CN119851903B - Monitoring and managing method and system for medicament inventory - Google Patents

Abstract

The present invention discloses a monitoring and management method and system for medicine inventory, which relates to the field of artificial intelligence technology, including deploying multi-source sensors, monitoring the status of medicine inventory in real time and analyzing it, and extracting key features; performing real-time fusion analysis on the extracted key features to generate a dynamic inventory status map; based on the dynamic inventory status map, constructing a reinforcement learning-driven adaptive inventory allocation model to obtain an optimal inventory allocation and scheduling strategy and update the inventory status; constructing a distributed expiration period prediction model based on federated learning according to the updated inventory status and expiration period status, generating expiration period prediction results and performing cross-warehouse collaborative optimization; based on the expiration period prediction results, constructing a dynamic risk factor assessment system of a digital twin to obtain a risk factor assessment result; the distributed expiration period prediction model based on federated learning improves the accuracy and adaptability of expiration period prediction.

Description

A monitoring and management method and system for pharmaceutical inventory

Technical Field

The present invention relates to the field of artificial intelligence technology, and in particular to a monitoring and management method and system for medicine inventory.

Background Art

With the rapid development of the pharmaceutical industry, the complexity of pharmaceutical inventory management is increasing. Traditional inventory management systems mainly rely on manual records and regular inventory checks, which is not only inefficient but also prone to errors, resulting in frequent problems of expired drugs or substandard storage conditions. In recent years, with the development of Internet of Things technology and artificial intelligence, more and more companies have begun to try to use sensor networks and data analysis technologies to improve inventory management. However, most existing solutions are limited to a single function, such as only monitoring temperature and humidity or only focusing on changes in inventory quantity, lacking the ability to comprehensively analyze multi-source data and intelligent decision support.

The existing technology has significant deficiencies in dealing with drug inventory management and expiration date prediction. On the one hand, traditional inventory management systems cannot monitor the specific status of drugs and their storage environment parameters in real time, making it difficult to detect potential risks in a timely manner. On the other hand, existing expiration date prediction methods are usually based on simple regression analysis of historical data, and fail to fully utilize the advantages of advanced algorithms such as federated learning, resulting in low prediction accuracy and difficulty in adapting to the different needs of different warehouses. The present invention deploys multi-source sensors and combines advanced technologies such as graph neural networks, reinforcement learning, and federated learning to achieve comprehensive monitoring and intelligent management of drug inventory status, significantly improving inventory management efficiency and safety.

Summary of the invention

In view of the above existing problems, the present invention is proposed.

Therefore, the present invention provides a monitoring and management method for medicine inventory to solve the problems of incomplete data monitoring and low expiration date prediction accuracy in traditional medicine inventory management systems.

In order to solve the above technical problems, the present invention provides the following technical solutions:

In a first aspect, the present invention provides a method for monitoring and managing drug inventory, which comprises:

Deploy multi-source sensors to monitor the status of drug inventory in real time and analyze and extract key features;

Perform real-time fusion analysis on the extracted key features to generate a dynamic inventory status map;

Based on the dynamic inventory status map, a reinforcement learning-driven adaptive inventory allocation model is constructed to obtain the optimal inventory allocation and scheduling strategy and update the inventory status;

According to the updated inventory status, a distributed expiration date prediction model based on federated learning is constructed to generate expiration date prediction results and perform collaborative optimization across warehouses.

Based on the failure period prediction results, a dynamic assessment system for the hazard factor of the digital twin is constructed to obtain the hazard factor assessment results.

As a preferred solution of the monitoring and management method of the medicine inventory of the present invention, wherein: deploying multi-source sensors, monitoring the status of the medicine inventory in real time and analyzing it, extracting key features includes the following steps:

Determine the location of sensor nodes based on warehouse layout and drug storage areas;

The deployed sensors collect drug inventory, storage environment parameters, physical characteristics and expiration dates;

De-noising, normalizing and time-stamping of drug inventory, storage environment parameters, physical properties and expiration dates;

Directly obtain the quantity and location information of each medicine from the processed medicine inventory;

Detection of color changes, odor concentration, and morphological changes in the physical properties of pharmaceuticals;

Use RFID tag technology to automatically read the production date and batch number of each batch of medicine.

As a preferred solution of the pharmaceutical inventory monitoring and management method of the present invention, the following steps are included: performing real-time fusion analysis on the extracted key features to generate a dynamic inventory status map:

Use graph neural networks to build association models to identify the relationship between the quantity of medicines, storage environment parameters, and physical properties of medicines;

Define nodes as each drug and its related attributes, and edges represent potential relationships between different attributes;

Build a graph structure based on defined nodes and edges;

Select the GNN variant that processes heterogeneous graph data, take the constructed graph structure as input, and update the node embedding vector;

Determine the location coordinates of each storage unit based on the actual layout of the warehouse;

The updated embedding vector of each node is associated with its corresponding position coordinate to generate a dynamic inventory status map of each medicine.

As a preferred solution of the monitoring and management method of the pharmaceutical inventory of the present invention, the following steps are included: based on the dynamic inventory status map, a reinforcement learning-driven adaptive inventory allocation model is constructed to obtain the optimal inventory allocation and scheduling strategy and update the inventory status:

Select the Deep Q Model as the reinforcement learning algorithm;

A state vector is defined based on the quantity of each medicine in the dynamic inventory state map, the remaining validity period of the medicine, the physical characteristics of the medicine, and the storage environment parameters;

Based on the inventory adjustment decision for each agent, an action vector is defined;

Set up reward functions to minimize inventory waste, maximize demand fulfillment, and reduce risk;

Collect historical sales data, market demand fluctuations, and upstream and downstream supply chain information;

Define simulation scenarios based on collected historical sales data, market demand fluctuations, and upstream and downstream supply chain information;

Run a deep Q-model in each scene to explore the environment and perform actions;

For each action execution result, record the state vector, action vector, reward function and new state vector to form an experience tuple;

Use the experience replay pool to store experience tuples and regularly extract samples from them for training;

Based on the trained deep Q model, priority scores are given to the expiration date, storage environment parameters, and physical properties of the agent;

For high-priority drugs, a transfer instruction is generated and sent to the automation equipment to execute the transfer operation;

For medium-priority drugs, perform inventory optimization operations, adjust storage locations, and optimize storage environments;

For low-priority drugs, perform routine inventory management, conduct regular inspections and record inventory status;

After the dispatch execution is completed, the inventory status is updated.

As a preferred solution of the pharmaceutical inventory monitoring and management method of the present invention, the following steps are included: according to the updated inventory status and expiration date status, a distributed expiration date prediction model based on federated learning is constructed, expiration date prediction results are generated, and cross-warehouse collaborative optimization is performed.

Deploy a long short-term memory network as a prediction model locally in each warehouse;

Use the updated inventory status as input features and input them into the prediction model for training;

The aggregation algorithm is used as the federated learning framework to perform weighted averaging on the trained LSTM model parameters to form a global prediction model.

The global prediction model parameters are sent to each warehouse to replace the local LSTM model parameters, and the updated global prediction model is used to predict the expiration date of each drug.

When the global prediction model predicts that the expiration date of a medicine in a certain warehouse is approaching and the inventory is insufficient, a cross-warehouse collaborative optimization instruction is triggered;

Filter candidate warehouses based on global inventory status;

The candidate warehouses are ranked based on a dynamic priority scoring system, and the warehouse with the highest total score is selected as the target warehouse;

When multiple candidate warehouses are tied for the highest score, the target warehouse will be selected for transfer based on the distance priority principle;

Set the inventory safety threshold. When there is only one candidate warehouse and its inventory after transfer is lower than the safety threshold, the maximum transferable quantity is automatically calculated and a partial transfer instruction is generated.

Transfer instructions are sent to automated equipment for execution, and the source warehouse, target warehouse inventory status and global forecasting model are updated simultaneously;

If the transfer fails, the supply chain collaborative response process will be triggered to generate purchase requisitions and production scheduling instructions.

As a preferred solution of the monitoring and management method of the pharmaceutical inventory of the present invention, based on the expiration date prediction result, a dynamic evaluation system of the risk factor of the digital twin is constructed, and the risk factor of each storage unit is calculated, including the following steps:

Select a digital twin platform, create a digital twin instance, and configure computing and storage resources;

Use 3D modeling tools to build the physical layout of the warehouse including storage units, shelves, aisles, and equipment, and import the modeling results into the digital twin platform to generate a digital twin model of the virtual warehouse;

Associating the inventory status of medicines monitored in real time by multi-source sensors with the storage units in the digital twin model of the virtual warehouse, and updating the environmental parameters and physical properties of medicines in the digital twin model of the virtual warehouse in real time;

Define the static and dynamic properties of the digital twin model, build simulation scenarios in the digital twin platform, set simulation parameters, and simulate risks under different conditions;

Based on the simulation results, calculate the risk factor of each storage unit .

As a preferred solution of the monitoring and management method of the pharmaceutical inventory of the present invention, the risk level is divided based on the calculated risk factor of each storage unit, and the risk factor evaluation result is obtained, including the following steps:

According to the physical characteristics of the medicine and the storage environment parameters, set is a high risk threshold. is the warning threshold;

when > When a high-risk storage unit is detected, it is marked as a high-risk state, a first-level response measure is generated, a No. 1 sound and light alarm is issued, the addition of reagents to the high-risk storage unit is automatically stopped, and the warehouse management personnel are notified to conduct manual inspection and processing;

when < ≤ When the alarm is reached, it is marked as an alarm state, a secondary response measure is generated, a second sound and light alarm is sounded, the addition of medicine to the alarm storage unit is automatically stopped, and the inspection frequency of the storage unit is increased;

when ≤ When the storage unit is in a safe state, it is marked as safe, the environmental parameters and the status of the reagents in the storage unit are continuously monitored, and the storage unit is inspected according to the standard inspection plan.

In a second aspect, the present invention provides a monitoring and management system for drug inventory, comprising:

The perception network module deploys multi-source sensors to monitor the status of drug inventory in real time and analyze and extract key features;

The status mapping module performs real-time fusion analysis on the extracted key features and generates a dynamic inventory status map for each drug;

The adaptive allocation module builds a reinforcement learning-driven adaptive inventory allocation model based on the dynamic inventory status map, obtains the optimal inventory allocation and scheduling strategy, and updates the inventory status;

The expiration date prediction module builds a distributed expiration date prediction model based on federated learning according to the updated inventory status and expiration date status, generates expiration date prediction results, and performs collaborative optimization across warehouses.

The hazard assessment module builds a dynamic hazard factor assessment system for the digital twin based on the failure period prediction results to obtain the hazard factor assessment results.

In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the method for monitoring and managing drug inventory as described in the first aspect of the present invention is implemented.

In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: the computer program, when executed by a processor, implements any step of the method for monitoring and managing drug inventory as described in the first aspect of the present invention.

The beneficial effects of the present invention are as follows: by deploying multi-source sensors, all-round real-time monitoring of the inventory status of medicines is achieved, effectively solving the problem of delayed risk identification caused by incomplete information collection in traditional systems; the extracted key feature information is fused and analyzed using a graph neural network to generate a dynamic inventory status map, providing accurate data support for subsequent inventory allocation; a reinforcement learning-driven adaptive inventory allocation model is used to formulate the optimal scheduling strategy based on the actual inventory status, maximizing market demand while reducing inventory waste; the distributed expiration date prediction model based on federated learning improves the accuracy and adaptability of expiration date prediction, and the dynamic risk factor assessment system of the digital twin ensures immediate response and effective control of high-risk storage units, which greatly improves the safety and efficiency of medicine inventory management as a whole.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

FIG. 1 is a flow chart of the method for monitoring and managing medicine inventory in Example 1.

FIG. 2 is a module diagram of the monitoring and management system for medicine inventory in Example 1.

DETAILED DESCRIPTION

In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

Embodiment 1, referring to FIG. 1 and FIG. 2 , is a first embodiment of the present invention, which provides a method for monitoring and managing drug inventory, comprising the following steps:

S1. Deploy multi-source sensors to monitor the status of drug inventory in real time and analyze it to extract key feature information.

S1.1. Determine the location of the sensor nodes based on the warehouse layout and drug storage area division.

Specifically, temperature and humidity sensors are evenly distributed at different heights and areas in the warehouse to avoid local environmental deviations, gas sensors are close to volatile medicine storage areas, and optical sensors are installed near medicine packaging lines or shelves to capture the appearance characteristics of medicines.

S1.2 collects drug inventory, storage environment parameters, physical properties and expiration dates through deployed sensors; denoises, normalizes and timestamps the status of drug inventory; directly obtains the quantity and location information of each drug from the processed drug inventory; measures the temperature and humidity, gas composition and lighting conditions in the storage environment; detects color changes, odor concentration and morphological changes in the physical properties of drugs; and for expiration dates, uses RFID tag technology to automatically read the production date and batch number of each batch of drugs.

Specifically, denoising is to remove data fluctuations caused by equipment noise, normalization is to convert data from different sources to a unified dimension for subsequent analysis, and timestamp marking is to add precise time information to each record.

S2. Performing real-time fusion analysis on the extracted key feature information to generate a dynamic inventory status map for each drug includes the following steps:

Use graph neural networks to build an association model to identify the association between the number of medicines, storage environment parameters, and physical properties of medicines; define nodes as each medicine and its related attributes (including but not limited to quantity, location, batch information, production date, etc.), and edges represent potential relationships between different attributes (such as the impact of temperature on color change, the impact of humidity on odor concentration, etc.); build a graph structure based on the defined nodes and edges; select a GNN variant that processes heterogeneous graph data, use the constructed graph structure as input, and update the node embedding vector; determine the location coordinates of each storage unit based on the actual layout of the warehouse; associate each updated node embedding vector with its corresponding location coordinates to generate a dynamic inventory status map for each medicine.

Specifically, the dynamic inventory status map is formed by constructing a three-dimensional space coordinate system based on the node embedding vectors output by the GNN model, combined with warehouse layout information, and using a three-dimensional graphics library (such as Three.js or Unity3D) to convert these vectors into a visual three-dimensional model. For each drug, its position in three-dimensional space is determined by its actual storage location, while attributes such as color and size are dynamically adjusted according to its current state (such as temperature, humidity, remaining validity period, etc.), and interactive functions are added to the three-dimensional view, allowing users to click on any drug to view detailed information, including but not limited to the drug name, quantity, most recent test results, predicted expiration date, etc.

It should be noted that by real-time fusion analysis of extracted key feature information, managers can quickly understand the inventory status and respond. The dynamic inventory status map provides a visualization tool for warehouse management, which helps to optimize the use of storage space and logistics scheduling, timely monitor the physical properties and expiration dates of drugs, and effectively prevent quality problems caused by improper storage.

S3. Based on the dynamic inventory status map of each medicine, a reinforcement learning-driven adaptive inventory allocation model is constructed to obtain the optimal inventory allocation and scheduling strategy and update the inventory status, including the following steps:

Select a deep Q model that can handle continuous action space as the reinforcement learning algorithm; define the state vector based on the quantity of each medicine in the dynamic inventory state map, the remaining validity period of the medicine, the physical characteristics of the medicine, and the storage environment parameters; define the action vector based on the inventory adjustment decision of each medicine; design a reward function to minimize inventory waste, maximize demand satisfaction rate and reduce risks; collect historical sales data, market demand fluctuations and upstream and downstream information of the supply chain; define simulation scenarios based on the collected data; run the deep Q model in each scenario to explore the environment and perform actions; record the state vector for each action execution result. The deep Q model is used to store the experience tuples, including the state vector, action vector, reward function and new state vector. The experience tuples are stored in the experience replay pool, and samples are regularly extracted from it for training. Based on the trained deep Q model, the remaining time to expiration, storage environment parameters and physical properties of the drugs are prioritized. For high-priority drugs, transfer instructions are generated and sent to the automated equipment to execute the transfer operations. For medium-priority drugs, inventory optimization operations are performed to adjust the storage location and optimize the storage environment. For low-priority drugs, routine inventory management is performed, with regular inspections and recording of inventory status. After the scheduling is completed, the inventory status is updated.

Furthermore, the simulation scenario is defined as follows:

Emergency allocation of medicines with expiration dates approaching: simulate the allocation of medicines with less than 7 days remaining before expiration. Isolation storage of high-risk medicines: simulate the isolation operation of medicines with high-risk risk levels of storage environment parameters. Demand fluctuation scenario: simulate the sudden increase or decrease in market demand.

Specifically, the priority scoring includes the evaluation of the remaining time to expiration, the evaluation of storage environment parameters, and the evaluation of the physical characteristics of the drug, as follows:

For each medicine, the number of days remaining before its expiration date is calculated, and a remaining validity threshold (such as 30 days, 60 days, etc.) is set. Medicines that are about to expire are classified and scored. For example, medicines with a remaining validity period of less than 30 days receive a high priority score.

Monitor key environmental indicators such as temperature, humidity, and gas composition in the storage area. For areas or medicines that do not meet ideal storage conditions, give corresponding priority scores based on the degree of deviation. For example, medicines with temperatures exceeding the appropriate range by more than 5 degrees will receive a higher priority score.

Consider factors such as changes in the potion's color, odor concentration, changes in morphology, etc. Any changes that indicate the potion's quality may be compromised will result in a higher priority score.

Based on the evaluation of the remaining time to expiration, the storage environment parameters and the physical properties of the agent, a comprehensive priority score is calculated using a weighted summation method.

It should be noted that automated processes reduce the need for manual operations, improve processing speed and accuracy, and promptly identify and address potential problems, such as medicines approaching their expiration dates or in poor storage conditions. This effectively reduces quality and safety risks, rationally allocates limited storage space and resources, maximizes the use of existing facilities, and reduces costs.

S4. According to the updated inventory status and expiration date status, a distributed expiration date prediction model based on federated learning is constructed to generate expiration date prediction results and perform collaborative optimization across warehouses.

S4.1. Deploy a long short-term memory network as a prediction model locally in each warehouse.

Further explanation: LSTM was chosen because it can effectively process time series data, which is particularly important for expiration date prediction. Each warehouse should adjust the architecture of the LSTM model (such as the number of layers, number of units, etc.) according to its own inventory characteristics and historical data to achieve the best prediction effect.

S4.2. Use local inventory data and storage environment parameters as input features and input them into the prediction model to predict the expiration date of each drug.

Specifically, the input features are a feature set constructed based on the characteristics of the medicine (such as type, production date, batch, etc.), inventory status (quantity, location, etc.), and storage conditions (temperature and humidity change trends, etc.).

S4.3. The aggregation algorithm is used as the federated learning framework to perform weighted averaging on the LSTM model parameters to form a global prediction model.

It is further explained that the aggregation algorithm is chosen as the basis of federated learning because it is simple and effective. The aggregation algorithm protects data privacy by synchronizing model weights among multiple parties instead of directly exchanging raw data.

S4.4. Send the global prediction model parameters to each warehouse, replace the local LSTM model parameters, and use the updated global prediction model to predict the expiration date of each drug.

To further explain, the purpose of replacing the local LSTM model parameters is to ensure the security and integrity of the transmission process. After receiving the global prediction model, each warehouse can choose to use some local data to fine-tune the global prediction model to improve its accuracy in a specific environment.

S4.5. When the global prediction model predicts that the expiration date of a drug in a certain warehouse is approaching and the inventory is insufficient, a cross-warehouse collaborative optimization instruction is triggered; candidate warehouses are screened according to the global inventory status; candidate warehouses are sorted based on a dynamic priority scoring system, and the warehouse with the highest total score is selected as the target warehouse; when multiple candidate warehouses are tied for the highest score, the target warehouse is selected for transfer based on the distance priority principle; an inventory safety threshold is set, and when there is only one candidate warehouse and its inventory after transfer is lower than the safety threshold, the maximum transferable quantity is automatically calculated and a partial transfer instruction is generated; the transfer instruction is sent to the automated equipment for execution, and the inventory status of the source warehouse and target warehouse and the global prediction model are updated synchronously; if the transfer fails, the supply chain collaborative response process is triggered to generate a purchase application and production scheduling instructions.

It is further explained that the triggering conditions for cross-warehouse collaborative optimization instructions include high-risk warnings, sudden demands, and storage environment abnormalities.

A high-risk warning means that the remaining time of the drug expiration date is ≤7 days and the inventory level is less than the safety inventory level; sudden demand means that a surge in market demand causes the inventory level to drop sharply to a critical value; storage environment abnormality means that it is detected that the environmental parameters of the storage unit are out of the safe range, and the drug needs to be transferred urgently.

The screening of candidate warehouses includes excluding warehouses with substandard storage environments (such as the risk of accelerated expiration), filtering warehouses with inventory quantities less than the minimum transfer quantity, and giving priority to warehouses with the same pharmaceutical storage qualifications.

The dynamic priority score is based on the allocation of weight factors and the setting of scoring rules. For example, inventory adequacy rate (30%), transportation cost (20%), storage stability (25%), historical collaborative efficiency (15%), and response time (10%). The total score of the candidate warehouses is calculated by weighting the weight factors, and the warehouse with the highest total score is selected as the preferred target warehouse.

If multiple warehouses meet the transfer conditions and there are inventory conflicts, the urgency level is graded into level one and level two.

Among them, the first-level emergency (such as life-saving drugs with an expiration date of ≤3 days) is mandatory to prioritize the allocation to the nearest warehouse, ignoring the difference in inventory; the second-level emergency (such as ordinary drugs with an expiration date of ≤14 days) is to select the best warehouse based on the score ranking;

When there is an inventory conflict, before the transfer instruction is issued, the target warehouse automatically reserves storage space corresponding to the transfer quantity to avoid repeated scheduling failures; if the reservation fails (such as being occupied by other tasks during the reservation period), a secondary priority reordering is triggered.

If there is only one candidate warehouse and its inventory after transfer is less than the safety threshold, the linkage strategy of partial transfer mechanism and supply chain collaborative response is implemented;

The specific operation of the partial transfer mechanism is as follows:

Calculate the maximum amount that can be transferred = min (remaining capacity of the target warehouse - safety threshold, requested transfer amount);

If the available allocation amount is ≥ 50% of the requested amount, partial allocation is performed and the safety threshold is updated;

If the available transfer amount is less than 50%, the transfer will be abandoned and a purchase requisition will be generated instead.

Supply chain collaboration refers to automatically triggering supplier warnings, pushing electronic purchase orders (including drug specifications, quantities, and urgency), and simultaneously notifying the production department to adjust production schedules and give priority to the production of short-supply drugs.

S4.6. After the transfer is completed, the inventory status of the source warehouse and the target warehouse is updated in real time.

S5. Based on the failure period prediction results, a dynamic evaluation system for the risk factor of the digital twin is constructed. The calculation of the risk factor of each storage unit includes the following steps:

Select a digital twin platform, create a digital twin instance, and configure computing resources and storage resources; use 3D modeling tools to build a physical warehouse layout including storage units, shelves, channels, and equipment, and import the modeling results into the digital twin platform to generate a digital twin model of the virtual warehouse; associate the inventory status of medicines monitored in real time by multi-source sensors with the storage units in the digital twin model of the virtual warehouse, and update the environmental parameters and physical properties of medicines in the digital twin model of the virtual warehouse in real time; define the static and dynamic properties of the digital twin model, build simulation scenarios in the digital twin platform, set simulation parameters, and simulate risks under different conditions; based on the simulation results, calculate the risk factor of each storage unit .

Furthermore, static properties include location, size and capacity, and structural characteristics.

Among them, location refers to the fixed coordinate position of each storage unit, shelf, channel and equipment in the warehouse, which is the basis for establishing a digital twin model to ensure that the virtual environment is consistent with the actual warehouse layout. Size and capacity are to clarify the maximum capacity limit of each storage unit, including the number and type of medicines that can be accommodated, which helps to optimize inventory management and prevent overloading. Structural characteristics such as shelf materials and strength are crucial for evaluating the safety and stability of storage units.

Dynamic properties include changes in state, environmental parameters, and physical characteristics.

Status changes include changes in the quantity of medicines, storage time, and approaching expiration dates. By updating these data in real time, you can keep up to date with inventory status. Environmental parameters refer to temperature, humidity, lighting conditions, etc. These factors directly affect the quality and safety of medicines. It is necessary to set up a sensor network for continuous monitoring and feed the data back to the digital twin model. Changes in physical properties refer to changes in color, odor concentration, shape, etc., which are important indicators of changes in medicine quality.

The simulation setting refers to the analysis of the impact of extreme weather conditions (such as high/low temperature simulation, flood/heavy rain simulation, and strong wind/typhoon simulation), evacuation route planning in emergency situations (such as fire escape routes, earthquake emergency response, and chemical leak handling), and the adjustment of relevant parameters to test the system's ability to respond to emergencies (for example, simulating a sudden power outage to see whether the backup power supply can be quickly switched to ensure the normal operation of important equipment, creating a variety of hypothetical scenarios, such as a surge in demand during holiday sales peaks, supply chain disruptions leading to raw material shortages, etc., to test the flexibility and adaptability of the supply chain management system).

Based on the simulation results, the calculation of the risk factor of each storage unit includes the following steps:

Extract extreme weather, emergency events and supply chain pressure data from the simulation results; calculate static attribute risk scores, dynamic attribute risk scores and simulation result scores based on the extracted data; and perform weighted aggregation on the calculated scores to obtain the risk factor of each storage unit.

S6. Based on the calculated risk factor of each storage unit, the risk level is divided, and the risk factor assessment result includes the following steps:

According to the physical characteristics of the medicine and the storage environment parameters, set is a high risk threshold. is the warning threshold; when > When the high-risk storage unit is in a high-risk state, it is marked as a high-risk state, a first-level response measure is generated, a No. 1 sound and light alarm is issued, the addition of drugs to the high-risk storage unit is automatically stopped, and the warehouse management personnel are notified to conduct manual inspection and processing; < ≤ When , it is marked as an alert state, generates a secondary response measure, issues a second sound and light alarm, automatically stops adding medicine to the alert storage unit, and increases the inspection frequency of the storage unit; when ≤ When the storage unit is in a safe state, it is marked as safe, the environmental parameters and drug status of the storage unit are continuously monitored, and the storage unit is inspected according to the standard inspection plan.

It should be noted that the dynamic hazard factor assessment system based on digital twin technology can not only reflect the current situation in real time, but also predict future risks. Combined with the Internet of Things (IoT) technology and artificial intelligence algorithms, it realizes intelligent risk warning, making management more flexible and efficient. Different from the traditional single response mode, this solution provides a complete set of hierarchical response strategies, with corresponding processing procedures from minor warnings to emergency shutdowns, strong adaptability and wide coverage.

This embodiment also provides a monitoring and management system for drug inventory, including:

The perception network module deploys multi-source sensors to monitor the status of drug inventory in real time and analyze and extract key features;

The status mapping module performs real-time fusion analysis on the extracted key features and generates a dynamic inventory status map;

The adaptive allocation module builds a reinforcement learning-driven adaptive inventory allocation model based on the dynamic inventory status map, obtains the optimal inventory allocation and scheduling strategy, and updates the inventory status;

The expiration date prediction module builds a distributed expiration date prediction model based on federated learning according to the updated inventory status and expiration date status, generates expiration date prediction results, and performs collaborative optimization across warehouses.

The hazard assessment module builds a dynamic hazard factor assessment system for the digital twin based on the failure period prediction results to obtain the hazard factor assessment results.

This embodiment also provides a computer device suitable for the case of a monitoring and management method for drug inventory, comprising: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the monitoring and management method for drug inventory proposed in the above embodiment.

The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

The present embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for monitoring and managing the inventory of medicines as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

In summary, the present invention realizes all-round real-time monitoring of the inventory status of medicines by deploying multi-source sensors, effectively solving the problem of delayed risk identification caused by incomplete information collection in traditional systems; the extracted key feature information is fused and analyzed by using graph neural networks to generate a dynamic inventory status map, providing accurate data support for subsequent inventory allocation; the adaptive inventory allocation model driven by reinforcement learning can formulate the optimal scheduling strategy according to the actual inventory status, maximize the satisfaction of market demand while reducing inventory waste; the distributed expiration date prediction model based on federated learning improves the accuracy and adaptability of expiration date prediction, and the dynamic risk factor assessment system of digital twins ensures immediate response and effective control of high-risk storage units, which greatly improves the safety and efficiency of medicine inventory management as a whole.

It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims (8)

1. A method for monitoring and managing medicament stock is characterized by comprising the following steps of,

Deploying a multi-source sensor, monitoring the state of the medicament stock in real time, analyzing the state, and extracting key characteristics;

Performing real-time fusion analysis on the extracted key features to generate a dynamic inventory state mapping diagram;

Based on the dynamic inventory status map, constructing a reinforcement learning driven adaptive inventory allocation model, obtaining an optimal inventory allocation and scheduling strategy and updating the inventory status,

Selecting a depth Q model as a reinforcement learning algorithm, defining a state vector and a motion vector, and setting a reward function;

Collecting historical sales data, market demand fluctuation conditions and supply chain upstream and downstream information, defining a simulation scene, running a depth Q model, exploring the environment and executing actions;

For each action execution result, recording a state vector, an action vector, a reward function and a new state vector, forming an experience tuple, and regularly extracting samples from the experience tuple for training;

based on the trained depth Q model, carrying out priority scoring on the failure period, the storage environment parameter and the physical characteristics of the medicament;

Generating an allocation instruction for the high-priority medicament, sending the allocation instruction to an automation device, executing allocation operation, performing inventory optimization operation for the medium-priority medicament, adjusting a storage position and optimizing a storage environment, performing conventional inventory management for the low-priority medicament, and periodically inspecting and recording inventory states;

after the scheduling execution is completed, updating the stock state, constructing a failure period distributed prediction model based on federal learning, generating a failure period prediction result and performing cross-warehouse collaborative optimization,

A long-term memory network is deployed locally in each warehouse to serve as a prediction model;

The updated stock state is used as an input characteristic and is input into a prediction model for training, and the trained LSTM model parameters are weighted and averaged to form a global prediction model;

Issuing global prediction model parameters to each warehouse, replacing local LSTM model parameters, and predicting the failure period of each medicament by using the updated global prediction model;

triggering a cross-warehouse collaborative optimization instruction when the global prediction model predicts that the medicament failure period of a warehouse is close and the inventory is insufficient;

screening candidate warehouses according to the global inventory status;

sorting the candidate warehouses based on a dynamic priority scoring system, wherein the highest total score is used as a target warehouse;

when a plurality of candidate warehouses are listed in parallel with the highest score, selecting a target warehouse for allocation according to a distance priority principle;

setting a stock quantity safety threshold, automatically calculating the maximum adjustable quantity and generating a partial adjustment instruction when only one candidate warehouse is arranged and the stock quantity of the candidate warehouse is lower than the safety threshold after the candidate warehouse is adjusted, and sending the partial adjustment instruction to an automation device for execution, and synchronously updating the stock states of a source warehouse and a target warehouse and a global prediction model;

If the allocation fails, triggering a supply chain cooperative response flow to generate a purchase application and a production scheduling instruction;

And constructing a digital twin risk coefficient dynamic evaluation system based on the failure period prediction result to obtain a risk coefficient evaluation result.

2. The method for monitoring and managing inventory of pharmaceutical agents of claim 1, wherein deploying the multi-source sensor, monitoring and analyzing the status of the inventory of pharmaceutical agents in real time, extracting key features comprises the steps of,

Determining the position of a sensor node according to the warehouse layout and the medicament storage area;

collecting the inventory of the medicament, storage environment parameters, physical characteristics and failure period through deployed sensors;

Denoising, normalizing and time stamping the medicament stock quantity, the storage environment parameters, the physical characteristics and the failure period;

Acquiring the quantity and position information of each medicament from the processed medicament stock quantity;

Detecting a color change, an odor concentration, and a morphological change of a physical property of the agent;

the production date and lot number of each lot of medicament is automatically read using RFID tag technology.

3. The method for monitoring and managing inventory of pharmaceutical agents of claim 2, wherein the step of performing real-time fusion analysis of the extracted key features to generate a dynamic inventory status map comprises the steps of,

Constructing a correlation model by using a graph neural network, and identifying the correlation relation among the quantity of the medicaments, the storage environment parameters and the physical characteristics of the medicaments;

defining nodes as each medicament and related attributes thereof, and enabling edges to represent potential relations among different attributes;

constructing a graph structure based on the defined nodes and edges;

selecting a GNN variant for processing the iso-composition data, taking the constructed graph structure as input, and updating the node embedded vector;

Determining the position coordinates of each storage unit according to the actual layout of the warehouse;

And associating the updated embedded vector of each node with the corresponding position coordinate to generate a dynamic inventory state mapping diagram of each medicament.

4. The method for monitoring and managing inventory of pharmaceutical agents according to claim 3, wherein constructing a digital twin risk factor dynamic evaluation system based on the result of the expiration date prediction, calculating the risk factor of each storage unit comprises the steps of,

Selecting a digital twin platform, creating a digital twin instance, and configuring computing resources and storage resources;

constructing a warehouse physical layout comprising storage units, shelves, channels and equipment by using a 3D modeling tool, importing modeling results into a digital twin platform, and generating a digital twin model of the virtual warehouse;

Correlating the medicament stock quantity monitored by the multi-source sensor in real time with a storage unit in a digital twin model of the virtual warehouse, and updating the environment parameters and the physical characteristics of medicaments in the digital twin model of the virtual warehouse in real time;

defining static attribute and dynamic attribute of the digital twin model, constructing simulation scene in the digital twin platform, setting simulation parameters, and simulating risks under different conditions;

Based on the simulation results, calculating the risk coefficient of each storage unit 。

5. The method for monitoring and managing inventory of pharmaceutical agents according to claim 4, wherein the step of classifying the risk based on the calculated risk factors of each storage unit to obtain risk factor evaluation results comprises the steps of,

Setting according to physical properties and storage environment parameters of the medicamentFor a high risk threshold value,Is an alert threshold;

When (when) >When the high risk state is marked, a first-level response measure is generated, an audible and visual alarm is sent, the addition of the medicament to the high risk storage unit is automatically stopped, and warehouse management personnel are informed to perform manual inspection and treatment;

When (when) <≤When the warning state is marked, a secondary response measure is generated, a secondary audible and visual alarm is sent out, the addition of the medicament to the warning storage unit is automatically stopped, and the inspection frequency of the storage unit is increased;

When (when) ≤And when the storage unit is marked as a safe state, continuously monitoring the environment parameters and the medicament state of the storage unit, and checking the storage unit according to a standard inspection plan.

6. A monitoring and managing system for medicament stock based on the method for monitoring and managing medicament stock according to any one of claims 1 to 5 is characterized by comprising,

The sensing network module is used for deploying a multi-source sensor, monitoring the state of the medicament stock in real time, analyzing the state, and extracting key characteristics;

the state mapping module performs real-time fusion analysis on the extracted key features to generate a dynamic inventory state mapping diagram;

The self-adaptive allocation module is used for constructing a self-adaptive inventory allocation model driven by reinforcement learning based on the dynamic inventory state mapping diagram to obtain an optimal inventory allocation and scheduling strategy and update the inventory state;

the failure period prediction module is used for constructing a failure period distributed prediction model based on federal learning according to the updated inventory state and the failure period state, generating a failure period prediction result and performing collaborative optimization across warehouses;

and the risk assessment module is used for constructing a digital twin risk coefficient dynamic assessment system based on the failure period prediction result to obtain a risk coefficient assessment result.

7. A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the computer program is characterized in that the processor realizes the steps of the method for monitoring and managing medicament stock according to any one of claims 1-5 when executing the computer program.

8. A computer-readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the steps of the method for monitoring and managing inventory of pharmaceutical agents according to any one of claims 1 to 5.