Intelligent drug expiration date management method and system

Abstract

The invention relates to the technical field of medicine management, in particular to an intelligent medicine expiration date management method and system, and the method comprises the steps: collecting environment parameters of medicine storage in real time; constructing a characteristic database of drug stability, and constructing a degradation rate model of the corresponding drug based on the characteristic database; based on the environmental parameters and a degradation rate model, calculating an accumulated value of the current storage condition to the drug quality, and generating a quality risk level; and generating a medicine optimization management instruction based on the quality risk level and the remaining time of the medicine fixed effective period. By means of the method, the problem that the medicine effect fails in advance due to the fact that dynamic environment factors are neglected in a traditional method is effectively solved, accurate early warning of quality deterioration is achieved through dynamic monitoring and degradation modeling, supervision blind areas are eliminated, and the risk of medical resource waste is reduced.

Description

Technical Field

[0001] This invention relates to the field of pharmaceutical management technology, and in particular to an intelligent method and system for managing the expiration date of pharmaceutical products. Background Technology

[0002] In the field of pharmaceutical distribution management, the current common practice is to adopt a fixed expiration date management model based on production date labeling. This model determines the usable period of drugs through a preset time cycle and mainly relies on manual periodic verification and the first-in, first-out (FIFO) principle for inventory turnover.

[0003] The calculation of fixed expiration dates is based on the assumption of ideal storage conditions and does not establish a correlation model between dynamic environmental parameters and drug degradation rates in actual transportation and warehousing. This leads to the deterioration of drug quality within the marked expiration date due to accumulated environmental stress in scenarios such as cold chain breakage and abnormal warehouse temperature control. This creates a regulatory blind spot of "the drug has lost its efficacy before the expiration date", which seriously threatens drug safety and wastes medical resources. Summary of the Invention

[0004] The purpose of this invention is to address the shortcomings of existing technologies by proposing an intelligent method and system for managing the expiration date of pharmaceutical products.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: an intelligent method for managing the expiration date of pharmaceutical products, comprising the following steps:

[0006] Real-time collection of environmental parameters for drug storage;

[0007] A feature database of drug stability is constructed, and a degradation rate model of the corresponding drug is constructed based on the feature database;

[0008] Based on the environmental parameters and degradation rate model, the cumulative value of the current storage conditions on drug quality is calculated, and a quality risk level is generated.

[0009] Based on the quality risk level and the remaining time of the drug's fixed shelf life, a drug optimization management instruction is generated.

[0010] Furthermore, a characteristic database of drug stability is constructed, including:

[0011] Obtain key stability parameters of the drug, including environmental sensitive factors and dosage form characteristics;

[0012] Based on the aforementioned key stability parameters, a multi-stress coupling model is established;

[0013] The multi-stress coupling model converts the real-time collected environmental parameter sequence into equivalent environmental stress cumulative values.

[0014] The feature database is generated by associating the equivalent environmental stress accumulation value with the drug batch characteristic data.

[0015] Furthermore, through the aforementioned multi-stress coupling model, the real-time acquired environmental parameter sequence is converted into equivalent cumulative environmental stress values, including:

[0016] The environmental parameters are dimensionless, and the stress contribution of each parameter is calculated.

[0017] Based on the weighting coefficients of the multi-stress coupling model, the equivalent cumulative environmental stress value is synthesized.

[0018] Furthermore, based on the feature database, a degradation rate model for the corresponding drug is constructed, including:

[0019] Based on the feature database, construct a multidimensional parameter mapping relationship;

[0020] Based on the collaborative modeling of physicochemical mechanism equations and real-time environmental data, a composite degradation rate function is generated;

[0021] Based on the composite degradation rate function, the model parameters are initialized and dynamically calibrated to obtain the degradation rate model.

[0022] Furthermore, the physicochemical mechanism equation is as follows:

[0023]

[0024] in, The total reaction rate is... Pre-exponential factor, For degradation activation energy, Let be the ideal gas constant. Thermodynamic temperature The critical relative humidity for pharmaceuticals. Relative humidity, and These are the sensitivity coefficient and the nonlinearity index, respectively. These are the spectral sensitivity weighting coefficients. For wavelength range, For a moment The wavelength is Light intensity, This is the starting point of the photodamage effect. This represents the current calculation time for the photodamage effect.

[0025] Furthermore, based on the aforementioned environmental parameters and degradation rate model, the cumulative effect of current storage conditions on drug quality is calculated, generating a quality risk level, including:

[0026] The environmental parameters are input into the degradation rate model for dynamic coupling;

[0027] The dynamic coupling results are accumulated in real time to generate a cumulative mass loss value that reflects changes in drug quality;

[0028] Risk levels are determined based on the cumulative quality loss value.

[0029] Furthermore, based on the aforementioned quality risk level and the remaining time of the drug's fixed expiration date, a drug optimization management instruction is generated, including:

[0030] Based on historical drug quality data and corresponding environmental parameters, risk-time mapping rules are obtained, and a dynamic strategy tree model containing multi-level decision nodes is constructed.

[0031] The real-time monitored quality risk level and the remaining expiration date data of the drug label are synchronously input into the dynamic measurement tree model to generate a strategy matching confidence score;

[0032] Based on the confidence score of the strategy, a preset management strategy is matched, and the drug optimization management instruction is generated.

[0033] Furthermore, the method also includes: establishing an evaluation index for the effect of the instructions by collecting quality tracking data after the drug distribution nodes execute the optimized management instructions, and dynamically correcting the parameter weights of the degradation rate model and the dynamic strategy tree model.

[0034] An intelligent drug expiration date management system includes:

[0035] The environmental parameter acquisition module collects environmental parameters of the drug storage area in real time.

[0036] The rate model construction module constructs a feature database of drug stability and builds a degradation rate model for the corresponding drug based on the feature database.

[0037] The risk level generation module calculates the cumulative value of the current storage conditions on drug quality based on the environmental parameters and degradation rate model, and generates a quality risk level.

[0038] The management instruction generation module generates drug optimization management instructions based on the quality risk level and the remaining time of the drug's fixed expiration date.

[0039] Furthermore, the risk level generation module includes:

[0040] The dynamic coupling unit inputs the environmental parameters into the degradation rate model for dynamic coupling;

[0041] The coupling accumulation unit accumulates the dynamic coupling results in real time to generate a cumulative mass loss value that reflects changes in drug quality.

[0042] The risk level is determined by the cumulative quality loss value.

[0043] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0044] This invention effectively solves the problem of "premature drug efficacy failure" caused by neglecting dynamic environmental factors in traditional methods. It achieves accurate early warning of quality deterioration through dynamic monitoring and degradation modeling, eliminating regulatory blind spots and reducing the risk of medical resource waste. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a flowchart illustrating an intelligent method for managing the expiration date of pharmaceutical products.

[0047] Figure 2 A flowchart illustrating the process of constructing a feature database for drug stability;

[0048] Figure 3 This is a schematic diagram illustrating the process of converting real-time acquired environmental parameter sequences into equivalent cumulative environmental stress values.

[0049] Figure 4 A schematic diagram illustrating the process of constructing a degradation rate model for a corresponding drug based on a feature database;

[0050] Figure 5 A flowchart illustrating the process for generating quality risk levels;

[0051] Figure 6 A flowchart illustrating the process for generating drug optimization management instructions. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0054] Example 1

[0055] like Figure 1 As shown, this invention provides an intelligent method for managing the expiration date of pharmaceutical products, the method comprising:

[0056] S1: Real-time collection of environmental parameters for drug storage;

[0057] Specifically, a sensor network is deployed in the drug storage and transportation environment to monitor key parameters such as temperature, humidity, and light in real time; the data sampling frequency is dynamically adjusted through preset acquisition rules, and abnormal fluctuation events are triggered for recording; at the same time, a sensor self-calibration mechanism and a data integrity verification process are established to ensure the real-time performance and reliability of environmental parameters, providing accurate input for subsequent quality risk assessment.

[0058] S2: Construct a feature database of drug stability and build a degradation rate model for the corresponding drug based on the feature database;

[0059] Specifically, a model is established to link drug quality degradation with dynamic environmental parameters, enabling a paradigm shift from passively relying on fixed expiration dates to proactively predicting quality risks. By integrating drug dosage form characteristics (such as thermosensitivity and photosensitivity), historical stability test data, and real-time environmental stress parameters, a digital feature map is constructed to characterize the synergistic effects of multiple factors. This step transforms discrete monitoring data into the ability to predict continuous quality evolution trajectories, expanding the determination of drug expiration dates from a single time dimension to a multi-dimensional space of "time-environment-dosage form," providing a quantitative analysis basis for differentiated risk warning.

[0060] S3: Based on environmental parameters and degradation rate models, calculate the cumulative value of the impact of current storage conditions on drug quality and generate a quality risk level;

[0061] Specifically, discrete environmental monitoring data is transformed into a visualized risk characterization of drug quality. By integrating the duration of environmental stress, the degree of attenuation predicted by degradation models, and the actual quality test results, a dynamic mapping relationship of "monitoring data → quality loss equivalent" is established to achieve continuous quantitative assessment of the degree of drug efficacy decline.

[0062] S4: Generate drug optimization management instructions based on the quality risk level and the remaining time of the drug's fixed expiration date.

[0063] Specifically, a dynamic decision-making mechanism for quality risk and timeliness pressure is established to address the drawbacks of the binary decision-making approach of "discard upon expiration" or "invalid before expiration" under the fixed expiration period system. By integrating real-time quality risk quantification results with the timeliness urgency of the remaining expiration period, a two-dimensional decision-making space is constructed, and intelligent algorithms are used to match the optimal circulation strategy.

[0064] This invention effectively solves the problem of "premature drug efficacy failure" caused by neglecting dynamic environmental factors in traditional methods. It achieves accurate early warning of quality deterioration through dynamic monitoring and degradation modeling, eliminating regulatory blind spots and reducing the risk of medical resource waste.

[0065] As a preferred embodiment of the above, such as Figure 2 As shown, a feature database for drug stability is constructed, including:

[0066] A10: Obtain key stability parameters for the drug, including environmental sensitivity factors and dosage form characteristics;

[0067] A20: Establish a multi-stress coupling model based on key stability parameters;

[0068] A30: Through a multi-stress coupling model, the real-time acquired environmental parameter sequence is converted into an equivalent cumulative environmental stress value;

[0069] A40: Correlate the cumulative value of equivalent environmental stress with the batch characteristic data of the drug to generate a feature database.

[0070] Specifically, firstly, key stability parameters are extracted for different drug categories, including environmentally sensitive factors such as temperature sensitivity coefficient, critical humidity threshold, and photodecomposition wavelength range, as well as dosage form characteristic indicators such as crystal stability of solid dosage forms and pH buffer capacity of liquid dosage forms, forming a drug stability metadata system. Then, a multi-stress coupling model is established using principal component analysis and response surface methodology, designing an environmental stress function that includes time cumulative effects and nonlinear interaction terms, such as the coupling weights of temperature fluctuation entropy and humidity gradient. Subsequently, real-time collected time-series environmental parameters are input into the model to calculate equivalent stress values, and a standardized stress accumulation curve is generated after eliminating dimensional differences using a dynamic normalization algorithm. Finally, the material characteristics of each batch of drugs (such as packaging barrier coefficient and initial impurity content) are correlated with the stress accumulation curve to construct a structured feature database containing unique batch codes, environmental stress spectra, and predicted mass decay values, supporting intelligent analysis based on a two-factor retrieval of drug "molecular fingerprint-environmental fingerprint".

[0071] As a preferred embodiment of the above, such as Figure 3 As shown, step A30 involves converting the real-time acquired environmental parameter sequence into equivalent cumulative environmental stress values ​​using a multi-stress coupling model, including:

[0072] A31: Dimensionless processing of environmental parameters and calculation of the stress contribution of each parameter;

[0073] A32: Based on the weighting coefficients of the multi-stress coupling model, synthesize the equivalent cumulative environmental stress value.

[0074] Specifically, the collected environmental parameters such as temperature, humidity, and light intensity are first standardized to eliminate differences in unit dimensions and map each parameter to a unified evaluation scale. The actual impact weight of each parameter is then calculated based on the characteristics of the drug; for example, high-temperature deviations have a stronger degradation-driving effect than low-temperature fluctuations. Next, dynamic weighted synthesis is performed according to pre-defined coupling rules, employing differentiated weight allocation strategies for different drug categories. For instance, cold-chain biological products emphasize the cumulative effect of temperature, while photosensitizing preparations increase the time integral calculation of light intensity. Simultaneously, a nonlinear correction factor is introduced to handle the synergistic effects of extreme environmental conditions. The final output equivalent environmental stress accumulation value exhibits time-dependent decay characteristics, reflecting both the current environmental impact intensity and the residual quality damage from historical storage conditions, thus establishing a standardized input for subsequent quality risk assessment.

[0075] As a preferred embodiment of the above, such as Figure 4 As shown, a degradation rate model for the corresponding drug is constructed based on the feature database, including:

[0076] B10: Construct multi-dimensional parameter mapping relationships based on the feature database;

[0077] B20: Based on the collaborative modeling of physicochemical mechanism equations and real-time environmental data, a composite degradation rate function is generated;

[0078] B30: Based on the composite degradation rate function, the model parameters are initialized and dynamically calibrated to obtain the degradation rate model.

[0079] Specifically, the complete process of constructing a drug degradation rate model begins with deep analysis of the feature database. Key parameters are extracted through data cleaning and feature engineering to establish a correlation map between environmental stress sequences and drug quality evolution. Principal component analysis and mutual information entropy calculation are used to identify core influencing factors, such as revealing the nonlinear enhancement effect of humidity fluctuations on solid dosage form degradation. A multi-dimensional parameter mapping framework is then built using deep neural networks to achieve end-to-end prediction of degradation rates from environmental time-series data. Based on this, physicochemical mechanism equations and real-time monitoring data are systematically integrated, using fundamental theoretical equations such as photolysis quantum efficiency as constraints. Simultaneously, LSTM networks are used to capture the characteristics of transient environmental events such as sudden temperature rises during transportation. Attention mechanisms are used to weightedly integrate mechanistic derivations and data-driven corrections, forming a composite degradation rate function that reflects scientific laws and can adapt to complex scenarios. Furthermore, Bayesian optimization and Kalman filtering are used to dynamically calibrate model parameters. Real-time data is continuously injected during drug distribution to iteratively update key weights such as humidity sensitivity coefficients, and cross-validation is performed using laboratory accelerated testing results. When the prediction error exceeds a threshold, model structure optimization is automatically triggered. The final released degradation rate model integrates version management and failure warning functions.

[0080] As a preferred embodiment of the above, the physicochemical mechanism equation is:

[0081]

[0082] in, The total reaction rate is... Pre-exponential factor, For degradation activation energy, Let be the ideal gas constant. Thermodynamic temperature The critical relative humidity for pharmaceuticals. Relative humidity, and These are the sensitivity coefficient and the nonlinearity index, respectively. These are the spectral sensitivity weighting coefficients. For wavelength range, For a moment The wavelength is Light intensity, This is the starting point of the photodamage effect. This represents the current calculation time for the photodamage effect.

[0083] Specifically, the temperature-dominant term adopts the Arrhenius equation. Describe the thermodynamic effects, including activation energy. Temperature reflects the energy threshold required for the breaking of molecular bonds in drugs. Increasing humidity will exponentially accelerate the degradation reaction; the humidity correction term passes... Quantifying the humidity over-limit effect, when relative humidity Breaking the critical value At that time, the physicochemical changes induced by water adsorption (such as hydrolysis and crystal transformation) will exhibit a nonlinear amplification effect; the photodamage integral term is weighted and integrated over the full spectrum of illumination in the time domain, where the spectral sensitivity coefficient The equation reflects the chemical bond excitation efficiency of light at different wavelengths (e.g., ultraviolet light has a higher weighting on the destructive effect on photosensitive drugs), and the integral calculation captures the cumulative damage effect of light exposure. This equation overcomes the limitations of traditional single-factor accelerated testing and achieves dynamic prediction of drug quality degradation rates under real storage conditions through multi-physics coupling modeling.

[0084] As a preferred embodiment of the above, such as Figure 5 As shown, step S3, based on environmental parameters and a degradation rate model, calculates the cumulative value of the impact of current storage conditions on drug quality, and generates a quality risk level, including:

[0085] S31: Input environmental parameters into the degradation rate model for dynamic coupling;

[0086] S32: Accumulate the dynamic coupling results in real time to generate a cumulative mass loss value that reflects changes in drug quality;

[0087] S33: Classify risk levels based on cumulative quality loss values.

[0088] Specifically, the system first inputs real-time environmental parameters into a multi-stress coupled degradation rate model, and then integrates the synergistic effects of various parameters through a dynamic weight allocation algorithm. For example, under conditions of high temperature and high humidity, the contribution weight of the humidity factor is automatically increased. Next, the degradation rate is continuously accumulated using a time convolution integral method, in which a time decay factor is introduced to simulate the irreversible characteristics of drug quality damage, generating a cumulative loss value that characterizes the degree of quality decay. Finally, dynamic risk boundaries are set according to drug registration standards and clinical safety thresholds. For example, the cumulative value is divided into four levels: safe (<5%), attention (5-10%), warning (10-20%), and high risk (>20%). For special drugs (such as vaccines and biological agents), a more stringent exponential segmentation standard is adopted, and the risk coefficient is adjusted in conjunction with the remaining shelf life. For example, under the same cumulative value, the risk level of a drug with 3 months left until expiration is one level higher than that with 12 months left. The global risk heat map is updated every 15 minutes, and the risk evolution trend in the next 72 hours is predicted through Monte Carlo simulation, providing multi-dimensional decision-making basis for the generation of management instructions.

[0089] As a preferred embodiment of the above, such as Figure 6 As shown, step S4 generates a drug optimization management instruction based on the quality risk level and the remaining time of the drug's fixed expiration date, including:

[0090] S41: Based on historical drug quality data and corresponding environmental parameters, risk-time mapping rules are obtained, and a dynamic strategy tree model containing multi-level decision nodes is constructed.

[0091] S42: Simultaneously input the real-time monitored quality risk level and the remaining expiration date data of the drug label into the dynamic measurement tree model to generate a strategy matching confidence score;

[0092] S43: Based on the confidence score of the strategy matching, match the preset management strategy and generate drug optimization management instructions.

[0093] Specifically, firstly, based on a historical database of drug quality decline cases and time-series data of corresponding environmental parameters, event association analysis and random forest algorithms are used to discover optimal disposal strategies under different combinations of risk levels and remaining expiration dates (such as priority recall of high-risk near-expiration drugs and targeted promotion of medium-risk mid-term drugs). A dynamic strategy tree is constructed, including multi-level decision nodes such as risk thresholds, expiration periods, and dosage forms. Then, the real-time monitored quality risk levels and the remaining expiration dates in the drug labels are input into the strategy tree model, and the matching probability of each branch is calculated through a Bayesian network. Finally, operation instructions are retrieved from a preset strategy database based on confidence thresholds. For example, temperature adjustment and route optimization are automatically triggered for high-risk batches in cold chain transportation, and promotional priority ranking is generated for near-expiration low-risk drugs. At the same time, verification sampling suggestions are pushed to the quality management department, and a manual strategy intervention interface is reserved to ensure a balance between automation and compliance in management instructions.

[0094] As a preferred embodiment of the above, the method further includes: establishing an instruction effect evaluation index by collecting quality tracking data after the drug distribution node executes the optimized management instruction, and dynamically correcting the parameter weights of the degradation rate model and the dynamic strategy tree model.

[0095] Specifically, firstly, intelligent monitoring equipment is deployed in the drug distribution process to collect quality tracking data in real time after the execution of management instructions, including inventory sampling results, environmental deviations during transportation, and market feedback information, forming a dataset of influencing factors covering the entire life cycle. Secondly, a multi-dimensional instruction effectiveness evaluation system is constructed, designing quantitative indicators such as quality fluctuation suppression rate, risk decay slope, and response timeliness ratio. A comprehensive performance score is calculated using the efficacy coefficient method to identify specific scenarios with significant model prediction bias. Finally, based on the evaluation results, a dynamic model parameter correction mechanism is initiated. Transfer learning technology is used to Bayesianly optimize the stress weights in the degradation rate model, while a strategy tree pruning algorithm is used to reconstruct the priority of decision nodes, such as increasing the confidence weight of repeatedly validated effective strategies and eliminating redundant branches with actual effects below a threshold. Version iterations record the logical basis for each parameter update and establish an adaptive learning channel for new drug dosage forms to ensure that the model system maintains synchronous evolution of prediction accuracy and decision effectiveness during continuous operation. Example 2

[0096] Based on the same inventive concept as the intelligent drug expiration date management method in the foregoing embodiments, the present invention also provides an intelligent drug expiration date management system, the system comprising:

[0097] The environmental parameter acquisition module collects environmental parameters of the drug storage area in real time.

[0098] The rate model construction module builds a feature database of drug stability and constructs a degradation rate model for the corresponding drug based on the feature database.

[0099] The risk level generation module calculates the cumulative value of the current storage conditions on drug quality based on environmental parameters and degradation rate models, and generates a quality risk level.

[0100] The management instruction generation module generates optimized drug management instructions based on the quality risk level and the remaining time of the drug's fixed expiration date.

[0101] The management system described above in this invention can effectively realize an intelligent drug expiration date management method, and the technical effects it can achieve are as described in the above embodiments, and will not be repeated here.

[0102] As a preferred embodiment of the above, the risk level generation module includes:

[0103] The dynamic coupling unit inputs environmental parameters into the degradation rate model for dynamic coupling;

[0104] The coupling accumulation unit accumulates the dynamic coupling results in real time to generate a cumulative mass loss value that reflects changes in drug quality.

[0105] The risk level is determined by the cumulative quality loss value.

[0106] Similarly, the above-mentioned optimization schemes for the system can also achieve the optimization effects corresponding to the methods in Embodiment 1, which will not be repeated here.

[0107] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. An intelligent method for managing the expiration date of pharmaceutical products, characterized in that, Includes the following steps: Real-time collection of environmental parameters for drug storage; A feature database of drug stability is constructed, and a degradation rate model of the corresponding drug is constructed based on the feature database; Based on the environmental parameters and degradation rate model, the cumulative value of the current storage conditions on drug quality is calculated, and a quality risk level is generated. Based on the quality risk level and the remaining time of the drug's fixed shelf life, a drug optimization management instruction is generated.

2. The intelligent drug expiration date management method according to claim 1, characterized in that, Construct a feature database of drug stability, including: Obtain key stability parameters of the drug, including environmental sensitive factors and dosage form characteristics; Based on the aforementioned key stability parameters, a multi-stress coupling model is established; The multi-stress coupling model converts the real-time collected environmental parameter sequence into equivalent environmental stress cumulative values. The feature database is generated by associating the equivalent environmental stress accumulation value with the drug batch characteristic data.

3. The intelligent drug expiration date management method according to claim 2, characterized in that, The multi-stress coupling model converts the real-time acquired environmental parameter sequence into equivalent cumulative environmental stress values, including: The environmental parameters are dimensionless, and the stress contribution of each parameter is calculated. Based on the weighting coefficients of the multi-stress coupling model, the equivalent cumulative environmental stress value is synthesized.

4. The intelligent drug expiration date management method according to claim 1, characterized in that, Based on the aforementioned feature database, a degradation rate model for the corresponding drug is constructed, including: Based on the feature database, construct a multidimensional parameter mapping relationship; Based on the collaborative modeling of physicochemical mechanism equations and real-time environmental data, a composite degradation rate function is generated; Based on the composite degradation rate function, the model parameters are initialized and dynamically calibrated to obtain the degradation rate model.

5. The intelligent drug expiration date management method according to claim 4, characterized in that, The physicochemical mechanism equation is as follows:

6. Among them, The total reaction rate is... Pre-exponential factor, For degradation activation energy, Let be the ideal gas constant. Thermodynamic temperature The critical relative humidity for pharmaceuticals. Relative humidity, and These are the sensitivity coefficient and the nonlinearity index, respectively. These are the spectral sensitivity weighting coefficients. For wavelength range, For a moment The wavelength is Light intensity, This is the starting point of the photodamage effect. This represents the current calculation time for the photodamage effect.

7. The intelligent drug expiration date management method according to claim 1, characterized in that, Based on the aforementioned environmental parameters and degradation rate model, the cumulative impact of current storage conditions on drug quality is calculated, generating a quality risk level, including: The environmental parameters are input into the degradation rate model for dynamic coupling; The dynamic coupling results are accumulated in real time to generate a cumulative mass loss value that reflects changes in drug quality; Risk levels are determined based on the cumulative quality loss value.

8. The intelligent drug expiration date management method according to claim 1, characterized in that, Based on the aforementioned quality risk level and the remaining time of the drug's fixed expiration date, a drug optimization management instruction is generated, including: Based on historical drug quality data and corresponding environmental parameters, risk-time mapping rules are obtained, and a dynamic strategy tree model containing multi-level decision nodes is constructed. The real-time monitored quality risk level and the remaining expiration date data of the drug label are synchronously input into the dynamic measurement tree model to generate a strategy matching confidence score; Based on the confidence score of the strategy, a preset management strategy is matched, and the drug optimization management instruction is generated.

9. The intelligent drug expiration date management method according to claim 1, characterized in that, The method further includes: collecting quality tracking data after the drug distribution nodes execute optimized management instructions, establishing instruction effect evaluation indicators, and dynamically correcting the parameter weights of the degradation rate model and the dynamic strategy tree model.

10. An intelligent drug expiration date management system, characterized in that, include: The environmental parameter acquisition module collects environmental parameters of the drug storage area in real time. The rate model construction module constructs a feature database of drug stability and builds a degradation rate model for the corresponding drug based on the feature database. The risk level generation module calculates the cumulative value of the current storage conditions on drug quality based on the environmental parameters and degradation rate model, and generates a quality risk level. The management instruction generation module generates drug optimization management instructions based on the quality risk level and the remaining time of the drug's fixed expiration date.

11. The intelligent drug expiration date management system according to claim 9, characterized in that, The risk level generation module includes: The dynamic coupling unit inputs the environmental parameters into the degradation rate model for dynamic coupling; The coupling accumulation unit accumulates the dynamic coupling results in real time to generate a cumulative mass loss value that reflects changes in drug quality. The risk level is determined by the cumulative quality loss value.

Images