Drug warehousing information storage method and system based on big data
By deploying sensor networks and optimizing three-dimensional point cloud models on drug carts, the problems of low efficiency and high error rate of traditional drug management are solved, and more efficient and accurate drug management and storage are achieved.
Patent Information
- Application Number
- CN202510142056.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-09
- Publication Date
- 2025-03-21
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional manual drug storage methods are difficult to meet the high efficiency requirements of modern medical service systems for drug management, especially due to the complexity of drug information, which leads to low management efficiency and high error rates.
By deploying RFID readers, temperature and humidity sensors, and position sensors on multiple drug carts, a sensor network is formed, and an initial three-dimensional point cloud model is created for each drug to be stored, optimized to determine the optimal storage and spatial layout.
Improve the efficiency and accuracy of drug management, and the optimized storage layout can make more efficient use of storage space, reduce the workload of manual management and adjustment, reduce error rates, and improve the storage efficiency of drugs.
Smart Images
Figure CN119671458A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of medical technology, and more specifically, to a method and system for storing drug inventory information based on big data. Background Art
[0002] In the modern medical service system, drug management is a key link to ensure patient safety and improve treatment efficiency. With the advancement of medical technology and the diversification of treatment options, drug management faces more and more challenges. With the continuous, stable and rapid development of the pharmaceutical industry and the popularization of the Internet, the standardization of drug information has become particularly important because it is directly related to the safety and effectiveness of drugs.
[0003] However, due to the complexity of drug information, including the multiple names, different manufacturers and diverse specifications of drugs, the traditional manual storage method has been unable to meet the high-efficiency requirements of drug management in the modern medical service system.
[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention
[0005] The embodiments of the present application provide a method and system for storing drug inventory information based on big data to solve the above-mentioned technical problems.
[0006] The present application provides a method for storing drug warehousing information based on big data, comprising: deploying multiple sensors on multiple drug display carts to form a sensor network; wherein the multiple sensors include RFID readers, temperature and humidity sensors, and position sensors; creating an initial three-dimensional point cloud model for each drug to be stored; mapping the attributes of the drug to be stored to the corresponding initial three-dimensional point cloud model to obtain a reference three-dimensional point cloud model; wherein the initial three-dimensional point cloud model includes the initial spatial position information of the drug and the identification information of the drug; each reference point cloud node of the reference three-dimensional point cloud model represents an attribute of the drug; receiving the attribute value of the drug to be stored; wherein the attribute value is a value corresponding to the attribute of the drug; optimizing the reference three-dimensional point cloud model based on the received attribute value of the drug to be stored; optimizing the storage layout and spatial layout of the drug to be stored according to the optimization result of the reference three-dimensional point cloud model; placing the drug to be stored on multiple drug display carts according to the optimized spatial layout of the drug to be stored.
[0007] The present application provides a drug storage information storage system based on big data, including: a sensor network formation module, which is used to deploy multiple sensors on multiple drug display carts to form a sensor network; wherein the multiple sensors include RFID readers, temperature and humidity sensors, and position sensors; a drug attribute information storage module, which is used to create an initial three-dimensional point cloud model for each drug to be stored; the attributes of the drug to be stored are mapped to the corresponding initial three-dimensional point cloud model to obtain a reference three-dimensional point cloud model; wherein the initial three-dimensional point cloud model includes the initial spatial position information of the drug and the identification information of the drug; each reference point cloud node of the reference three-dimensional point cloud model represents an attribute of the drug; a drug attribute value receiving module, which is used to receive the attribute value of the drug to be stored; wherein the attribute value is a value corresponding to the attribute of the drug; a drug storage optimization module, which is used to optimize the reference three-dimensional point cloud model based on the received attribute value of the drug to be stored; according to the optimization result of the reference three-dimensional point cloud model, the storage layout and spatial layout of the drug to be stored are optimized; according to the optimized spatial layout of the drug to be stored, the drug to be stored is placed on multiple drug display carts.
[0008] Based on the embodiments provided in the present application, a variety of sensors are deployed on multiple drug display carts to form a sensor network; wherein the multiple sensors include RFID readers, temperature and humidity sensors, and position sensors; an initial three-dimensional point cloud model is created for each drug to be stored; the attributes of the drug to be stored are mapped to the corresponding initial three-dimensional point cloud model to obtain a reference three-dimensional point cloud model; wherein the initial three-dimensional point cloud model includes the initial spatial position information of the drug and the identification information of the drug; each reference point cloud node of the reference three-dimensional point cloud model represents an attribute of the drug; the attribute value of the drug to be stored is received; wherein the attribute value is a value corresponding to the attribute of the drug; based on the received attribute value of the drug to be stored, the reference three-dimensional point cloud model is optimized; according to the optimization result of the reference three-dimensional point cloud model, the storage layout and spatial layout of the drug to be stored are optimized; according to the optimized spatial layout of the drug to be stored, the drug to be stored is placed on multiple drug display carts. The following are achieved: improving the efficiency and accuracy of drug management: by deploying RFID readers, temperature and humidity sensors, and position sensors on multiple drug display carts to form a sensor network, the location, status, and environmental conditions of drugs can be monitored in real time, thereby improving the efficiency and accuracy of drug management; improving the accuracy of storage layout: by referencing the optimization of the three-dimensional point cloud model, the location of drugs in the storage system can be accurately determined; the optimized storage layout can make more effective use of storage space; by optimizing the storage layout of drugs, the problems of low picking efficiency and increased error rate caused by unreasonable layout are solved; the optimized storage layout can be dynamically adjusted according to changes in drug attribute values, solving the problem of storage layout not adapting when drug attribute values change; the optimized storage layout reduces the workload of manual management and adjustment, and solves the problems of high complexity and high labor costs in drug management; by optimizing the storage layout and spatial layout of the drugs to be stored, the storage efficiency of drugs can be improved, and the problem of difficult drug traceability can be solved; the optimized storage layout and spatial layout can reduce bottlenecks in drug management. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] The drawings described herein are used to provide a further understanding of the embodiments of the present invention and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 It is a flowchart of an optional method for storing drug warehousing information based on big data according to an embodiment of the present application; Figure 2 This is a structural diagram of an optional big data-based drug warehousing information storage system according to an embodiment of the present application.
[0010] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0011] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0012] like Figure 1 As shown, the present application provides a method for storing drug warehousing information based on big data, including: S101, deploying a plurality of sensors on a plurality of medicine display carts to form a sensor network; wherein the plurality of sensors include RFID readers, temperature and humidity sensors, and position sensors; S102, creating an initial three-dimensional point cloud model for each drug to be stored; mapping the attributes of the drug to be stored to the corresponding initial three-dimensional point cloud model to obtain a reference three-dimensional point cloud model; wherein the initial three-dimensional point cloud model includes the initial spatial position information of the drug and the identification information of the drug; each reference point cloud node of the reference three-dimensional point cloud model represents an attribute of the drug; S103, receiving the attribute value of the drug to be stored; wherein the attribute value is a value corresponding to the attribute of the drug; S104, optimizing the reference three-dimensional point cloud model based on the received attribute values of the drugs to be stored; optimizing the storage layout and spatial layout of the drugs to be stored according to the optimization results of the reference three-dimensional point cloud model; S105, placing the drugs to be stored on a plurality of medicine display carts according to the optimized spatial layout of the drugs to be stored.
[0013] Based on the embodiments provided in the present application, a variety of sensors are deployed on multiple drug display carts to form a sensor network; wherein the multiple sensors include RFID readers, temperature and humidity sensors, and position sensors; an initial three-dimensional point cloud model is created for each drug to be stored; the attributes of the drug to be stored are mapped to the corresponding initial three-dimensional point cloud model to obtain a reference three-dimensional point cloud model; wherein the initial three-dimensional point cloud model includes the initial spatial position information of the drug and the identification information of the drug; each reference point cloud node of the reference three-dimensional point cloud model represents an attribute of the drug; the attribute value of the drug to be stored is received; wherein the attribute value is a value corresponding to the attribute of the drug; based on the received attribute value of the drug to be stored, the reference three-dimensional point cloud model is optimized; according to the optimization result of the reference three-dimensional point cloud model, the storage layout and spatial layout of the drug to be stored are optimized; according to the optimized spatial layout of the drug to be stored, the drug to be stored is placed on multiple drug display carts. The following are achieved: Improve the efficiency and accuracy of drug management: By deploying RFID readers, temperature and humidity sensors, and position sensors on multiple drug display carts to form a sensor network, the location, status, and environmental conditions of drugs can be monitored in real time, thereby improving the efficiency and accuracy of drug management; Improve the accuracy of storage layout: By referencing the optimization of the three-dimensional point cloud model, the location of drugs in the storage system can be accurately determined; the optimized storage layout can make more effective use of storage space; by optimizing the storage layout of drugs, the problems of low picking efficiency and increased error rate caused by unreasonable layout are solved; the optimized storage layout can be dynamically adjusted according to changes in drug attribute values, solving the problem of storage layout not adapting when drug attribute values change; the optimized storage layout reduces the workload of manual management and adjustment, and solves the problems of high complexity and high labor costs in drug management; by optimizing the storage layout and spatial layout of drugs to be stored, the storage efficiency of drugs can be improved, and the problem of difficult drug traceability can be solved; the optimized storage layout and spatial layout can reduce bottlenecks in drug management.
[0014] like Figure 2 As shown, the present application provides a drug storage information storage system based on big data, including: The sensor network forming module 201 is used to deploy multiple sensors on multiple medicine placing carts to form a sensor network; wherein the multiple sensors include RFID readers, temperature and humidity sensors, and position sensors; The drug attribute information storage module 202 is used to create an initial three-dimensional point cloud model for each drug to be stored; map the attributes of the drug to be stored to the corresponding initial three-dimensional point cloud model to obtain a reference three-dimensional point cloud model; The initial three-dimensional point cloud model includes the initial spatial position information of the drug and the identification information of the drug; each reference point cloud node of the reference three-dimensional point cloud model represents an attribute of the drug; The drug attribute value receiving module 203 is used to receive the attribute value of the drug to be stored; wherein the attribute value is the value corresponding to the attribute of the drug; The drug storage optimization module 204 is used to optimize the reference three-dimensional point cloud model based on the received attribute values of the drugs to be stored; optimize the storage layout and spatial layout of the drugs to be stored according to the optimization results of the reference three-dimensional point cloud model; and place the drugs to be stored on multiple medicine display carts according to the optimized spatial layout of the drugs to be stored.
[0015] Furthermore, the properties of the drugs to be stored are mapped to the corresponding initial three-dimensional point cloud model to obtain a reference three-dimensional point cloud model, including: Associating the properties of the drugs to be stored with the initial point cloud nodes of the initial three-dimensional point cloud model; Determine the position of each initial point cloud node in space, and establish a spatial hierarchical structure of the initial point cloud nodes according to the position of each initial point cloud node in three-dimensional space; According to the spatial hierarchical structure of the established initial point cloud nodes, a reference three-dimensional point cloud model is determined; wherein each reference point cloud node of the reference three-dimensional point cloud model indicates the status and mutual relationship of the drugs in the storage environment through spatial position and hierarchical relationship.
[0016] Further, the attributes include the name, specification, production batch number, expiration date, manufacturer, storage time and storage requirements of the drug; determining the position of each initial point cloud node in the three-dimensional space, and establishing a spatial hierarchical structure of the initial point cloud node according to the position of each initial point cloud node in the space; determining a reference three-dimensional point cloud model according to the established spatial hierarchical structure of the initial point cloud node, including: Establishing a reference three-dimensional coordinate system for the storage area of the medicine; wherein the reference three-dimensional coordinate system is used to determine the position of the medicine attribute in the storage area according to the position of each initial point cloud node or the position of each reference point cloud node; According to the categories between the attributes corresponding to each initial point cloud node, an initial three-dimensional coordinate is assigned to each initial point cloud node to determine the position of each initial point cloud node in the reference three-dimensional coordinate system; According to the attribute hierarchy rules of the drug, the association relationship between the attributes corresponding to each initial point cloud node and the position of each initial point cloud node in the reference three-dimensional coordinate system, a spatial hierarchical structure of the initial point cloud node is established; According to the spatial hierarchical structure of the initial point cloud nodes, a reference 3D point cloud model is constructed.
[0017] Further, according to the categories between the attributes corresponding to each initial point cloud node, an initial three-dimensional coordinate is assigned to each initial point cloud node to determine the position of each initial point cloud node in the reference three-dimensional coordinate system; according to the attribute hierarchy rules of the drug, the association relationship between the attributes corresponding to each initial point cloud node and the position of each initial point cloud node in the reference three-dimensional coordinate system, a spatial hierarchical structure of the initial point cloud node is established; according to the spatial hierarchical structure of the initial point cloud node, a reference three-dimensional point cloud model is constructed, including: Using the simulated bifurcation algorithm, the initial point cloud node set is determined according to the categories between the attributes corresponding to each initial point cloud node. The bifurcation probability of It is composed of the initial point cloud nodes; According to the initial point cloud node set The bifurcation probability is used to assign an initial three-dimensional coordinate to each initial point cloud node to determine the position of each initial point cloud node in the reference three-dimensional coordinate system; Using the three-dimensional normal distribution transformation algorithm, the spatial hierarchical structure of the initial point cloud nodes is established according to the attribute hierarchy rules of the drug, the association relationship between the attributes corresponding to each initial point cloud node, and the position of each initial point cloud node in the reference three-dimensional coordinate system; An objective function is constructed according to the position of the initial point cloud node in the reference three-dimensional coordinate system and the spatial hierarchical structure of the initial point cloud node, and a reference three-dimensional point cloud model is constructed based on the objective function.
[0018] Further, ; in, Represents the initial point cloud node set The bifurcation probability is based on the initial point cloud node set The property of the drug corresponding to a certain initial point cloud node includes determining the probability of the position allocation of the initial point cloud node in the three-dimensional coordinate system; The higher the value of , the greater the change in spatial position caused by the drug properties; Is the initial point cloud node set The Similarity scores of attributes corresponding to the initial point cloud nodes; Used to measure the similarity between drug attributes. For example, if two drugs have the same production batch number, their similarity score on the production batch number attribute will be high. Is the initial point cloud node set The number of initial point cloud nodes in ; It is The weight of the attribute corresponding to each initial point cloud node is used to adjust the importance of different attributes in the calculation of the bifurcation probability. The weight can be set according to the importance of the attribute to the drug storage location. For example, the manufacturer may have a greater impact on the location allocation than the drug name. It is a preset similarity threshold, which can be set according to the actual storage requirements and the importance of the drug attributes, and is used to determine whether the attribute similarity score is high enough to affect the spatial location allocation of the drug; is a parameter that controls the probability of forking, affecting the steepness of the curve; The larger the value of , the more significant the impact of the attribute similarity score on the bifurcation probability. This formula calculates the bifurcation probability of the location allocation of drugs in the storage space by combining multiple attributes of the drug and their similarity scores. This design makes the location allocation of drugs not only rely on a single attribute, but also comprehensively considers the influence of all relevant attributes, thereby more accurately simulating the distribution of drugs in the storage space. In this way, we can ensure a more reasonable location allocation of drugs and optimize storage efficiency and inventory management.
[0019] Furthermore, the similarity measure of the spatial hierarchical structure of the initial point cloud nodes is: ; in, Represents two initial point cloud nodes and The spatial hierarchical structure similarity between the nodes indicates the similarity between two nodes in space and attributes, and is used to establish the spatial hierarchical structure of drugs; Is a node and The Euclidean distance between is the distance attenuation parameter, which is used to adjust the sensitivity of distance to similarity. A value of means that two drugs are considered similar only if they are very close; It is a parameter that controls the effect of spatial distance on the similarity of spatial hierarchical structure and is used to determine the weight of the distance factor in the calculation of total similarity; It is an attribute difference measure that measures the degree to which two drugs differ in their attributes; this can be some measure based on the difference in attribute values, such as the cosine similarity of attribute vectors; is the attribute difference attenuation parameter, which is used to adjust the sensitivity of attribute differences to similarity. The value means that two drugs are considered dissimilar only if they are very different in their attributes; It is a parameter that controls the effect of attribute differences on the similarity of the hierarchical structure; it determines the weight of the attribute difference factor in the total similarity calculation.
[0020] This formula more comprehensively describes the spatial hierarchical relationship between drugs by combining spatial distance and attribute differences. In this way, we can ensure that the location allocation of drugs is not only based on spatial proximity, but also takes into account the similarity of attributes, thereby more accurately simulating the distribution of drugs in the storage space. This method of comprehensively considering spatial and attribute information helps to optimize the storage layout of drugs and improve the efficiency of inventory management.
[0021] ; in, It is the objective function used to evaluate the fitness of the spatial position and attribute information of each initial point cloud node when constructing the reference 3D point cloud model. The smaller the value of this function, the more the position and attribute information of the drug node are adapted to the requirements of the model. It is the spatial coordinate of the initial point cloud node, indicating the position of the drug in the reference three-dimensional coordinate system. Is the initial point cloud node The synergy score between the two drugs measures the interaction and synergy between different drug attributes; and These are the indices of the initial point cloud nodes. : The degree of compliance with the attribute rules reflects the initial point cloud node set The degree of compliance with pre-set rules; , , is a weight parameter used to balance the impact of fork probability, hierarchical similarity, synergy between attributes, and attribute rule compliance on model optimization. , , They can be 0.41, 0.25, 0.85, and 0.66 respectively. These parameters can be adjusted according to the needs of the actual application scenario to ensure that the model optimization objectives are consistent with the business objectives.
[0022] It plays a core role in the process of building a reference 3D point cloud model. It comprehensively considers the spatial position and attribute information of the drug. By optimizing this objective function, we can find the best drug node position so that the spatial distribution of the drug not only meets the similarity and synergy between attributes, but also meets the preset attribute rules. In this way, a reference 3D point cloud model that considers both spatial relationships and attribute information can be constructed, thereby optimizing the storage layout of drugs and improving the efficiency of inventory management. In this way, the model can not only accurately represent the spatial location of drugs, but also reflect the complex relationship between drug attributes, providing strong support for drug management and retrieval.
[0023] Further, based on the received attribute values of the drugs to be stored, the reference three-dimensional point cloud model is optimized; according to the optimization result of the reference three-dimensional point cloud model, the storage layout and spatial layout of the drugs to be stored are optimized, including: Based on the analysis result of the attribute value of the received medicine to be stored, adjusting the position of the reference point cloud node in the reference three-dimensional point cloud model; For example, the distribution of drugs in three-dimensional space can be adjusted according to their volume and weight, and their hierarchical position in the warehouse can be adjusted according to the storage conditions of the drugs. Heavier drugs may need to be placed on the bottom layer to avoid crushing other drugs, while larger drugs may require more space. As drugs are put in and taken out of the warehouse, the reference three-dimensional point cloud model needs to be dynamically updated. This can be achieved by monitoring the changes in the properties and spatial positions of drugs in real time to ensure that the model always reflects the latest storage status.
[0024] A user interface can be provided to allow warehouse managers to intuitively view and manipulate the reference 3D point cloud model. Through the visualization tool, users can easily identify the location of drugs, adjust the storage layout, and monitor the storage status of the warehouse.
[0025] The Apriori algorithm is used to optimize the storage layout and spatial layout of the drugs to be stored according to the optimization results of the reference three-dimensional point cloud model.
[0026] In the optimization of drug storage layout, the Apriori algorithm can help identify drug combinations that are often purchased together, and then arrange the placement of drugs reasonably to reduce the time customers spend looking for drugs and improve sales efficiency. The Apriori algorithm analyzes the sales pattern and association rules of drugs and proposes an optimization strategy to minimize the picking path, improve the utilization of storage space, and increase inventory turnover.
[0027] Furthermore, the drug storage information storage system based on big data also includes: The drug real-time information display module is used to display the real-time information of the drugs to be stored to medical staff in the form of graphics, text and color coding through flexible display technology; the real-time information of the drugs to be stored includes status, physical location, storage location, storage environment and expiration date; The risk warning mode adjustment module is used to receive modification instructions input by medical staff and adjust the display mode and warning mode of the interactive interface; wherein the modification instructions are determined based on the needs of medical work.
[0028] Furthermore, the drug storage information storage system based on big data also includes: The drug tracking and recall module is used to track the circulation path of the drugs to be stored based on the RFID reader tags of the drugs to be stored; when the drugs to be stored have quality problems, locate and recall the relevant batches of drugs; The drug management optimization module is used to identify and warn of potential safety issues of drugs to be stored based on real-time information of the drugs to be stored; and to feed back potential safety issues to the drug supplier management system to optimize the procurement plan and inventory management specifications of the drugs to be stored.
[0029] It should be noted that in the present application, the embodiments implemented by the drug warehousing information storage system based on big data can be cross-referenced with the embodiments implemented by the drug warehousing information storage method based on big data, and the present application will not go into details one by one.
[0030] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.
Claims
1. A method for storing drug warehousing information based on big data, characterized in that: include: Deploy multiple sensors on multiple medicine carts to form a sensor network; wherein the multiple sensors include RFID readers, temperature and humidity sensors, and position sensors; An initial three-dimensional point cloud model is created for each drug to be stored; the attributes of the drug to be stored are mapped to the corresponding initial three-dimensional point cloud model to obtain a reference three-dimensional point cloud model; wherein the initial three-dimensional point cloud model includes the initial spatial position information of the drug and the identification information of the drug; each reference point cloud node of the reference three-dimensional point cloud model represents an attribute of the drug; Receive the attribute value of the drug to be stored; wherein the attribute value is a value corresponding to the attribute of the drug; Based on the received attribute values of the drugs to be stored, the reference three-dimensional point cloud model is optimized; according to the optimization result of the reference three-dimensional point cloud model, the storage layout and spatial layout of the drugs to be stored are optimized; According to the optimized spatial layout of the drugs to be stored, the drugs to be stored are placed on a plurality of medicine display carts.
2. A drug storage information storage system based on big data, the system implementing the drug storage information storage method based on big data as claimed in claim 1, characterized in that: include: A sensor network forming module, used to deploy multiple sensors on multiple medicine placing carts to form a sensor network; wherein the multiple sensors include RFID readers, temperature and humidity sensors, and position sensors; The drug attribute information storage module is used to create an initial three-dimensional point cloud model for each drug to be stored; the attributes of the drug to be stored are mapped to the corresponding initial three-dimensional point cloud model to obtain a reference three-dimensional point cloud model; The initial three-dimensional point cloud model includes the initial spatial position information of the drug and the identification information of the drug; each reference point cloud node of the reference three-dimensional point cloud model represents an attribute of the drug; The drug attribute value receiving module is used to receive the attribute value of the drug to be stored; wherein the attribute value is a value corresponding to the attribute of the drug; The drug storage optimization module is used to optimize the reference three-dimensional point cloud model based on the received attribute values of the drugs to be stored; optimize the storage layout and spatial layout of the drugs to be stored according to the optimization results of the reference three-dimensional point cloud model; and place the drugs to be stored on multiple medicine display carts according to the optimized spatial layout of the drugs to be stored.
3. The drug storage information storage system based on big data according to claim 2 is characterized in that: The method of mapping the properties of the drugs to be stored to the corresponding initial three-dimensional point cloud model to obtain a reference three-dimensional point cloud model includes: Associating the properties of the drugs to be stored with the initial point cloud nodes of the initial three-dimensional point cloud model; Determine the position of each initial point cloud node in space, and establish a spatial hierarchical structure of the initial point cloud nodes according to the position of each initial point cloud node in three-dimensional space; The reference three-dimensional point cloud model is determined based on the established spatial hierarchical structure of the initial point cloud nodes; wherein each reference point cloud node of the reference three-dimensional point cloud model indicates the status and mutual relationship of drugs in the storage environment through spatial position and hierarchical relationship.
4. The drug storage information storage system based on big data according to claim 3 is characterized in that: The attributes include the name, specification, production batch number, validity period, manufacturer, storage time and storage requirements of the drug; the position of each initial point cloud node in the three-dimensional space is determined, and the spatial hierarchical structure of the initial point cloud node is established according to the position of each initial point cloud node in the space; Determining the reference three-dimensional point cloud model according to the established spatial hierarchical structure of the initial point cloud nodes includes: Establishing a reference three-dimensional coordinate system for the storage area of the medicine; wherein the reference three-dimensional coordinate system is used to determine the position of the medicine attribute in the storage area according to the position of each initial point cloud node or the position of each reference point cloud node; According to the categories between the attributes corresponding to each initial point cloud node, an initial three-dimensional coordinate is assigned to each initial point cloud node to determine the position of each initial point cloud node in the reference three-dimensional coordinate system; According to the attribute hierarchy rules of the drug, the association relationship between the attributes corresponding to each initial point cloud node and the position of each initial point cloud node in the reference three-dimensional coordinate system, a spatial hierarchical structure of the initial point cloud node is established; The reference three-dimensional point cloud model is constructed according to the spatial hierarchical structure of the initial point cloud nodes.
5. The drug storage information storage system based on big data according to claim 4 is characterized in that: According to the categories between the attributes corresponding to each initial point cloud node, an initial three-dimensional coordinate is assigned to each initial point cloud node to determine the position of each initial point cloud node in the reference three-dimensional coordinate system; according to the attribute hierarchy rules of the drug, the association relationship between the attributes corresponding to each initial point cloud node and the position of each initial point cloud node in the reference three-dimensional coordinate system, a spatial hierarchical structure of the initial point cloud node is established; Constructing the reference three-dimensional point cloud model according to the spatial hierarchical structure of the initial point cloud nodes includes: Using the simulated bifurcation algorithm, the initial point cloud node set is determined according to the categories between the attributes corresponding to each initial point cloud node. The bifurcation probability of; wherein, the initial point cloud node set Consisting of the initial point cloud nodes; According to the initial point cloud node set The bifurcation probability is , assigning an initial three-dimensional coordinate to each initial point cloud node to determine the position of each initial point cloud node in the reference three-dimensional coordinate system; Using a three-dimensional normal distribution transformation algorithm, according to the attribute hierarchy rules of the drug, the association relationship between the attributes corresponding to each initial point cloud node, and the position of each initial point cloud node in the reference three-dimensional coordinate system, a spatial hierarchical structure of the initial point cloud node is established; An objective function is constructed according to the position of the initial point cloud node in the reference three-dimensional coordinate system and the spatial hierarchical structure of the initial point cloud node, and the reference three-dimensional point cloud model is constructed based on the objective function.
6. The drug storage information storage system based on big data according to claim 5 is characterized by: ； in, Represents the initial point cloud node set The bifurcation probability is based on the initial point cloud node set The property of the drug corresponding to a certain initial point cloud node includes determining the probability of the position allocation of the initial point cloud node in the three-dimensional coordinate system; The higher the value of , the greater the change in spatial position caused by the drug properties; is the initial point cloud node set The Similarity scores of attributes corresponding to the initial point cloud nodes; Used to measure the similarity between drug attributes; is the initial point cloud node set The number of initial point cloud nodes in ; It is The weight of the attribute corresponding to the initial point cloud node is used to adjust the importance of different attributes in the calculation of the bifurcation probability; is a preset similarity threshold used to determine whether the similarity score of the attribute is high enough to affect the spatial location allocation of the drug; is a parameter that controls the probability of forking, affecting the steepness of the curve; The larger the value of , the more significant the impact of the attribute similarity score on the bifurcation probability.
7. The drug storage information storage system based on big data according to claim 5 is characterized in that: The similarity measure of the spatial hierarchical structure of the initial point cloud nodes is: ； in, Represents two initial point cloud nodes and The spatial hierarchical structure similarity between the nodes indicates the similarity between two nodes in space and attributes, and is used to establish the spatial hierarchical structure of drugs; Is a node and The Euclidean distance between is the distance attenuation parameter, which is used to adjust the sensitivity of distance to similarity; It is a parameter that controls the effect of spatial distance on the similarity of spatial hierarchical structure and is used to determine the weight of the distance factor in the calculation of total similarity; is the attribute difference measure; is the attribute difference attenuation parameter, which is used to adjust the sensitivity of attribute difference to similarity; It is a parameter that controls the effect of attribute differences on the similarity of the hierarchical structure.
8. The drug storage information storage system based on big data according to claim 2 is characterized in that: The step of optimizing the reference three-dimensional point cloud model based on the received attribute values of the drugs to be stored; and optimizing the storage layout and spatial layout of the drugs to be stored according to the optimization result of the reference three-dimensional point cloud model, includes: Based on the analysis result of the received attribute values of the medicine to be stored, adjusting the position of the reference point cloud node in the reference three-dimensional point cloud model; The Apriori algorithm is used to optimize the storage layout and spatial layout of the drugs to be stored according to the optimization result of the reference three-dimensional point cloud model.
9. The drug storage information storage system based on big data according to claim 2 is characterized in that: The drug storage information storage system based on big data also includes: The real-time information display module of drugs is used to display the real-time information of the drugs to be stored to medical staff in the form of graphics, text and color coding through flexible display technology; wherein the real-time information of the drugs to be stored includes status, physical location, storage location, storage environment and expiration date; The risk warning mode adjustment module is used to receive modification instructions input by medical staff and adjust the display mode and warning mode of the interactive interface; wherein the modification instructions are determined based on the medical work needs.
10. The drug storage information storage system based on big data according to claim 9 is characterized in that: The drug storage information storage system based on big data also includes: A drug tracking and recall module, for tracking the circulation path of the drug to be stored based on the RFID reader tag of the drug to be stored; locating and recalling the relevant batches of drugs when the drug to be stored has quality problems; The drug management optimization module is used to identify and warn about potential safety issues of the drugs to be stored based on the real-time information of the drugs to be stored; and to feed back the potential safety issues to the drug supplier management system to optimize the procurement plan and inventory management specifications of the drugs to be stored.