Logistics system and method for recovery instrument recovery robot based on hospital HIS system

Abstract

The invention relates to the technical field of medical instrument logistics management, and discloses a logistics system and method of a redisinfection instrument recovery robot based on a hospital HIS (hospital information system), and the system comprises an HIS data interface module, a dynamic path planning module, a task distribution module, an instrument identification module, a recovery processing module and the like. The HIS data interface module obtains the use record of the repeated disinfection instrument; the dynamic path planning module plans a path based on a multi-target ant colony optimization algorithm; the task allocation module allocates tasks by using a game theory model; the instrument identification module identifies instruments by adopting a radio frequency identification and visual fusion algorithm; and the recovery processing module processes the instruments according to the pollution level and updates the inventory state of the HIS system. The recovery efficiency and accuracy of the recovery instrument are improved, deep fusion with an HIS system is achieved, hospital logistics management is optimized, the labor cost is reduced, and the practical value is remarkable.

Description

Technical Field

[0001] The present invention relates to the technical field of medical device logistics management, and in particular to a logistics system and method of a recycling robot for reprocessing devices based on a hospital HIS system. Background Art

[0002] In the daily operations of hospitals, the recycling and management of reprocessed instruments is a complex and important task. With the development of medical technology and the expansion of hospital scale, the traditional manual recycling method of reprocessed instruments has exposed many problems.

[0003] Manual recycling is inefficient. Hospitals have numerous departments, and the usage time and number of reprocessed instruments in each department vary. This makes it difficult for manual labor to quickly and accurately track instrument usage across departments, leading to delayed recycling and impacting instrument turnover efficiency, which in turn may affect the normal operation of medical services. In some large hospitals, the number of reprocessed instruments that need to be recycled daily is enormous, and manual recycling often consumes a significant amount of time and labor, and is prone to omissions or duplicate collections.

[0004] The accuracy of manual recycling is difficult to guarantee. Identifying the type, contamination level, and integrity status of reprocessed instruments primarily relies on manual judgment, which is susceptible to subjective factors. Different staff members may use different criteria for contamination level, and misidentification may occur for similar-looking instruments, potentially affecting subsequent disinfection or disposal, and increasing medical risks.

[0005] The complex hospital environment, with its frequent personnel and equipment turnover, presents significant challenges for the recycling of reprocessed instruments. Traditional manual recycling methods struggle to plan optimal recycling routes within this complex environment, and are prone to congestion and collisions. This not only reduces recycling efficiency but can also disrupt the normal operation of the hospital.

[0006] Although the hospital information system (HIS) records the usage information of reused medical devices, this information has not been fully utilized and cannot be effectively linked with the recycling process of reused medical devices, resulting in serious information island phenomenon, which is not conducive to the hospital's overall management of medical devices and resource allocation.

[0007] With the continuous development of artificial intelligence, robotics, and the Internet of Things, there is enormous potential for applying these advanced technologies to the management of hospital reprocessing equipment recycling. Therefore, it is urgent to develop an efficient and intelligent logistics system and method for reprocessing equipment recycling robots based on the hospital's HIS system to address the many problems existing in traditional manual recycling methods and improve hospital management and medical service quality. Summary of the Invention

[0008] The purpose of the present invention is to provide a logistics system and method for a reprocessing instrument recovery robot based on a hospital HIS system to solve the problems raised in the above background technology.

[0009] To achieve the above objectives, the present invention provides the following technical solution: a logistics system for a robot for recycling reprocessing instruments based on a hospital HIS system, the system comprising:

[0010] The HIS data interface module is used to obtain the use records of re-disposal equipment in each department of the hospital HIS system in real time, including equipment type, usage time, number to be recycled and location coordinates;

[0011] A dynamic path planning module generates a dynamic path weight based on the position coordinates, the robot's real-time position and the environment map using a multi-objective ant colony optimization algorithm. The dynamic path weight is a combination of path length, obstacle density and task urgency.

[0012] A task allocation module, which calculates the priority coefficient of each robot task based on the number of devices to be recycled and the type of devices through a game theory model, and allocates recycling tasks according to the priority coefficient;

[0013] The device identification module, equipped with radio frequency identification and visual fusion algorithms, identifies the type, contamination level and integrity status of the device to be recycled;

[0014] The recycling processing module selects a disinfection mode or a scrapping processing strategy according to the pollution level and updates the equipment inventory status in the HIS system.

[0015] Preferably, the dynamic path planning module includes:

[0016] The environmental modeling submodule converts the hospital floor plan into a three-dimensional rasterized map and annotates the real-time locations of dynamic obstacles;

[0017] The weight calculation submodule assigns a time penalty factor based on the urgency of the current task and generates a dynamic path weight based on the grid passage difficulty coefficient;

[0018] The path update submodule recalculates the global optimal path at preset intervals during the robot's movement and dynamically adjusts the local obstacle avoidance path.

[0019] Preferably, the objective function of the multi-objective ant colony optimization algorithm is:

[0020]

[0021] Among them, W is the comprehensive weight of the path, L k is the length of the kth path, D k is the obstacle density of the kth segment, T delayis the task delay time, α, β, γ are normalization coefficients.

[0022] Preferably, the task assignment module further includes:

[0023] The priority calculation submodule assigns risk weight R according to the device contamination level i , the remaining time of the task is given a timeliness weight T i , and calculate the priority coefficient P by linear weighting i =λR i +(1-λ)T i , where λ is an adjustable parameter;

[0024] The game decision submodule regards multiple robots as game participants and allocates tasks through the Nash equilibrium model to ensure that the global task completion time is minimized.

[0025] Preferably, the utility function of the game decision submodule is:

[0026]

[0027] Among them, U j is the utility value of robot j, C ij is the estimated time required for robot j to perform task i, and ∈ is a zero-proof constant.

[0028] Preferably, the system further comprises:

[0029] The communication coordination module, based on the 5G and LoRa hybrid communication protocol, realizes state synchronization and conflict resolution among robot clusters, including task preemption signals and path overlap warnings.

[0030] Preferably, the conflict resolution strategy includes:

[0031] When path overlap is detected, the passage order is dynamically adjusted according to the robot task priority coefficient, the low-priority robot enters a temporary waiting state, and local path replanning is triggered.

[0032] Preferably, the visual fusion algorithm of the device recognition module includes:

[0033] For devices without RFID tags, the YOLOv7 model is used to identify the device outline, perform feature matching with the standard template library, and output the device category confidence score.

[0034] If the confidence level is lower than the threshold, the manual remote review process is initiated.

[0035] Preferably, the system further comprises:

[0036] The exception handling module monitors the robot's power level, robotic arm status, and communication link strength in real time. When any indicator exceeds the preset threshold, the task migration protocol is triggered to transfer the current task to an idle robot.

[0037] Preferably, the present invention also includes a logistics method for a reprocessing instrument recovery robot based on a hospital HIS system, the method comprising the following steps:

[0038] Step 1: Obtain the use records of recycled instruments in each department of the hospital HIS system in real time through the HIS data interface module. The use records include instrument type, usage time, quantity to be recycled, and location coordinates;

[0039] Step 2: Using the dynamic path planning module, based on the acquired position coordinates, the robot's real-time position, and the environment map, a multi-objective ant colony optimization algorithm is used to generate a dynamic path weight. This dynamic path weight takes into account the path length, obstacle density, and task urgency.

[0040] Step 3: Using the task allocation module, based on the number of devices to be recycled and the type of equipment, a game theory model is used to calculate the priority coefficient of each robot task, and then the recycling tasks are allocated according to the priority coefficient;

[0041] Step 4: Use the device identification module, equipped with radio frequency identification and visual fusion algorithms, to identify the type, contamination level and integrity status of the device to be recycled;

[0042] Step 5: With the help of the recycling and processing module, according to the identified contamination level, select the corresponding disinfection mode or scrapping treatment strategy, and simultaneously update the equipment inventory status in the HIS system.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] In terms of improving recycling efficiency, the HIS data interface module obtains the use records of the reused instruments in each department in real time. The system can quickly grasp the status of the instruments to be recycled. Combined with the dynamic path planning module based on the dynamic path weights generated by the multi-objective ant colony optimization algorithm, the robot can plan the optimal path that avoids obstacles and comprehensively considers the urgency of the task, greatly reducing the travel time in the complex environment of the hospital. The task allocation module uses the game theory model to reasonably allocate tasks, avoiding task conflicts and waste of resources between robots, making the entire recycling process more efficient and orderly. Compared with traditional manual recycling, the recycling efficiency can be increased several times, and it can quickly respond to the needs of various departments, reduce the idle time of instruments, improve the turnover utilization rate of instruments, and effectively ensure the smooth progress of medical work.

[0045] To enhance recognition accuracy, the device identification module utilizes RFID and visual fusion algorithms, which complement each other to significantly improve the accuracy of identifying the type, contamination level, and integrity status of re-sterilized devices. For devices missing RFID tags, the YOLOv7 model, combined with a standard template library, performs identification and initiates a manual remote review process when confidence is low. This effectively avoids processing errors caused by misidentification, reduces medical risks, ensures accurate subsequent disinfection or disposal, and safeguards medical safety.

[0046] In terms of optimizing hospital logistics management, this invention achieves deep integration with the HIS system. After processing the equipment, the recycling and processing module promptly updates the equipment inventory status in the HIS system, enabling the hospital to have real-time access to equipment inventory information and facilitate resource allocation and management decisions. The communication coordination module, based on a hybrid 5G and LoRa communication protocol, achieves state synchronization and conflict resolution between robot clusters, ensuring the collaborative operation of robots in complex hospital environments, enhancing the intelligent level of hospital logistics management, reducing interference from human factors, and making hospital operations more efficient and smoother.

[0047] From the perspective of reducing labor costs, the use of reprocessing instrument recovery robots reduces reliance on large numbers of workers, saving labor costs. Robots can work continuously, unaffected by factors such as fatigue, and have relatively low maintenance costs. In the long term, this saves hospitals significant operating funds, allowing them to invest more resources in medical services and scientific research innovation. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a diagram showing the working principle of the system of the present invention;

[0049] Figure 2 This is the workflow diagram of the dynamic path planning module;

[0050] Figure 3 This is the workflow diagram of the communication coordination module;

[0051] Figure 4 This is the workflow diagram of the visual fusion algorithm of the instrument recognition module. DETAILED DESCRIPTION

[0052] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0053] See also Figure 1-4The present invention provides a technical solution: a logistics system for a robot for recycling reprocessing equipment based on a hospital HIS system, the system comprising:

[0054] HIS Data Interface Module: This module establishes a real-time connection with the hospital's HIS system, capturing real-time usage records of reprocessed instruments across all departments. These records include key information such as instrument type, usage time, quantity to be recycled, and location coordinates. This allows the system to keep abreast of the usage of reprocessed instruments in each department, providing accurate data support for subsequent recycling tasks.

[0055] Dynamic Path Planning: Based on the location coordinates obtained from the HIS data interface module, the robot's real-time position, and a pre-built environmental map, a multi-objective ant colony optimization algorithm is used to generate dynamic path weights. This dynamic path weight takes into account factors such as path length, obstacle density, and task urgency to ensure the robot plans the optimal recovery path and improve recovery efficiency.

[0056] Task Allocation Module: Based on the number of items to be recycled and the type of equipment, a game theory model is used to calculate the priority coefficient for each robot's task. This rational calculation method determines the priority of each robot in the recycling task, and then allocates recycling tasks according to the priority coefficient, making task allocation more scientific and reasonable, and improving overall recycling efficiency.

[0057] Device Identification Module: Equipped with a fusion algorithm of radio frequency identification and vision, it can identify the type, contamination level, and integrity status of recycled devices. This module leverages the strengths of both technologies to improve identification accuracy and provide a precise basis for subsequent processing.

[0058] Recycling and Processing Module: Based on the contamination level identified by the device identification module, the module selects the appropriate disinfection mode or scrapping strategy. At the same time, this module will promptly update the device inventory status in the HIS system to ensure the accuracy and real-time status of the device inventory information in the HIS system.

[0059] The present invention will be further described below in conjunction with Examples 1 to 6:

[0060] Example 1:

[0061] This embodiment mainly provides a detailed description of the dynamic path planning module, which is used to plan dynamic paths for the robot more accurately and efficiently, improve the robot's mobility efficiency in complex hospital environments, reduce time waste caused by unreasonable path planning, and thereby improve the execution efficiency of the entire reprocessing instrument recovery task.

[0062] The dynamic path planning module includes an environment modeling submodule, a weight calculation submodule and a path updating submodule.

[0063] The environmental modeling submodule converts the hospital floor plan into a 3D rasterized map. This conversion utilizes advanced mapping technology and image processing algorithms to accurately translate various hospital areas, such as wards, corridors, and departments, into a rasterized representation. Simultaneously, sensors monitor the location of dynamic obstacles, such as beds and carts moving through the hospital corridors, in real time and mark them on the 3D rasterized map. This allows the robot to avoid these dynamic obstacles in real time when planning its path, ensuring safe movement.

[0064] The weight calculation submodule assigns a time penalty factor based on the urgency of the current task. When a department urgently needs to recycle the equipment for the next round of medical operations, the urgency of the task is high and the time penalty factor will increase accordingly. At the same time, a dynamic path weight is generated in combination with the grid passage difficulty coefficient. The grid passage difficulty coefficient is determined based on factors such as the position of the grid and whether there are obstacles. For example, the grid passage difficulty coefficient is low near the ward door and without obstacles, while the grid passage difficulty coefficient is high in a narrow passage where people often walk. The objective function of the multi-objective ant colony optimization algorithm is:

[0065]

[0066] Among them, W is the comprehensive weight of the path, L k is the length of the kth path, D k is the obstacle density of the kth segment, T delay is the task delay time, and α, β, and γ are normalization coefficients. By adjusting these coefficients, we can balance the impact of path length, obstacle density, and task urgency on path weight according to actual needs. Generally, if the hospital environment is relatively stable and obstacles are few, the weight of α can be appropriately increased, making path length the dominant factor in path planning. If the hospital environment is complex and obstacles are numerous, the weight of β can be increased to prioritize obstacle avoidance.

[0067] During the robot's movement, the path update submodule recalculates the global optimal path at preset intervals (for example, 10 seconds). During the recalculation, factors such as the robot's real-time position, the latest environmental information, and the urgency of the task are taken into consideration. At the same time, if the robot detects new obstacles in the local area or changes in the path during movement, it will dynamically adjust the local obstacle avoidance path. When the robot is on its way to a department to recycle equipment and suddenly encounters a temporary obstacle in the corridor ahead that is being cleaned, the path update submodule will quickly adjust the local path and guide the robot to its destination through other feasible channels to ensure that the recycling task is not affected.

[0068] Example 2:

[0069] The task allocation module further includes a priority calculation submodule and a game decision submodule.

[0070] The priority calculation submodule assigns risk weight R according to the device contamination level. i For devices with high contamination levels, the risk weight is higher because handling such devices requires more protective measures and special processing procedures. Prioritizing the recovery of high-contamination devices can reduce the risk of cross infection. At the same time, the timeliness weight T is assigned according to the remaining time of the task. i The closer the task is to the specified recycling time, the higher the timeliness weight is. The priority coefficient P is calculated by linear weighting. i =λR i +(1-λ)T i , where λ is an adjustable parameter. In practice, hospitals can adjust the value of λ based on their specific circumstances and needs. During periods of high infectious disease prevalence, to reduce infection risk, the value of λ can be appropriately increased, giving the contamination level a greater weight in priority calculations. During normal times, if timeliness is a priority, the value of λ can be lowered.

[0071] The game decision submodule treats multiple robots as game participants and allocates tasks through the Nash equilibrium model to ensure that the global task completion time is minimized. Its utility function is:

[0072]

[0073] Among them, U j is the utility value of robot j, C ij is the estimated time required for robot j to perform task i, and ∈ is a zero-proof constant. When assigning tasks, each robot calculates the utility of performing each task based on factors such as its own performance, current location, and task priority. The robot selects the task with the highest utility value. In this way, the global task completion time is minimized while satisfying the Nash equilibrium. Suppose there are three robots, R1, R2, and R3, located at different locations. They are assigned three recycling tasks, T1, T2, and T3, with different priorities, and each robot has a different estimated time to perform each task. Through the calculations of the game decision submodule, R1 will choose the task with the highest utility value, and R2 and R3 will make similar choices. Ultimately, tasks are rationally allocated and overall recycling efficiency is improved.

[0074] Example 3:

[0075] The communication coordination module, based on a hybrid 5G and LoRa communication protocol, enables state synchronization and conflict resolution among robot clusters, including task preemption signals and path overlap warnings. The 5G communication protocol boasts high speed and low latency, enabling rapid transmission of large amounts of data, such as the robot's real-time location and task progress, ensuring that each robot has timely access to the latest task status. The LoRa communication protocol, with its low power consumption and long-distance transmission capabilities, is suitable for data transmission over a wide area of the hospital, particularly in areas with weak signals, where LoRa communication ensures stable communication between robots.

[0076] When path overlap is detected, the conflict resolution strategy dynamically adjusts the order of travel based on the robot's task priority coefficient. Low-priority robots enter a temporary waiting state, triggering local path replanning. In a hospital corridor, the planned paths of Robots A and B overlap. Based on the task priority coefficient, Robot B has a lower priority. Robot B enters a temporary waiting state and initiates a local path replanning algorithm. The local path replanning algorithm replans a path that avoids conflicting areas based on Robot B's current position, surrounding environment information, and task objectives. During the replanning process, the safety and feasibility of the path are prioritized to ensure that Robot B can resume task execution as quickly as possible without impacting the normal operation of other robots.

[0077] Example 4:

[0078] This embodiment details the visual fusion algorithm of the device identification module, which is used to improve the accuracy of identifying devices to be recycled, especially when the radio frequency tag is missing, so as to accurately identify the type of the device and provide a reliable basis for subsequent processing.

[0079] The visual fusion algorithm of the device recognition module is mainly used for devices with missing RFID tags. When encountering a device without an RFID tag, the device outline is identified using the YOLOv7 model. The YOLOv7 model is an advanced target detection model that is fast and accurate. During the recognition process, the model analyzes the captured image and extracts the device's outline features. The extracted outline features are then matched with the standard template library and the device category confidence score is output. (Corresponding to the corresponding pollution The dyeing level can be evaluated according to the proportional function, and the coefficient is set by the system or by default). The standard template library stores the standard contour features and related information of various re-elimination instruments. If the confidence level is lower than the threshold (for example, 0.8), the manual remote review process is started. In actual applications, the accuracy of recognition may be affected by factors such as stains on the surface of the instrument and light. When the confidence level is low, the category of the instrument can be further confirmed through manual remote review to avoid problems in subsequent processing due to recognition errors. For example, when identifying a re-elimination instrument of a special shape, the recognition confidence of the YOLOv7 model is low due to partial wear on its surface. At this time, manual remote review is started. By manually viewing the image and related information, the category of the instrument can be accurately determined, thereby ensuring the accuracy of subsequent processing.

[0080] Example 5:

[0081] This embodiment introduces an exception handling module, which is used to monitor the operating status of the robot in real time and take timely measures when an abnormal situation occurs to ensure that the recovery task can continue and avoid task interruption due to robot failure.

[0082] The exception handling module monitors the robot's battery level, robotic arm status, and communication link strength in real time. Regarding the robot's battery level, when it falls below a preset threshold (e.g., 20%), it indicates that the robot is running low and may be unable to complete the current task. At this point, the exception handling module triggers the task migration protocol, transferring the current task to an idle robot. When transferring a task, relevant information about the task, such as the task objective and the location of the equipment to be recovered, is also transmitted to the idle robot to ensure that the idle robot can successfully take over the task.

[0083] The task migration protocol is also triggered when the robot arm detects abnormal conditions, such as a jam or inability to properly grasp an instrument. The robot arm is a critical component of the robot's instrument recovery, and its proper functioning is directly related to the execution of the recovery mission. In this case, timely transfer of the task to another functioning robot ensures that the recovery mission is not affected.

[0084] Communication link strength is also a key metric monitored by the exception handling module. When the communication link strength falls below a preset threshold, data transmission between the robot and the system may become unstable, impacting task execution. At this point, the exception handling module attempts to reestablish the communication connection. If normal communication cannot be restored after multiple attempts, the task migration protocol is triggered, transferring the task to a robot with normal communication, ensuring the smooth execution of the entire reprocessing instrument recovery task.

[0085] Example 6:

[0086] In this embodiment, a comprehensive hospital is taken as an example to illustrate the specific application of the logistics system of the recycling robot for reprocessing instruments based on the hospital HIS system.

[0087] The hospital has multiple departments, including surgery, internal medicine, and obstetrics and gynecology, each of which uses a large number of reusable instruments on a daily basis. After completing a surgery in the surgical operating room, medical staff will enter information about the reusable instruments used in the HIS system, including the instrument type (such as scalpels, hemostats, suture needles, etc.), usage time, and number of instruments to be recycled. They will also mark the coordinates of the instrument's location (for example, the specific shelf location in the instrument storage area of operating room A). Medical staff will then issue a recycling request in the HIS system, triggering the activation of the logistics management system.

[0088] Data Acquisition Phase: The HIS data interface module begins operating, acquiring real-time records of surgical instruments entered into the HIS system. This module maintains a stable data connection with the HIS system to ensure accurate and timely data transmission. Through this module, it successfully retrieved information on the five scalpels, eight hemostats, and three packages of suture needles used in this surgery, all located in the instrument storage area of operating room A, along with their respective usage times and quantities awaiting recovery.

[0089] Path planning stage: After receiving the data, the dynamic path planning module begins to plan the robot's path of action. The environmental modeling submodule converts the hospital floor plan into a three-dimensional raster map and marks the location of dynamic obstacles in real time, such as carts transporting medical supplies in the corridor, equipment temporarily placed in the passage, etc. The weight calculation submodule assigns a time penalty factor according to the urgency of the current surgical instrument recovery task, and uses a multi-objective ant colony optimization algorithm to calculate the dynamic path weight based on the grid passage difficulty coefficient. Assuming that the surgical instruments need to be recycled urgently for the next operation, the time penalty factor is set to a high level. Through the formula The comprehensive path weight W is calculated, where L k is the length of the kth path, D k is the obstacle density of the kth segment, T delay is the task delay time, and α, β, and γ are normalization coefficients. During the robot's movement, the path update submodule recalculates the global optimal path at a preset interval (e.g., 5 minutes) and dynamically adjusts the local obstacle avoidance path to ensure that the robot can reach the target location efficiently and safely.

[0090] Task allocation stage: The task allocation module calculates the priority coefficient of each robot task based on the number and type of equipment to be recycled through the game theory model. The priority calculation submodule assigns risk weight R according to the equipment contamination level. i , the remaining time of the task is given a timeliness weight T i and through the linear weighted formula P i =λR i +(1-λ)T iCalculate the priority coefficient, where λ is an adjustable parameter. Assuming the surgical instrument being retrieved has a high contamination level and is close to being used in the next surgery, the priority coefficient for this task is high. The game decision submodule treats multiple robots as participants in the game and allocates tasks using a Nash equilibrium model to minimize the overall task completion time. Ultimately, robot number R001 is assigned to the instrument storage area in operating room A to perform the retrieval task.

[0091] Equipment recognition phase: After the R001 robot reaches the designated location, the equipment recognition module starts working , based on the model calculation Identify the type, contamination level, and integrity of the device to be recycled . This module is equipped with radio frequency identification and visual fusion algorithms. It first reads the relevant information of the instrument through radio frequency identification technology. For some instruments with missing radio frequency tags, the YOLOv7 model is used to identify the instrument outline, and feature matching is performed with the standard template library to output the instrument category confidence. If the confidence is lower than the threshold (such as 0.8), the manual remote review process is started. For example, when identifying a scalpel, due to the damage of the radio frequency tag, the visual fusion algorithm identifies the instrument category with a confidence of 0.75, triggering a manual remote review, and professional medical staff confirm that the instrument is a scalpel to ensure the accuracy of identification.

[0092] Recycling and processing stage: The recycling and processing module selects the corresponding disinfection mode or scrapping treatment strategy according to the pollution level identified by the device identification module. If the pollution level of the device is light pollution, the conventional disinfection mode is selected; if it is heavy pollution, the Remind clinical departments to make on-site pretreatment judgments (the system generates corresponding on-site pretreatment reminder information and sends it to On-site personnel, such as sending it to their PAD / EDA terminals, etc., to remind on-site personnel to make on-site pre-processing judgments) and conduct on-site On-site pre-processing judgment: If there is a problem with the integrity of the device, it will be scrapped and recycled, and the nurse will be reminded to write an IOU: Department X, certain On a certain day of a certain month in a certain year, a certain instrument of the disinfection supply center was damaged, along with the name, work number, etc. After the interruption, the system continues Continued Select enhanced disinfection mode. After processing is completed, the recycling processing module will synchronously update the equipment inventory status in the HIS system, changing the status of the recovered equipment from "in use" to "pending disinfection" or "scrapped", ensuring the real-time and accurate equipment inventory information in the HIS system.

[0093] For the above-mentioned identified and recovered instruments, the on-site pre-processing results of each clinical department can be counted and generated. Corresponding monthly reports. Evaluate the on-site pretreatment monthly reports of each clinical department and sort out the clinical departments with poor on-site pretreatment. Department rankings are fed back to the Nursing Department Quality Management Committee and the Medical Department for supervision and assessment.

[0094] For departments that rank low (the system sets the ranking threshold, such as ranking lower than 5), the system automatically Punishment measures: The system sends a warning to the corresponding department PC or the responsible person of the corresponding department. Account or terminal APP, etc., sends a reminder notification (link can be attached in the notification) to remind medical staff Pay attention to the on-site pre-treatment of medical devices after use. Penalty measures Implementation: Watch the video on correct on-site pretreatment.

[0095] Communication coordination and exception handling: Throughout the entire process, the communication coordination module uses a hybrid communication protocol of 5G and LoRa to achieve state synchronization and conflict resolution between robot clusters. If it is detected that the paths of the R001 robot and other robots overlap, the passage order is dynamically adjusted according to the robot task priority coefficient, the low-priority robot enters a temporary waiting state, and triggers local path replanning. At the same time, the exception handling module monitors the power level, robotic arm status, and communication link strength of the R001 robot in real time. If the robot's power level is lower than the preset threshold (such as 20%), the task migration protocol is triggered to transfer the current task to the idle robot to ensure the smooth progress of the recycling task.

[0096] Through the above embodiments, the effective application of the logistics system of the recycling robot for re-disposal instruments based on the hospital HIS system in actual hospital scenarios is demonstrated, realizing the intelligent and efficient management of the recycling of re-disposal instruments.

[0097] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0098] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A logistics system for recycling robots of reprocessing instruments based on the hospital HIS system, characterized by: include: The HIS data interface module is used to obtain the use records of re-disposal equipment in each department of the hospital HIS system in real time, including equipment type, usage time, number to be recycled and location coordinates; A dynamic path planning module generates a dynamic path weight based on the position coordinates, the robot's real-time position and the environment map using a multi-objective ant colony optimization algorithm. The dynamic path weight is a combination of path length, obstacle density and task urgency. A task allocation module, which calculates the priority coefficient of each robot task based on the number of devices to be recycled and the type of devices through a game theory model, and allocates recycling tasks according to the priority coefficient; The device identification module, equipped with radio frequency identification and visual fusion algorithms, identifies the type, contamination level and integrity status of the device to be recycled; The recycling processing module selects a disinfection mode or a scrapping processing strategy according to the pollution level and updates the equipment inventory status in the HIS system.

2. The system according to claim 1, wherein: The dynamic path planning module includes: The environmental modeling submodule converts the hospital floor plan into a three-dimensional rasterized map and annotates the real-time locations of dynamic obstacles; The weight calculation submodule assigns a time penalty factor based on the urgency of the current task and generates a dynamic path weight based on the grid passage difficulty coefficient; The path update submodule recalculates the global optimal path at preset intervals during the robot's movement and dynamically adjusts the local obstacle avoidance path.

3. The system according to claim 2, characterized in that The objective function of the multi-objective ant colony optimization algorithm is: Among them, W is the comprehensive weight of the path, L k is the length of the kth path, D k is the obstacle density of the kth segment, T delay is the task delay time, α, β, γ are normalization coefficients.

4. The system according to claim 1, wherein: The task allocation module further includes: The priority calculation submodule assigns risk weight R according to the device contamination level i , the remaining time of the task is given a timeliness weight T i , and calculate the priority coefficient P by linear weighting i =λR i +(1-λ)T i , where λ is an adjustable parameter; The game decision submodule regards multiple robots as game participants and allocates tasks through the Nash equilibrium model to ensure that the global task completion time is minimized.

5. The system according to claim 4, characterized in that The utility function of the game decision submodule is: Among them, U j is the utility value of robot j, C ij is the estimated time required for robot j to perform task i, and ∈ is a zero-proof constant.

6. The system according to claim 1, wherein: Also includes: The communication coordination module, based on the 5G and LoRa hybrid communication protocol, realizes state synchronization and conflict resolution among robot clusters, including task preemption signals and path overlap warnings.

7. The system according to claim 6, characterized in that The conflict resolution strategy includes: When path overlap is detected, the passage order is dynamically adjusted according to the robot task priority coefficient, the low-priority robot enters a temporary waiting state, and local path replanning is triggered.

8. The system according to claim 1, wherein: The visual fusion algorithm of the device recognition module includes: For devices without RFID tags, the YOLOv7 model is used to identify the device outline, perform feature matching with the standard template library, and output the device category confidence score. If the confidence level is lower than the threshold, the manual remote review process is initiated.

9. The system according to claim 1, wherein: Also includes: The exception handling module monitors the robot's power level, robotic arm status, and communication link strength in real time. When any indicator exceeds the preset threshold, the task migration protocol is triggered to transfer the current task to an idle robot.

10. A logistics method for recycling robots of reprocessing instruments based on the hospital HIS system, characterized in that: The following steps are involved: Step 1: Obtain the use records of recycled instruments in each department of the hospital HIS system in real time through the HIS data interface module. The use records include instrument type, usage time, quantity to be recycled, and location coordinates; Step 2: Using the dynamic path planning module, based on the acquired position coordinates, the robot's real-time position, and the environment map, a multi-objective ant colony optimization algorithm is used to generate a dynamic path weight. This dynamic path weight takes into account the path length, obstacle density, and task urgency. Step 3: Using the task allocation module, based on the number of devices to be recycled and the type of equipment, a game theory model is used to calculate the priority coefficient of each robot task, and then the recycling tasks are allocated according to the priority coefficient; Step 4: Use the device identification module, equipped with radio frequency identification and visual fusion algorithms, to identify the type, contamination level and integrity status of the device to be recycled; Step 5: With the help of the recycling and processing module, according to the identified contamination level, select the corresponding disinfection mode or scrapping treatment strategy, and simultaneously update the equipment inventory status in the HIS system.

Images