A dynamic cooperation-based inpatient nurse scheduling method and system

Abstract

This invention proposes a method and system for scheduling inpatient nurses based on dynamic collaboration. It constructs a task-item-bound mobile warehouse model, designs particle encoding and fitness functions to support dynamic collaboration, and introduces an adaptive learning mechanism to dynamically adjust model parameters. Combined with an environment simulator, it implements an intelligent execution strategy of "on-demand retrieval and minimal cart movement." This method can automatically generate scheduling schemes that encourage inter-nurse material relay and reduce ineffective cart movement, thereby improving nursing efficiency and resource utilization.

Description

Technical Field

[0001] This invention belongs to the field of intelligent medical resource scheduling technology, specifically relating to a method and system for scheduling inpatient nurses based on dynamic collaboration. Background Technology

[0002] Inpatient ward nurse scheduling is the core of optimizing the allocation of medical resources. Its scheduling efficiency is directly related to the quality of nursing services, the utilization rate of medical resources, and the workload of nurses. Existing scheduling methods generally bind treatment carts to nurses. Nurses must push their dedicated treatment carts throughout the entire process of performing all nursing tasks. Even if they only need to retrieve a small number of items, they cannot work independently without the treatment cart. This results in a large number of ineffective cart movements, which not only increases the physical exertion of nurses and the time cost of task execution, but also prevents the treatment carts and the nursing supplies they carry from being efficiently allocated and shared globally.

[0003] Meanwhile, the existing solution lacks an underlying design for real-time perception and dynamic adjustment, and cannot flexibly schedule tasks based on the real-time task status of the ward, the dynamic location of nurses, and the matching of their skills. When faced with scenarios such as changes in task priority, insertion of emergency tasks, and changes in nurse status, the adaptability and execution efficiency of the scheduling solution are greatly reduced, which can easily lead to problems such as task delays and resource mismatch, further exacerbating the waste of nursing resources. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention proposes a method and system for scheduling inpatient nurses based on dynamic collaboration. It employs an intelligent scheduling method that integrates a dynamic collaboration network, a multi-dimensional activation function, and an adaptive learning mechanism to achieve efficient utilization of nursing resources and a systematic improvement in nurses' collaborative abilities.

[0005] On the one hand, a method for scheduling inpatient nurses based on dynamic collaboration is provided, including: Based on the location information of nursing tasks and required items, a mobile warehouse model with task-item binding is constructed; A particle encoding and initialization mechanism supporting dynamic collaboration awareness is designed for nursing tasks to obtain an initial scheduling scheme for each nurse; each particle represents a complete task allocation and execution sequence scheme. A fitness function integrating a dynamic cooperative network and multi-dimensional incentives is constructed to evaluate the overall performance of the scheduling scheme; and the fitness function is adaptively updated by dynamically adjusting the weight coefficients in the fitness function through an improved particle swarm optimization iteration that integrates an adaptive learning mechanism. The particle scheme with the optimal fitness function value is selected, parsed into a specific sequence of nurse task instructions, and the final scheduling scheme for each nurse is obtained and sent to the nurse terminal for execution. During the simulated task execution, nurses first check the status of the global treatment cart. If the required item is on a nearby vehicle and the distance does not exceed a set threshold, they walk to retrieve the item without pushing the cart. If the distance exceeds the threshold, they decide whether to push the cart and combine it with the other vehicle or return to the treatment room to retrieve the item based on the vehicle's load.

[0006] Furthermore, the mobile warehouse model binds all items required for nursing tasks to a unique task identifier, and the items are stored in the treatment room, treatment cart, or on the nurse's person; once an item is placed in the treatment cart, it enters a globally accessible state, allowing other nurses to directly retrieve it when performing the corresponding task, without the original retriever's involvement.

[0007] Furthermore, the fitness function of the fusion dynamic cooperative network and multidimensional incentives is: ; in: The cost of the trolley is defined as the sum of the distances all nurse trolleys travel. The cost of returning to the warehouse is defined as the number of times the patient has to return to the treatment room due to not finding the shared item, multiplied by the distance of a single round trip. To calculate the benefits of collaboration, a multi-dimensional collaboration incentive function is used, including item value weight, distance decay weight, skill matching weight, and timeliness weight. This represents the system's tendency to reduce physical exertion and improve collaborative efficiency, with an initial sum of 1.

[0008] Furthermore, the multidimensional cooperative activation function The specific calculation method is as follows: ; in: This represents the set of all tasks that involve relay collaboration. Value of the item; Distance decay weights; The distance between the nurse and the vehicle containing the items; Indicates the attenuation coefficient; Weighting skills accordingly It's a score based on the difficulty level of the task. It is a score based on the nurse's competence; Timeliness weighting.

[0009] Furthermore, the dynamic collaboration network is structured as a graph, with nodes representing nurses. Edge weights are calculated based on historical collaboration frequency, task completion efficiency, and skill complementarity, and are updated before each fitness assessment.

[0010] Furthermore, the final scheduling scheme for nurses includes the task sequence for each nurse, vehicle pick-up and return nodes, and item transfer records, and supports visual display and real-time adjustment.

[0011] On the other hand, a dynamic collaborative inpatient nurse scheduling system is provided, including: Mobile Warehouse Modeling Module: Used to build a task-item-bound mobile warehouse model based on the location information of nursing tasks and required items; Particle Encoding and Initialization Module: Used to design a particle encoding and initialization mechanism that supports dynamic collaboration awareness for nursing tasks, resulting in an initial scheduling scheme for each nurse; where each particle represents a complete task allocation and execution sequence scheme; Fitness function module: used to construct a fitness function that integrates dynamic cooperative network and multi-dimensional incentives to evaluate the comprehensive performance of scheduling schemes; and through improved particle swarm optimization iteration with integrated adaptive learning mechanism, dynamically adjust the weight coefficients in the fitness function to adaptively update the fitness function; The optimal solution parsing module is used to select the particle solution with the optimal fitness function value, parse it into a specific nurse task instruction sequence, obtain the final scheduling plan for each nurse, and send it to the nurse terminal for execution. Simulated execution strategy module: When simulating task execution, it controls the nurse to first check the status of the global treatment cart. If the required item is on a nearby vehicle and the distance does not exceed a set threshold, the nurse will walk to retrieve the item without pushing the cart. If the distance exceeds the threshold, the nurse will decide whether to push the cart or return to the treatment room to retrieve the item based on the vehicle's load.

[0012] Furthermore, an electronic device is also provided, including: Memory, used for non-transitory storage of computer-readable instructions; and Processor, for executing the computer-readable instructions, When the computer-readable instructions are executed by the processor, they perform the method described in the first aspect above.

[0013] In another aspect, a storage medium is also provided for non-transitory storage of computer-readable instructions, wherein when the non-transitory computer-readable instructions are executed by a computer, the method described in the first aspect is performed.

[0014] In another aspect, a computer program product is also provided, including a computer program that, when run on one or more processors, is used to implement the method described in the first aspect above.

[0015] The above technical solution has the following advantages or beneficial effects: This invention discloses a method and system for scheduling inpatient nurses based on dynamic collaboration. It constructs a task-item-bound mobile warehouse model, designs particle encoding and fitness functions to support dynamic collaboration, and introduces an adaptive learning mechanism to dynamically adjust model parameters. Combined with an environment simulator, it implements an intelligent execution strategy of "on-demand retrieval and minimal cart movement." This method can automatically generate scheduling schemes that encourage material relay among nurses and reduce ineffective cart movement, improving nursing efficiency and resource utilization. It is particularly suitable for achieving efficient collaboration and dynamic scheduling among nursing tasks, nurses, and treatment carts under limited nursing resources through intelligent optimization algorithms. Attached Figure Description

[0016] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0017] Figure 1 This is a flowchart of a method for scheduling inpatient nurses based on dynamic collaboration, provided in Embodiment 1 of the present invention. Detailed Implementation

[0018] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0019] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments of the invention. The terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0020] In this embodiment of the invention, "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the description of this invention, "multiple" refers to two or more.

[0021] Furthermore, to facilitate a clear description of the technical solutions of the embodiments of the present invention, the terms "first" and "second" are used in the embodiments of the present invention to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and the terms "first" and "second" are not necessarily different.

[0022] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0023] All data acquisition in this embodiment is carried out in accordance with laws and regulations and with user consent, and the data is used legally.

[0024] Example 1 This embodiment provides a method for scheduling inpatient nurses based on dynamic collaboration, such as... Figure 1 As shown, it includes the following steps: Based on the location information of nursing tasks and required items, a mobile warehouse model with task-item binding is constructed; A particle encoding and initialization mechanism supporting dynamic collaboration awareness is designed for nursing tasks to obtain a scheduling scheme for each nurse; each particle represents a complete task allocation and execution sequence scheme. A fitness function integrating a dynamic cooperative network and multi-dimensional incentives is constructed to evaluate the overall performance of the scheduling scheme; and the fitness function is adaptively updated by dynamically adjusting the weight coefficients in the fitness function through an improved particle swarm optimization iteration that integrates an adaptive learning mechanism. The particle scheme with the optimal fitness function value is selected, parsed into a specific sequence of nurse task instructions, and the nurse scheduling scheme is obtained and sent to the nurse terminal for execution. During the simulated task execution, nurses first check the status of the global treatment cart. If the required item is on a nearby vehicle and the distance does not exceed a set threshold, they walk to retrieve the item without pushing the cart. If the distance exceeds the threshold, they decide whether to push the cart and combine it with the other vehicle or return to the treatment room to retrieve the item based on the vehicle's load.

[0025] S1: Based on the location information of nursing tasks and required items, construct a mobile warehouse model that binds tasks and items; The mobile warehouse model binds all items required for nursing tasks to a unique task identifier. Items can be stored in the treatment room, treatment cart, or on the nurse's person. Once an item is placed in the treatment cart, it becomes globally accessible, allowing other nurses to retrieve it directly when performing the corresponding task, without the original retriever's involvement.

[0026] In one embodiment, the unique identifier of an item is generated by combining the task ID and the bed number, in the form of: To ensure the precise binding of items with tasks and locations, here... This refers to a hash function that ensures that the item corresponding to each task is unique in the system.

[0027] S2: A particle encoding and initialization mechanism supporting dynamic collaboration awareness is designed for nursing tasks to obtain an initial scheduling scheme for each nurse; each particle represents a complete task allocation and execution sequence scheme. The particles are encoded as multi-dimensional vectors, with each element corresponding to the nurse ID assigned to the task. In the initialization phase, geographical affinity is introduced to guide the task allocation to nurses whose current location is closer to the bed, thereby accelerating the convergence of the algorithm.

[0028] The geographic affinity guidance calculates the Euclidean distance between the nurse's current location and each bed, and uses the softmax function to assign probabilities, ensuring the rationality of the initialization phase.

[0029] S3: Construct a fitness function that integrates a dynamic cooperative network and multi-dimensional incentives to evaluate the overall performance of the scheduling scheme; and dynamically adjust the weight coefficients in the fitness function through improved particle swarm optimization iteration with integrated adaptive learning mechanism to adaptively update the fitness function, specifically including: S31: Construct a fitness function that integrates a dynamic collaborative network and multi-dimensional incentives; The fitness function is used to evaluate the overall performance of a scheduling scheme, and its expression is:

[0030] in: The cost of the trolley is defined as the sum of the distances all nurse trolleys travel. The cost of returning to the warehouse is defined as the number of times the patient has to return to the treatment room due to not finding the shared item, multiplied by the distance of a single round trip. To calculate the benefits of collaboration, a multi-dimensional collaboration incentive function is used, including item value weight, distance decay weight, skill matching weight, and timeliness weight. This represents the system's inclination towards "reducing physical exertion" and "improving collaborative efficiency," with an initial sum of 1.

[0031] In one embodiment, a multidimensional cooperative activation function The specific calculation method is as follows:

[0032] in: This represents the set of all tasks that involve relay collaboration. The value of an item is determined by both the urgency and scarcity of the medicine, ranging from 1 to 5 points. Emergency medicines are worth far more than ordinary consumables. For distance decay weights, The distance between the nurse and the vehicle containing the items. This represents the attenuation coefficient, which determines how quickly the willingness to cooperate decreases as distance increases; Weighting skills accordingly It's a score based on the difficulty level of the task. This is a score based on the nurse's competence. The closer the two scores are, the smaller the denominator, and the closer the weight is to 1. The timeliness factor means that the closer a task is to its deadline, the higher the reward for collaboration, encouraging the prioritization of urgent tasks.

[0033] The dynamic collaboration network is built based on nurses’ real-time location, skill tags and historical collaboration data, and is used to prioritize combinations with high collaboration efficiency in fitness assessments.

[0034] In one embodiment, the dynamic collaboration network is structured as a graph, with nodes representing nurses. Edge weights are calculated based on historical collaboration frequency, task completion efficiency, and skill complementarity, and are updated before each fitness assessment.

[0035] S32: Perform improved particle swarm optimization (PSO) iterations with integrated adaptive learning mechanisms; During the PSO iteration process, the environment simulator is invoked each time the particle fitness is evaluated; after each iteration, the weight coefficients in the fitness function are dynamically adjusted based on historical scheduling performance. This enables the system to adaptively optimize the balance between cart costs, return costs, and collaborative benefits.

[0036] In one embodiment, the adaptive learning mechanism is specifically implemented as follows:

[0037]

[0038]

[0039] in This represents the deviation rate of each indicator relative to the historical baseline, used to dynamically adjust weights to adapt to the current scheduling environment. For example, if the push distance in the current round... Much higher than the historical average, then A positive result leads to the next round. Increase.

[0040] S4: Select the particle scheme with the optimal fitness function value, parse it into a specific nurse task instruction sequence, output the final nurse scheduling scheme, and send it to the nurse terminal for execution; During the simulated task execution, nurses first check the status of the global treatment cart. If the required item is on a nearby vehicle and the distance does not exceed a set threshold, they walk to retrieve the item without pushing the cart. If the distance exceeds the threshold, they decide whether to push the cart and combine it with the other vehicle or return to the treatment room to retrieve the item based on the vehicle's load.

[0041] Implement the "on-demand retrieval, minimum cart size" execution strategy in the environment simulator. The final scheduling scheme output includes the task sequence of each nurse, retrieval and return nodes, and item transfer records, and supports visualization and real-time adjustment.

[0042] The system supports real-time task insertion and priority adjustment, and can dynamically respond to changes in emergency tasks or nurse status during scheduling. All scheduling processes undergo multiple rounds of evaluation and optimization in a simulation environment to ensure that the output plan has high robustness and feasibility before actual execution.

[0043] In one embodiment, the distance threshold is dynamically set based on the ward layout and the average walking speed of nurses, with a value range of 3-10 meters.

[0044] Example 2 This embodiment provides a hospital nurse dispatching system based on dynamic collaboration, including: Mobile Warehouse Modeling Module: Used to build a task-item-bound mobile warehouse model based on the location information of nursing tasks and required items; Particle encoding and initialization module: Used to design a particle encoding and initialization mechanism that supports dynamic collaboration awareness for nursing tasks, resulting in a scheduling scheme for each nurse; where each particle represents a complete task allocation and execution sequence scheme; Fitness function module: used to construct a fitness function that integrates dynamic cooperative network and multi-dimensional incentives to evaluate the comprehensive performance of scheduling schemes; and through improved particle swarm optimization iteration with integrated adaptive learning mechanism, dynamically adjust the weight coefficients in the fitness function to adaptively update the fitness function; Optimal Solution Analysis Module: Used to select the particle solution with the optimal fitness function value, analyze it into a specific nurse task instruction sequence, and send it to the nurse terminal for execution; Simulated execution strategy module: When simulating task execution, it controls the nurse to first check the status of the global treatment cart. If the required item is on a nearby vehicle and the distance does not exceed a set threshold, the nurse will walk to retrieve the item without pushing the cart. If the distance exceeds the threshold, the nurse will decide whether to push the cart or return to the treatment room to retrieve the item based on the vehicle's load.

[0045] The descriptions of each embodiment in the above embodiments have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0046] The proposed system can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and the division of modules described above is only a logical functional division. In actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed.

[0047] Example 3 This embodiment also provides an electronic device, including: one or more processors, one or more memories, and one or more computer programs; wherein, the processor is connected to the memory, and the one or more computer programs are stored in the memory. When the electronic device is running, the processor executes the one or more computer programs stored in the memory to cause the electronic device to perform the method described in Embodiment 1.

[0048] It should be understood that in this embodiment, the processor can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0049] Memory may include read-only memory and random access memory, and provides instructions and data to the processor. A portion of memory may also include non-volatile random access memory. For example, memory may also store information about the device type.

[0050] In the implementation process, each step of the above method can be completed by the integrated logic circuits in the processor hardware or by software instructions.

[0051] The method in Embodiment 1 can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor. The software modules can reside in readily available storage media in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory; the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, a detailed description is not provided here.

[0052] Those skilled in the art will recognize that the units and algorithm steps described in connection with the various examples of this embodiment can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention.

[0053] Example 4 This embodiment also provides a computer-readable storage medium for storing computer instructions, which, when executed by a processor, complete the method described in Embodiment 1.

[0054] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for scheduling inpatient nurses based on dynamic collaboration, characterized in that, include: Based on the location information of nursing tasks and required items, a mobile warehouse model with task-item binding is constructed; A particle encoding and initialization mechanism supporting dynamic collaboration awareness is designed for nursing tasks to obtain an initial scheduling scheme for each nurse; each particle represents a complete task allocation and execution sequence scheme. A fitness function integrating a dynamic cooperative network and multi-dimensional incentives is constructed to evaluate the overall performance of the scheduling scheme; and the fitness function is adaptively updated by dynamically adjusting the weight coefficients in the fitness function through an improved particle swarm optimization iteration that integrates an adaptive learning mechanism. The particle scheme with the optimal fitness function value is selected, parsed into a specific sequence of nurse task instructions, and the final scheduling scheme for each nurse is obtained and sent to the nurse terminal for execution. During the simulated task execution, nurses first check the status of the global treatment cart. If the required item is on a nearby vehicle and the distance does not exceed a set threshold, they walk to retrieve the item without pushing the cart. If the distance exceeds the threshold, they decide whether to push the cart and combine it with the other vehicle or return to the treatment room to retrieve the item based on the vehicle's load.

2. The inpatient nurse scheduling method based on dynamic collaboration according to claim 1, characterized in that, The mobile warehouse model binds all items required for nursing tasks to a unique task identifier. Items are stored in the treatment room, treatment cart, or on the nurse's person. Once an item is placed in the treatment cart, it becomes globally accessible, allowing other nurses to retrieve it directly when performing the corresponding task, without the original retriever's involvement.

3. The inpatient nurse scheduling method based on dynamic collaboration according to claim 1, characterized in that, The fitness function of the integrated dynamic cooperative network and multidimensional incentives is: ; in: The cost of the trolley is defined as the sum of the distances all nurse trolleys travel. The cost of returning to the warehouse is defined as the number of times the patient has to return to the treatment room due to not finding the shared item, multiplied by the distance of a single round trip. To calculate the benefits of collaboration, a multi-dimensional collaboration incentive function is used, including item value weight, distance decay weight, skill matching weight, and timeliness weight. This represents the system's tendency to reduce physical exertion and improve collaborative efficiency, with an initial sum of 1.

4. The inpatient nurse scheduling method based on dynamic collaboration according to claim 3, characterized in that, The multidimensional cooperative activation function The specific calculation method is as follows: ; in: This represents the set of all tasks that involve relay collaboration. Value of the item; Distance decay weights; The distance between the nurse and the vehicle containing the items; Indicates the attenuation coefficient; Weighting skills accordingly It's a score based on the difficulty level of the task. It is a score based on the nurse's competence; Timeliness weighting.

5. The inpatient nurse scheduling method based on dynamic collaboration according to claim 1, characterized in that, The dynamic collaboration network is structured as a graph, with nodes representing nurses. Edge weights are calculated based on historical collaboration frequency, task completion efficiency, and skill complementarity, and are updated before each fitness assessment.

6. The inpatient nurse scheduling method based on dynamic collaboration according to claim 1, characterized in that, The final scheduling scheme for nurses includes each nurse's task sequence, vehicle pick-up and return nodes, and item delivery records, and supports visual display and real-time adjustment.

7. A hospital nurse dispatching system based on dynamic collaboration, characterized in that, include: Mobile Warehouse Modeling Module: Used to build a task-item-bound mobile warehouse model based on the location information of nursing tasks and required items; Particle Encoding and Initialization Module: Used to design a particle encoding and initialization mechanism that supports dynamic collaboration awareness for nursing tasks, resulting in an initial scheduling scheme for each nurse; where each particle represents a complete task allocation and execution sequence scheme; Fitness function module: used to construct a fitness function that integrates dynamic cooperative network and multi-dimensional incentives to evaluate the comprehensive performance of scheduling schemes; and through improved particle swarm optimization iteration with integrated adaptive learning mechanism, dynamically adjust the weight coefficients in the fitness function to adaptively update the fitness function; The optimal solution parsing module is used to select the particle solution with the optimal fitness function value, parse it into a specific nurse task instruction sequence, obtain the final scheduling plan for each nurse, and send it to the nurse terminal for execution. Simulated execution strategy module: When simulating task execution, it controls the nurse to first check the status of the global treatment cart. If the required item is on a nearby vehicle and the distance does not exceed a set threshold, the nurse will walk to retrieve the item without pushing the cart. If the distance exceeds the threshold, the nurse will decide whether to push the cart or return to the treatment room to retrieve the item based on the vehicle's load.

8. An electronic device, comprising: Memory is used to store computer-readable instructions in a non-transitory manner. as well as Processor, for executing the computer-readable instructions, When the computer-readable instructions are executed by the processor, they perform the inpatient nurse scheduling method based on dynamic collaboration as described in any one of claims 1-6.

9. A storage medium for non-transitory storage of computer-readable instructions, wherein, When a non-transitory computer-readable instruction is executed by a computer, the method for scheduling inpatient nurses based on dynamic collaboration as described in any one of claims 1-6 is performed.

10. A computer program product comprising a computer program, which, when run on one or more processors, implements the dynamic collaboration-based inpatient nurse scheduling method according to any one of claims 1-6.

Images