A medicine dispensing, transplanting and managing method, system, device and storage medium

Abstract

The application relates to the medical technical field, in particular to a medicine dispensing and transplanting management method, system and device and a storage medium, the method comprises the following steps: in response to a dispensing task demand, generating medicine attribute information to be prepared; according to the medicine attribute information to be prepared, determining position information of the medicine to be prepared; based on the medicine attribute information to be prepared and the position information, generating a medicine grabbing scheme, the medicine grabbing scheme is used for placing the medicine to be prepared on a preparation area; when an end message is acquired, generating a medicine preparation instruction, performing a medicine preparation operation based on the medicine preparation instruction, obtaining a medicine preparation result, and generating a medicine conveying instruction according to the medicine preparation result; and based on the medicine conveying instruction, placing the prepared medicine on a preset placement area. The application has the effect of improving the operation accuracy of the whole process of medicine dispensing and transplanting.

Description

Technical Field

[0001] This application relates to the field of medical technology, and in particular to a method, system, device and storage medium for drug dispensing and transfer management. Background Technology

[0002] Currently, in precision-driven scenarios such as modern pharmaceutical manufacturing, bioengineering, and the preparation of high-value-added chemicals, automated dispensing and transfer of pharmaceuticals or key materials are core components ensuring precise control, high efficiency, stability, compliance with aseptic or cleanroom standards, and full traceability of the production process. This technology typically relies on automated equipment and intelligent control systems to precisely execute a series of complex and interconnected operations, from material identification, spatial positioning, secure grasping, transfer and conveying between different workstations, necessary physical or chemical processing such as mixing and formulation, to final precise placement.

[0003] Existing drug dispensing and transfer management systems typically use preset fixed gripping paths and forces to pick up and place medicine bottles. A robotic arm handles the drug transport, and the dispensing process is then completed manually or by a separate dispensing module. For drug identification, barcodes or fixed brackets are usually used for positioning. Regarding dispensing control, most systems lack the ability to dynamically generate mixing parameters based on drug properties. During placement, the gripper release is often an open-loop control, which can easily cause container displacement or unstable placement, affecting overall operational safety and consistency. Therefore, there is room for improvement. Summary of the Invention

[0004] To improve the operational accuracy of the entire process of drug preparation and transplantation, this application provides a method, system, equipment, and storage medium for drug preparation and transplantation management.

[0005] The above-mentioned objective of this application is achieved through the following technical solution: A method for managing drug preparation and transplanting, the method comprising: In response to the requirements of the dispensing task, generate the attribute information of the drug to be dispensed; Based on the attribute information of the drug to be prepared, the location information of the drug to be prepared is determined. Based on the attribute information of the drug to be prepared and the location information, a drug grasping plan is generated. The drug grasping plan is used to grasp the drug to be prepared and place it on the preparation area. When the placement end message is received, a drug preparation instruction is generated, a drug preparation operation is performed based on the drug preparation instruction, a drug preparation result is obtained, and a drug delivery instruction is generated based on the drug preparation result. Based on the drug delivery instruction, the prepared drug is placed in the preset placement area.

[0006] By adopting the above technical solution, and by responding to the needs of the dispensing task and generating the attribute information of the drugs to be dispensed, the original task can be transformed into standardized and accurate drug data, thereby providing a clear and unified operational basis. By determining the location information of the drugs to be dispensed based on the drug attribute information and generating a drug retrieval plan based on this, the automated search, positioning, and retrieval path planning of drugs can be realized, thereby significantly improving the efficiency and accuracy of drug dispensing. When the end message of drug placement in the dispensing area is obtained, a drug dispensing instruction is generated to perform the dispensing operation, and a drug delivery instruction is generated based on the drug dispensing result. This enables automated and precise control of the dispensing process and process connection based on quality feedback, thereby ensuring the uniformity and reliability of drug dispensing quality and optimizing the overall operation rhythm. Furthermore, by accurately placing the dispensed drugs in the preset placement area based on the drug delivery instruction, the automated and standardized placement of the dispensed drugs can be completed, thereby facilitating subsequent traceability, inspection, or distribution, and improving the orderliness and management level of drug circulation.

[0007] In a preferred embodiment, this application can be further configured such that: determining the location information of the drug to be prepared based on the attribute information of the drug to be prepared specifically includes: Based on the attribute information of the drug to be prepared, obtain the storage area information of the drug to be prepared; Obtain the image of the storage area corresponding to the storage area information, and determine whether the medicine to be prepared is in the storage area using an image recognition algorithm; If the drug to be prepared is stored in the storage area, the coordinate position information of the drug to be prepared in the three-dimensional spatial coordinate system is calculated by the pose estimation algorithm, and the coordinate position information is used as the position information of the drug to be prepared.

[0008] By adopting the above technical solution, the storage area information of the drug to be prepared is first obtained based on the attribute information of the drug to be prepared, which can quickly narrow down the search range of the target drug and improve the initial efficiency of positioning. By obtaining the image corresponding to the storage area and using the image recognition algorithm to determine whether the drug actually exists in the area, the presence of the drug can be objectively confirmed by machine vision, thereby avoiding invalid operations on empty storage locations or incorrect targets and improving the accuracy of positioning. Furthermore, if the drug exists, the pose estimation algorithm is used to further calculate its precise position information in the three-dimensional spatial coordinate system, which can obtain the three-dimensional coordinates and posture of the drug required for robot operation. This provides key spatial data support for the subsequent precise and collision-free grasping of the robotic arm and significantly improves the success rate of grasping.

[0009] In a preferred embodiment, this application can be further configured such that: the step of generating a drug retrieval plan based on the attribute information of the drug to be prepared and the location information specifically includes: Based on the location information of the medicine to be prepared, a gripper grasping path and obstacle avoidance strategy are generated through a preset path planning algorithm. Based on the attribute information of the drug to be prepared, the target grasping parameters are determined, and the drug grasping plan is generated according to the gripper grasping path and obstacle avoidance strategy and the target grasping parameters.

[0010] By adopting the above technical solution, and using the precise location information of the drug to be prepared and a preset path planning algorithm, the robot gripper's grasping path and corresponding obstacle avoidance strategy are generated. This allows for the planning of a safe and efficient motion trajectory, ensuring that the robotic arm can move flexibly in complex environments and actively avoid obstacles. This significantly improves the safety, stability, and efficiency of robot operation, and reduces the risk of collisions. Furthermore, based on the specific attribute information of the drug to be prepared, the core parameters required for target grasping are determined. Combined with the planned grasping path and obstacle avoidance strategy, the final drug grasping scheme is generated. The grasping force, speed, and posture can be customized according to the characteristics of the drug, forming a refined and complete grasping operation instruction. This ensures the stability and reliability of the grasping action and the effective protection of the drug, greatly improving the adaptability and success rate of grasping different types of drugs.

[0011] In a preferred embodiment, this application can be further configured as follows: when a placement end message is received, a drug preparation instruction is generated, and a drug preparation operation is performed based on the drug preparation instruction to obtain a drug preparation result, specifically including: When the placement end message is received, the drug number, preparation dosage and ratio parameters are obtained from the drug attribute information to be prepared; The drug number, the preparation dosage, and the ratio parameters are input into the mixing parameter calculation model to obtain the mixing parameters, and the drug preparation instruction is generated based on the mixing parameters. Perform drug preparation operations according to the drug preparation instructions, record the drug preparation process parameters, compare the drug preparation process parameters with the preset target preparation parameters, and generate the corresponding drug preparation results.

[0012] By adopting the above technical solution, after the medicine is accurately placed in the preparation area, the medicine number, target preparation dosage, and key ratio parameters are extracted from the attribute information of the medicine to be prepared. This ensures the accuracy of all core data before the preparation operation. These parameters are then input into a preset mixing parameter calculation model to obtain optimized mixing parameters, and specific medicine preparation instructions are generated accordingly. The mixing parameter calculation model can improve the scientific nature and consistency of the preparation process, increase preparation efficiency, and improve the stability of medicine quality. By executing the preparation operation according to the medicine preparation instructions, the actual process parameters are recorded simultaneously, and the differences between these parameters and the preset target values ​​are compared to generate the medicine preparation results. This enables quantitative monitoring and automatic quality assessment of the preparation process, thereby ensuring the accurate achievement of the preparation results and providing data support for quality traceability and process improvement.

[0013] In a preferred embodiment, this application may be further configured such that, prior to the step of inputting the drug number, the prepared dosage, and the ratio parameter into the mixing parameter calculation model, the drug preparation and transplanting management method further includes: Obtain the formulation data of each drug and the historical drug mixing quality assessment results, and obtain the historical mixing operation record data from the historical drug mixing quality assessment results; Based on the drug formulation data, the drug attribute information to be prepared and the actual applied mixing process parameters in the historical mixing operation record data are marked accordingly to obtain historical working condition model training data. The historical drug mixture quality assessment results are matched and associated with the training data of each historical operating condition model to obtain the model training dataset; The initial regression model is trained using supervised learning based on the model training dataset. When the number of iterations of the initial regression model exceeds the preset number of iterations, the mixing parameter calculation model is output.

[0014] By adopting the above technical solution, and by acquiring historical formula data, historical drug mixing quality assessment results, and corresponding historical mixing operation records of various drugs, it is possible to systematically collect historical experience and objective effectiveness data related to drug mixing processes. By matching and associating historical drug mixing quality assessment results with each set of historical operating condition data, it is possible to provide training samples with clear effect labels for supervised learning, thereby ensuring the goal orientation of model training and the effectiveness of final prediction. By using this model training dataset to conduct supervised learning training on the initial regression model, the final output is a mixing parameter calculation model that can guide practice. It is possible to use machine learning to extract patterns from historical experience and realize the output of mixing parameters, thereby improving the formulation efficiency of drug mixing processes and the stability and predictability of finished product quality.

[0015] In a preferred embodiment, this application can be further configured such that: the generation of a drug delivery instruction based on the drug preparation result specifically includes: Based on the drug preparation results, obtain the spatial position parameters of the preset placement area in the three-dimensional spatial coordinate system; The drug parameters of the prepared drug are obtained, including container type, mass data and size information, and the end motion path of the container loaded with the prepared drug from the current height to the spatial position parameter is calculated based on the drug parameters. Based on the end motion path, the required release posture in the deceleration phase of the end motion path is determined by the falling inertia. The required release posture includes the end posture angle, the eccentric displacement, and the opening range of the gripper. Based on the end-effector motion path and the required release posture, a drug delivery command is generated.

[0016] By adopting the above technical solution, the spatial position parameters of the preset placement area in the three-dimensional coordinate system are accurately obtained after the medicine is prepared and qualified. This provides a clear and calibrated three-dimensional target point. By obtaining the actual physical parameters of the prepared medicine, the optimized end-effector motion path for the medicine container to move from the current position to the target spatial position is calculated. This improves the adaptability and safety of the delivery path and effectively avoids instability or collisions during movement. Based on the planned end-effector motion path and considering factors such as falling inertia, the precise release posture required for the robot gripper to release the medicine in the deceleration phase of the end-effector motion path is precisely determined. Through pre-compensation and fine adjustment, the accuracy of the medicine placement point and the stability of the posture can be significantly improved. By integrating the end-effector motion path and the precise required release posture, detailed medicine delivery instructions are generated, ensuring that the prepared medicine is delivered to the designated location accurately, gently and efficiently, thus improving the quality of operation.

[0017] In a preferred embodiment, this application can be further configured such that: the step of placing the prepared medicine on a preset placement area based on the medicine delivery instruction specifically includes: According to the drug delivery instruction, the gripper is controlled to grasp the container, and the robotic arm is driven to move along the end-effector path to the preset placement area. When entering the deceleration phase of the end motion path, the end state of the gripper is adjusted according to the required release posture, and a release operation is performed. When the container is detected to be stably in contact with the preset placement area, and the end of the gripper is within the release posture tolerance range, the gripper is released and retracted to complete the placement operation of the medicine.

[0018] By adopting the above technical solution, the gripper is controlled to stably hold the medicine container according to the medicine delivery command, and the robotic arm is driven to move strictly along the planned end motion path to the preset placement area. This enables high-precision trajectory tracking and attitude maintenance of the medicine container during the delivery process. When the robotic arm enters the deceleration section of the end motion path, the end state of the gripper is dynamically adjusted according to the preset required release posture parameters, and the release operation is performed at the optimal time. This enables precise alignment of the container posture before placement and accurate control of the release timing, thereby significantly improving the success rate of the placement action and the gentleness of the operation, and reducing the impact on the medicine. After the release operation, the gripper detects in real time whether the medicine container has stably contacted the surface of the preset placement area, and at the same time confirms that the end posture of the gripper is within the preset tolerance range. Only under these two conditions is the gripper instructed to fully release and safely retract, avoiding any form of interference or secondary collision to the successfully placed medicine container or other surrounding equipment or objects during the retraction process, thus completing the operation.

[0019] The second objective of this invention is achieved through the following technical solution: A drug dispensing and transplanting management system, the drug dispensing and transplanting management system comprising: The drug attribute information generation module is used to generate the attribute information of the drug to be prepared in response to the requirements of the dispensing task; The drug positioning and grasping scheme generation module is used to determine the location information of the drug to be prepared based on the attribute information of the drug to be prepared, and generate a drug grasping scheme based on the attribute information of the drug to be prepared and the location information. The drug grasping scheme is used to grasp the drug to be prepared and place it on the preparation area. The drug preparation and delivery instruction generation module is used to generate a drug preparation instruction when a placement end message is received, perform drug preparation operations based on the drug preparation instruction, obtain drug preparation results, and generate a drug delivery instruction based on the drug preparation results. The drug placement execution module is used to place the prepared drug in a preset placement area based on the drug delivery instruction.

[0020] By adopting the above technical solution, and by responding to the needs of the dispensing task and generating the attribute information of the drugs to be dispensed, the original task can be transformed into standardized and accurate drug data, thereby providing a clear and unified operational basis. By determining the location information of the drugs to be dispensed based on the drug attribute information and generating a drug retrieval plan based on this, the automated search, positioning, and retrieval path planning of drugs can be realized, thereby significantly improving the efficiency and accuracy of drug dispensing. When the end message of drug placement in the dispensing area is obtained, a drug dispensing instruction is generated to perform the dispensing operation, and a drug delivery instruction is generated based on the drug dispensing result. This enables automated and precise control of the dispensing process and process connection based on quality feedback, thereby ensuring the uniformity and reliability of drug dispensing quality and optimizing the overall operation rhythm. Furthermore, by accurately placing the dispensed drugs in the preset placement area based on the drug delivery instruction, the automated and standardized placement of the dispensed drugs can be completed, thereby facilitating subsequent traceability, inspection, or distribution, and improving the orderliness and management level of drug circulation.

[0021] The above-mentioned objective three of this application is achieved through the following technical solution: A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described drug dispensing and transplanting management method.

[0022] The fourth objective of this application is achieved through the following technical solution: A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described drug dispensing and transplanting management method.

[0023] In summary, this application includes at least one of the following beneficial technical effects: 1. By adopting the above technical solution, and by responding to the needs of the dispensing task and generating the attribute information of the drugs to be dispensed, the original task can be transformed into standardized and accurate drug data, thereby providing a clear and unified operational basis. By determining the location information of the drugs to be dispensed based on the drug attribute information and generating a drug grasping plan based on this, the automated search, positioning, and grasping path planning of drugs can be realized, thereby significantly improving the efficiency and accuracy of drug dispensing. When the end message of placing the drug in the dispensing area is obtained, a drug dispensing instruction is generated to perform the dispensing operation, and a drug delivery instruction is generated based on the drug dispensing result. This enables automated and precise control of the dispensing process and process connection based on quality feedback, thereby ensuring the uniformity and reliability of drug dispensing quality and optimizing the overall operation rhythm. Furthermore, by accurately placing the dispensed drugs in the preset placement area based on the drug delivery instruction, the automated and standardized placement of the dispensed drugs can be completed, thereby facilitating subsequent traceability, inspection, or distribution, and improving the orderliness and management level of drug circulation. 2. By acquiring historical formula data, historical drug mixing quality assessment results, and corresponding historical mixing operation records for various drugs, we can systematically collect historical experience and objective performance data related to drug mixing processes. By matching and associating historical drug mixing quality assessment results with each set of historical operating condition data, we can provide training samples with clear effect labels for supervised learning, thereby ensuring the goal orientation of model training and the effectiveness of final prediction. By using this model training dataset to conduct supervised learning training on the initial regression model, we can finally output a mixing parameter calculation model that can guide practice. We can use machine learning to extract patterns from historical experience and realize the output of mixing parameters, thereby improving the formulation efficiency of drug mixing processes and the stability and predictability of finished product quality. Attached Figure Description

[0024] Figure 1 This is a flowchart illustrating the implementation of a drug dispensing and transplanting management method in one embodiment of this application; Figure 2 This is a flowchart illustrating the implementation of step S20 in a drug preparation and transplantation management method according to an embodiment of this application. Figure 3 This is another implementation flowchart of step S20 in the drug dispensing and transplanting management method in one embodiment of this application; Figure 4 This is a flowchart illustrating the implementation of step S30 in a drug preparation and transplantation management method according to an embodiment of this application. Figure 5 This is another implementation flowchart of the drug dispensing and transplanting management method in one embodiment of this application; Figure 6 This is another implementation flowchart of step S30 in the drug dispensing and transplanting management method in one embodiment of this application; Figure 7 This is a flowchart illustrating the implementation of step S40 in a drug preparation and transplantation management method according to an embodiment of this application. Figure 8 This is a schematic diagram of a drug dispensing and transplanting management system according to one embodiment of this application; Figure 9 This is a schematic diagram of the internal structure of a computer device according to an embodiment of this application. Detailed Implementation

[0025] The following embodiments will help those skilled in the art to further understand the function of this application, but do not limit this application in any way. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of this application. These all fall within the protection scope of this application.

[0026] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, circuits, and methods are omitted so as not to obscure the description of this application with unnecessary detail.

[0027] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0028] The present application will be further described in detail below with reference to the accompanying drawings.

[0029] In one embodiment, such as Figure 1 As shown, this application discloses a method for drug preparation and transplanting management, which specifically includes the following steps: S10: In response to the requirements of the drug dispensing task, generate the attribute information of the drug to be dispensed.

[0030] Specifically, when a dispensing instruction or a manually created dispensing task is received, such as a dispensing request containing patient prescription information received from the Hospital Information System (HIS), or a research dispensing requirement manually entered into the laboratory system, the core drug-related elements are obtained by parsing the task requirement, such as the drug's generic name, brand name, specifications, production batch number, required dosage, concentration requirements, dosage form, and specific preparation precautions. This obtained data is then used to form a structured data record, namely the attribute information of the drug to be dispensed, which uniquely identifies and describes in detail the various characteristics of the drug required for this dispensing task.

[0031] S20: Based on the attribute information of the drug to be prepared, determine the location information of the drug to be prepared. Based on the attribute information and location information of the drug to be prepared, generate a drug grabbing plan. The drug grabbing plan is used to grab the drug to be prepared and place it on the preparation area.

[0032] Specifically, firstly, based on the generated attribute information of the drug to be prepared, such as the drug's unique identification code or name and specifications, the storage location of the drug is queried in the preset drug database. After obtaining the location information, the physical characteristics of the drug, such as size, weight, and fragility, which can be obtained from the attribute information of the drug to be prepared, as well as the surrounding environment information of the location, are combined with the built-in motion planning algorithm to calculate one or more feasible robot arm motion trajectories, and determine the appropriate gripper type, gripping force, and posture. All of this information is combined to form a complete drug grasping scheme. This drug grasping scheme ensures that the robot can accurately and safely retrieve the target drug from the storage location and transfer it to the designated preparation workbench or container interface.

[0033] S30: When the placement end message is received, a drug preparation instruction is generated, a drug preparation operation is performed based on the drug preparation instruction, a drug preparation result is obtained, and a drug delivery instruction is generated based on the drug preparation result.

[0034] Specifically, once it is confirmed that the drug has been successfully grasped and placed in the preparation area—for example, by a sensor detecting that the drug has stabilized in a predetermined position on the preparation table, or by the robotic arm indicating that the placement action has been completed and releasing the gripper—a placement completion message is generated. Upon receiving this placement completion message, the drug preparation process is triggered, generating drug preparation instructions. Drug preparation is then performed according to the aforementioned preparation task requirements, such as detailed parameters and sequence of steps involving weighing, dissolving, diluting, and mixing. These instructions are sent to the corresponding preparation execution units, such as automatic weighing modules, liquid handling workstations, and mixers, to perform the actual drug preparation operation. During or after the preparation process, key data from the preparation process and the characteristics of the final product are collected or analyzed to form drug preparation results, such as actual weighing values, mixing uniformity test reports, and concentration titration results. Based on the degree of conformity of these results with preset standards, it is determined whether the next step is to release the drug as qualified and generate a drug delivery instruction, or to rework or discard it.

[0035] S40: Based on the drug delivery instruction, place the prepared drug in the preset placement area.

[0036] Specifically, the robot control unit receives the generated drug delivery instruction, which defines in detail the movement trajectory of the robotic arm and the operation sequence of the gripper. It then drives the motors of each joint of the robotic arm, causing its end effector, i.e., the gripper, to grasp the prepared drug container and move it from the preparation area to the preset placement area, such as a designated point on the workbench of the finished product storage area or the inspection area, strictly following the path planned in the instruction. The entire movement process is monitored in real time to ensure smooth and accurate path execution. The ultimate goal is to make stable contact between the bottom of the drug container or the designated support surface and the surface of the preset placement area, thus completing the placement of the drug.

[0037] In one embodiment, such as Figure 2 As shown, in step S20, the location information of the drug to be prepared is determined based on the attribute information of the drug to be prepared, specifically including: S21: Based on the attribute information of the drug to be prepared, obtain the storage area information of the drug to be prepared.

[0038] Specifically, by utilizing key information in the generated drug attribute information, such as drug ID, drug name, or batch number, the system accesses the drug inventory location database or warehouse management information table, searches for entries matching the drug attribute in the database or information table, and thus reads the logical or physical area identifier where the drug is currently allocated and stored. For example, shelf number A, layer 03, a specific pallet number inside refrigerated cabinet 2, or a specific storage unit code in an automated warehouse. This information is the storage area information of the drug to be prepared.

[0039] S22: Obtain the image of the storage area corresponding to the storage area information, and determine whether the medicine to be prepared is in the storage area through an image recognition algorithm.

[0040] Specifically, based on the storage area information obtained above, such as shelf A, layer 03, the image acquisition device corresponding to that area is controlled, such as a camera fixedly installed in that shelf area or a vision sensor carried by a mobile robot, to capture or retrieve real-time high-definition image data of that storage area. Then, the image recognition module is called. This module has learned the features of various drug packaging and labels, and analyzes and processes the acquired storage area images. For example, through template matching, deep learning object detection algorithms such as YOLO and SSD, it searches for targets in the image that match the attribute information of the drug to be prepared, such as the appearance and packaging features of the drug, and outputs the judgment result, thereby confirming whether the target drug exists in the currently captured storage area.

[0041] S23: If the drug to be prepared is stored in the storage area, the coordinate position information of the drug to be prepared in the three-dimensional spatial coordinate system is calculated by the pose estimation algorithm, and the coordinate position information is used as the position information of the drug to be prepared.

[0042] Specifically, after the image recognition algorithm confirms that the drug to be prepared exists in the image of the storage area and initially locates its region on the two-dimensional image, for example by marking it with a bounding box, the pose estimation algorithm, such as the PnP algorithm based on binocular vision, is further used to analyze the pixel coordinates, size and possible depth information of the drug in the image. Combined with the intrinsic and extrinsic parameters of the camera and the transformation relationship between the pre-calibrated robot coordinate system and the camera coordinate system, the precise xyz coordinates and attitude information such as rotation angle of the drug in the three-dimensional Cartesian coordinate system used in the robot's workspace are calculated. The three-dimensional coordinates and attitude information together constitute the precise position information of the drug to be prepared.

[0043] In one embodiment, such as Figure 3 As shown, in step S20, a drug retrieval plan is generated based on the attribute information and location information of the drug to be prepared, specifically including: S24: Based on the location information of the medicine to be prepared, generate the gripper grasping path and obstacle avoidance strategy through a preset path planning algorithm.

[0044] Specifically, the precise coordinates of the drug to be prepared in three-dimensional space are used as the target point. Simultaneously, the position and orientation of the robot's end effector (gripper) are acquired, and an environmental map is invoked. This map contains information about fixed obstacles such as shelves, walls, and other equipment. Using path planning algorithms, such as the RRT or PRM algorithm, and considering the kinematic and dynamic constraints of each robot joint, a collision-free or low-collision-risk continuous trajectory from the starting point to the target drug location is searched and calculated. This trajectory contains sequence data on how each joint of the robot should move. Simultaneously, obstacle avoidance logic is integrated into this path planning process. For example, a safe distance threshold is set. When dynamic or unmodeled obstacles are detected on the planned path or in real-time, the path can be dynamically adjusted or emergency strategies such as pausing or detouring can be triggered. These two parts together constitute the gripper's grasping path and obstacle avoidance strategy.

[0045] S25: Based on the attribute information of the drug to be prepared, determine the target grasping parameters, and generate a drug grasping plan according to the gripper grasping path, obstacle avoidance strategy and target grasping parameters.

[0046] Specifically, parameters directly related to the grasping operation are obtained from the generated drug attribute information, such as the weight of the drug, the packaging material (e.g., glass bottle, plastic bag, cardboard box) and dimensions, and the fragility of the drug. By calling a detailed mapping table between various descriptive attributes of the drug and specific robot grasping execution parameters, the target grasping parameters can be determined based on these parameters. For example, when the drug attributes indicate that the packaging material is a vial and the nominal weight is 20 grams, a specific gripper type code can be directly associated and output by looking up the table. If a two-finger parallel gripper is selected and the fragility level in the attribute information is marked as high, the maximum allowable grasping acceleration is adjusted to a lower value of 0.2 meters per square second, and the end-effector approach speed is set to 30 millimeters per second. Then, these target grasping parameters are integrated with the gripper grasping path and obstacle avoidance strategy generated above. For example, when approaching the medicine at the end of the path, fine grasping posture adjustment instructions and gripper opening and closing control instructions including force and speed are incorporated to ensure that the medicine can be picked up in the best way when it reaches the medicine position, thus forming a complete and executable medicine grasping scheme that includes a series of actions such as path navigation, environmental perception, precise alignment and gentle gripping.

[0047] In one embodiment, such as Figure 4 As shown, in step S30, when the placement end message is received, a drug preparation instruction is generated, and a drug preparation operation is performed based on the drug preparation instruction to obtain the drug preparation result, specifically including: S31: When the placement end message is received, obtain the drug number, preparation dosage and ratio parameters from the drug attribute information to be prepared.

[0048] Specifically, when a placement completion message indicating that the drug has been accurately placed on the preparation station is received, such as when the end sensor of the robotic arm confirms that the drug has been removed from the fixture and stabilized on the preparation table, the system immediately accesses the attribute information of the drug to be prepared, which stores detailed information about this preparation task. From this attribute information, key data items for subsequent mixing operations are extracted, including the drug number that uniquely identifies the drug, the precise target dose required for this preparation task, such as how many milligrams or milliliters, and the ratio that should be followed between the components when multiple components are mixed, i.e., the mixing parameters, such as mixing component A and component B in a 2:1 mass ratio or volume ratio.

[0049] S32: Input the drug number, preparation dosage and ratio parameters into the mixing parameter calculation model to obtain the mixing parameters, and generate the drug preparation instruction based on the mixing parameters.

[0050] Specifically, the obtained drug number, dosage, and proportion parameters of each component are passed as input data to a pre-built and trained mixing parameter calculation model. This model contains a prediction function obtained through machine learning, which calculates a set of optimal or recommended mixing process parameters based on these inputs, such as the speed of the stirrer, the stirring time, and the temperature control during mixing. Based on these mixing parameters output by the model, combined with standard operating procedures, a detailed set of drug preparation instructions that can be directly executed by automated equipment is generated, such as starting the stirrer to 300 RPM, stirring continuously for 5 minutes, and maintaining the temperature at 25 degrees Celsius.

[0051] S33: Perform drug preparation operations according to the drug preparation instructions, record the drug preparation process parameters, compare the drug preparation process parameters with the preset target preparation parameters, and generate the corresponding drug preparation results.

[0052] Specifically, the generated drug preparation instructions are sent to the corresponding automated preparation equipment or prompt the human operator to execute the instructions. For example, the instructions might instruct a precision liquid processor to extract a specific volume of solvent, a powder dispenser to weigh a specific mass of drug powder, or a mixing device to stir at a specific speed and time. Throughout the preparation process, various sensors connected to the equipment, such as weighing sensors, flow meters, temperature sensors, speed sensors, and image sensors, collect and record the actual process parameters in real time. Examples include the actual mass of drug powder weighed as 50.2 mg, the actual volume of solvent added as 9.98 mL, and the maximum stirring speed as 295 RPM. After the preparation operation is completed, these recorded actual process parameters are compared and analyzed item by item with the target parameters set in the preparation instructions, such as a target mass of 50.0 mg, a target volume of 10.0 mL, and a target speed of 300 RPM. The deviations or compliance are calculated, and based on the preset quality tolerance standards, a deviation of less than ±2% is considered acceptable. A comprehensive evaluation is then performed to generate the final result of the drug preparation, indicating whether it is acceptable, has some parameters exceeding the standard, or is unacceptable.

[0053] In one embodiment, such as Figure 5 As shown, prior to step S32, the drug dispensing and transplanting management method further includes: S301: Obtain the formulation data of each drug and the historical drug mixing quality assessment results, and obtain the historical mixing operation record data from the historical drug mixing quality assessment results.

[0054] Specifically, the process begins by retrieving drug formulation data and historical drug mixing quality assessment results from a database containing at least drug manufacturing process specification documents and standard formulation data for different types or batches of drugs. These drug formulation data details the components of each drug, the precise dosage or proportion of each component, and the technical requirements for the final product. From the production or experimental batch records corresponding to these historical quality assessment results, detailed records of the actual process parameters and operating steps used during the mixing operation are screened and extracted. For example, the model of the agitator used, the speed setting, the mixing time, the order of adding materials, and the ambient temperature are recorded. These are the historical mixing operation record data.

[0055] S302: Based on the drug formulation data, the attribute information of the drugs to be prepared and the actual mixing process parameters applied in the historical mixing operation record data are marked accordingly to obtain the historical working condition model training data.

[0056] Specifically, the collected drug formulation data are used as a reference benchmark. Historical mixing operation records are processed one by one. For each historical record, the corresponding standard component information and dosage requirements are first found from the formulation data based on the drug name or number involved. This information constitutes the drug attribute information to be prepared in the historical record. The actual mixing process parameters recorded in the historical record, such as the specific model of the stirrer, impeller type, actual speed curve, mixing time, operating temperature, and feeding rate, are also extracted. The drug attributes and process parameters of these two parts are matched and labeled. For example, a record may be labeled as drug A, component X content 5 mg / mL, component Y content 10 mg / mL; stirrer model S1, speed 300 rpm, time 10 min, temperature 25°C. By performing this kind of processing on a large number of historical records, a historical working condition model training data containing multiple sets of drug attributes and corresponding mixing process parameters is formed for subsequent model training.

[0057] S303: Match and correlate the historical drug mixture quality assessment results with the model training data for each historical operating condition to obtain the model training dataset.

[0058] Specifically, for each established historical operating condition model training data, the actual quality assessment data obtained from the mixing operation is found and matched in the previously collected historical drug mixing quality assessment results using its original batch number, experiment number, or other unique identifier. For example, if the effective ingredient uniformity of this batch of drugs is RSD 0.5%, dissolution rate is 95%, or appearance score is excellent, this quality assessment result is used as the label or output result of the historical operating condition data for association. In other words, each combination of drug attributes and mixing process parameters corresponds to a known, actual mixing quality result. By collecting a large number of such operating condition-result pairing data, a complete model training dataset that can be used for supervised learning is formed.

[0059] S304: Supervised learning training of the initial regression model is performed based on the model training dataset. When the number of iterations of the initial regression model exceeds the preset number of iterations, the model for calculating the mixing parameters is output.

[0060] Specifically, a suitable initial regression model algorithm is selected, such as Support Vector Regression (SVR), Gradient Boosting Regression Tree (GBRT), neural network, or multiple linear regression. The generated model training dataset is used, with drug attributes and homogenization process parameters as feature inputs and historical drug mixing quality assessment results as the target output. A supervised learning training paradigm is adopted, and by continuously adjusting the parameters inside the model, such as weights and biases, the error between the model's predicted homogenization quality results and the actual quality assessment results in the dataset is minimized, such as mean squared error or mean absolute error. Alternatively, an upper limit on the number of iterations may be set during the training process, such as 1000 rounds of training or when the model's performance on the validation set does not improve significantly for several consecutive rounds. Once this preset number of iterations or other convergence conditions are reached, the training process is stopped, and the trained model at this point is saved. This final output model is the homogenization parameter calculation model.

[0061] In one embodiment, such as Figure 6 As shown, in step S30, based on the drug preparation results, a drug delivery instruction is generated, which specifically includes: S34: Based on the drug preparation results, obtain the spatial position parameters of the preset placement area in the three-dimensional spatial coordinate system.

[0062] Specifically, after the drug preparation is completed and the preparation result is obtained, if the result indicates that the drug meets the delivery requirements, the next delivery process will begin. At this time, the precise spatial location information of the target preset placement area will be read. This information is usually set during equipment initialization calibration or workflow design and is represented as one or more specific coordinate points (x, y, z) in the robot's working reference three-dimensional coordinate system, as well as possible attitude parameters (such as pitch, yaw, and roll angles when the container needs to be placed at a specific angle). For example, the finished product inspection table A1 position has coordinates (350.5, 210.0, 50.2) and an orientation of 0 degrees. These parameters together define the target position and state where the prepared drug should be placed.

[0063] S35: Obtain the drug parameters of the prepared drug, including container type, mass data and size information, and calculate the end motion path of the container loaded with the prepared drug from the current height to the spatial position parameter based on the drug parameters.

[0064] Specifically, the relevant physical parameters of the prepared medicine and its container are first retrieved or measured, such as the type of container (e.g., vial, ampoule, infusion bag), the total mass of the container and the medicine, and the precise external dimensions of the container (e.g., height, diameter, and mouth size). By combining these medicine parameters, especially the size and weight of the container, with the spatial position parameters of the preset placement area and the height and posture of the current medicine preparation station (i.e., the starting position and posture), robot kinematics and dynamics planning algorithms are used to calculate a trajectory for the robotic arm end effector (the gripper holding the container) to move smoothly and efficiently from the current position to the target spatial position. This trajectory takes into account avoiding collisions with the surrounding environment and may optimize the movement speed and acceleration to ensure the stability of the medicine container.

[0065] S36: Based on the end-effector path, determine the required release posture during the deceleration phase of the end-effector path by taking advantage of the falling inertia. The required release posture includes the end-effector attitude angle, the amount of eccentric displacement, and the opening range of the gripper hand.

[0066] Specifically, based on the pre-planned end-effector path from the current position to the target placement area, special attention is paid to the deceleration and final placement phases at the end of the path. Considering that the container will fall due to gravity when released, a precise release strategy calculation is required to ensure that the container lands accurately and stably at the designated point in the preset placement area, rather than shifting or tipping due to inertia. This includes analyzing the container's weight, shape, and expected release height difference, and using physical models or empirical data to calculate the ideal posture angle of the robotic arm's end effector gripper relative to the target placement point at the moment of release. For example, if the bottom of the container is uneven, it may need to be slightly tilted to ensure contact with the stable point first, as well as the possible small horizontal eccentric displacement, which is used to compensate for lateral drift during the release process. At the same time, the opening speed and final opening range of the gripper must be precisely set to ensure that the container can detach smoothly without interference. These parameters together constitute the precise release posture required for the deceleration phase.

[0067] S37: Generate drug delivery instructions based on the end-effector motion path and the required release posture.

[0068] Specifically, the previously calculated complete end-effector path from the current position to the preset placement area is integrated and arranged with the precise release posture required to perform the release operation at the deceleration phase at the end of the path. This forms a time-synchronized composite instruction sequence that includes continuous motion control and discrete gripper motion control. For example, the instruction robot first moves quickly along the planned path to approach the target area, then adjusts to a specific release posture during the deceleration phase, and opens the gripper at the precisely calculated moment with the set opening range and speed. This generates a detailed drug delivery instruction that can be directly parsed and executed by the robot control system, ensuring that the drug container is accurately and gently delivered and placed in the predetermined position.

[0069] In one embodiment, such as Figure 7 As shown, in step S40, based on the drug delivery instruction, the prepared drug is placed in the preset placement area, specifically including: S41: According to the drug delivery instruction, the gripper is controlled to grasp the container and the robotic arm is driven to move along the end effector path to the preset placement area.

[0070] Specifically, upon receiving the drug delivery instruction, the first step is to perform the gripping part of the instruction, ensuring that the gripper firmly holds or adsorbs the container containing the prepared drug with appropriate force and posture. Then, according to the end-effector motion path parameters defined in the drug delivery instruction, the servo motor system of the robotic arm is controlled to drive the linkages and joints of the robotic arm to move in a coordinated manner. This allows the gripper, along with the drug container it is carrying, to move precisely along this planned three-dimensional spatial trajectory, starting from its current position, such as the preparation table, smoothly and continuously towards the target preset placement area, such as the designated receiving point on the conveyor belt or an empty space on the sample rack.

[0071] S42: When entering the deceleration phase of the end motion path, adjust the end state of the gripper according to the required release posture and perform the release operation.

[0072] Specifically, when the robotic arm controls its end effector gripper and the medicine container it holds to move along the planned end-effector path and is about to reach the preset placement area, when it enters the deceleration phase specially set in the path planning, such as the section a few centimeters or tens of millimeters away from the target position, it will finely adjust the gripper's attitude angle according to the required release attitude parameters included in the medicine delivery instruction. This includes fine-tuning the pitch and roll angles to make it parallel to the target placement plane or at a specific angle. It may also perform minor horizontal position compensation, i.e., adjustment of the eccentric displacement, to ensure the accurate landing point of the container after release. At the precise moment when the end state is adjusted and the movement speed drops to a very low level or stops completely, the robotic arm controls the gripper's drive mechanism, such as a cylinder or motor, to perform the release action according to the gripper's opening range and opening speed parameters set in the instruction. This means releasing the gripper's grippers or releasing the suction force.

[0073] S43: When the container is detected to be stably in contact with the preset placement area and the end of the gripper is within the release posture tolerance range, release and retract the gripper to complete the placement operation of the medicine.

[0074] Specifically, during the release operation, force sensors, tactile sensors, or vision systems installed on the gripper are used for real-time monitoring to determine whether the medicine container has made stable and unshaky contact with the surface of the preset placement area, such as a tray or workbench. For example, the force sensor detects that the supporting force has reached a preset threshold, or the vision system confirms that the bottom of the container is in good contact with the placement surface. At the same time, it also verifies whether the actual end posture of the gripper, i.e., its position and angle, is still within the allowable small error range of the previously calculated required release posture, i.e., the posture tolerance. For example, the angle deviation is less than 0.5 degrees and the position deviation is less than 1 millimeter. Only when both conditions, namely stable contact of the container and gripper posture within the tolerance, are met simultaneously, is the release finally confirmed as successful. The gripper is then immediately controlled to completely release its grip on the container and then quickly lifted and moved away along the preset safe retraction path to avoid collision with the placed container or the surrounding environment, thereby completing the entire medicine placement operation.

[0075] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0076] In one embodiment, a drug dispensing and transplanting management system is provided, which corresponds one-to-one with the drug dispensing and transplanting management method described in the above embodiments. For example... Figure 8 As shown, the drug dispensing and transplanting management system includes a drug attribute information generation module, a drug positioning and retrieval scheme generation module, a drug preparation and delivery instruction generation module, and a drug placement execution module. Detailed descriptions of each functional module are as follows: The drug attribute information generation module is used to generate the attribute information of the drug to be prepared in response to the requirements of the dispensing task; The drug positioning and grasping scheme generation module is used to determine the location information of the drug to be prepared based on the attribute information of the drug to be prepared, and generate a drug grasping scheme based on the attribute information and location information of the drug to be prepared. The drug grasping scheme is used to grasp the drug to be prepared and place it on the preparation area. The drug preparation and delivery instruction generation module is used to generate a drug preparation instruction when a placement end message is received, perform drug preparation operations based on the drug preparation instruction, obtain the drug preparation result, and generate a drug delivery instruction based on the drug preparation result; The drug placement execution module is used to place the prepared drugs into a preset placement area based on drug delivery instructions.

[0077] Optionally, the drug location and capture solution generation module specifically includes: The storage area information acquisition submodule is used to acquire the storage area information of the drug to be prepared based on the attribute information of the drug to be prepared; The drug image recognition and existence determination submodule is used to obtain the storage area image corresponding to the storage area information, and to determine whether the drug to be prepared is in the storage area through image recognition algorithm; The three-dimensional pose estimation submodule for drugs is used to calculate the coordinate position information of the drugs to be prepared in the three-dimensional spatial coordinate system by using a pose estimation algorithm if the drugs to be prepared are stored in the storage area, and then use the coordinate position information as the position information of the drugs to be prepared.

[0078] Optionally, the drug location and capture solution generation module specifically includes: The gripping path and obstacle avoidance strategy planning submodule is used to generate the gripping path and obstacle avoidance strategy of the fixture based on the location information of the medicine to be prepared and through a preset path planning algorithm. The grabbing parameter determination and scheme integration submodule is used to determine the target grabbing parameters based on the attribute information of the drug to be prepared, and generate a drug grabbing scheme according to the gripper grabbing path and obstacle avoidance strategy and the target grabbing parameters.

[0079] Optionally, the drug preparation and delivery instruction generation module specifically includes: The core parameter extraction submodule is used to obtain the drug number, preparation dosage and ratio parameters from the drug attribute information when the placement end message is received; The mixing parameter calculation and preparation instruction generation submodule is used to input the drug number, preparation dosage and ratio parameters into the mixing parameter calculation model to obtain the mixing parameters, and generate drug preparation instructions based on the mixing parameters. The drug preparation execution and result evaluation submodule is used to perform drug preparation operations according to drug preparation instructions, record drug preparation process parameters, compare the drug preparation process parameters with preset target preparation parameters, and generate corresponding drug preparation results.

[0080] Optionally, the drug dispensing and transfer management system may also include: The historical data and formula acquisition module is used to acquire formula data for each drug and historical drug mixing quality assessment results, and to acquire historical mixing operation record data from the historical drug mixing quality assessment results; The historical operating condition data labeling module is used to label the attribute information of the drugs to be prepared and the actual applied mixing process parameters in the historical mixing operation record data based on the drug formulation data, so as to obtain the historical operating condition model training data. The model training data integration module is used to match and associate historical drug mixture quality assessment results with model training data for each historical operating condition to obtain the model training dataset. The mixed parameter calculation model training module is used to supervise the training of the initial regression model based on the model training dataset. When the number of iterations of the initial regression model exceeds the preset number of iterations, the mixed parameter calculation model is output.

[0081] Optionally, the drug preparation and delivery instruction generation module specifically includes: The target placement area location acquisition submodule is used to obtain the spatial position parameters of the preset placement area in the three-dimensional coordinate system based on the drug preparation results. The drug parameter acquisition and end-point path calculation submodule is used to acquire the drug parameters of the prepared drug, including container type, mass data and size information, and calculate the end-point motion path of the container loaded with the prepared drug from the current height to the spatial position parameter based on the drug parameters. The release attitude optimization submodule is used to determine the required release attitude in the deceleration phase of the end motion path based on the falling inertia. The required release attitude includes the end attitude angle, eccentric displacement, and gripper opening range. The drug delivery instruction generation submodule is used to generate drug delivery instructions based on the end-effector movement path and the required release posture.

[0082] Optionally, the drug placement execution module specifically includes: The drug gripping and path-moving control submodule is used to control the gripper to grip the container according to the drug delivery instruction, and to drive the robotic arm to move along the end motion path to the preset placement area. The end-effector attitude adjustment and release execution submodule is used to adjust the end state of the gripper according to the required release attitude when entering the deceleration phase of the end motion path, and then perform the release operation. The placement confirmation and gripper retraction submodule is used to release and retract the gripper when the container is detected to be stably in contact with the preset placement area and the end of the gripper is within the release posture tolerance range, thus completing the placement operation of the medicine.

[0083] Specific limitations regarding the drug dispensing and transplanting management system can be found in the limitations of the drug dispensing and transplanting management method described above, and will not be repeated here. Each module in the aforementioned drug dispensing and transplanting management system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0084] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data such as the properties of the drugs to be prepared, drug retrieval plans, drug preparation results, and mixing parameter calculation models. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a drug preparation and transfer management method.

[0085] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps: In response to the requirements of the dispensing task, generate the attribute information of the drug to be dispensed; Based on the attribute information of the drug to be prepared, the location information of the drug to be prepared is determined. Based on the attribute information and location information of the drug to be prepared, a drug grasping plan is generated. The drug grasping plan is used to grasp the drug to be prepared and place it on the preparation area. When the placement end message is received, a drug preparation instruction is generated, a drug preparation operation is performed based on the drug preparation instruction, a drug preparation result is obtained, and a drug delivery instruction is generated based on the drug preparation result. Based on the drug delivery instructions, the prepared drugs are placed in the preset placement area.

[0086] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor: In response to the requirements of the dispensing task, generate the attribute information of the drug to be dispensed; Based on the attribute information of the drug to be prepared, the location information of the drug to be prepared is determined. Based on the attribute information and location information of the drug to be prepared, a drug grasping plan is generated. The drug grasping plan is used to grasp the drug to be prepared and place it on the preparation area. When the placement end message is received, a drug preparation instruction is generated, a drug preparation operation is performed based on the drug preparation instruction, a drug preparation result is obtained, and a drug delivery instruction is generated based on the drug preparation result. Based on the drug delivery instructions, the prepared drugs are placed in the preset placement area.

[0087] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0088] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0089] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for managing the transplanting and preparation of pharmaceutical products, characterized in that, The drug dispensing and transfer management method includes: In response to the requirements of the dispensing task, generate the attribute information of the drug to be dispensed; Based on the attribute information of the drug to be prepared, the location information of the drug to be prepared is determined. Based on the attribute information of the drug to be prepared and the location information, a drug grasping plan is generated. The drug grasping plan is used to grasp the drug to be prepared and place it on the preparation area. When the placement end message is received, a drug preparation instruction is generated, a drug preparation operation is performed based on the drug preparation instruction, a drug preparation result is obtained, and a drug delivery instruction is generated based on the drug preparation result. Based on the drug delivery instruction, the prepared drug is placed in the preset placement area.

2. The method for drug preparation and transplanting management according to claim 1, characterized in that, The step of determining the location information of the drug to be prepared based on the attribute information of the drug to be prepared specifically includes: Based on the attribute information of the drug to be prepared, obtain the storage area information of the drug to be prepared; Obtain the image of the storage area corresponding to the storage area information, and determine whether the medicine to be prepared is in the storage area using an image recognition algorithm; If the drug to be prepared is stored in the storage area, the coordinate position information of the drug to be prepared in the three-dimensional spatial coordinate system is calculated by the pose estimation algorithm, and the coordinate position information is used as the position information of the drug to be prepared.

3. The method for drug preparation and transplanting management according to claim 2, characterized in that, The step of generating a drug retrieval plan based on the attribute information of the drug to be prepared and the location information specifically includes: Based on the location information of the medicine to be prepared, a gripper grasping path and obstacle avoidance strategy are generated through a preset path planning algorithm. Based on the attribute information of the drug to be prepared, the target grasping parameters are determined, and the drug grasping plan is generated according to the gripper grasping path and obstacle avoidance strategy and the target grasping parameters.

4. The method for drug preparation and transplanting management according to claim 1, characterized in that, When a placement completion message is received, a drug preparation instruction is generated, and a drug preparation operation is performed based on the drug preparation instruction to obtain the drug preparation result, specifically including: When the placement end message is received, the drug number, preparation dosage and ratio parameters are obtained from the drug attribute information to be prepared; The drug number, the preparation dosage, and the ratio parameters are input into the mixing parameter calculation model to obtain the mixing parameters, and the drug preparation instruction is generated based on the mixing parameters. Perform drug preparation operations according to the drug preparation instructions, record the drug preparation process parameters, compare the drug preparation process parameters with the preset target preparation parameters, and generate the corresponding drug preparation results.

5. The method for drug preparation and transplanting management according to claim 4, characterized in that, Before the step of inputting the drug number, the prepared dosage, and the ratio parameters into the mixing parameter calculation model, the drug preparation and transplanting management method further includes: Obtain the formulation data of each drug and the historical drug mixing quality assessment results, and obtain the historical mixing operation record data from the historical drug mixing quality assessment results; Based on the drug formulation data, the drug attribute information to be prepared and the actual applied mixing process parameters in the historical mixing operation record data are marked accordingly to obtain historical working condition model training data. The historical drug mixture quality assessment results are matched and associated with the training data of each historical operating condition model to obtain the model training dataset; The initial regression model is trained using supervised learning based on the model training dataset. When the number of iterations of the initial regression model exceeds the preset number of iterations, the mixing parameter calculation model is output.

6. The method for managing drug dispensing and transplanting according to claim 1, characterized in that, The step of generating a drug delivery instruction based on the drug preparation results specifically includes: Based on the drug preparation results, obtain the spatial position parameters of the preset placement area in the three-dimensional spatial coordinate system; The drug parameters of the prepared drug are obtained, including container type, mass data and size information, and the end motion path of the container loaded with the prepared drug from the current height to the spatial position parameter is calculated based on the drug parameters. Based on the end motion path, the required release posture in the deceleration phase of the end motion path is determined by the falling inertia. The required release posture includes the end posture angle, the eccentric displacement, and the opening range of the gripper. Based on the end-effector motion path and the required release posture, a drug delivery command is generated.

7. The method for managing drug preparation and transplanting according to claim 6, characterized in that, The step of placing the prepared medicine in a preset placement area based on the medicine delivery instruction specifically includes: According to the drug delivery instruction, the gripper is controlled to grasp the container, and the robotic arm is driven to move along the end-effector path to the preset placement area. When entering the deceleration phase of the end motion path, the end state of the gripper is adjusted according to the required release posture, and a release operation is performed. When the container is detected to be stably in contact with the preset placement area, and the end of the gripper is within the release posture tolerance range, the gripper is released and retracted to complete the placement operation of the medicine.

8. A drug dispensing and transplanting management system, characterized in that, The drug dispensing and transfer management system includes: The drug attribute information generation module is used to generate the attribute information of the drug to be prepared in response to the requirements of the dispensing task; The drug positioning and grasping scheme generation module is used to determine the location information of the drug to be prepared based on the attribute information of the drug to be prepared, and generate a drug grasping scheme based on the attribute information of the drug to be prepared and the location information. The drug grasping scheme is used to grasp the drug to be prepared and place it on the preparation area. The drug preparation and delivery instruction generation module is used to generate a drug preparation instruction when a placement end message is received, perform drug preparation operations based on the drug preparation instruction, obtain drug preparation results, and generate a drug delivery instruction based on the drug preparation results. The drug placement execution module is used to place the prepared drug in a preset placement area based on the drug delivery instruction.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the drug dispensing and transplanting management method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the drug dispensing and transplanting management method as described in any one of claims 1 to 7.

Images