographical location as the location node, the encrypted biometric hash as the time node, and the warning conflict intensity as the intensity node; Define that the edge connecting the personal node and the location node represents that the operator has accessed the device location where the operator is currently operating during the current period t; define the edge between the personal node and the time node as that the operator has submitted a biometric sample during the current period t; define the edge between the personal node and the intensity node as the risk assessment result of the current operation; Construct a spatio-temporal and biological joint map based on the defined nodes and edges; Use a predefined risk assessment model to analyze the paths and connections in the spatio-temporal and biological joint map, and calculate the real-time risk score for the current period; Perform a weighted sum of the real-time risk score and the early warning conflict intensity to obtain a comprehensive risk assessment value; Based on the comprehensive risk assessment value, set an interception threshold range. If the comprehensive risk assessment value is less than the minimum value of the interception threshold range, it is determined that the current operation of the operator is risk-free and no interception is performed; If the comprehensive risk assessment value is greater than or equal to the minimum value of the interception threshold range and less than or equal to the maximum value of the interception threshold range, it is determined that the current operation of the operator is risky, and an interception instruction is generated; If the comprehensive risk assessment value is greater than the maximum value of the interception threshold range, it is determined that the current operation of the operator is highly risky, an interception instruction is generated and physical isolation measures are executed, and an alarm message is sent simultaneously; Integrate the identifier of the operator himself, the geographical location of the operator, the encrypted biometric hash and the early warning conflict intensity, as well as the corresponding spatio-temporal and biological joint map, real-time risk score, comprehensive risk assessment value and the final interception decision, and encrypt them through the Advanced Encryption Standard to form an encrypted evidence chain package.

[0012] Furthermore, the generation methods of the audit report and the drug flow heat map include: Generate a drug management trajectory file by combining the operation risk score, the early warning conflict intensity and the encrypted evidence chain package; Based on the knowledge graph technology, construct a visual audit graph according to the drug management trajectory file, and generate an audit report and a drug flow heat map according to the visual audit graph.

[0013] Furthermore, an intelligent psychotropic drug management method includes: S1: The operator performs verification based on the operation context parameters to obtain an operation risk score, and then constructs a knowledge-driven decision rule base to dynamically generate the operator's verification strategy, and cooperates with multiple nodes to verify the multi-modal biometric identifier set of the operator to obtain a verification result and a biometric hash; S2: Based on the verification result, capture the full-department drug use data of the patient, and gradually verify the dosage specification and clinical path compliance through a white-box rule engine, and identify high-risk combinations through a pharmacokinetic interaction matrix to obtain the early warning conflict intensity; S3: Based on the operator's geographical location, combine the encrypted biometric hash, operation risk score, prescription data, and warning conflict intensity to construct a spatio-temporal - biological joint map, and then obtain a real-time risk score. Combine the real-time risk score and the warning conflict intensity to generate a comprehensive risk assessment value. According to the comprehensive risk assessment value, generate an interception instruction to execute multi-level intervention and blocking measures for high-risk behaviors, and obtain an encrypted evidence chain package; S4: Generate a drug management trajectory file based on the operation risk score, warning conflict intensity, and encrypted evidence chain package, construct a visual audit map, and generate an audit report and a heat map of drug flow; S5: Dynamically adjust the operation risk threshold interval according to the audit report and the heat map of drug flow, and update the knowledge-driven decision rule base and the verification strategy configuration plan.

[0014] The technical effects and advantages of an intelligent narcotic and psychotropic drug management system and method of the present invention: By processing operation context parameters and calculating the operation risk score, and dynamically generating a personalized verification strategy in combination with the knowledge-driven decision rule base, the present invention ensures high-precision operator identity verification; then, uses a white-box rule engine to gradually verify the drug dosage specification and clinical path compliance level by level, and identifies potential high-risk drug combinations through a pharmacokinetic interaction matrix, effectively preventing medication risks; then, constructs a spatio-temporal - biological joint map based on the operator's geographical location and other key information, evaluates risks in real time and executes multi-level intervention and blocking measures, realizing an instant response to high-risk behaviors; subsequently, generates a detailed visual audit report based on the operation risk score and the encrypted evidence chain package, enhancing the transparency and traceability of the system; finally, by dynamically adjusting the operation risk threshold interval and optimizing the verification strategy configuration plan, continuously improving the system's self-learning and optimization capabilities, and reducing the need for manual intervention. Overall, this solution not only improves the safety and accuracy of medical operations, but also significantly enhances the intelligence level and response efficiency of the system. Brief Description of the Drawings

[0015] Figure 1 It is a schematic flow diagram of an intelligent narcotic and psychotropic drug management system of the present invention; Figure 2 It is a schematic unit flow diagram of an intelligent narcotic and psychotropic drug management system of the present invention; Figure 3 It is a schematic diagram of an intelligent narcotic and psychotropic drug management method of the present invention. Detailed Embodiments

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Embodiment 1

[0018] See also Figure 1 and Figure 2 As shown, this embodiment provides an intelligent narcotic drug management system, including: Operator identity authentication and dynamic generation verification unit: The operator is verified based on the operation context parameters to obtain the operation risk score, and then a knowledge-driven decision rule base is built to dynamically generate the operator's verification strategy, and the operator's multimodal biometric identifier set is verified through multi-node collaboration to obtain the verification result and biometric hash; Prescription data verification and early warning conflict strength calculation unit: Based on the verification results, the patient's medication data in all departments is captured, and the drug dosage specifications and clinical pathway compliance are verified step by step through the white box rule engine. High-risk combinations are identified through the pharmacokinetic interaction matrix to obtain the early warning conflict strength; Real-time risk assessment and multi-level intervention blocking unit: Based on the operator's geographic location, combined with encrypted biometric hash, operation risk score, prescription data and warning conflict strength, a spatiotemporal-biological joint map is constructed to obtain a real-time risk score. Combined with the real-time risk score and warning conflict strength, a comprehensive risk assessment value is generated. Based on the comprehensive risk assessment value, an interception instruction is generated to execute multi-level intervention blocking measures for high-risk behaviors and obtain an encrypted evidence chain package; Visual report generation unit: Generate drug management track files based on operational risk scores, warning conflict strength and encrypted evidence chain packages, build visual audit maps, generate audit reports and drug flow heat maps; Dynamic adjustment and optimization unit: dynamically adjust the operational risk threshold interval, update the knowledge-driven decision rule base and verify the strategy configuration plan based on the audit report and drug flow heat map; Operator identity authentication and dynamic generation verification unit → Prescription data verification and early warning conflict strength calculation unit: Static verification will lead to low credibility of prescription review data, and wrong verification results will lead to subsequent misjudgments. Multi-node verification ensures that the biometric hash is authentic and reliable, providing reliable input for prescription verification; Prescription data verification and early warning conflict intensity calculation unit → Real-time risk assessment and multi-level intervention blocking unit: Deviations in early warning conflict intensity calculation can affect risk assessment, and inaccurate early warnings can lead to excessive / inadequate blocking. Improve the accuracy of early warnings through pharmacokinetic tensors + organ corrections (liver function + kidney function corrections); Real-time risk assessment and multi-level intervention blocking unit → Visual report generation unit: The integrity of the encrypted evidence chain depends on the quality of real-time data. Evidence tampering can lead to audit failures. Build an anti-tampering evidence system through spatio-biological maps + double-chain evidence storage; Visual report generation unit → Dynamic adjustment and optimization unit: Manual analysis reports are difficult to drive the self-optimization of the system, and strategy iteration lags behind risk changes. Through a visual heat map → optimization algorithm → automatic parameter adjustment closed-loop; The construction methods of the knowledge-driven decision rule base include: The operation context parameters include time granularity (the time when the operation occurs. Since some time periods (such as late at night) are non-working hours, operations during non-working hours can be determined to be of higher risk. The division of different time periods can be set by relevant experts according to specific circumstances during use), the pharmaceutical pedigree and the corresponding drug control level (the types of drugs being processed and their potential risk levels. Narcotic and psychotropic drugs usually have high risks. By scanning the drug RFID tag and reading the control level field, the classification criteria are as follows: [control level (category I; category II; category III), risk label (high risk; medium risk; low risk), trigger conditions (morphine, fentanyl; tramadol, codeine; compound oral solution containing codeine)]), historical behavior credit value (extracting the operator's historical operation records from the database to evaluate their behavior patterns), geographical location (the geographical location information where the operation occurs), and device information (the type of device used and the safety status of the device); Use the weighted average method to calculate all influencing factors within the operation context parameters, obtain the operation risk score, and set the operation risk threshold range. Divide the operation risk score into different operation risk levels, such as low risk, medium risk, and high risk levels; Set the geofence and the maximum deviation distance (such as a radius of 50m. For example, the coordinates of the hospital pharmacy are 31.2304N, 121.4737E. If the set geofence has a radius of 50m, the area of the geofence is the range within 50m radius of the hospital pharmacy). If the actual path distance between the geographical location and the geofence range is greater than the maximum deviation distance, mark it as a location anomaly; if the actual path distance between the geographical location and the geofence range is less than or equal to the maximum deviation distance, mark it as a normal location; Use the normal location and the location anomaly as the corresponding location status of the geographical location; Combine different time granularities, location statuses, drug control levels, and operation risk levels as an operation scenario; Randomly select one or more verification strategies from the verification strategy set, and randomly select one verification occurrence method from the edge and cloud center verifications. Combine the selected verification strategies and verification occurrence methods to form a verification strategy combination; Among them, the verification strategy set includes vein recognition, fingerprint recognition, iris recognition, and dynamic passwords. The edge and cloud center verifications include local node verification and cloud node verification. The local node is a local server, and the cloud node is a remote data center; For each operation scenario, randomly select a verification strategy combinations from all the strategy combinations as the initial verification strategy set for the operation scenario; In one example, an operation scenario is [time granularity = 10.30AM (belonging to the daytime working period); location status (abnormal location); drug control level (category three); operation risk level (medium risk)]. Randomly select 2, and the generated verification strategy combinations are [multi-modal biometric identifier set (fingerprint + iris), local node verification], and [multi-modal biometric identifier set (fingerprint + iris + vein recognition + dynamic password), cloud node verification]; Integrate all operation scenarios and their corresponding initial verification strategy sets to construct an initial operation scenario-verification strategy mapping table; According to the operation scenario-verification strategy mapping table, randomly assign a verification strategy combination to each operation scenario to obtain an initial operation scenario-verification strategy combination. Then, integrate all the initial operation scenario-verification strategy combinations to obtain a complete set of verification strategy configuration schemes (that is, randomly match all operation scenarios with one verification strategy combination in the corresponding initial verification strategy set, and then integrate all operation scenarios with the matched verification strategies to obtain a set of verification strategy configuration schemes); Repeat the assignment operation b times to obtain b different verification strategy configuration schemes, and then form an initial strategy configuration pool; Based on the initial strategy configuration pool, calculate the effective value of each initial operation scenario-verification strategy combination in each verification strategy configuration scheme, and take the average value to obtain the average effective value of each verification strategy configuration scheme; An exemplary formula for the effective value is: ; Among them, represents the effective value, , and represent preset proportionality factors, and , represents the verification success rate, which is used to represent the reliability of the strategy combination, is equal to the ratio of the number of successful verifications to the total number of verifications, represents the safety factor, which is used to represent the strength enhancement of multi-factor verification, ; ( )Indicates security optimization items, directly reflecting the reliability of the policy combination, non-linearly enhancing multi-factor authentication (e.g., two-factor aq = 2, three-factor aq = 3), through the proportional factor reflects the principle of security priority (recommended ≥0.6); yzcl represents the number of verification factors, that is, the number of verification methods in the verification policy combination. For example, if (fingerprint + iris + vein recognition + dynamic password) is used in a verification policy combination, then the number of verification factors is 3, represents the average verification time, which is used to represent the user experience and system real-time performance, that is, the mean value of the single verification time consumption (the weighted average of the single verification time consumption of the local node and the cloud node), represents the maximum tolerance time, which is used to represent the business scenario constraints, that is, the longest verification time threshold allowed by the system (e.g., usually set to 5 seconds in medical applications); ( ) represents the efficiency penalty item, and the penalty intensifies when the verification time exceeds the tolerance threshold (e.g., if it times out by 50%, then the deduction is 0.5× ), promoting the system to optimize the response speed under the premise of security (in the emergency scenario, it needs to be ≥ ); represents the resource consumption, which is used to represent the hardware and communication costs, that is, the device CPU occupancy + network bandwidth + storage IO, represents the resource upper limit, which is used to represent the infrastructure limitations, that is, the upper limit of the system resource capacity; ( ) represents the resource penalty item, and the closer the resource occupancy is to the upper limit, the higher the deduction ratio (e.g., when the CPU occupancy is 90%, the deduction is 0.9× ), to avoid overloading of edge devices (in the primary hospital scenario, it needs to be ≥0.1); For the setting of the formula weights, in addition to manual setting, the optimal weights can be determined through historical data training (such as grid search + cross-validation). In the emergency scenario, it is recommended: ( =0.5, , ), in the pharmacy scenario, it is recommended: ( =0.7, , ); In addition, the valid values can be customized according to the specific situation, such as true positive rate, recall rate, true negative rate, precision rate, response time, computational complexity, resource utilization rate; For each operation scenario, extract the verification policy combination with the highest valid value from the c verification policy configuration schemes with the highest average valid value, obtain a new operation scenario-verification policy combination, and then integrate it into a new verification policy configuration scheme; Replace the validation strategy configuration solution with the lowest average valid value in the initial strategy configuration pool using a new validation strategy configuration solution, and repeat the iterative operations of valid value calculation, extraction, and replacement until the maximum number of iterations is reached or the valid values of all operation scenario - validation strategy combinations no longer increase, and obtain the best validation strategy combination for all operation scenarios; Update the operation scenario - validation strategy mapping table using the best validation strategy combination, and use an expert rule engine to generate a knowledge - driven decision rule base based on the updated operation scenario - validation strategy mapping table; According to the knowledge - driven decision rule base, match a validation strategy combination for the operator. According to the matched validation strategy combination, obtain the operator's multi - modal biometric identifiers through the device the operator is currently operating on, and integrate them into a biometric identifier set; Among them, the multi - modal biometric identifiers include vein biometric identifiers, fingerprint biometric identifiers, iris biometric identifiers, and one - time password biometric identifiers; Perform preliminary processing on the operator's biometric identifier set, including image pre - processing, biometric identifier extraction, and multi - modal biometric identifier fusion; Image pre - processing is to perform noise elimination and contrast enhancement processing on the operator's vein image, fingerprint image, and iris image during the processes of vein recognition, fingerprint recognition, and iris recognition; Biometric identifier extraction is to respectively extract vein features, fingerprint features, iris features, and one - time password features from the vein image, fingerprint image, and iris image after image pre - processing, and the one - time password of the one - time verification code type using feature extraction techniques; Multi - modal biometric identifier fusion is to convert the corresponding features into a unified vector space according to the validation strategy, and then perform multi - modal fusion through the weighted fusion method; If the matched validation strategy is for local node verification, send the preliminarily processed multi - modal biometric identifier set to the local node; If the matched validation strategy is for cloud node verification, send the preliminarily processed multi - modal biometric identifier set to the local node and d cloud nodes (such as municipal medical certification centers, provincial medical certification centers), and d is greater than 1; For the device the operator is currently operating on and each participating verification node, independently use its own database to perform feature comparison (such as Hamming distance calculation, cosine similarity) on the received biometric identifier set to obtain the corresponding verification results, including whether it matches and the corresponding confidence score; According to all the verification results, calculate the difference value between all the verification results. If the difference value is less than the preset difference value threshold, determine that the verification results are correct, use them as the final verification results, and generate corresponding verification result signals. The types of verification result signals include verification success signals and verification failure signals; If the difference value is greater than or equal to the preset difference value threshold, it is determined that the current verification has abnormal behavior, triggering the locking mechanism and generating a verification failure signal, while providing feedback to the operator; Based on the verification success signal, the biometric identifier set is converted into a biometric hash value, and the biometric hash value, the final verification result and the operation risk score are encrypted; It should be noted that existing systems often use fixed strategies for identity verification and cannot dynamically adjust verification strength according to real-time risks, resulting in insufficient security protection in high-risk scenarios and low verification efficiency in low-risk scenarios. For example, traditional fingerprint verification is easily copied and used when picking up high-risk drugs at night, while dynamic passwords add unnecessary complexity to routine operations during the day. Static verification strategies cannot perceive the operation context. There is a contradiction between the accuracy and efficiency of multimodal biometric verification. There is a lack of collaborative decision-making between local and cloud node verification, resulting in a high misjudgment rate. The operator identity authentication and dynamic generation verification unit builds a knowledge-driven decision rule base, dynamically generates verification strategy combinations based on operational risk scores, and achieves a balance between security and efficiency through multi-node collaborative verification; The ways to obtain the early warning conflict intensity include: Based on the encrypted final verification result, obtain the patient's prescription data, including the drug name and dosage, and then obtain the corresponding prescription dosage; Capture and analyze the prescription medication data of all departments of patients through the hospital HIS system, and calculate the cumulative dosage of similar drugs within 24 hours; Use the white box rule engine to retrieve the corresponding drug instructions in the hospital HIS system and extract the maximum single dose and 24-hour cumulative dose thresholds; The 24-hour cumulative dose threshold is adjusted according to the patient's liver and kidney function status to obtain a revised cumulative dose threshold; Based on the cumulative dose of similar drugs and the revised cumulative dose threshold, if the cumulative dose is less than or equal to the cumulative dose threshold, the drug dose is determined to be in compliance with the specification; If the cumulative dose is greater than the cumulative dose threshold, it is determined that the drug dose does not meet the specification and a drug dose warning is generated; Obtain the patient's disease, allergy history, liver and kidney function indicators and treatment plan, and then build an association rule base of drug-disease-test indicator-treatment plan, and use the association rule base to build a clinical pathway knowledge graph; Use the clinical pathway knowledge graph to perform subgraph matching operations on the current prescription data and calculate the clinical pathway compliance (i.e., calculate the cosine similarity between the drugs in the prescription data and the clinical pathway, and use the cosine similarity value as the clinical pathway compliance); When the clinical pathway compliance is greater than or equal to the preset clinical pathway compliance threshold, it is determined that the clinical pathway compliance meets the specification; When the clinical pathway compliance is less than the preset clinical pathway compliance threshold, it indicates a deviation from the standard pathway. It is determined that the clinical pathway compliance does not meet the specification, and a clinical pathway compliance warning is generated; Use the pharmacokinetic interaction matrix to detect high-risk interaction combinations in the prescription drug data of the entire department; If a high-risk interaction combination is detected, it is determined that there is a high-risk interaction combination in the prescription, and a high-risk warning is generated; if no high-risk combination is detected, it is determined that there is no high-risk interaction combination in the prescription; According to the determination results of the drug dosage specification, clinical pathway compliance, and high-risk interaction combinations, obtain the warning conflict intensity (one method is to record the drug dosage compliance as 1, non-compliance as 0, the clinical pathway compliance as 1, non-compliance as 0, the existence of a high-risk interaction combination as 0, and the non-existence of a high-risk interaction combination as 1, that is, the drug dosage specification determination result = [0, 1], the clinical pathway compliance determination result = [0, 1], the high-risk interaction combination determination result = [0, 1], add the three determination results to obtain the warning conflict intensity. In an example, the drug dosage specification meets the specification, that is, the drug dosage specification determination result is 1, the clinical pathway compliance does not meet the specification, that is, the clinical pathway compliance determination result is 0, there is no high-risk interaction combination, that is, the high-risk interaction combination determination result is 1, then the warning conflict intensity is 2); It should be noted that traditional fingerprint verification has a high false recognition rate under fatigue operation. In an example, according to the time granularity (night) and drug control level (category I), intravenous + iris verification can be dynamically enabled; The ways to modify the cumulative dose threshold include: Obtain the patient's liver function index and kidney function index through the hospital HIS system, and use the Cockcroft-Gault formula to calculate the kidney function correction factor through the kidney function index; Use the Child-Pugh scoring system to evaluate and obtain the liver function correction factor; Combine the kidney function correction factor and the liver function correction factor to construct a multi-organ function adjustment model based on the minimum value rule, and output the correction coefficient of the cumulative dose threshold; The multi-organ function adjustment model based on the minimum value rule is: ; where represents the correction coefficient of the cumulative dose threshold, represents the kidney function correction factor, represents the liver function correction factor; Multiply the correction coefficient by the 24-hour cumulative dose threshold to obtain the modified cumulative dose threshold; The construction method of the pharmacokinetic interaction matrix includes: Collect data on all psychotropic drugs and all other drugs with known interactions with psychotropic drugs, and integrate them into a set of drug categories, including the name, main ingredient, common dosage range, administration route, known interactions between different drugs and their mechanisms (such as inhibiting or inducing CYP450 isozymes), and main pharmacokinetic parameters, including, for example, half-life, clearance rate, bioavailability, volume of distribution; these parameters are crucial for evaluating potential interactions between drugs; According to the known interactions of drugs, classify the drugs into different categories according to the mechanism, such as inhibiting or inducing CYP450 isozymes, competitively binding plasma proteins, changing gastrointestinal pH to affect absorption; for the classified drugs, assign an interaction intensity to each pair of interacting drugs (the interaction intensity is assigned according to expert experience, which can be a grade, such as mild, moderate, severe, or an intensity value, such as 0.3, 0.5, 0.8); Use one drug as the row and another drug as the column to construct a two-dimensional matrix. If n drugs are considered, the matrix is a square matrix of size n×n, and each cell in the matrix represents the interaction between a pair of drugs; For each pair of drug combinations, fill in the corresponding interaction information in the corresponding cell of the matrix, including the interaction type (such as CYP450 inhibition), interaction intensity (mild, moderate, severe), and any relevant changes in pharmacokinetic parameters; for the diagonal cells of the matrix (i.e., the case where the same drug is paired with itself), mark it as none because the interaction of the same drug with itself is usually not considered; obtain the constructed pharmacokinetic interaction matrix; It should be noted that traditional prescription review mostly relies on manual experience, making it difficult to detect drug interactions across departments in real time, especially lagging in identifying hidden threats such as metabolic pathway conflicts and dose accumulation risks. For example, doctors may overlook dose corrections for patients with liver and kidney insufficiency or fail to detect toxicity superposition caused by competitive inhibition of CYP3A4 enzymes; That is, single-point dose verification does not consider the dynamic changes of organ function, clinical pathway matching is only based on the diagnosis name, lacks semantic association of quality programs, and the drug interaction library is updated laggingly, unable to cover the risks of new combinations; The prescription data verification and early warning conflict intensity calculation unit introduces a white-box rule engine, dynamically adjusts the dose threshold in combination with correction factors of organ function (including liver function and kidney function), and real-time scans the risks of multi-drug combination through a pharmacokinetic interaction tensor (three-dimensional structure), realizing the quantitative output of the early warning conflict intensity; The method for obtaining the encrypted evidence chain package includes: Take the identifier of the operator himself as the personal node, the geographical location of the operator as the location node, the encrypted biometric hash as the time node, and the early warning conflict intensity as the intensity node; Define that the edge connecting the personal node and the location node represents that the operator has accessed the device location where the operator is currently operating during the current period t; define the edge between the personal node and the time node as that the operator has submitted a biometric sample during the current period t; define the edge between the personal node and the intensity node represents the risk assessment result of the current operation; Construct a spatio-temporal-biometric joint map according to the defined nodes and edges; Use a predefined risk assessment model (the risk assessment model can be constructed and trained through a linear regression model or a machine learning model, and is used to take the spatio-temporal-biometric joint map as input and output a real-time risk score) to analyze the paths and connections in the spatio-temporal-biometric joint map, and calculate the real-time risk score at the current period; Perform a weighted sum of the real-time risk score and the early warning conflict intensity to obtain a comprehensive risk assessment value; Based on the comprehensive risk assessment value, set an interception threshold interval. If the comprehensive risk assessment value is less than the minimum value of the interception threshold interval, it is determined that the current operation of the operator is risk-free and no interception is performed; If the comprehensive risk assessment value is greater than or equal to the minimum value of the interception threshold interval and less than or equal to the maximum value of the interception threshold interval, it is determined that the current operation of the operator is risky, and an interception instruction is generated (the interception instruction can be to reject the operator's further access, that is, to reject the operator's current drug application); If the comprehensive risk assessment value is greater than the maximum value of the interception threshold interval, it is determined that the current operation of the operator is highly risky, an interception instruction is generated and a physical isolation measure is executed (the physical isolation measure can be to forcibly lock the narcotic and psychotropic drug management cabinet for a certain period of time, such as 30 seconds, or 30 minutes, during which it cannot be opened by non-destructive means, and can continue to operate only when the locking time ends), and an alarm message is sent at the same time; Integrate the identifier of the operator himself, the geographical location of the operator, the encrypted biometric hash, the early warning conflict intensity, and the corresponding spatio-temporal-biometric joint map, real-time risk score, comprehensive risk assessment value, and the final interception decision, and encrypt them through the Advanced Encryption Standard to form an encrypted evidence chain package; It should be noted that most of the existing risk interception type methods rely on single-dimensional data (such as the number of prescriptions), and cannot identify spatio-temporal abnormal patterns (such as high-frequency drug collection across regions) and biometric fraud behaviors, resulting in too high a missed detection rate for risks of the type of "illegal operation with legal identity". In the existing technology, geographical location data and biometric verification results are often analyzed in isolation, the risk scoring model is static, and it cannot adapt to the evolution of abuse means. The blocking measures are single (such as only pop-up prompts), and there is a lack of a hierarchical response mechanism; The real-time risk assessment and multi-level intervention blocking unit analyzes the operator's trajectory, biometric hash, and prescription data by constructing a spatio-biological joint map. By constructing a comprehensive risk assessment value, it triggers hierarchical blocking (such as monitoring / alerting / physical isolation) and generates an encrypted evidence chain package to support judicial traceability; The generation methods of the audit report and the drug flow heat map include: Combining the operation risk score, warning conflict intensity, and encrypted evidence chain package to generate a drug management trajectory file, which contains the operator's basic information, operation time series, geographical location, biometric verification results, warning conflict intensity, and intervention measures taken; Using a cross-chain deposit protocol (such as blockchain technology or other cross-chain deposit protocols), store the generated drug management trajectory file on a distributed ledger to ensure its immutability and transparency, and adopt a multi-party verification mechanism (such as a multi-node consensus algorithm) to enhance the credibility of the file; Based on knowledge graph technology, construct a visual audit graph according to the drug management trajectory file. According to the visual audit graph, generate an audit report and a drug flow heat map; display the key information in the drug management trajectory file. The visual audit graph includes the operator's activity path, risk assessment results, warning conflict intensity, and drug flow information; Using optimization algorithms (such as genetic algorithms, ant colony algorithms) to dynamically update the operation risk threshold interval based on the audit report, and update the knowledge-driven decision rule base and verification strategy configuration plan according to the updated operation risk threshold interval, reducing manual intervention and enhancing the system's self-learning and optimization capabilities; Deploy the updated rule base and verification strategy configuration plan, continuously monitor the system's performance, and further adjust the parameters according to the latest data to ensure the continuous optimization of the system.

[0019] Embodiment 2 Please refer to Figure 3 As shown, for the parts not described in detail in this embodiment, refer to the description content of Embodiment 1. Provide an intelligent anesthetic and psychotropic drug management method, including: S1: The operator verifies based on the operation context parameters to obtain an operation risk score, and then constructs a knowledge-driven decision rule base to dynamically generate the operator's verification strategy, and cooperates with multiple nodes to verify the multi-modal biometric identifier set of the operator to obtain the verification result and biometric hash; S2: Based on the verification result, grab the patient's full-department drug use data, gradually verify the dosage specification and clinical path compliance through a white-box rule engine, and identify high-risk combinations through a pharmacokinetic interaction matrix to obtain the warning conflict intensity; S3: Based on the operator's geographical location, combining the encrypted biometric hash, operation risk score, prescription data, and warning conflict intensity, construct a spatio-temporal - biological joint map, and then obtain a real-time risk score. Combine the real-time risk score and warning conflict intensity to generate a comprehensive risk assessment value. According to the comprehensive risk assessment value, generate an interception instruction to execute multi-level intervention and blocking measures for high-risk behaviors, and obtain an encrypted evidence chain package; S4: Generate a drug management trajectory file based on the operation risk score, warning conflict intensity, and encrypted evidence chain package, construct a visual audit map, and generate an audit report and a heat map of drug flow; S5: Dynamically adjust the operation risk threshold range according to the audit report and the heat map of drug flow, and update the knowledge-driven decision rule base and the verification strategy configuration plan.

[0020] Embodiment III

[0021] This embodiment publicly provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the operation mode of the above-provided intelligent narcotic and psychotropic drug management method.

[0022] Since the electronic device introduced in this embodiment is the electronic device used to implement an intelligent narcotic and psychotropic drug management method in an embodiment of the present application, based on the intelligent narcotic and psychotropic drug management method introduced in an embodiment of the present application, those skilled in the art can understand the specific implementation manner and various variations of the electronic device in this embodiment. Therefore, the implementation of how this electronic device realizes the method in an embodiment of the present application will not be described in detail here. As long as those skilled in the art implement the electronic device used in an intelligent narcotic and psychotropic drug management method in an embodiment of the present application, it belongs to the scope of protection of the present application.

[0023] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula that is closest to the actual situation. The preset parameters and threshold selection in the formulas are set by those skilled in the art according to the actual situation.

[0024] The above are only the preferred embodiments of the present invention. The protection scope of the present invention is not limited to the above embodiments. All technical solutions falling within the idea of the present invention belong to the protection scope of the present invention. It should be noted that for ordinary technical users in the technical field, several improvements and refinements made without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. An intelligent narcotic drug management system, characterized in that: include: Operator identity authentication and dynamic generation verification unit: The operator is verified based on the operation context parameters to obtain the operation risk score, and then a knowledge-driven decision rule base is built to dynamically generate the operator's verification strategy, and the operator's multimodal biometric identifier set is verified through multi-node collaboration to obtain the verification result and biometric hash; Prescription data verification and early warning conflict strength calculation unit: Based on the verification results, the patient's medication data in all departments is captured, and the drug dosage specifications and clinical pathway compliance are verified step by step through the white box rule engine. High-risk combinations are identified through the pharmacokinetic interaction matrix to obtain the early warning conflict strength; Real-time risk assessment and multi-level intervention blocking unit: Based on the operator's geographic location, combined with encrypted biometric hash, operation risk score, prescription data and warning conflict strength, a spatiotemporal-biological joint map is constructed to obtain a real-time risk score. Combined with the real-time risk score and warning conflict strength, a comprehensive risk assessment value is generated. Based on the comprehensive risk assessment value, an interception instruction is generated to execute multi-level intervention blocking measures for high-risk behaviors and obtain an encrypted evidence chain package; Visual report generation unit: Generate drug management track files based on operational risk scores, warning conflict strength and encrypted evidence chain packages, build visual audit maps, generate audit reports and drug flow heat maps; Dynamic adjustment and optimization unit: Dynamically adjust the operational risk threshold interval, update the knowledge-driven decision rule base and verify the strategy configuration plan based on the audit report and drug flow heat map.

2. The intelligent narcotic drug management system according to claim 1 is characterized in that: The construction method of the knowledge-driven decision rule base includes: Operational context parameters include time granularity, pharmaceutical pedigree and corresponding drug control level, historical behavior reputation value, geographic location, and device information; Use the weighted average method to calculate all influencing factors within the operational context parameters to obtain the operational risk score, and set the operational risk threshold range to divide the operational risk score into different operational risk levels; Set the geo-fence and maximum deviation distance. If the actual path distance between the geographic location and the geo-fence range is greater than the maximum deviation distance, it will be marked as a location anomaly. If the actual path distance between the geographic location and the geographic fence range is less than or equal to the maximum deviation distance, the location is marked as normal; the normal location and abnormal location are regarded as the location status of the geographic location; Combine different time granularities, location status, drug control levels, and operational risk levels as an operational scenario; One or more verification strategies are randomly selected from the verification strategy set, and a verification occurrence mode is randomly selected from the edge and cloud center verification, and the selected verification strategies and verification occurrence modes are combined to form a verification strategy combination; Among them, the verification strategy set includes vein recognition, fingerprint recognition, iris recognition and dynamic password. The edge and cloud center verification includes local node verification and cloud node verification. The local node is the local server and the cloud node is the remote data center. For each operation scenario, a type is randomly selected from all strategy combinations as the initial verification strategy set for the operation scenario; Integrate all operation scenarios and corresponding initial verification strategy sets to construct an initial operation scenario-verification strategy mapping table; The initial operation scenario-verification strategy mapping table is updated, and an expert rule engine is used to generate a knowledge-driven decision rule base according to the updated operation scenario-verification strategy mapping table.

3. The intelligent narcotic drug management system according to claim 2 is characterized in that: The method of updating the initial operation scenario-verification strategy mapping table includes: According to the initial operation scenario-verification strategy mapping table, a verification strategy combination is randomly assigned to each operation scenario to obtain the initial operation scenario-verification strategy combination, and then all initial operation scenario-verification strategy combinations are integrated to obtain a complete set of verification strategy configuration schemes; the allocation operation is repeated b times to obtain b different verification strategy configuration schemes, which then constitute the initial strategy configuration pool; Based on the initial policy configuration pool, calculate the effective value of each initial operation scenario-verification policy combination in each verification policy configuration scheme, and take the average value to obtain the average effective value of each verification policy configuration scheme; For each operation scenario, extract the verification strategy combination with the highest effective value from the c verification strategy configuration schemes with the highest average effective value, obtain a new operation scenario-verification strategy combination, and then integrate it into a new verification strategy configuration scheme; Use the new verification strategy configuration scheme to replace the verification strategy configuration scheme with the lowest average effective value in the initial strategy configuration pool, and repeat the iterative effective value calculation, extraction and replacement operations until the maximum number of iterations is reached or the effective values ​​of all operation scenario-verification strategy combinations are no longer increasing, and then the best verification strategy combination for all operation scenarios is obtained; The operation scenario-verification strategy mapping table is updated using the best verification strategy combination to obtain an updated operation scenario-verification strategy mapping table.

4. The intelligent narcotic drug management system according to claim 3 is characterized in that: The verification result and the biometric hash are obtained by: According to the knowledge-driven decision rule base, a verification strategy combination is matched for the operator, and according to the matched verification strategy combination, a multimodal biometric identifier of the operator is obtained through a device currently operated by the operator, and the multimodal biometric identifier is integrated into a biometric identifier set; Among them, multimodal biometric identifiers include vein biometric identifiers, fingerprint biometric identifiers, iris biometric identifiers, and dynamic password biometric identifiers; Perform preliminary processing of the operator's biometric identifier set, including image preprocessing, biometric identifier extraction, and multimodal biometric identifier fusion; If the matched verification strategy is local node verification, the preliminarily processed multimodal biometric identifier set is sent to the local node; If the matched verification strategy is cloud node verification, the preliminarily processed multimodal biometric identifier set is sent to the local node and d cloud nodes, where d is greater than 1; For the device currently operated by the operator and each node participating in the verification, the operator independently uses its own database to perform feature comparison on the received biometric identifier set to obtain the corresponding verification result, including whether it matches and the corresponding confidence score; According to all the verification results, the difference values ​​between all the verification results are calculated. If the difference value is less than the preset difference value threshold, the verification result is determined to be correct and is used as the final verification result. A corresponding verification result signal is generated. The types of verification result signals include verification success signal and verification failure signal. If the difference value is greater than or equal to the preset difference value threshold, it is determined that the current verification has abnormal behavior, triggering the locking mechanism and generating a verification failure signal, while providing feedback to the operator; Based on the verification success signal, the biometric identifier set is converted into a biometric hash value and encrypted to obtain an encrypted biometric hash.

5. The intelligent narcotic drug management system according to claim 4 is characterized in that: The methods of warning conflict intensity include: Based on the encrypted final verification result, the patient's prescription data is obtained, and then the corresponding prescription dosage is obtained; Capture and analyze the prescription medication data of all departments of patients through the hospital HIS system, and calculate the cumulative dosage of similar drugs within 24 hours; Use the white box rule engine to retrieve the corresponding drug instructions in the hospital HIS system and extract the maximum single dose and 24-hour cumulative dose thresholds; The 24-hour cumulative dose threshold is adjusted according to the patient's liver and kidney function status to obtain a revised cumulative dose threshold; Based on the cumulative dose of similar drugs and the revised cumulative dose threshold, if the cumulative dose is less than or equal to the cumulative dose threshold, the drug dose is determined to be in compliance with the specification; If the cumulative dose is greater than the cumulative dose threshold, it is determined that the drug dose does not meet the specification and a drug dose warning is generated; Obtain the patient's disease, allergy history, liver and kidney function indicators and treatment plan, and then build an association rule base of drug-disease-test indicator-treatment plan, and use the association rule base to build a clinical pathway knowledge graph; Use the clinical pathway knowledge graph to perform subgraph matching operations on the current prescription data and calculate the clinical pathway compliance; If the clinical pathway compliance is greater than or equal to the preset clinical pathway compliance threshold, the clinical pathway compliance is determined to be in compliance with the specification; If the clinical pathway compliance is less than the preset clinical pathway compliance threshold, it means that the standard pathway is deviated, the clinical pathway compliance is judged to be non-compliant, and a clinical pathway compliance warning is generated; Apply the pharmacokinetic interaction matrix to detect high-risk interaction combinations in department-wide prescription medication data; If a high-risk interaction combination is detected, the prescription is determined to have a high-risk interaction combination and a high-risk warning is generated; if no high-risk combination is detected, the prescription is determined to have no high-risk interaction combination; The warning conflict intensity is obtained based on the determination results of drug dosage specifications, clinical pathway compliance, and high-risk interaction combinations.

6. The intelligent narcotic drug management system according to claim 5, characterized in that: The modified cumulative dose threshold is obtained by: The patient's liver function index and renal function index were obtained through the hospital HIS system, and the renal function correction factor was calculated using the Cockcroft-Gault formula based on the renal function index; The Child-Pugh scoring system was used to evaluate the liver function correction factor; Combining the correction factors of renal function and liver function, a multi-organ function adjustment model based on the minimum value rule was constructed, and the correction coefficient of the cumulative dose threshold was output; The product of the correction coefficient and the 24-hour cumulative dose threshold is taken to obtain the corrected cumulative dose threshold.

7. The intelligent narcotic drug management system according to claim 6, characterized in that: The pharmacokinetic interaction matrix is ​​constructed in the following manner: Collect data on all narcotic drugs and all other drugs with known interactions with narcotic drugs, and integrate them into drug category sets, including the name, main ingredients, common dosage range, route of administration, known interactions between different drugs and their mechanisms, and the main pharmacokinetic parameters of each drug; Based on the known interactions of drugs, the drugs are divided into different categories according to their mechanisms, and the interaction strength is assigned to each pair of drugs that interact with each other according to the classified drugs; A two-dimensional matrix is ​​constructed with one drug as a row and another drug as a column. Each cell in the matrix represents the interaction between a pair of drugs. For each pair of drug combinations, the corresponding interaction information is filled in the corresponding cells in the matrix to obtain the constructed pharmacokinetic interaction matrix.

8. The intelligent narcotic drug management system according to claim 7 is characterized in that: The method of obtaining the encrypted evidence chain package includes: The operator's own identifier is used as the personal node, the operator's geographical location is used as the location node, the encrypted biometric hash is used as the time node, and the warning conflict intensity is used as the intensity node; The edge connecting the personal node and the location node is defined to indicate that the operator has visited the device location currently operated by the operator in the current period t; the edge connecting the personal node and the time node is defined to indicate that the operator has submitted a biometric sample in the current period t; the edge connecting the personal node and the strength node is defined to indicate the risk assessment result of the current operation; Based on the defined nodes and edges, a spatiotemporal-biological joint graph is constructed; Use a predefined risk assessment model to analyze the paths and connections in the spatiotemporal-biological joint graph and calculate a real-time risk score for the current period; The real-time risk score and the warning conflict intensity are weighted and summed to obtain a comprehensive risk assessment value; Based on the comprehensive risk assessment value, an interception threshold interval is set. If the comprehensive risk assessment value is less than the minimum value of the interception threshold interval, the operator's current operation is judged to be risk-free and will not be intercepted; If the comprehensive risk assessment value is greater than or equal to the minimum value of the interception threshold interval, and less than or equal to the maximum value of the interception threshold interval, the operator's current operation is determined to be risky, and an interception instruction is generated; If the comprehensive risk assessment value is greater than the maximum value of the interception threshold range, the operator's current operation is judged to be high-risk, an interception instruction is generated, physical isolation measures are executed, and an alarm message is issued; The operator's own identifier, the operator's geographic location, the encrypted biometric hash and warning conflict strength, as well as the corresponding spatiotemporal-biological joint map, real-time risk score, comprehensive risk assessment value and final interception decision are integrated and encrypted through the Advanced Encryption Standard to form an encrypted evidence chain package.

9. The intelligent narcotic drug management system according to claim 8, characterized in that: The audit report and the drug flow heat map are generated by: Combine operational risk scores, warning conflict strength, and encrypted evidence chain packages to generate medication management trajectory profiles; Based on knowledge graph technology, a visual audit map is constructed according to the drug management trajectory archive, and based on the visual audit map, an audit report and a heat map of drug flow are generated.

10. An intelligent narcotic drug management method, applied to the intelligent narcotic drug management system according to any one of claims 1 to 9, characterized in that: include: S1: The operator verifies based on the operation context parameters and obtains the operation risk score, then builds a knowledge-driven decision rule base to dynamically generate the operator's verification strategy, and verifies the operator's multimodal biometric identifier set through multi-node collaboration to obtain the verification result and biometric hash; S2: Based on the verification results, the drug use data of all departments of the patients are captured, and the drug dosage specifications and clinical pathway compliance are verified step by step through the white box rule engine. The high-risk combinations are identified through the pharmacokinetic interaction matrix to obtain the warning conflict intensity; S3: Based on the operator's geographic location, combined with encrypted biometric hash, operation risk score, prescription data and warning conflict strength, a spatiotemporal-biological joint map is constructed to obtain a real-time risk score. Combined with the real-time risk score and warning conflict strength, a comprehensive risk assessment value is generated. Based on the comprehensive risk assessment value, an interception instruction is generated to execute multi-level intervention blocking measures for high-risk behaviors, and an encrypted evidence chain package is obtained; S4: Generate drug management trajectory files based on operational risk scores, warning conflict strength, and encrypted evidence chain packages, build visual audit maps, and generate audit reports and drug flow heat maps; S5: Based on the audit report and drug flow heat map, dynamically adjust the operational risk threshold interval, update the knowledge-driven decision rule base and verify the strategy configuration plan.

Images