Air-ground integrated hospital intelligent logistics system and method

Abstract

The invention discloses an air-ground integrated hospital intelligent logistics system and method, and relates to the technical field of hospital intelligent logistics, and the method comprises the steps: receiving a material distribution task sent by a hospital information system, and according to a floor where a specified target department in the task is located, carrying out the distribution of materials; determining a corresponding target parking apron as an air access node from a three-dimensional layered parking apron network deployed on the external facade of the high-rise public building of the hospital; scheduling the unmanned aerial vehicle to carry the intelligent transfer cabin to fly against the target parking apron, realizing positioning through UWB and millimeter wave radar in the approaching process, and identifying a guide identifier on the parking apron by using a visual sensor to complete attitude calibration; after the unmanned aerial vehicle lands and makes contact with a target parking apron, the docking stability is maintained through force feedback adjustment, an electromagnetic adsorption mechanism is started to achieve physical locking, and then the intelligent transfer cabin is transferred to a conveying mechanism of the parking apron to complete handover; and the central control platform calls the intelligent logistics middleware to analyze the distribution task after confirming that handover is completed.

Description

Technical Field

[0001] This invention relates to the field of smart logistics technology for hospitals, and in particular to an integrated air-ground smart logistics system and method for hospitals. Background Technology

[0002] Hospital smart logistics technology refers to a set of technologies that utilize next-generation information technologies such as the Internet of Things, artificial intelligence, automated control, and big data analytics to build an intelligent material transportation system covering both the internal and external aspects of a hospital. This system enables the efficient, safe, and traceable unmanned or semi-automated flow of medical supplies such as medicines, test samples, consumables, medical instruments, and sterile packages throughout the hospital. Therefore, how to utilize advanced technologies to improve the intelligence level and security of hospital smart logistics has become one of the most pressing issues to be addressed.

[0003] In the field of smart logistics in hospitals, existing technologies mostly use fixed robotic arms for capture or simple platform landing. The docking process lacks proactive adaptability. In the complex environment of urban hospitals, docking failure or even crashes are easily caused by positioning deviations or airflow disturbances. Moreover, traditional logistics systems operate independently in each link, lacking a global coordination mechanism, making it difficult to cope with emergencies. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides an integrated air-ground smart logistics method for hospitals to address the problems in existing technologies where drones often use fixed robotic arms for capture or simple platform landing, lacking proactive adaptability during docking. In the complex environment of urban hospitals, docking failures or even crashes are easily caused by positioning deviations or airflow disturbances. Furthermore, traditional logistics systems operate independently in each link, lacking a global coordination mechanism, making it difficult to cope with emergencies.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides an integrated air-ground smart logistics method for hospitals, comprising: Receive material delivery tasks from the hospital information system, and determine the corresponding target helipad as an air access node from the three-dimensional, layered helipad network deployed on the exterior of the hospital's high-rise public buildings, based on the floor of the target department specified in the task. The drone carrying the intelligent transfer cabin was dispatched to the target helipad. During the approach, it was located by UWB and millimeter-wave radar, and its attitude was calibrated by using visual sensors to identify the guidance marks on the helipad. After the drone lands and touches the target helipad, it maintains docking stability through force feedback adjustment and activates the electromagnetic adsorption mechanism to achieve physical locking. Then, the intelligent transfer cabin is transferred to the conveyor mechanism on the helipad to complete the handover. After the central control platform confirms the handover, it calls the intelligent logistics middleware to analyze the delivery task and selects the appropriate indoor transmission carrier based on the status of the logistics equipment on the floor where the destination room is located. The selected indoor transport vehicle travels to the helipad docking port to receive the intelligent transfer cabin and transports it to the destination room. Upon arrival at the destination, the system automatically opens the transfer cabin door to complete the delivery process after verifying the identity of authorized personnel.

[0007] As a preferred embodiment of the air-ground integrated smart logistics method for hospitals described in this invention, the step of determining the corresponding target helipad as the air access node from the three-dimensional layered helipad network deployed on the exterior facade of the hospital's high-rise public buildings, based on the floor of the target department specified in the task, is as follows: Receive material delivery tasks from the hospital information system, the tasks including the name of the destination department and the target room number; Call the hospital building information model database to parse the physical floor number corresponding to the target room number; Query the preset three-dimensional layered helipad configuration table to determine whether there is an external helipad on this physical floor; If it exists, the helipad on the exterior facade of that floor will be defined as the target helipad for this mission. If it does not exist, find the floor in the configuration table that is one floor above the current floor and the closest configured helipad. Define the exterior helipad on that floor as the temporary target helipad and mark it as needing to start the vertical transfer process inside the building.

[0008] As a preferred embodiment of the air-ground integrated smart hospital logistics method of the present invention, the dispatching drone carrying the intelligent transfer cabin flies to the target helipad, achieves positioning through UWB and millimeter-wave radar during the approach, and completes attitude calibration by recognizing guidance marks on the helipad using a visual sensor. The specific steps are as follows: The central control platform sends flight mission instructions to the standby drones, which include the geographical coordinates of the target landing pad and flight safety altitude parameters. After the drone takes off, it flies along a preset route. When it enters the radius R of the target landing pad, it activates the near-field guidance mode. UWB base station clusters perform high-precision positioning of the drone's current location and obtain its three-dimensional spatial coordinates; Millimeter-wave radar continuously scans the area beneath the drone, detecting dynamic obstacles and updating the local obstacle avoidance path; The drone switches to low-speed hovering mode, and the front-end binocular vision system acquires dynamic LED guide array images of the target helipad surface; The pixel coordinates of the center point of the guide array are extracted based on image processing algorithms and compared with the ideal alignment position; Calculate the two-dimensional offset and, in combination with the camera intrinsic parameters, deduce the horizontal and pitch angle deviations of the UAV relative to the helipad. Based on the angular deviation, a flight control correction is generated to adjust the rotor thrust distribution, so that the UAV is aligned with the center area of ​​the target landing pad.

[0009] As a preferred embodiment of the air-ground integrated smart logistics method for hospitals described in this invention, the following steps are taken: After the UAV lands and contacts the target helipad, force feedback is used to maintain docking stability, and an electromagnetic adsorption mechanism is activated to achieve physical locking. Subsequently, the intelligent transfer cabin is transferred to the conveyor mechanism on the helipad to complete the handover. After completing attitude correction based on angular and spatial deviations, the UAV slowly descends to the surface of the elastic buffer layer of the target landing pad in a uniform deceleration manner. The buffer layer integrates a six-dimensional force sensor to measure the normal force and tangential shear force at the moment of contact. If the tangential shear force exceeds the threshold of the product of the preset friction coefficient and the normal force, it is determined that there is a slippage tendency. The central control platform sends fine-tuning commands to the drone, which generates a counter-compensation torque by adjusting the rotor thrust difference to eliminate sideslip; After confirming stable contact, the electromagnetic adsorption array on the target landing pad surface is activated. Its magnetic induction intensity acts on the ferromagnetic material of the UAV base, generating an adsorption force, expressed as: ; in, For adsorption force, The magnetic induction intensity generated by the electromagnetic adsorption array. The effective contact area between the drone base and the landing pad. The material coupling coefficient; Once the adsorption force reaches the preset locking threshold, the drone release mechanism is triggered to unlock, smoothly transferring the smart transfer cabin to the horizontal conveyor belt built into the helipad. The conveyor belt starts, transporting the intelligent transfer cabin to the connection window inside the building, completing the physical handover between the aerial section and the ground section.

[0010] As a preferred embodiment of the air-ground integrated smart logistics method for hospitals described in this invention, the central control platform, after confirming the handover, calls the intelligent logistics middleware to analyze the delivery task and selects a suitable indoor transmission carrier based on the status of the logistics equipment on the floor where the destination room is located. The specific steps are as follows: The weight sensor at the docking window detected the smart transfer cabin entering the indoor side and generated a handover completion signal. The central control platform receives the handover completion signal and reads the task ID and material information from the RFID tag in the smart transfer cabin; Send the task ID and destination room number to the intelligent logistics middleware; The middleware queries the set of currently available indoor transmission devices on the target floor, where each device has operating status and type attributes; Select devices with an idle status from the device status set. If there is a device of type railcar, select the railcar as the transmission carrier first. If no available track vehicle is available, an idle AMR robot will be selected as the transport vehicle. Generate scheduling instructions compatible with the communication protocol of the selected transmission carrier and send them to its control terminal; During the equipment selection process, a priority scoring function is used for decision-making, the expression of which is: ; in, For equipment The rating value For its equipment type, For indicator functions, This is the normalized value of the current task queue length for this device. , These are the weighting coefficients.

[0011] As a preferred embodiment of the air-ground integrated smart logistics method for hospitals described in this invention, the selected indoor transport vehicle travels to the helipad docking port to receive the intelligent transfer cabin and transports it to the destination room. The specific steps are as follows: After receiving the scheduling instruction, the selected transmission carrier starts the autonomous navigation system and plans the optimal path from the current location to the docking point; The platform travels along the path to the designated docking position at the connection point, aligning its support platform with the end of the conveyor belt. The mechanical positioning pin is inserted into the positioning hole of the transmission carrier platform; The conveyor belt pushes the intelligent transfer cabin onto the carrier platform of the transfer vehicle. The magnetic latches on the platform automatically close after detecting that the cabin is in place, thus completing the grabbing. The transmission carrier plans the indoor path from the connection point to the destination room, where the path cost function is defined as: ; in, The total cost of the path. The path's geometric length. The travel time is estimated based on real-time pedestrian density. The thermal integral value is the value of the path traversing a high-traffic area. , , Configurable weighting coefficients; The transmission carrier travels along the least-cost path and stops within one meter of the doorway of the destination room. During the journey, it continuously detects obstacles ahead using lidar and depth cameras, and dynamically adjusts the local path to avoid pedestrians or other moving objects.

[0012] As a preferred embodiment of the air-ground integrated smart logistics method for hospitals described in this invention, the step of automatically opening the transfer cabin door to complete delivery after arriving at the destination by verifying the authorized personnel information through identity recognition is as follows: After the transmission medium stops, the facial recognition camera is activated to capture facial images of the people in front of it; Simultaneously activate the RFID reader to scan the employee's work badge information; Input facial images into a pre-trained face recognition model and output the identity matching score; Query the hospital's permission database to obtain the set of authorized personnel for the current task. If the person corresponding to the employee badge information belongs to the authorized recipient set and the identity matching degree is greater than the preset recognition threshold, then the identity verification is deemed successful. The electric door of the intelligent transfer cabin is controlled to open, and stops when the opening angle reaches 90 degrees; Once the hatch is opened, a timer is started. If no materials are detected to have been removed from the hatch within the set waiting time, an abnormality alert is sent to the central control platform. If the supplies are detected to have been taken and the hatch is closed, a delivery completion record is generated and uploaded to the hospital information system, thus ending the logistics task. The decision function of the face recognition model is: ; in, The output is the identity matching score. For the input facial image, The feature vector extracted by the deep convolutional neural network. For the classification weight vector, For bias terms, Use the Sigmoid activation function; During the delivery process, the delivery confidence level is calculated using the following expression: ; Among them, the overall delivery confidence level is... For facial recognition matching accuracy, This is the result of the employee ID card access verification. For fusion weighting coefficients.

[0013] Secondly, the present invention provides an integrated air-ground smart logistics system for hospitals, comprising: Task parsing module, over-the-air access module, adaptive docking module, middleware scheduling module, indoor transmission module, and last-mile delivery module; The task parsing module is used to receive material delivery tasks issued by the hospital information system, parse the floor where the target department is located, and determine the corresponding target helipad as an air access node from the three-dimensional layered helipad network. The air access module is used to schedule the UAV carrying the intelligent transfer cabin to fly to the target helipad. During the approach, it achieves precise positioning through UWB and millimeter-wave radar, and uses visual sensors to identify guidance signs on the helipad to complete attitude calibration. The adaptive docking module is used to maintain docking stability through force feedback adjustment after the UAV lands and contacts the target landing pad, activate the electromagnetic adsorption mechanism to achieve physical locking, and transfer the intelligent transfer cabin to the conveying mechanism on the landing pad to complete the handover. The middleware scheduling module is used to call the intelligent logistics middleware to parse the delivery task after the handover is confirmed, and select the appropriate indoor transmission carrier according to the status of the logistics equipment on the floor where the destination room is located. The indoor transmission module is used to control the selected indoor transmission carrier to travel to the helipad docking port to receive the intelligent transfer cabin and transport it to the location of the destination room; The last-mile delivery module is used to automatically open the transfer cabin door to complete the delivery of materials after the materials arrive at the destination by verifying the information of authorized personnel through identity recognition, and generating a closed-loop traceability record.

[0014] Thirdly, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein when the computer program is executed by the processor, it implements any step of the air-ground integrated smart logistics method for hospitals as described in the first aspect of the present invention.

[0015] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the air-ground integrated smart hospital logistics method as described in the first aspect of the present invention.

[0016] The beneficial effects of this invention are as follows: By constructing a three-dimensional, layered helipad network, drones can directly reach the target floor on demand, breaking through the path redundancy bottleneck of traditional rooftop centralized reception and improving delivery efficiency. The adaptive docking mechanism, which combines vision, UWB, and millimeter-wave radar multi-source fusion positioning with force feedback adjustment and electromagnetic adsorption, effectively copes with complex urban weather and building micro-vibration interference, improving the reliability and security of aerial access. Through intelligent logistics middleware, protocol parsing and unified scheduling of heterogeneous in-hospital logistics systems are achieved, breaking down barriers between equipment manufacturers and ensuring seamless connection between air and ground transportation. Combined with an end-of-line delivery mechanism that integrates identity recognition and multimodal verification, the accurate and safe delivery of high-value materials and emergency supplies is ensured. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of the air-ground integrated smart logistics method for hospitals in Example 1.

[0019] Figure 2 This is a schematic diagram of the integrated air-ground hospital smart logistics system in Example 1.

[0020] Figure 3 This is a schematic diagram of the layout of the helipad in Example 2.

[0021] Figure 4 This is a side view of the helipad in Example 2.

[0022] In the diagram: 1. Wall; 2. Window frame; 3. Conveyor belt; 4. Conveyor roller; 5. Mounting component; 6. Built-in motor; 7. Delivery robot; 8. Corridor; 9. Elevator shaft; 10. Window. Detailed Implementation

[0023] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0024] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0025] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0026] Example 1, referring to Figure 1 and Figure 2 This is the first embodiment of the present invention, which provides an integrated air-ground smart logistics method for hospitals, including the following steps: S1. Receive material delivery tasks from the hospital information system, and determine the corresponding target helipad as an air access node from the three-dimensional layered helipad network deployed on the exterior of the hospital's high-rise public buildings, based on the floor of the target department specified in the task. Furthermore, it receives material delivery tasks from the hospital information system, the tasks including the name of the destination department and the target room number; Call the hospital building information model database to parse the physical floor number corresponding to the target room number; Query the preset three-dimensional layered helipad configuration table to determine whether there is an external helipad on this physical floor; If it exists, the helipad on the exterior facade of that floor will be defined as the target helipad for this mission. If it does not exist, find the floor in the configuration table that meets the requirement of being one floor higher and the closest configured helipad to the current floor, define the exterior helipad on that floor as the temporary target helipad, and mark it as needing to start the vertical transfer process inside the building; It should be noted that the deployment of the three-dimensional, layered helipad network is deeply integrated with the hospital building structure. Each exterior helipad is directly connected to the internal logistics system of each floor through a dedicated channel, avoiding the problem of secondary transfer by elevator or manual labor after the drones land on the top floor in the traditional solution. This achieves vertical direct access from the air to the target floor, improving the efficiency of emergency supplies delivery. At the same time, the configuration table supports dynamic updates and can be flexibly changed according to hospital function adjustments or temporary construction status to ensure the continuous adaptability of the system operation.

[0027] S2. The drone carrying the intelligent transfer cabin is dispatched to the target helipad. During the approach, the drone is positioned by UWB and millimeter-wave radar, and the attitude is calibrated by visual sensors to identify the guidance marks on the helipad. Furthermore, the central control platform sends flight mission instructions to the standby drones, the instructions including the geographical coordinates of the target landing pad and flight safety altitude parameters; After the drone takes off, it flies along a preset route. When it enters the radius R of the target landing pad, it activates the near-field guidance mode. UWB base station clusters perform high-precision positioning of the drone's current location and obtain its three-dimensional spatial coordinates; Millimeter-wave radar continuously scans the area beneath the drone, detecting dynamic obstacles and updating the local obstacle avoidance path; The drone switches to low-speed hovering mode, and the front-end binocular vision system acquires dynamic LED guide array images of the target helipad surface; The pixel coordinates of the center point of the guide array are extracted based on image processing algorithms and compared with the ideal alignment position; Calculate the two-dimensional offset and, in combination with the camera intrinsic parameters, deduce the horizontal and pitch angle deviations of the UAV relative to the helipad. Based on the angular deviation, a flight control correction is generated to adjust the rotor thrust distribution so that the UAV is aligned with the center area of ​​the target landing pad. It should be noted that the near-field guidance mode adopts a multi-sensor redundancy design. UWB provides sub-meter level coarse positioning for path pre-alignment, millimeter-wave radar can still stably perceive obstacles under complex weather conditions, and the binocular vision system achieves centimeter-level precise alignment. The three work together to form a full-stage perception closed loop from long-distance navigation to final landing, effectively overcoming the problems of airflow disturbance and signal blockage between urban buildings, and ensuring the safe and accurate landing of UAVs in high-density urban environments.

[0028] S3. After the UAV lands and touches the target helipad, the docking stability is maintained through force feedback adjustment, and the electromagnetic adsorption mechanism is activated to achieve physical locking. Then, the intelligent transfer cabin is transferred to the conveyor mechanism on the helipad to complete the handover. Furthermore, after the UAV completes attitude correction based on angular and spatial deviations, it slowly descends to the surface of the elastic buffer layer of the target landing pad in a uniform deceleration manner. The buffer layer integrates a six-dimensional force sensor to measure the normal force and tangential shear force at the moment of contact. If the tangential shear force exceeds the threshold of the product of the preset friction coefficient and the normal force, it is determined that there is a slippage tendency. The central control platform sends fine-tuning commands to the drone, which generates a counter-compensation torque by adjusting the rotor thrust difference to eliminate sideslip; After confirming stable contact, the electromagnetic adsorption array on the target landing pad surface is activated. Its magnetic induction intensity acts on the ferromagnetic material of the UAV base, generating an adsorption force, expressed as: ; in, For adsorption force, The magnetic induction intensity generated by the electromagnetic adsorption array. The effective contact area between the drone base and the landing pad. The material coupling coefficient; Once the adsorption force reaches the preset locking threshold, the drone release mechanism is triggered to unlock, smoothly transferring the smart transfer cabin to the horizontal conveyor belt built into the helipad. The conveyor belt starts, transporting the intelligent transfer cabin to the connection window inside the building, completing the physical handover between the air section and the ground section; It should be noted that the adaptive docking process achieves a technological leap from rigid locking to flexible active adaptation through the linkage control of force feedback and electromagnetic adsorption. The elastic buffer layer absorbs the initial impact energy, the six-dimensional force sensor monitors the contact state in real time, and the reverse thrust compensation eliminates the risk of sideslip. The electromagnetic adsorption provides a high-strength fixing force after stable contact. This mechanism not only improves the docking reliability, but also reduces the extreme dependence on the accuracy of the UAV's autonomous landing, and enhances the system's fault tolerance and engineering feasibility.

[0029] S4. After confirming the handover, the central control platform calls the intelligent logistics middleware to analyze the delivery task and selects the appropriate indoor transmission carrier based on the status of the logistics equipment on the floor where the destination room is located. Furthermore, the weight sensor at the docking window detects the smart transfer cabin entering the interior and generates a handover completion signal; The central control platform receives the handover completion signal and reads the task ID and material information from the RFID tag in the smart transfer cabin; Send the task ID and destination room number to the intelligent logistics middleware; The middleware queries the set of currently available indoor transmission devices on the target floor, where each device has operating status and type attributes; Select devices with an idle status from the device status set. If there is a device of type railcar, select the railcar as the transmission carrier first. If no available track vehicle is available, an idle AMR robot will be selected as the transport vehicle. Generate scheduling instructions compatible with the communication protocol of the selected transmission carrier and send them to its control terminal; During the equipment selection process, a priority scoring function is used for decision-making, the expression of which is: ; in, For equipment The rating value For its equipment type, For indicator functions, This is the normalized value of the current task queue length for this device. , where are weighting coefficients; It should be noted that the intelligent logistics middleware adopts a plug-in protocol adaptation architecture, with pre-installed communication driver modules for different brands and types of in-hospital logistics equipment. It can automatically identify the equipment type and load the corresponding protocol converter to achieve seamless issuance of scheduling instructions. The middleware supports plug-and-play equipment and dynamic status registration, which facilitates the hospital's later expansion of the logistics network and reduces system integration complexity and operation and maintenance costs.

[0030] S5. The selected indoor transport vehicle travels to the helipad docking port to receive the intelligent transfer cabin and transports it to the location of the destination room. Furthermore, after receiving the scheduling instruction, the selected transmission carrier activates its autonomous navigation system to plan the optimal path from its current location to the docking point. The platform travels along the path to the designated docking position at the connection point, aligning its support platform with the end of the conveyor belt. The mechanical positioning pin is inserted into the positioning hole of the transmission carrier platform; The conveyor belt pushes the intelligent transfer cabin onto the carrier platform of the transfer vehicle. The magnetic latches on the platform automatically close after detecting that the cabin is in place, thus completing the grabbing. The transmission carrier plans the indoor path from the connection point to the destination room, where the path cost function is defined as: ; in, The total cost of the path. The path's geometric length. The travel time is estimated based on real-time pedestrian density, and the thermal integral value is the value of the path traversing high-pedestrian areas. , , Configurable weighting coefficients; The transmission carrier travels along the least-cost path and stops within one meter of the doorway of the destination room. During the journey, it continuously detects obstacles ahead using lidar and depth cameras, and dynamically adjusts the local path to avoid pedestrians or other moving objects. It should be noted that the path planning in the indoor transmission process integrates static spatial topology and dynamic pedestrian flow information. The path cost function comprehensively considers distance, time, and passage safety, enabling the transmission carrier to actively avoid densely populated areas while ensuring efficiency and reducing interference with medical order. The fusion perception of lidar and depth camera further enhances local obstacle avoidance capabilities, ensuring stable operation in complex corridors, lobbies, and other scenarios, and improving the safety and stability of the overall transportation process.

[0031] S6. Upon arrival at the destination, the transfer cabin door is automatically opened to complete the delivery after the authorized personnel information is verified through identity recognition. Furthermore, after the transmission medium stops, the facial recognition camera is activated to capture facial images of the people in front of it; Simultaneously activate the RFID reader to scan the employee's work badge information; Input facial images into a pre-trained face recognition model and output the identity matching score; Query the hospital's permission database to obtain the set of authorized personnel for the current task. If the person corresponding to the employee badge information belongs to the authorized recipient set and the identity matching degree is greater than the preset recognition threshold, then the identity verification is deemed successful. The electric door of the intelligent transfer cabin is controlled to open, and stops when the opening angle reaches 90 degrees; Once the hatch is opened, a timer is started. If no materials are detected to have been removed from the hatch within the set waiting time, an abnormality alert is sent to the central control platform. If the supplies are detected to have been taken and the hatch is closed, a delivery completion record is generated and uploaded to the hospital information system, thus ending the logistics task. The decision function of the face recognition model is: ; in, The output is the identity matching score. For the input facial image, The feature vector extracted by the deep convolutional neural network. For the classification weight vector, For bias terms, Use the Sigmoid activation function; During the delivery process, the delivery confidence level is calculated using the following expression: ; in, To assess overall delivery confidence, For facial recognition matching accuracy, This is the result of the employee ID card access verification. For fusion weighting coefficients; It should be noted that the aforementioned end-of-line delivery mechanism employs dual verification of facial recognition and RFID work badges, combined with a delivery confidence model for comprehensive decision-making, effectively preventing the risks of identity theft and misdelivery. The delivery confidence level is determined by weighted fusion of biometric matching degree and authorization data consistency, setting dynamic thresholds to determine whether to open the hatch, thereby improving the security level of delivery of sensitive materials such as high-value medicines and blood products. The timed monitoring and anomaly alert mechanism further ensures the closed-loop operation and traceability in unattended scenarios.

[0032] This embodiment also provides an integrated air-ground smart logistics system for hospitals, including: Task parsing module, over-the-air access module, adaptive docking module, middleware scheduling module, indoor transmission module, and last-mile delivery module; The task parsing module is used to receive material delivery tasks issued by the hospital information system, parse the floor where the target department is located, and determine the corresponding target helipad as an air access node from the three-dimensional hierarchical helipad network. The air access module is used to schedule the UAV carrying the intelligent transfer cabin to fly to the target helipad. During the approach, it achieves precise positioning through UWB and millimeter-wave radar, and uses visual sensors to identify guidance marks on the helipad to complete attitude calibration. The adaptive docking module is used to maintain docking stability through force feedback adjustment after the UAV lands and contacts the target helipad, activate the electromagnetic adsorption mechanism to achieve physical locking, and transfer the intelligent transfer cabin to the conveyor mechanism on the helipad to complete the handover. The middleware scheduling module is used to call the intelligent logistics middleware to parse the delivery task after the handover is confirmed, and select the appropriate indoor transmission carrier according to the status of the logistics equipment on the floor where the destination room is located. The indoor transmission module is used to control the selected indoor transmission carrier to travel to the helipad docking port to receive the smart transfer cabin and transport it to the location of the destination room; The last-mile delivery module is used to automatically open the transfer cabin door to complete the delivery of materials after the materials arrive at the destination by verifying the information of authorized personnel through identity recognition, and generating a closed-loop traceability record.

[0033] This embodiment also provides a computer device applicable to the integrated air-ground hospital smart logistics method, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the integrated air-ground hospital smart logistics method proposed in the above embodiment.

[0034] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices 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 and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0035] This embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements the hospital smart logistics method for integrated air and ground operations as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0036] In summary, this invention enables UAVs to directly reach target floors on demand by constructing a three-dimensional, layered helipad network, breaking through the path redundancy bottleneck of traditional rooftop centralized reception and improving delivery efficiency. It employs an adaptive docking mechanism combining vision, UWB, and millimeter-wave radar multi-source fusion positioning with force feedback adjustment and electromagnetic adsorption, effectively addressing complex urban weather conditions and building micro-vibration interference, thus improving the reliability and security of aerial access. Through intelligent logistics middleware, it achieves protocol parsing and unified scheduling of heterogeneous in-hospital logistics systems, breaking down barriers between equipment manufacturers and ensuring seamless connection between air and ground transportation. Combined with an end-of-line delivery mechanism based on identity recognition and multimodal verification, it ensures the accurate and safe delivery of high-value materials and emergency supplies.

[0037] Example 2, refer to Figure 3 and Figure 4 This is a second embodiment of the present invention, which provides a helipad for an integrated air-ground hospital smart logistics system, comprising: 1. Wall, 2. Window frame, 3. Conveyor belt, 4. Conveyor roller, 5. Mounting component, 6. Built-in motor, 7. Delivery robot, 8. Corridor, 9. Elevator, and 10. Window.

[0038] The window frame 2 is fixedly embedded on one side of the exterior facade of the wall 1, forming the structural frame of the building's exterior window.

[0039] The window 10 is connected to the window frame 2 by a hinge and adopts a top-hung tilt-open structure, that is, the window 10 can be opened from the top and down. After opening, its inner surface forms a horizontal or near-horizontal support platform, which serves as a working surface for the temporary landing of drones and temporary storage of materials.

[0040] Furthermore, the design allows the window 10 to maintain the building's airtightness when closed, and transform into a functional helipad platform when open, without requiring additional external space.

[0041] On the platform formed by opening the window 10, mounting parts 5 are symmetrically arranged along its left and right edges. The mounting parts 5 are fixed to the inner surface of the window 10 and serve as the support base for the transmission mechanism.

[0042] Each mounting component 5 is equipped with a set of conveyor rollers 4. The axis of the conveyor rollers 4 is perpendicular to the opening direction of the window 10, and both ends are rotatably supported inside the mounting component 5 by bearings.

[0043] A circular conveyor belt 3 is tensioned and laid between the two sets of conveyor rollers 4. The upper surface of the conveyor belt 3 is flush with the window 10 platform to ensure that the intelligent transfer cabin is placed stably.

[0044] Inside the side frames of window 10, there are built-in motors 6.

[0045] The output shaft of each built-in motor 6 is connected to the corresponding conveyor roller 4 via a coupling or synchronous belt.

[0046] When the drone accurately deploys the intelligent transfer cabin carrying supplies onto the platform formed by the opening of window 10, the central control platform starts the built-in motors 6 on both sides, which synchronously drive the conveyor rollers 4 to rotate, thereby driving the conveyor belt 3 to run inward, smoothly transporting the intelligent transfer cabin from the window 10 platform to the indoor connection area.

[0047] A delivery robot 7 is located inside the window 10, directly opposite the end of the conveyor belt 3.

[0048] Delivery robot 7 is positioned at the beginning of corridor 8, with its top support platform at the same height as the end of conveyor belt 3, and it has automatic alignment and gripping functions. When the intelligent transfer cabin is pushed to the end by conveyor belt 3, delivery robot 7 identifies the positioning signal through position sensors, activates the magnetic latches or mechanical clamping devices on its platform, and firmly fixes the transfer cabin to its own support surface, completing the handover from the air segment to the ground segment.

[0049] Corridor 8 serves as the main indoor logistics corridor, connecting various departments and functional areas. After receiving the transfer cabin, delivery robot 7 autonomously navigates along corridor 8. If the destination room is located on another floor, delivery robot 7 enters the adjacent elevator lobby 9. Elevator lobby 9 is equipped with an intelligent elevator system that supports autonomous elevator calling and entry / exit for robots. After entering the elevator car, delivery robot 7 is transported by the elevator to the target floor, and then re-enters corridor 8 on the corresponding floor to continue to the door of the destination room to complete the delivery.

[0050] The entire system integrates the helipad and transport platform functions through the openable structure of window 10: window frame 2 provides structural support and motion guidance, window 10 serves as a dynamic working surface, built-in motor 6 drives transport roller 4 to drive conveyor belt 3 to complete cabin transfer, mounting component 5 ensures the stable installation of transmission components, wall 1 bears the overall load and connects indoor and outdoor spaces, delivery robot 7 performs transportation tasks in corridor 8 and can achieve cross-floor delivery through elevator 9; all structural components work together to form a compact, efficient, air-ground integrated smart logistics helipad system for hospitals that requires no additional external parking facilities.

[0051] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A smart hospital logistics method integrating air and ground transportation, characterized in that: include: Receive material delivery tasks from the hospital information system, and determine the corresponding target helipad as an air access node from the three-dimensional, layered helipad network deployed on the exterior of the hospital's high-rise public buildings, based on the floor of the target department specified in the task. The drone carrying the intelligent transfer cabin was dispatched to the target helipad. During the approach, it was located by UWB and millimeter-wave radar, and its attitude was calibrated by using visual sensors to identify the guidance marks on the helipad. After the drone lands and touches the target helipad, it maintains docking stability through force feedback adjustment and activates the electromagnetic adsorption mechanism to achieve physical locking. Then, the intelligent transfer cabin is transferred to the conveyor mechanism on the helipad to complete the handover. After the central control platform confirms the handover, it calls the intelligent logistics middleware to analyze the delivery task and selects the appropriate indoor transmission carrier based on the status of the logistics equipment on the floor where the destination room is located. The selected indoor transport vehicle travels to the helipad docking port to receive the intelligent transfer cabin and transports it to the destination room. Upon arrival at the destination, the system automatically opens the transfer cabin door to complete the delivery process after verifying the identity of authorized personnel.

2. The integrated air-ground hospital smart logistics method as described in claim 1, characterized in that: The specific steps for determining the corresponding target helipad as the air access node based on the floor of the target department specified in the task, from the three-dimensional, layered helipad network deployed on the exterior of the hospital's high-rise public buildings, are as follows: Receive material delivery tasks from the hospital information system, the tasks including the name of the destination department and the target room number; Call the hospital building information model database to parse the physical floor number corresponding to the target room number; Query the preset three-dimensional layered helipad configuration table to determine whether there is an external helipad on this physical floor; If it exists, then the exterior helipad of that floor will be defined as the target helipad for this mission. If it does not exist, find the floor in the configuration table that is one floor above the current floor and the closest configured helipad. Define the exterior helipad on that floor as the temporary target helipad and mark it as needing to start the vertical transfer process inside the building.

3. The integrated air-ground hospital smart logistics method as described in claim 2, characterized in that: The dispatching drone, carrying an intelligent transfer capsule, flies to the target helipad. During the approach, it achieves positioning via UWB and millimeter-wave radar, and uses visual sensors to identify guidance markings on the helipad to complete attitude calibration. The specific steps are as follows: The central control platform sends flight mission instructions to the standby drones, which include the geographical coordinates of the target landing pad and flight safety altitude parameters. After the drone takes off, it flies along a preset route. When it enters the radius R of the target landing pad, it activates the near-field guidance mode. UWB base station clusters perform high-precision positioning of the drone's current location and obtain its three-dimensional spatial coordinates; Millimeter-wave radar continuously scans the area beneath the drone, detecting dynamic obstacles and updating the local obstacle avoidance path; The drone switches to low-speed hovering mode, and the front-end binocular vision system acquires dynamic LED guide array images of the target helipad surface; The pixel coordinates of the center point of the guide array are extracted based on image processing algorithms and compared with the ideal alignment position; Calculate the two-dimensional offset and, in combination with the camera intrinsic parameters, deduce the horizontal and pitch angle deviations of the UAV relative to the helipad. Based on the angular deviation, a flight control correction is generated to adjust the rotor thrust distribution, so that the UAV is aligned with the center area of ​​the target landing pad.

4. The integrated air-ground hospital smart logistics method as described in claim 3, characterized in that: After the UAV lands and contacts the target helipad, force feedback is used to maintain docking stability, and an electromagnetic adsorption mechanism is activated to achieve physical locking. The intelligent transfer capsule is then transferred to the conveyor mechanism on the helipad to complete the handover. The specific steps are as follows: After completing attitude correction based on angular and spatial deviations, the UAV slowly descends to the surface of the elastic buffer layer of the target landing pad in a uniform deceleration manner. The buffer layer integrates a six-dimensional force sensor to measure the normal force and tangential shear force at the moment of contact. If the tangential shear force exceeds the threshold of the product of the preset friction coefficient and the normal force, it is determined that there is a slippage tendency. The central control platform sends fine-tuning commands to the drone, which generates a counter-compensation torque by adjusting the rotor thrust difference to eliminate sideslip; After confirming stable contact, the electromagnetic adsorption array on the target landing pad surface is activated. Its magnetic induction intensity acts on the ferromagnetic material of the UAV base, generating an adsorption force, expressed as: ; in, For adsorption force, The magnetic induction intensity generated by the electromagnetic adsorption array. The effective contact area between the drone base and the landing pad. The material coupling coefficient; Once the adsorption force reaches the preset locking threshold, the drone release mechanism is triggered to unlock, smoothly transferring the smart transfer cabin to the horizontal conveyor belt built into the helipad. The conveyor belt starts, transporting the intelligent transfer cabin to the connection window inside the building, completing the physical handover between the aerial section and the ground section.

5. The integrated air-ground hospital smart logistics method as described in claim 4, characterized in that: After confirming the handover, the central control platform calls the intelligent logistics middleware to analyze the delivery task and selects the appropriate indoor transmission medium based on the status of the logistics equipment on the floor where the destination room is located. The specific steps are as follows: The weight sensor at the docking window detected the smart transfer cabin entering the indoor side and generated a handover completion signal. The central control platform receives the handover completion signal and reads the task ID and material information from the RFID tag in the smart transfer cabin; Send the task ID and destination room number to the intelligent logistics middleware; The middleware queries the set of currently available indoor transmission devices on the target floor, where each device has operating status and type attributes; Select devices with an idle status from the device status set. If there is a device of type railcar, select the railcar as the transmission carrier first. If no available track vehicle is available, an idle AMR robot will be selected as the transport vehicle. Generate scheduling instructions compatible with the communication protocol of the selected transmission carrier and send them to its control terminal; During the equipment selection process, a priority scoring function is used for decision-making, the expression of which is: ； in, For equipment The rating value For its equipment type, For indicator functions, This is the normalized value of the current task queue length for this device. , These are the weighting coefficients.

6. The integrated air-ground hospital smart logistics method as described in claim 5, characterized in that: The selected indoor transport vehicle travels to the apron docking point to receive the intelligent transfer cabin and transports it to the destination room. The specific steps are as follows: After receiving the scheduling instruction, the selected transmission carrier starts the autonomous navigation system and plans the optimal path from the current location to the docking point; The platform travels along the path to the designated docking position at the connection point, aligning its support platform with the end of the conveyor belt. The mechanical positioning pin is inserted into the positioning hole of the transmission carrier platform; The conveyor belt pushes the intelligent transfer cabin onto the carrier platform of the transfer vehicle. The magnetic latches on the platform automatically close after detecting that the cabin is in place, thus completing the grabbing. The transmission carrier plans the indoor path from the connection point to the destination room, where the path cost function is defined as: ； in, The total cost of the path. The path's geometric length. The travel time is estimated based on real-time pedestrian density. The thermal integral value is the value of the path traversing a high-traffic area. , , Configurable weighting coefficients; The transmission carrier travels along the least-cost path and stops within one meter of the doorway of the destination room. During the journey, it continuously detects obstacles ahead using lidar and depth cameras, and dynamically adjusts the local path to avoid pedestrians or other moving objects.

7. The integrated air-ground hospital smart logistics method as described in claim 6, characterized in that: Upon arrival at the destination, the transfer cabin door is automatically opened to complete the delivery after verifying the authorized personnel's information through identity recognition. The specific steps are as follows: After the transmission medium stops, the facial recognition camera is activated to capture facial images of the people in front of it; Simultaneously activate the RFID reader to scan the employee's work badge information; Input facial images into a pre-trained face recognition model and output the identity matching score; Query the hospital's permission database to obtain the set of authorized personnel for the current task. If the person corresponding to the employee badge information belongs to the authorized recipient set and the identity matching degree is greater than the preset recognition threshold, then the identity verification is deemed successful. The electric door of the intelligent transfer cabin is controlled to open, and stops when the opening angle reaches 90 degrees; Once the hatch is opened, a timer is started. If no materials are detected to have been removed from the hatch within the set waiting time, an abnormality alert is sent to the central control platform. If the supplies are detected to have been taken and the hatch is closed, a delivery completion record is generated and uploaded to the hospital information system, thus ending the logistics task. The decision function of the face recognition model is: ； in, The output is the identity matching score. For the input facial image, The feature vector extracted by the deep convolutional neural network. For the classification weight vector, For bias terms, Use the Sigmoid activation function; During the delivery process, the delivery confidence level is calculated using the following expression: ; in, To assess overall delivery confidence, For facial recognition matching accuracy, This represents the employee ID card authorization verification result, and the fusion weight coefficient.

8. An integrated air-ground hospital smart logistics system, based on the integrated air-ground hospital smart logistics method according to any one of claims 1 to 7, characterized in that: include: Task parsing module, over-the-air access module, adaptive docking module, middleware scheduling module, indoor transmission module, and last-mile delivery module; The task parsing module is used to receive material delivery tasks issued by the hospital information system, parse the floor where the target department is located, and determine the corresponding target helipad as an air access node from the three-dimensional layered helipad network. The air access module is used to schedule the UAV carrying the intelligent transfer cabin to fly to the target helipad. During the approach, it achieves precise positioning through UWB and millimeter-wave radar, and uses visual sensors to identify guidance signs on the helipad to complete attitude calibration. The adaptive docking module is used to maintain docking stability through force feedback adjustment after the UAV lands and contacts the target landing pad, activate the electromagnetic adsorption mechanism to achieve physical locking, and transfer the intelligent transfer cabin to the conveying mechanism on the landing pad to complete the handover. The middleware scheduling module is used to call the intelligent logistics middleware to parse the delivery task after the handover is confirmed, and select the appropriate indoor transmission carrier according to the status of the logistics equipment on the floor where the destination room is located. The indoor transmission module is used to control the selected indoor transmission carrier to travel to the helipad docking port to receive the intelligent transfer cabin and transport it to the location of the destination room; The last-mile delivery module is used to automatically open the transfer cabin door to complete the delivery of materials after the materials arrive at the destination by verifying the information of authorized personnel through identity recognition, and generating a closed-loop traceability record.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the air-ground integrated smart logistics method for hospitals as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the air-ground integrated smart logistics method for hospitals as described in any one of claims 1 to 7.

Images