Pharmacy management method based on internet of things perception and behavior analysis

Abstract

The application discloses a pharmacy management method based on Internet of Things sensing and behavior analysis, and belongs to the technical field of pharmacy management. The pharmacy management method comprises the following steps: acquiring sensing data and pharmacy business data in a pharmacy environment, wherein the sensing data comprises mobile trajectory data of each pharmacist, weight sensing data corresponding to medicine taking and placing actions, and video image data; generating a business association graph and a physical time consumption graph according to the sensing data and the pharmacy business data, wherein the business association graph is a directed graph, the vertex is a medicine, and the edge is the probability of continuous operation of two medicines; the physical time consumption graph is a directed graph, the vertex is a medicine position, and the edge is the corresponding use time of two medicine positions; and generating a pharmacy management strategy according to the business association graph and the physical time consumption graph, wherein the pharmacy management strategy comprises a medicine position adjustment strategy and a medicine grabbing optimization strategy, and the pharmacy management method has the beneficial effect of improving the pharmacy management efficiency.

Description

Technical Field

[0001] This invention relates to the field of pharmacy management technology, and in particular to a pharmacy management method based on Internet of Things (IoT) sensing and behavior analysis. Background Technology

[0002] With the pursuit of medical efficiency, there is a growing demand for efficient pharmacy management. Hospital pharmacies generally rely on manual experience for drug display and picking route planning. Drug placement layouts are often fixed and out of touch with clinical medication habits, causing pharmacists to frequently travel between distant drug locations during prescription dispensing. This results in long walking distances, low retrieval efficiency, and difficulty adapting to dynamic changes in drug usage frequency. Current technologies are largely limited to simple inventory information management, lacking real-time awareness of pharmacist movement, drug retrieval sequence, and weight changes. They cannot establish a mapping relationship between drug business relationships and spatial locations, and are even less capable of data-driven dynamic optimization of drug placement layouts and intelligent planning of picking routes, thus contributing to decreased pharmacy management efficiency.

[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main objective of this invention is to provide a pharmacy management method based on Internet of Things (IoT) sensing and behavior analysis, aiming to improve pharmacy management efficiency. To achieve the above objective, this invention provides a pharmacy management method based on IoT sensing and behavior analysis, which includes the following steps: Acquire sensor data and pharmaceutical business data within the pharmacy environment. The sensor data includes: movement trajectory data of each pharmacist, weight sensing data corresponding to drug handling actions, and video image data. Based on the perceived data and pharmaceutical business data, a business association graph and a physical time consumption graph are generated. The business association graph is a directed graph, with vertices representing drugs and edges representing the probability of consecutive operation of two drugs. The physical time consumption graph is a directed graph, with vertices representing drug positions and edges representing the corresponding usage time of two drug positions. A pharmacy management strategy is generated based on the business relationship diagram and the physical time consumption diagram. The pharmacy management strategy includes: a drug location adjustment strategy and a drug retrieval optimization strategy.

[0005] Optionally, the pharmaceutical business data includes: prescription information data, and the step of generating a business association diagram and a physical time consumption diagram based on the perception data and pharmaceutical business data includes: Statistically analyze the drug co-occurrence information corresponding to each prescription to obtain the drug co-occurrence probability; Based on the perceived data, drug grasping information and drug location information are determined; The business association graph is determined based on the drug co-occurrence probability and the drug retrieval information; The physical time consumption diagram is determined based on the drug capture information and the drug location information.

[0006] Optionally, the step of determining drug retrieval information and drug location information based on the sensing data includes: The drug identifier and the time of each drug retrieval / placement action are determined based on the weight sensing data. The starting and ending drug positions for each drug grabbing action are determined based on the movement trajectory data and the grabbing and placing times. The drug retrieval information is determined based on the starting drug position, the ending drug position, and the retrieval / placement time. The target drug location for each drug is determined based on the video image data, thus obtaining the drug location information.

[0007] Optionally, the step of determining the business association graph based on the drug co-occurrence probability and the drug retrieval information includes: The co-occurrence frequency between each pair of drugs is determined based on the drug co-occurrence probability. The co-occurrence frequencies are weighted according to the drug capture information to obtain weighted co-occurrence frequencies; The business association graph is constructed based on the weighted co-occurrence frequency.

[0008] Optionally, the step of determining the physical time-consuming graph based on the drug grabbing information and the drug location information includes: The number of times each pair of drug positions is counted based on the drug grabbing information. Calculate the actual movement time between each pair of drug sites based on the movement trajectory data; Calculate the average movement time between each pair of drug positions based on the number of grabs and the actual movement time. The physical time consumption map is constructed based on the average movement time.

[0009] Optionally, the step of generating a pharmacy management strategy based on the business relationship graph and the physical time consumption graph includes: Determine high-frequency drug association pairs based on the aforementioned business association diagram; The physical movement cost between each pair of drug sites is determined based on the physical time consumption diagram. Calculate drug location associated misscheduling based on the high-frequency drug association pairs and the physical movement cost; The drug location adjustment strategy is determined based on the drug location-related misalignment. The drug retrieval optimization strategy is determined based on the business association graph, the physical time consumption graph, and the current prescription information.

[0010] Optionally, the step of acquiring sensing data within the pharmacy environment includes: The movement trajectory data is obtained by collecting the real-time location data of each pharmacist through radio frequency identification equipment; The weight sensing data is obtained by collecting weight change data corresponding to the medicine picking and placing actions through a weight sensing device. The video image data is obtained by collecting video stream data of the pharmacy operation area through video surveillance equipment.

[0011] Furthermore, to achieve the above objectives, the present invention also provides a pharmacy management device based on Internet of Things (IoT) sensing and behavior analysis, the pharmacy management device based on IoT sensing and behavior analysis comprising: The acquisition module is used to acquire perception data and pharmaceutical business data within the pharmacy environment. The perception data includes: movement trajectory data of each pharmacist, weight sensing data corresponding to drug handling actions, and video image data. The analysis module is used to generate a business association graph and a physical time consumption graph based on the perceived data and pharmaceutical business data. The business association graph is a directed graph with vertices representing drugs and edges representing the probability of consecutive operation of two drugs. The physical time consumption graph is a directed graph with vertices representing drug positions and edges representing the corresponding usage time of two drug positions. The management module is used to generate pharmacy management strategies based on the business relationship graph and the physical time consumption graph. The pharmacy management strategies include: drug location adjustment strategies and drug retrieval optimization strategies.

[0012] Furthermore, to achieve the above objectives, the present invention also provides a pharmacy management device based on Internet of Things (IoT) sensing and behavior analysis. The pharmacy management device based on IoT sensing and behavior analysis includes: a memory, a processor, and a pharmacy management program based on IoT sensing and behavior analysis stored in the memory and executable on the processor. The pharmacy management program based on IoT sensing and behavior analysis is configured to implement the steps of the pharmacy management method based on IoT sensing and behavior analysis described above.

[0013] In addition, to achieve the above objectives, the present invention also provides a storage medium storing a pharmacy management program based on Internet of Things (IoT) sensing and behavior analysis, wherein when the pharmacy management program based on IoT sensing and behavior analysis is executed by a processor, it implements the steps of the pharmacy management method based on IoT sensing and behavior analysis described above.

[0014] This invention proposes a pharmacy management method based on IoT sensing and behavior analysis. This method acquires sensing data and pharmaceutical business data within the pharmacy environment, generates a business relationship graph and a physical time consumption graph based on the sensing data and pharmaceutical business data, and generates a pharmacy management strategy based on the business relationship graph and the physical time consumption graph. Compared to current methods limited to simple inventory information management, this method can track pharmacists' work behavior and combine it with business data to analyze optimizable locations in the scenario, achieving precise pharmacy management and thus improving the pharmacy's operational efficiency. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the structure of a pharmacy management device based on Internet of Things (IoT) sensing and behavior analysis, which is part of the hardware operating environment of the embodiment of the present invention. Figure 2 This is a flowchart illustrating the first embodiment of the pharmacy management method based on Internet of Things sensing and behavior analysis of the present invention. Figure 3 This is a flowchart illustrating the second embodiment of the pharmacy management method based on Internet of Things sensing and behavior analysis of the present invention.

[0016] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0017] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0018] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of a pharmacy management device based on Internet of Things (IoT) sensing and behavior analysis, which is part of the hardware operating environment of the embodiment of the present invention.

[0019] like Figure 1As shown, the pharmacy management device based on IoT sensing and behavior analysis may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, an interactive device 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The interactive device 1003 may include a display screen or an input unit such as a keyboard. Optionally, the interactive device 1003 may also connect to the communication bus via standard wired or wireless interfaces. The network interface 1004 may optionally include standard wired or wireless interfaces (such as a Wi-Fi interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0020] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on pharmacy management devices based on IoT sensing and behavior analysis, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0021] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a data storage module, a network communication module, a user interface module, and a pharmacy management program based on Internet of Things (IoT) sensing and behavior analysis.

[0022] exist Figure 1 In the pharmacy management device based on IoT sensing and behavior analysis shown, the network interface 1004 is mainly used for data communication with other devices; the interactive device 1003 is mainly used for data interaction with users; the processor 1001 and memory 1005 in the pharmacy management device based on IoT sensing and behavior analysis of the present invention can be set in the pharmacy management device based on IoT sensing and behavior analysis. The pharmacy management device based on IoT sensing and behavior analysis calls the pharmacy management program based on IoT sensing and behavior analysis stored in the memory 1005 through the processor 1001 and executes the pharmacy management method based on IoT sensing and behavior analysis provided in the embodiment of the present invention.

[0023] This invention provides a pharmacy management method based on IoT sensing and behavior analysis, referring to... Figure 2 , Figure 2This is a flowchart illustrating the first embodiment of a pharmacy management method based on Internet of Things (IoT) sensing and behavior analysis according to the present invention.

[0024] In this embodiment, the pharmacy management method based on IoT sensing and behavior analysis includes: Step S1: Acquire sensor data and pharmaceutical business data within the pharmacy environment. The sensor data includes: movement trajectory data of each pharmacist, weight sensing data corresponding to drug handling actions, and video image data. In this embodiment, high-precision sensors are installed in the pharmacy environment to acquire information about the environment. Specifically, pressure sensors are installed at specific locations to collect changes in medication dosage. Optionally, since medications are stored differently, not every medication can be detected by pressure sensors. Therefore, image sensors can also be used to collect information about specific medications. Furthermore, camera devices can be used to collect user action information, allowing the pharmacist to understand the time and actions required to retrieve medications from the prescription. Further, RFID tags can be used to accurately determine the order in which the pharmacist retrieves medications from the prescription. Typically, pharmacists wear tag readers, and corresponding RFID tags are affixed to the locations of the medications. This allows the pharmacist's work status to be determined by sensing the pharmacy environment. Subsequent data aggregation can optimize pharmacy management.

[0025] Step S2: Generate a business association graph and a physical time consumption graph based on the perception data and pharmaceutical business data. The business association graph is a directed graph, with vertices representing drugs and edges representing the probability of consecutive operation of two drugs. The physical time consumption graph is a directed graph, with vertices representing drug positions and edges representing the corresponding usage time of two drug positions. In this embodiment, by analyzing and mining the perceived data and pharmaceutical business data, a directed graph representing the current operational status of the pharmacy is generated. Specifically, the pharmaceutical business data includes prescription data. This involves analyzing the co-occurrence of drugs in multiple prescriptions, i.e., analyzing all drugs present in a prescription, where all drugs in the prescription have co-occurrence relationships. Any two drugs are marked as co-occurring once. A business association graph is determined based on the co-occurrence data. In this embodiment, the perceived data also needs to be analyzed to extract the order in which pharmacists retrieve drugs and the time required for the drug retrieval process. A physical time consumption graph is determined based on this information, where the drug location is associated with the drug information.

[0026] Step S3: Generate a pharmacy management strategy based on the business association graph and the physical time consumption graph. The pharmacy management strategy includes: a drug location adjustment strategy and a drug retrieval optimization strategy.

[0027] It should be noted that after obtaining the business association graph and the physical time consumption graph, a cam-based algorithm can be used to optimize pharmacy management strategies. Optionally, a community detection algorithm can be used to identify strongly correlated drug clusters in the business association graph and assign frequently co-occurring drug clusters to nearby drug location nodes in the physical time consumption graph to shorten the retrieval path. Of course, it should be noted that this allocation method needs to be based on fundamental drug management methods. Commonly, there are special drug zones, such as cold chain zones, cool zones, and dedicated storage areas. The temperature in the cold chain zone is generally 2-8 degrees Celsius, typically used for storing biological products and insulin. The cool zone generally requires a storage temperature not exceeding 20 degrees Celsius. Dedicated storage areas are generally used to store valuable drugs and flammable, explosive, or hazardous materials. Furthermore, for the drug retrieval optimization strategy, the path optimization problem is solved based on the edge weights of the physical time consumption graph, planning the retrieval order and path that minimizes the total walking time for the prescription drug set. This allows for a certain degree of optimization of the order in which pharmacists obtain drugs, thereby improving efficiency.

[0028] In this embodiment, by acquiring sensory data and pharmaceutical business data within the pharmacy environment, a business association diagram and a physical time consumption diagram are generated based on the sensory data and pharmaceutical business data. A pharmacy management strategy is then generated based on the business association diagram and the physical time consumption diagram. Compared to the current method which is limited to simple inventory information management, this method can track pharmacists' work behavior and combine it with business data to analyze optimizable locations in the scenario, thereby achieving precise management of the pharmacy and improving its operational efficiency.

[0029] Furthermore, based on the first embodiment, a second embodiment of the pharmacy management method based on IoT sensing and behavior analysis of the present invention is proposed. In this embodiment, reference is made to... Figure 3 The pharmaceutical business data includes: prescription information data. The step of generating a business association diagram and a physical time consumption diagram based on the perception data and pharmaceutical business data includes: Step S21: Calculate the drug co-occurrence information for each prescription to obtain the drug co-occurrence probability; The drug co-occurrence information for each prescription is statistically analyzed. Each prescription may contain multiple co-occurrence pairs; for example, a prescription may contain three or more drugs, resulting in more than one co-occurrence pair. Conversely, if a prescription contains only two drugs, the number of co-occurrence pairs is one. It should be noted that a co-occurrence pair here refers to two different drugs appearing in the same prescription. All co-occurrence pairs are statistically analyzed, and the probability of each pair is calculated to obtain the drug co-occurrence probability. Optionally, in other embodiments, specifically, an association rule mining algorithm is used to statistically analyze the frequency of any two drugs appearing in the same prescription, and this frequency is divided by the total number of prescriptions or the number of times a specific drug appears to calculate the drug co-occurrence probability.

[0030] Step S22: Determine drug grasping information and drug location information based on the perceived data; Optionally, by analyzing video image data to identify pharmacist hand posture and drug barcodes, and combining the abrupt change in weight sensing data to determine the timestamp of the drug grasping action and the drug identity, the specific drug location coordinates during the grasping action are determined using the coordinate sequence in the movement trajectory data. From this, a triplet of data containing drug ID, grasping time, and drug location is extracted to form structured drug grasping information and drug location information, providing accurate behavior-location mapping data for subsequent association of business logic and physical space.

[0031] Step S23: Determine the business association graph based on the drug co-occurrence probability and the drug retrieval information; Specifically, a directed graph is constructed with the drugs as vertices. The existence threshold of the edges is determined based on the drug co-occurrence probability calculated in step S21. Combined with the temporal order in the drug grabbing information extracted in step S22, the conditional probability of two drugs appearing consecutively in adjacent grabbing actions is calculated as the weight of the directed edges.

[0032] It should be noted that the business association graph actually integrates the static preferences in prescription information with the dynamic transfer patterns of actual crawling behavior, forming an objective graph form describing the relationships between drugs, thus providing a data-driven basis based on clinical practice for subsequent drug location clustering and layout optimization.

[0033] Step S24: Determine the physical time consumption diagram based on the drug grabbing information and the drug location information.

[0034] Optionally, the "pharmacy location" here refers to the position where the medicine is placed. Specifically, a directed graph is constructed with the pharmacy location as the vertex. Based on the medicine location information determined in step S22, the medicine is mapped to the specific pharmacy location node. The actual walking distance and time are calculated using the coordinate difference between adjacent capture times in the pharmacist's movement trajectory data, or estimated using the Euclidean distance and speed model, and used as the weight of the directed edge connecting two pharmacy location nodes. This physical time consumption graph quantifies the actual passage cost in the pharmacy spatial layout, complementing the business association graph in step S23, and jointly supporting subsequent shortest path planning and layout optimization decisions.

[0035] In this embodiment, by statistically analyzing the drug co-occurrence information corresponding to each prescription, the drug co-occurrence probability is obtained. Based on the perceived data, drug capture information and drug location information are determined. Based on the drug co-occurrence probability and the drug capture information, the business association graph is determined. Based on the drug capture information and the drug location information, the physical time consumption graph is determined. Thus, two related data graphs reflecting the pharmacy situation can be obtained. Based on the data graphs, subsequent pharmacy management decisions can be made more convenient.

[0036] Furthermore, based on the first or second embodiment, a third embodiment of the pharmacy management method based on IoT sensing and behavior analysis of the present invention is proposed. In this embodiment, the step of determining drug retrieval information and drug location information based on the sensing data includes: The drug identifier and the time of each drug retrieval / placement action are determined based on the weight sensing data. The starting and ending drug positions for each drug grabbing action are determined based on the movement trajectory data and the grabbing and placing times. The drug retrieval information is determined based on the starting drug position, the ending drug position, and the retrieval / placement time. The target drug location for each drug is determined based on the video image data, thus obtaining the drug location information.

[0037] In this embodiment, by analyzing the abrupt changes and differences in the weight sensing data and comparing them with a drug weight feature database, the specific drug identity and its occurrence time that triggered the action are identified. This process transforms the physical weight signal into a structured drug behavior event, providing a precise time stamp for subsequent association with the pharmacist's movement trajectory. Based on the aforementioned pharmacist movement trajectory data stream indexed by the pick-up and put-down time, the drug location coordinates corresponding to that time are located using a spatiotemporal matching algorithm. Furthermore, the starting drug location, ending drug location, and pick-up and put-down time are associated and fused with the drug identifier to construct drug retrieval information that includes the retrieval path, time consumption, and drug attributes. This information represents the complete spatiotemporal characteristics of a single dispensing action and is used to subsequently calculate the edge weights in the physical time consumption graph.

[0038] Furthermore, the step of determining the business association graph based on the drug co-occurrence probability and the drug retrieval information includes: The co-occurrence frequency between each pair of drugs is determined based on the drug co-occurrence probability. The co-occurrence frequencies are weighted according to the drug capture information to obtain weighted co-occurrence frequencies; The business association graph is constructed based on the weighted co-occurrence frequency.

[0039] In this embodiment, it should be noted that the co-occurrence probability does not directly represent the pharmacist's fetching path. It is necessary to determine whether the pharmacist executed the corresponding path based on the aforementioned drug fetching information. For example, for a prescription, which includes: type A drug, type B drug, and type C drug. The acquisition method can be in different orders, such as: in the order of type A drug, type B drug, and type C drug. In this case, there is no actual fetching association between type A drug and type C drug. Therefore, in this embodiment, it is necessary to generate corresponding weighted values ​​based on the movement probabilities of each position in the drug fetching information, and calculate the weighted co-occurrence frequency based on the weighted values ​​and the co-occurrence frequency. And construct the business association graph based on the weighted co-occurrence frequency.

[0040] In this embodiment, the system constructs a business association graph with drugs as vertices and weighted co-occurrence frequencies as directed edge weights. The graph topology integrates medical prescription compatibility habits and real crawling behavior characteristics. The edge weight values ​​represent the business closeness and allocation coordination needs between drugs, providing data-driven association metrics for subsequent drug placement clustering algorithms, and realizing the transformation from behavioral data to layout optimization knowledge.

[0041] Furthermore, based on any of the above embodiments, a fourth embodiment of the pharmacy management method based on IoT sensing and behavior analysis of the present invention is proposed. In this embodiment, the step of determining the physical time consumption map based on the drug grabbing information and the drug location information includes: The number of times each pair of drug positions is counted based on the drug grabbing information. Calculate the actual movement time between each pair of drug sites based on the movement trajectory data; Calculate the average movement time between each pair of drug positions based on the number of grabs and the actual movement time. The physical time consumption map is constructed based on the average movement time. The physical time consumption diagram is an asymmetric diagram, where the time taken from the first drug position to the second drug position is not equal to the time taken from the second drug position to the first drug position.

[0042] In this embodiment, it should be noted that due to the limitations of different sensor accuracy, the movement time and drug retrieval time cannot be directly determined under certain conditions. Therefore, optionally, when the equipment accuracy is not high, the actual movement time can include the time for grabbing the drug. For example, the time from the change in the weight of type A drug to the change in the weight of type B drug can be used as the actual movement time; alternatively, under more accurate conditions, the time between the stop point of the change in the weight of type A drug and the start point of the change in the weight of type B drug can be used as the actual movement time. In this embodiment, it is not required that the actual movement time be in the most accurate state. Further, the starting and ending drug positions in the drug grabbing information are traversed, and frequency statistics are performed on each pair of ordered drug position combinations to calculate the number of grabbing actions between a specific starting and ending drug position. This statistic quantifies the intensity of passage demand between different drug positions in the actual dispensing operation, identifies high-frequency passage paths and hotspot connections, and provides a reliable sample base for subsequent calculation of average movement time, ensuring that the edge weights of the physical time graph reflect the real business load rather than random events. Optionally, the number of times each pair of drug positions is grasped is used as the denominator, and the corresponding actual movement time is accumulated as the numerator. A weighted average calculation is then performed to obtain the average movement time between each pair of drug positions. This average value eliminates the noise effect of a single abnormally fast or slow passage and robustly represents the typical passage time between drug positions in a specific direction.

[0043] In addition, it should be noted that the physical time consumption diagram mentioned here is an asymmetric diagram, corresponding to two drug positions. The time consumption from the first drug position to the second drug position is not necessarily equal to the time consumption from the second drug position to the first drug position. They are two independent time consumption values ​​and are not required to be equal.

[0044] In this embodiment, the number of times each pair of drug positions is grasped is counted based on the drug grasping information, the actual movement time between each pair of drug positions is calculated based on the movement trajectory data, the average movement time between each pair of drug positions is calculated based on the number of grasps and the actual movement time, and the physical time consumption map is constructed based on the average movement time, thereby improving the accuracy of the data.

[0045] Furthermore, based on any of the above embodiments, a fifth embodiment of the pharmacy management method based on IoT sensing and behavior analysis of the present invention is proposed. In this embodiment, the step of generating a pharmacy management strategy according to the business association graph and the physical time consumption graph includes: Determine high-frequency drug association pairs based on the aforementioned business association diagram; The physical movement cost between each pair of drug sites is determined based on the physical time consumption diagram. Calculate drug location associated misscheduling based on the high-frequency drug association pairs and the physical movement cost; The drug location adjustment strategy is determined based on the drug location-related misalignment. The drug retrieval optimization strategy is determined based on the business association graph, the physical time consumption graph, and the current prescription information.

[0046] In this embodiment, it needs to be explained that drug location association mismatch is a quantitative indicator that measures the degree of matching between business needs and physical space configuration. Its calculation method is as follows: for drug association pairs with higher edge weights in the business association graph, the actual movement time between their corresponding drug locations in the physical time consumption graph is retrieved, and the result is obtained by weighting the business association strength with the physical movement cost; specifically, the formula can be used: Drug location-related mis-scheduling = Service-related frequency × Physical movement time; The business association frequency here refers to the weight of the edges in the business association graph. Optionally, it can be the deviation between the normalized business association strength and the preset ideal proximity threshold. If the two drugs have extremely high business association but are physically far apart, the mis-scheduling rate is significantly high, indicating that the current layout fails to meet the high-frequency allocation requirements and urgently needs to be adjusted.

[0047] Furthermore, the step of acquiring sensing data within the pharmacy environment includes: The movement trajectory data is obtained by collecting the real-time location data of each pharmacist through radio frequency identification equipment; The weight sensing data is obtained by collecting weight change data corresponding to the medicine picking and placing actions through a weight sensing device. The video image data is obtained by collecting video stream data of the pharmacy operation area through video surveillance equipment.

[0048] In this embodiment, high-definition video surveillance equipment is deployed in the pharmacy's drug handling area. Computer vision algorithms are used to analyze the video data, identifying pharmacist hand gestures, drug packaging features, and the background environment of the drug placement area. This data serves as a verification layer for multimodal perception, cross-validating with RFID trajectory and weight sensing data to improve the accuracy of drug grasping and location information recognition, ensuring the reliability of data for subsequent graph construction and strategy generation.

[0049] Furthermore, this invention also proposes a pharmacy management device based on Internet of Things (IoT) sensing and behavior analysis, the pharmacy management device comprising: The acquisition module is used to acquire perception data and pharmaceutical business data within the pharmacy environment. The perception data includes: movement trajectory data of each pharmacist, weight sensing data corresponding to drug handling actions, and video image data. The analysis module is used to generate a business association graph and a physical time consumption graph based on the perceived data and pharmaceutical business data. The business association graph is a directed graph with vertices representing drugs and edges representing the probability of consecutive operation of two drugs. The physical time consumption graph is a directed graph with vertices representing drug positions and edges representing the corresponding usage time of two drug positions. The management module is used to generate pharmacy management strategies based on the business relationship graph and the physical time consumption graph. The pharmacy management strategies include: drug location adjustment strategies and drug retrieval optimization strategies.

[0050] Furthermore, this invention also proposes a pharmacy management device based on Internet of Things (IoT) sensing and behavior analysis. The pharmacy management device based on IoT sensing and behavior analysis includes: a memory, a processor, and a pharmacy management program based on IoT sensing and behavior analysis stored in the memory and executable on the processor. The pharmacy management program based on IoT sensing and behavior analysis is configured to implement the steps of any of the above-described embodiments of the pharmacy management method based on IoT sensing and behavior analysis.

[0051] Furthermore, this invention also proposes a storage medium storing a pharmacy management program based on Internet of Things (IoT) sensing and behavior analysis. When the pharmacy management program based on IoT sensing and behavior analysis is executed by a processor, it implements the steps of any of the above-described embodiments of the pharmacy management method based on IoT sensing and behavior analysis.

[0052] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0053] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0054] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0055] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A pharmacy management method based on Internet of Things (IoT) sensing and behavior analysis, characterized in that, The pharmacy management method based on IoT sensing and behavior analysis includes the following steps: Acquire sensor data and pharmaceutical business data within the pharmacy environment. The sensor data includes: movement trajectory data of each pharmacist, weight sensing data corresponding to drug handling actions, and video image data. Based on the perceived data and pharmaceutical business data, a business association graph and a physical time consumption graph are generated. The business association graph is a directed graph, with vertices representing drugs and edges representing the probability of consecutive operation of two drugs. The physical time consumption graph is a directed graph, with vertices representing drug positions and edges representing the corresponding usage time of two drug positions. A pharmacy management strategy is generated based on the business relationship diagram and the physical time consumption diagram. The pharmacy management strategy includes: a drug location adjustment strategy and a drug retrieval optimization strategy.

2. The pharmacy management method based on IoT sensing and behavior analysis as described in claim 1, characterized in that, The pharmaceutical business data includes: prescription information data. The step of generating a business association diagram and a physical time consumption diagram based on the perception data and pharmaceutical business data includes: Statistically analyze the drug co-occurrence information corresponding to each prescription to obtain the drug co-occurrence probability; Based on the perceived data, drug grasping information and drug location information are determined; The business association graph is determined based on the drug co-occurrence probability and the drug retrieval information; The physical time consumption diagram is determined based on the drug capture information and the drug location information.

3. The pharmacy management method based on IoT sensing and behavior analysis as described in claim 2, characterized in that, The step of determining drug retrieval information and drug location information based on the sensing data includes: The drug identifier and the time of each drug retrieval / placement action are determined based on the weight sensing data. The starting and ending drug positions for each drug grabbing action are determined based on the movement trajectory data and the grabbing and placing times. The drug retrieval information is determined based on the starting drug position, the ending drug position, and the retrieval / placement time. The target drug location for each drug is determined based on the video image data, thus obtaining the drug location information.

4. The pharmacy management method based on IoT sensing and behavior analysis as described in claim 2, characterized in that, The step of determining the business association graph based on the drug co-occurrence probability and the drug retrieval information includes: The co-occurrence frequency between each pair of drugs is determined based on the drug co-occurrence probability. The co-occurrence frequencies are weighted according to the drug capture information to obtain weighted co-occurrence frequencies; The business association graph is constructed based on the weighted co-occurrence frequency.

5. The pharmacy management method based on IoT sensing and behavior analysis as described in claim 2, characterized in that, The step of determining the physical time-consuming graph based on the drug capture information and the drug location information includes: The number of times each pair of drug positions is counted based on the drug grabbing information. Calculate the actual movement time between each pair of drug sites based on the movement trajectory data; Calculate the average movement time between each pair of drug positions based on the number of grabs and the actual movement time. The physical time consumption map is constructed based on the average movement time.

6. The pharmacy management method based on IoT sensing and behavior analysis as described in claim 1, characterized in that, The step of generating a pharmacy management strategy based on the business relationship diagram and the physical time consumption diagram includes: Determine high-frequency drug association pairs based on the aforementioned business association diagram; The physical movement cost between each pair of drug sites is determined based on the physical time consumption diagram. Calculate drug location associated misscheduling based on the high-frequency drug association pairs and the physical movement cost; The drug location adjustment strategy is determined based on the drug location-related misalignment. The drug retrieval optimization strategy is determined based on the business association graph, the physical time consumption graph, and the current prescription information.

7. The pharmacy management method based on IoT sensing and behavior analysis as described in any one of claims 1 to 6, characterized in that, The steps for acquiring sensing data within the pharmacy environment include: The movement trajectory data is obtained by collecting the real-time location data of each pharmacist through radio frequency identification equipment; The weight sensing data is obtained by collecting weight change data corresponding to the medicine picking and placing actions through a weight sensing device. The video image data is obtained by collecting video stream data of the pharmacy operation area through video surveillance equipment.

8. A pharmacy management device based on Internet of Things (IoT) sensing and behavior analysis, characterized in that, The pharmacy management device based on IoT sensing and behavior analysis includes: The acquisition module is used to acquire perception data and pharmaceutical business data within the pharmacy environment. The perception data includes: movement trajectory data of each pharmacist, weight sensing data corresponding to drug handling actions, and video image data. The analysis module is used to generate a business association graph and a physical time consumption graph based on the perceived data and pharmaceutical business data. The business association graph is a directed graph with vertices representing drugs and edges representing the probability of consecutive operation of two drugs. The physical time consumption graph is a directed graph with vertices representing drug positions and edges representing the corresponding usage time of two drug positions. The management module is used to generate pharmacy management strategies based on the business relationship graph and the physical time consumption graph. The pharmacy management strategies include: drug location adjustment strategies and drug retrieval optimization strategies.

9. A pharmacy management device based on Internet of Things (IoT) sensing and behavior analysis, characterized in that, The pharmacy management device based on IoT sensing and behavior analysis includes: a memory, a processor, and a pharmacy management program based on IoT sensing and behavior analysis stored in the memory and executable on the processor. The pharmacy management program based on IoT sensing and behavior analysis is configured to implement the steps of the pharmacy management method based on IoT sensing and behavior analysis as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores a pharmacy management program based on Internet of Things (IoT) sensing and behavior analysis. When the pharmacy management program based on IoT sensing and behavior analysis is executed by the processor, it implements the steps of the pharmacy management method based on IoT sensing and behavior analysis as described in any one of claims 1 to 7.

Images