Intelligent order dispatching method, device and equipment for hospital logistics operation and maintenance, medium and product

Abstract

The invention discloses a hospital logistics operation and maintenance intelligent order dispatching method, device and equipment, a medium and a product, and relates to the technical field of positioning and big data analysis combination. The method comprises the following steps: firstly, receiving position state acquisition data from all hospital logistics operation and maintenance resource objects in real time, and then when a hospital logistics operation and maintenance work order from a hospital logistics management system is received, selecting M hospital logistics operation and maintenance resource objects of which the current states are to-be-distributed states according to the acquisition data, then the work order distribution scheme is optimized based on a genetic optimization algorithm by applying the work order position, the work order feature information, the current position of the object and the object feature information, the optimal work order distribution scheme with the highest fitness is obtained, and finally order distribution is completed according to the optimal work order distribution scheme. Therefore, intelligent allocation and accurate scheduling of hospital logistics operation and maintenance tasks can be realized, the management efficiency is remarkably improved, the resource allocation is optimized, and the timeliness, high efficiency and accuracy of logistics services are ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of the combination of positioning and big data analysis, and particularly relates to a smart dispatching method, device, equipment, medium and product for hospital logistics operation and maintenance. Background Art

[0002] With the rapid development of medical technology and the improvement of people's requirements for the quality of medical services, hospital operation and management are facing increasingly complex challenges. The expansion of hospital scale and the subdivision of departments have led to a sharp increase in the quantity and variety of medical equipment, and the technical content and precision of these equipment have reached a new height. At the same time, the hospital building layout has become more extensive and complex, involving numerous floors and functional areas, along with frequent and intensive human flow and logistics transportation.

[0003] In this context, the traditional hospital logistics operation and maintenance mode shows many deficiencies, mainly manifested in insufficient informatization, relying on manual operation and empirical judgment, slow information transmission and easy to make mistakes. For example, equipment fault reporting and repair often communicate by phone, resulting in possible deviations or delays in information recording and transmission, affecting the maintenance personnel's timely and accurate understanding of the fault situation and equipment location, prolonging the equipment downtime, and affecting the normal development of medical services. At the same time, in terms of resource allocation, due to the lack of accurate data support, blind allocation often occurs, resulting in overstocking and waste of materials or supply shortages, affecting the hospital operation efficiency. And because the information systems of each department are independent of each other, forming information silos, data is difficult to share and collaborate, making it difficult for the logistics operation and maintenance work to form an efficient overall force.

[0004] The rapid development of positioning technology and big data analysis technology provides new possibilities for solving the above problems, that is, through precise positioning technology, it is possible to track and locate the real-time positions of personnel or equipment in the hospital, providing accurate spatial information for operation and maintenance work; big data technology can deeply mine and analyze a large amount of logistics operation and maintenance data (such as equipment operation data, personnel work data, and material flow data, etc.). Therefore, how to combine positioning technology and big data analysis technology to provide a smart dispatching solution applied to hospital logistics operation and maintenance management, so as to realize the intelligent allocation and precise scheduling of hospital logistics operation and maintenance tasks, significantly improve management efficiency, optimize resource allocation, ensure the timeliness, efficiency and accuracy of logistics services, thereby strongly supporting the improvement of the overall medical service quality of the hospital and enhancing the core competitiveness of the hospital in the medical market competition is an urgent research topic for those skilled in the art. Summary of the Invention

[0005] The purpose of the present invention is to provide a smart dispatching method, device, computer equipment, computer-readable storage medium and computer program product for hospital logistics operation and maintenance, so as to solve the problems of blind allocation and low operation and maintenance work efficiency existing in the existing hospital logistics operation and maintenance management scheme in terms of dispatching.

[0006] To achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, a method for intelligent dispatching of hospital logistics operation and maintenance is provided, including:

[0008] Receiving in real time the location status acquisition data from all hospital logistics operation and maintenance resource objects, where the hospital logistics operation and maintenance resource objects refer to hospital logistics operation and maintenance personnel or hospital logistics operation and maintenance equipment, and the location status acquisition data includes the current location and current status of the corresponding objects;

[0009] When receiving hospital logistics operation and maintenance work orders from the hospital logistics management system, according to the location status acquisition data of all hospital logistics operation and maintenance resource objects, select M hospital logistics operation and maintenance resource objects whose current status is the to-be-assigned status from all hospital logistics operation and maintenance resource objects, where, represents a positive integer, and M represents a positive integer greater than or equal to ;

[0010] Applying the work order location and work order feature information of each hospital logistics operation and maintenance work order in the hospital logistics operation and maintenance work orders and the current location and object feature information of each hospital logistics operation and maintenance resource object in the M hospital logistics operation and maintenance resource objects, and based on the genetic optimization algorithm, optimize the work order allocation plan for allocating the hospital logistics operation and maintenance work orders to the M hospital logistics operation and maintenance resource objects to obtain an optimal work order allocation plan with the highest fitness, where the work order allocation plan is represented by an M-dimensional vector corresponding one-to-one to the M hospital logistics operation and maintenance resource objects. When any element in the M-dimensional vector is a zero value, it means that the hospital logistics operation and maintenance resource object corresponding to the any element is not assigned the hospital logistics operation and maintenance work order, and when any element in the M-dimensional vector is a positive integer, it means that the hospital logistics operation and maintenance resource object corresponding to the any element is assigned a certain hospital logistics operation and maintenance work order and the serial number of the certain hospital logistics operation and maintenance work order in the hospital logistics operation and maintenance work orders is the positive integer, and the fitness function is designed based on the work order processing duration dimension, the work order processing satisfaction dimension, and the resource utilization rate dimension during the work order processing;

[0011] According to the optimal work order allocation plan, dispatch each hospital logistics operation and maintenance work order to the hospital logistics operation and maintenance resource object corresponding to the vector element with the corresponding serial number.

[0012] Based on the above invention content, a new solution for intelligent dispatching of hospital logistics operation and maintenance by combining positioning technology with big data analysis technology is provided. That is, first, real-time receive the location status collection data from all hospital logistics operation and maintenance resource objects. Then, when receiving a hospital logistics operation and maintenance work order from the hospital logistics management system, select M hospital logistics operation and maintenance resource objects whose current status is to be assigned based on the collection data. Then, apply the work order location and work order feature information, as well as the current location and object feature information of the object, and optimize the work order allocation plan based on the genetic optimization algorithm to obtain the optimal work order allocation plan with the highest fitness. Finally, complete the dispatching according to the optimal work order allocation plan. In this way, the intelligent allocation and precise scheduling of hospital logistics operation and maintenance tasks can be realized, significantly improving the management efficiency, optimizing the resource allocation, ensuring the timeliness, efficiency and precision of logistics services, thus strongly supporting the improvement of the overall medical service quality of the hospital, enhancing the core competitiveness of the hospital in the medical market competition, and facilitating practical application and promotion.

[0013] In a possible design, the work order feature information includes work order type, urgency level, and / or complexity level;

[0014] And / or, the object feature information includes operation and maintenance skill level, historical processing duration of various work orders, historical service scores of various work orders, workload within the current assessment period, and / or the value of the order assignment uniformity index within the current assessment period.

[0015] In a possible design, apply the work order location and work order feature information of each hospital logistics operation and maintenance work order in the hospital logistics operation and maintenance work orders, and the current location and object feature information of each hospital logistics operation and maintenance resource object in the M hospital logistics operation and maintenance resource objects, and optimize the work order allocation plan for allocating the hospital logistics operation and maintenance work orders to the M hospital logistics operation and maintenance resource objects based on the genetic optimization algorithm to obtain the optimal work order allocation plan with the highest fitness, including the following steps S31 - S35:

[0016] S31. Initialize the genetic optimization algorithm with algorithm parameters including population size N and maximum number of iterations T max and initialize the current number of iterations T = 0, then execute step S32;

[0017] S32. Randomly generate, respectively, in line with the constraints of the allocation plan and used for allocating the N work order assignment plans for assigning a hospital logistics operation and maintenance work order to the M hospital logistics operation and maintenance resource objects, and using the N work order assignment plans as N individuals one by one to form an initial population, and then performing step S33, where the work order assignment plan is represented by an M-dimensional vector corresponding one by one to the M hospital logistics operation and maintenance resource objects. When any element in the M-dimensional vector is a zero value, it means that the hospital logistics operation and maintenance resource object corresponding to the any element is not assigned the hospital logistics operation and maintenance work order. When any element in the M-dimensional vector is a positive integer, it means that the hospital logistics operation and maintenance resource object corresponding to the any element is assigned a certain hospital logistics operation and maintenance work order, and the serial number of the certain hospital logistics operation and maintenance work order in the N hospital logistics operation and maintenance work orders is the positive integer. The assignment plan constraint conditions are as follows: each element in the M-dimensional vector belongs to the interval [0, M] and any two elements in the M-dimensional vector are not equal;

[0018] S33. For each individual in the current population, apply the work order positions and work order characteristic information of each hospital logistics operation and maintenance work order in the N hospital logistics operation and maintenance work orders and the current positions and object characteristic information of each hospital logistics operation and maintenance resource object in the M hospital logistics operation and maintenance resource objects, and calculate the corresponding fitness based on the artificial intelligence algorithm, and then perform step S34, where the fitness function is designed based on the work order processing duration dimension, the work order processing satisfaction dimension, and the resource utilization rate dimension in the work order processing process;

[0019] S34. Determine whether the current iteration number T has reached the maximum iteration number T max max. If so, select the individual corresponding to the highest fitness from the current population as the optimal work order assignment plan. Otherwise, increment the current iteration number T by 1, and then perform step S35;

[0020] S35. According to each individual and the fitness of each individual, through the selection operation, crossover operation, and mutation operation in the genetic optimization algorithm, obtain N new individuals that meet the assignment plan constraint conditions to form a new population, and then return to perform step S33.

[0021] In a possible design, for each individual in the current population, apply the work order positions and work order characteristic information of each hospital logistics operation and maintenance work order in the N hospital logistics operation and maintenance work orders and the current positions and object characteristic information of each hospital logistics operation and maintenance resource object in the M hospital logistics operation and maintenance resource objects, and calculate the corresponding fitness based on the artificial intelligence algorithm, including:

[0022] For a certain individual in the current population, applying the work order positions and work order characteristic information of each hospital logistics operation and maintenance work order among the hospital logistics operation and maintenance work orders, and the current locations and object characteristic information of each hospital logistics operation and maintenance resource object among the M hospital logistics operation and maintenance resource objects, calculating, based on an artificial intelligence algorithm, respective work order processing duration prediction values, respective work order processing satisfaction prediction values, and respective resource utilization prediction values during the work order processing that correspond one-to-one to each element in the corresponding individual;

[0023] Calculating the fitness F of the certain individual according to the following formula:

[0024]

[0025] In the formula, m represents a positive integer less than or equal to M, w 1 represents a preset weight coefficient in the dimension of work order processing duration, w 2 represents a preset weight coefficient in the dimension of work order processing satisfaction, w 3 represents a preset weight coefficient in the dimension of resource utilization, t m represents the work order processing duration prediction value corresponding to the m-th element in the certain individual, p m represents the work order processing satisfaction prediction value corresponding to the m-th element in the certain individual, η m represents the resource utilization prediction value corresponding to the m-th element in the certain individual.

[0026] In a possible design, for a certain individual in the current population, applying the work order positions and work order characteristic information of each hospital logistics operation and maintenance work order among the hospital logistics operation and maintenance work orders, and the current locations and object characteristic information of each hospital logistics operation and maintenance resource object among the M hospital logistics operation and maintenance resource objects, calculating, based on an artificial intelligence algorithm, respective work order processing duration prediction values, respective work order processing satisfaction prediction values, and respective resource utilization prediction values during the work order processing that correspond one-to-one to each element in the corresponding individual, including:

[0027] For a certain individual in the current population, reading each element in the corresponding individual;

[0028] For an element in a certain individual, if the corresponding element is zero, directly obtain that the predicted value of the work order processing duration corresponding to it is infinite, the predicted value of the work order processing satisfaction corresponding to it is zero, and the predicted value of the resource utilization rate corresponding to it is infinite; otherwise, obtain the shortest path length corresponding and between the current location of the hospital logistics operation and maintenance resource object corresponding to the corresponding element and the work order location of the hospital logistics operation and maintenance work order with the corresponding element as the serial number.

[0029] Import the shortest path length corresponding to the certain element, the operation and maintenance skill level in the object feature information of the hospital logistics operation and maintenance resource object corresponding to the certain element, the historical processing duration of similar work orders, and the work order type and emergency level in the work order feature information of the hospital logistics operation and maintenance work order with the serial number of the certain element into the work order processing duration prediction model pre-trained based on the first artificial intelligence algorithm, and output the predicted value of the work order processing duration corresponding to the certain element, where the similar work orders refer to the work orders with the work order type in the work order feature information of the hospital logistics operation and maintenance work order with the serial number of the certain element.

[0030] Import the predicted value of the work order processing duration corresponding to the certain element, the historical service score of the similar work orders in the object feature information of the hospital logistics operation and maintenance resource object corresponding to the certain element, and the complexity level in the work order feature information of the hospital logistics operation and maintenance work order with the serial number of the certain element into the work order processing satisfaction prediction model pre-trained based on the second artificial intelligence algorithm, and output the predicted value of the work order processing satisfaction corresponding to the certain element.

[0031] Import the workload within the current assessment period and the value of the order distribution uniformity index within the current assessment period in the object feature information of the hospital logistics operation and maintenance resource object corresponding to the certain element, and the work order type in the work order feature information of the hospital logistics operation and maintenance work order with the serial number of the certain element into the resource utilization rate prediction model pre-trained based on the third artificial intelligence algorithm, and output the predicted value of the resource utilization rate corresponding to the certain element.

[0032] In a possible design, after the respective hospital logistics operation and maintenance work orders are respectively dispatched to the hospital logistics operation and maintenance resource objects corresponding to the vector elements with the corresponding serial numbers, the method further includes:

[0033] Adjust the function design of the fitness and / or the algorithm parameters of the genetic optimization algorithm according to the processing result feedback data of the respective hospital logistics operation and maintenance work orders.

[0034] In a second aspect, a smart dispatching device for hospital logistics operation and maintenance is provided, including a data collection and reception unit, a resource object selection unit, a distribution plan optimization unit, and a work order dispatching and execution unit;

[0035] The data collection and reception unit is configured to receive in real time the location status collection data from all hospital logistics operation and maintenance resource objects, where the hospital logistics operation and maintenance resource objects refer to hospital logistics operation and maintenance personnel or hospital logistics operation and maintenance equipment, and the location status collection data includes the current location and current status of the corresponding object;

[0036] The resource object selection unit is communicatively connected to the data collection and reception unit and is used to, when receiving hospital logistics operation and maintenance work orders from the hospital logistics management system, select M hospital logistics operation and maintenance resource objects whose current status is the to-be-assigned status from all the hospital logistics operation and maintenance resource objects according to the location status collection data of all the hospital logistics operation and maintenance resource objects, where represents a positive integer, and M represents a positive integer greater than or equal to ;

[0037] The distribution plan optimization unit is communicatively connected to the data collection and reception unit and the resource object selection unit respectively, and is used to apply the work order location and work order feature information of each hospital logistics operation and maintenance work order in the hospital logistics operation and maintenance work orders and the current location and object feature information of each hospital logistics operation and maintenance resource object in the M hospital logistics operation and maintenance resource objects, and optimize the work order distribution plan for assigning the hospital logistics operation and maintenance work orders to the M hospital logistics operation and maintenance resource objects based on the genetic optimization algorithm to obtain an optimal work order distribution plan with the highest fitness. The work order distribution plan is represented by an M-dimensional vector corresponding one-to-one to the M hospital logistics operation and maintenance resource objects. When any element in the M-dimensional vector is a zero value, it means that the hospital logistics operation and maintenance resource object corresponding to the any element is not assigned the hospital logistics operation and maintenance work order, and when any element in the M-dimensional vector is a positive integer, it means that the hospital logistics operation and maintenance resource object corresponding to the any element is assigned a certain hospital logistics operation and maintenance work order, and the serial number of the certain hospital logistics operation and maintenance work order in the hospital logistics operation and maintenance work orders is the positive integer. The fitness function is designed based on the work order processing duration dimension, the work order processing satisfaction dimension, and the resource utilization rate dimension during the work order processing;

[0038] The work order dispatching execution unit, communicatively connected to the allocation scheme optimization unit, is configured to dispatch each hospital logistics operation and maintenance work order to the hospital logistics operation and maintenance resource object corresponding to the vector element with the corresponding serial number according to the optimal work order allocation scheme.

[0039] In a third aspect, the present invention provides a computer device, including a memory, a processor, and a transceiver communicatively connected in sequence. Among them, the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the hospital logistics operation and maintenance intelligent dispatching method described in the first aspect or any possible design in the first aspect.

[0040] In a fourth aspect, the present invention provides a computer-readable storage medium, on which instructions are stored. When the instructions run on a computer, the hospital logistics operation and maintenance intelligent dispatching method described in the first aspect or any possible design in the first aspect is executed.

[0041] In a fifth aspect, the present invention provides a computer program product, including a computer program or instructions. When the computer program or the instructions are executed by a computer, the hospital logistics operation and maintenance intelligent dispatching method described in the first aspect or any possible design in the first aspect is implemented.

[0042] Beneficial effects of the above solution:

[0043] (1) The present invention creatively provides a new solution for intelligent dispatching of hospital logistics operation and maintenance by combining positioning technology and big data analysis technology. That is, first, the position status collection data from all hospital logistics operation and maintenance resource objects is received in real time. Then, when receiving a hospital logistics operation and maintenance work order from the hospital logistics management system, M hospital logistics operation and maintenance resource objects with the current status of pending order distribution are selected according to the collection data. Then, the work order location, work order feature information, the current location of the object, and the object feature information are used to optimize the work order allocation scheme based on the genetic optimization algorithm to obtain the optimal work order allocation scheme with the highest fitness. Finally, the dispatching is completed according to the optimal work order allocation scheme. In this way, the intelligent allocation and precise scheduling of hospital logistics operation and maintenance tasks can be realized, significantly improving the management efficiency, optimizing the resource configuration, ensuring the timeliness, efficiency, and precision of logistics services, thus strongly supporting the improvement of the overall medical service quality of the hospital, enhancing the core competitiveness of the hospital in the medical market competition, and facilitating practical application and promotion;

[0044] (2) It can ensure that work orders can be quickly and accurately assigned to the operation and maintenance resource objects that are geographically closest and have the best skill match. As a result, it not only improves the response speed and service quality of hospital logistics operation and maintenance, but also reduces the operating costs, enhances the competitiveness of the hospital in the medical market, and realizes the all-round and full-process efficient management and collaborative operation of hospital logistics operation and maintenance. Description of the Drawings

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0046] Figure 1 It is a flowchart showing the method for intelligent work order dispatching in hospital logistics operation and maintenance provided by an embodiment of the present application.

[0047] Figure 2 It is a flowchart showing the optimization of the work order assignment scheme in the method for intelligent work order dispatching in hospital logistics operation and maintenance provided by an embodiment of the present application.

[0048] Figure 3 It is a flowchart showing the prediction of work order processing duration, the prediction of work order processing satisfaction, and the prediction of resource utilization rate in the method for intelligent work order dispatching in hospital logistics operation and maintenance provided by an embodiment of the present application.

[0049] Figure 4 It is a schematic structural diagram of the intelligent work order dispatching device for hospital logistics operation and maintenance provided by an embodiment of the present application.

[0050] Figure 5 It is a schematic structural diagram of the computer device provided by an embodiment of the present application. Detailed Embodiments

[0051] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will introduce the present invention in combination with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structure of the drawings is only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other embodiments can be obtained based on these embodiments. It should be noted here that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation to the present invention.

[0052] It should be understood that although terms such as first and second may be used herein to describe various objects, these objects should not be limited by these terms. These terms are only used to distinguish one object from another. For example, the first object may be referred to as the second object, and similarly, the second object may be referred to as the first object, without departing from the scope of the exemplary embodiments of the present invention.

[0053] It should be understood that for the term "and / or" that may appear herein, it is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, B exists alone, or A and B exist simultaneously; for another example, A, B, and / or C may represent any one of A, B, and C or any combination of them; for the term " / and" that may appear herein, it is a description of another association object relationship, indicating that two relationships may exist. For example, A / and B may represent two situations: A exists alone or A and B exist simultaneously; in addition, for the character " / " that may appear herein, generally, it represents an "or" relationship between the associated objects before and after.

[0054] Embodiment

[0055] As Figures 1 to 3 shown, the hospital logistics operation and maintenance intelligent dispatching method provided in the first aspect of this embodiment can be, but is not limited to, executed by a computer device with certain computing resources, such as a cloud server, a personal computer (Personal Computer, PC, referring to a multi-purpose computer suitable for personal use in terms of size, price, and performance; desktop computers, laptop computers, small laptop computers, tablet computers, and ultrabooks, etc. all belong to personal computers), a smart phone, a personal digital assistant (Personal Digital Assistant, PDA), or a wearable device and other electronic devices. As Figure 1 shown, the hospital logistics operation and maintenance intelligent dispatching method can be, but is not limited to, including the following steps S1 to S4.

[0056] S1. Real-time receive the location status collection data from all hospital logistics operation and maintenance resource objects, where the hospital logistics operation and maintenance resource objects refer to hospital logistics operation and maintenance personnel or hospital logistics operation and maintenance equipment, and the location status collection data includes, but is not limited to, the current location and current status of the corresponding objects, etc.

[0057] In the step S1, the current location of the hospital logistics operation and maintenance resource object can be obtained by regular collection and upload of a bound wireless positioning system, and is not limited thereto. For example, a GPS (Global Positioning System) satellite positioning module and a wireless data transmission module connected by communication can be built into the work permit of hospital logistics operation and maintenance personnel. Among them, the GPS satellite positioning module is used to collect and obtain the current location of the hospital logistics operation and maintenance personnel in real time, and the wireless data transmission module is used to report the current location to the local computer device; the specific collection method of the current location of the hospital logistics operation and maintenance equipment is similar, and will not be elaborated here. The current status of the hospital logistics operation and maintenance resource object can be obtained by regular collection and upload of a bound status collection system, and is not limited thereto. For example, a working status collection module and a wireless data transmission module connected by communication can be built into the hospital logistics operation and maintenance equipment. Among them, the working status collection module is used to collect and obtain the current working status of the hospital logistics operation and maintenance equipment in real time (such as busy status, idle status, or fault status, etc.), and the wireless data transmission module is used to report the current working status to the local computer device; the specific collection method of the current status of the hospital logistics operation and maintenance personnel (such as busy status, idle status, or leave status, etc.) is similar, and will not be elaborated here. In addition, the hospital logistics operation and maintenance equipment specifically includes, but is not limited to, chillers, cooling pumps, air conditioners, floor cleaning robots, and / or intelligent material handling vehicles, etc.

[0058] S2. When receiving hospital logistics operation and maintenance work orders from the hospital logistics management system, according to the location status collection data of all hospital logistics operation and maintenance resource objects, select M hospital logistics operation and maintenance resource objects whose current status is the to-be-assigned status from all hospital logistics operation and maintenance resource objects, where represents a positive integer, and M represents a positive integer greater than or equal to .

[0059] In the step S2, the hospital logistics management system is an existing system, and the specific generation method of the hospital logistics operation and maintenance work order is an existing conventional automatic generation method, which will not be elaborated here. The to-be-assigned status specifically includes, but is not limited to, the idle status, etc., indicating that the corresponding object can receive orders at any time. In addition, since the delivery relationship between the hospital logistics operation and maintenance work order and the hospital logistics operation and maintenance resource object is one-to-one, M must be greater than or equal to to avoid the situation that there are excess work orders that cannot be delivered.

[0060] S3. Apply in the The work order positions and work order feature information of each hospital logistics operation and maintenance work order, and the current locations and object feature information of each hospital logistics operation and maintenance resource object among the M hospital logistics operation and maintenance resource objects. Based on the genetic optimization algorithm, optimize the work order allocation plan for allocating the hospital logistics operation and maintenance work orders to the M hospital logistics operation and maintenance resource objects to obtain an optimal work order allocation plan with the highest fitness. Among them, the work order allocation plan is represented by an M-dimensional vector corresponding one-to-one to the M hospital logistics operation and maintenance resource objects. When any element in the M-dimensional vector is a zero value, it means that the hospital logistics operation and maintenance resource object corresponding to the any element is not assigned the hospital logistics operation and maintenance work order. When any element in the M-dimensional vector is a positive integer, it means that the hospital logistics operation and maintenance resource object corresponding to the any element is assigned a certain hospital logistics operation and maintenance work order, and the serial number of the certain hospital logistics operation and maintenance work order among the hospital logistics operation and maintenance work orders is the positive integer. The fitness function is designed based on the dimensions of work order processing duration, work order processing satisfaction, and resource utilization rate during work order processing.

[0061] In the step S3, specifically, the work order feature information includes but is not limited to work order type, urgency level, and / or complexity level, etc.; the work order location is used to reflect the information of the required execution place of the corresponding operation and maintenance task, and it can be carried in the hospital logistics operation and maintenance work order together with the work order feature information. The object feature information specifically includes but is not limited to operation and maintenance skill level, historical processing duration of various work orders, historical service scores of various work orders, workload within the current assessment period, and / or the value of the order distribution uniformity index within the current assessment period, etc. Among them, the historical processing duration and historical service scores of the foregoing various work orders can be obtained by regular statistics based on the historical operation and maintenance data of the corresponding objects; the foregoing assessment period can be but is not limited to the current day, current week, or current month, etc.; the foregoing workload is used to reflect the current and historical workloads, and can be but is not limited to being regularly quantified based on the order assignment volume and / or the total work order processing duration within the current assessment period (that is, the larger the order assignment volume and / or the longer the total work order processing duration, the higher the workload, and vice versa); the foregoing value of the order distribution uniformity index is used to reflect whether the past work orders are evenly distributed, and can be but is not limited to being regularly quantified based on the difference between the order assignment volume within the current assessment period and the average order assignment volume of all objects and / or the difference between the total work order processing duration and the average total work order processing duration of all objects (that is, the larger the difference, the higher the value of the order distribution uniformity index, and vice versa). The Genetic Algorithm (GA) is an optimization algorithm that simulates natural selection and genetic mechanisms, that is, it solves optimization problems by simulating inheritance and variation in the process of biological evolution. Its basic idea is to use genetic operations such as Selection, Crossover, and Mutation to search for the optimal solution. To achieve the purpose of quickly optimizing the work order assignment plan based on the genetic optimization algorithm, preferably, as Figure 2 shown, applying the work order location and work order feature information of each hospital logistics operation and maintenance work order in the hospital logistics operation and maintenance work orders and the current location and object feature information of each hospital logistics operation and maintenance resource object in the M hospital logistics operation and maintenance resource objects, optimizing the work order assignment plan for assigning the hospital logistics operation and maintenance work orders to the M hospital logistics operation and maintenance resource objects based on the genetic optimization algorithm, and obtaining the optimal work order assignment plan with the highest fitness, including but not limited to the following steps S31 to S35.

[0062] S31. Initialize the genetic optimization algorithm and include algorithm parameters such as population size N and maximum number of iterations T max and initialize the current number of iterations T = 0, and then execute step S32.

[0063] S32. Randomly generate N work order allocation schemes that respectively meet the constraints of the allocation scheme and are used to allocate the hospital logistics operation and maintenance work orders to the M hospital logistics operation and maintenance resource objects, and use the N work order allocation schemes as N individuals one by one to form an initial population, and then execute step S33. Among them, the work order allocation scheme is represented by an M-dimensional vector corresponding one by one to the M hospital logistics operation and maintenance resource objects. When any element in the M-dimensional vector is a zero value, it means that the hospital logistics operation and maintenance resource object corresponding to the any element is not allocated with the hospital logistics operation and maintenance work order. When any element in the M-dimensional vector is a positive integer, it means that the hospital logistics operation and maintenance resource object corresponding to the any element is allocated with a certain hospital logistics operation and maintenance work order, and the serial number of the certain hospital logistics operation and maintenance work order in the hospital logistics operation and maintenance work orders is the positive integer. The constraints of the allocation scheme are as follows: each element in the M-dimensional vector belongs to the interval [0, M], and any two elements in the M-dimensional vector are not equal.

[0064] In step S32, for example, if M takes the value of 7, and takes the value of 5, then the M-dimensional vector specifically [0, 0, 1, 2, 3, 4, 5] can be used as a work order allocation scheme that meets the constraints of the allocation scheme: for the first two of the M hospital logistics operation and maintenance resource objects, no work order is dispatched. The hospital logistics operation and maintenance work order with serial number 1 is dispatched to the third hospital logistics operation and maintenance resource object among the M hospital logistics operation and maintenance resource objects. The hospital logistics operation and maintenance work order with serial number 2 is dispatched to the fourth hospital logistics operation and maintenance resource object among the M hospital logistics operation and maintenance resource objects. The hospital logistics operation and maintenance work order with serial number 3 is dispatched to the fifth hospital logistics operation and maintenance resource object among the M hospital logistics operation and maintenance resource objects. The hospital logistics operation and maintenance work order with serial number 4 is dispatched to the sixth hospital logistics operation and maintenance resource object among the M hospital logistics operation and maintenance resource objects. The hospital logistics operation and maintenance work order with serial number 5 is dispatched to the seventh hospital logistics operation and maintenance resource object among the M hospital logistics operation and maintenance resource objects. And M-dimensional vectors specifically [0, 0, 1, 2, 8, 4, 5] or [0, 0, 1, 2, 4, 4, 5] etc. cannot be used as work order allocation schemes that meet the constraints of the allocation scheme.

[0065] S33. For each individual in the current population, apply the The work order positions and work order feature information of each hospital logistics operation and maintenance work order in the hospital logistics operation and maintenance work orders, and the current locations and object feature information of each hospital logistics operation and maintenance resource object in the M hospital logistics operation and maintenance resource objects are used to calculate the corresponding fitness based on an artificial intelligence algorithm, and then step S34 is executed. Among them, the function of the fitness is designed based on the dimensions of work order processing duration, work order processing satisfaction, and resource utilization rate during the work order processing process.

[0066] In step S33, the artificial intelligence algorithm is a core algorithm that specifically studies how a computer simulates or implements human learning behaviors to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve its own performance. It is the fundamental way to make a computer intelligent. Specifically, the artificial intelligence algorithm can, but is not limited to, adopt machine learning algorithms based on support vector machines, stochastic gradient descent methods, multivariable linear regression, multi-layer perceptrons, decision trees, backpropagation neural networks, or radial basis function networks, etc. The fitness is used to comprehensively reflect the effectiveness and efficiency of the work order dispatching scheme. The reasons and details for the function design based on the dimensions of work order processing duration, work order processing satisfaction, and resource utilization rate are as follows:

[0067] (1) Dimension of work order processing duration: The work order processing duration is a direct manifestation of efficiency, that is, the work order processing duration is a direct indicator to measure the duration required for a work order from receipt to completion, and it directly affects the hospital logistics response efficiency; in addition, in terms of priority consideration, work orders with different urgencies have different requirements for processing duration, and the fitness function can give higher priority to urgent work orders through the processing duration.

[0068] (B) Dimension of work order processing satisfaction: The work order processing satisfaction is a quantification of service quality, that is, the satisfaction (such as the satisfaction score ranges from 1 to 5 points) is an important indicator to measure the service level, and it reflects the matching degree between the work order processing result and the user's expectation; in addition, in terms of long-term operation consideration, high satisfaction can enhance the hospital's reputation and patient loyalty, which is crucial for the hospital's long-term operation.

[0069] (C) Dimension of resource utilization rate during the work order processing process: The resource utilization rate is related to cost control, that is, the resource utilization rate reflects the usage efficiency of operation and maintenance personnel and materials, and high utilization rate means effective cost control; in addition, in terms of balancing the workload, by optimizing the resource utilization rate, the situation where some operation and maintenance personnel are overloaded while others are idle can be avoided, and the workload can be balanced.

[0070] In step S33, specifically, for each individual in the current population, apply the For each hospital logistics operation and maintenance work order, the work order location and work order feature information, and for each hospital logistics operation and maintenance resource object among the M hospital logistics operation and maintenance resource objects, the current location and object feature information, calculate the corresponding fitness value based on an artificial intelligence algorithm, including but not limited to the following steps S331 to S332.

[0071] S331. For a certain individual in the current population, apply the work order location and work order feature information of each hospital logistics operation and maintenance work order among the hospital logistics operation and maintenance work orders, and the current location and object feature information of each hospital logistics operation and maintenance resource object among the M hospital logistics operation and maintenance resource objects, and calculate, based on an artificial intelligence algorithm, each work order processing duration prediction value, each work order processing satisfaction prediction value, and each resource utilization prediction value during the work order processing, which respectively correspond one by one to each element in the corresponding individual.

[0072] In step S331, specifically, as Figure 3 shown, for a certain individual in the current population, apply the work order location and work order feature information of each hospital logistics operation and maintenance work order among the hospital logistics operation and maintenance work orders, and the current location and object feature information of each hospital logistics operation and maintenance resource object among the M hospital logistics operation and maintenance resource objects, and calculate, based on an artificial intelligence algorithm, each work order processing duration prediction value, each work order processing satisfaction prediction value, and each resource utilization prediction value during the work order processing, which respectively correspond one by one to each element in the corresponding individual, including but not limited to the following steps S3311 to S3315.

[0073] S3311. For a certain individual in the current population, read each element in the corresponding individual.

[0074] S3312. For a certain element in the certain individual, if the corresponding element is zero, directly obtain that the corresponding work order processing duration prediction value is infinite, the corresponding work order processing satisfaction prediction value is zero, and the corresponding resource utilization prediction value is infinite; otherwise, obtain the shortest path length corresponding to and between the current location of the corresponding hospital logistics operation and maintenance resource object and the work order location of the hospital logistics operation and maintenance work order with the corresponding element as the serial number.

[0075] In the step S3312, the path between the above two positions can be obtained conventionally based on existing path planning techniques. Since there may be multiple planned paths, the length of the shortest path can be selected as the subsequent model input item to obtain an accurate work order processing duration. In addition, when the element is zero, the corresponding work order processing duration prediction value is designed to be infinity, the corresponding work order satisfaction prediction value is designed to be zero, and the corresponding resource utilization prediction value is designed to be infinity, so that the corresponding fitness contribution is zero during the fitness calculation in the subsequent step S332 to conform to the actual situation.

[0076] S3313. Import the shortest path length corresponding to the certain element, the operation and maintenance skill level in the object feature information of the hospital logistics operation and maintenance resource object corresponding to the certain element, the historical processing duration of similar work orders, and the work order type and emergency level in the work order feature information of the hospital logistics operation and maintenance work order with the serial number of the certain element into the work order processing duration prediction model pre-trained based on the first artificial intelligence algorithm, and output the work order processing duration prediction value corresponding to the certain element, where the similar work orders refer to the work orders with the work order type in the work order feature information of the hospital logistics operation and maintenance work order with the serial number of the certain element.

[0077] In the step S3313, the first artificial intelligence algorithm specifically but not limited to adopts machine learning algorithms based on support vector machine, stochastic gradient descent method, multivariable linear regression, multi-layer perceptron, decision tree, backpropagation neural network or radial basis function network, etc. The specific training process of the work order processing duration prediction model is the prior art, that is, a certain amount of historical sample data with the model input items being the shortest path length, operation and maintenance skill level (because the skill level of the resource object affects the processing speed), historical processing duration of similar work orders, work order type (because different types of work orders may have different processing durations) and emergency level (because urgent work orders may require faster response), etc., and the model output item being the work order processing duration can be used to train the work order processing duration prediction model through a conventional calibration and verification modeling process (specifically including the calibration process and verification process of the model, that is, first comparing the model simulation results with the measured data, and then adjusting the model parameters according to the comparison results to make the simulation results coincide with the actual situation). In addition, in the calibration and verification modeling process of the work order processing duration prediction model, the Bayesian optimization algorithm based on the tree structure can be used to optimize the model parameters.

[0078] S3314. Import the predicted value of the work order processing duration corresponding to the certain element, the historical service score of the same type of work orders in the object feature information of the hospital logistics operation and maintenance resource object corresponding to the certain element, and the complexity level in the work order feature information of the hospital logistics operation and maintenance work order with the serial number of the certain element into the work order processing satisfaction prediction model pre-trained based on the second artificial intelligence algorithm, and output the predicted value of the work order processing satisfaction corresponding to the certain element.

[0079] In the step S3314, the second artificial intelligence algorithm is also specifically but not limited to machine learning algorithms based on support vector machines, stochastic gradient descent methods, multivariable linear regression, multi-layer perceptrons, decision trees, backpropagation neural networks, or radial basis function networks, etc. The specific training process of the work order processing satisfaction prediction model is also the prior art, that is, a certain amount of historical sample data with the model input items being the work order processing duration (because the processing duration may affect user satisfaction), the historical service score of the same type of work orders, and the complexity level (because complex work orders may be more difficult to obtain high satisfaction) and the model output item being the work order processing satisfaction can be used. Through the conventional calibration verification modeling process (specifically including the calibration process and the verification process of the model, that is, first comparing the model simulation results with the measured data, and then adjusting the model parameters according to the comparison results to make the simulation results coincide with the actual situation), the work order processing satisfaction prediction model is trained. In addition, in the calibration verification modeling process of the work order processing satisfaction prediction model, the Bayesian optimization algorithm based on the tree structure can also be used to optimize the model parameters.

[0080] S3315. Import the workload within the current assessment period and the value of the order distribution uniformity index within the current assessment period in the object feature information of the hospital logistics operation and maintenance resource object corresponding to the certain element, and the work order type in the work order feature information of the hospital logistics operation and maintenance work order with the serial number of the certain element into the resource utilization prediction model pre-trained based on the third artificial intelligence algorithm, and output the predicted value of the resource utilization corresponding to the certain element.

[0081] In the step S3315, the third artificial intelligence algorithm is also specific but not limited to machine learning algorithms based on support vector machines, stochastic gradient descent, multivariate linear regression, multi-layer perceptrons, decision trees, backpropagation neural networks, or radial basis function networks, etc. The specific training process of the resource utilization prediction model is also the prior art, that is, a certain amount of historical sample data with the model input items being the workload within the historical assessment period, the single assignment uniformity index value within the historical assessment period, and the work order type (because different types of work orders have different resource requirements), etc., and the model output item being the resource utilization rate can be pre-based. Through the conventional calibration and verification modeling process (specifically including the calibration process and verification process of the model, that is, first comparing the model simulation results with the measured data, and then adjusting the model parameters according to the comparison results to make the simulation results coincide with the actual situation), the resource utilization prediction model is trained. In addition, in the calibration and verification modeling process of the resource utilization prediction model, the Bayesian optimization algorithm based on the tree structure can also be used to optimize the model parameters.

[0082] S332. Calculate the fitness F of the certain individual according to the following formula:

[0083]

[0084] In the formula, m represents a positive integer less than or equal to M, w 1 represents the preset weight coefficient in the dimension of work order processing duration, w 2 represents the preset weight coefficient in the dimension of work order processing satisfaction, w 3 represents the preset weight coefficient in the dimension of resource utilization rate, t m represents the predicted value of the work order processing duration corresponding to the mth element in the certain individual, p m represents the predicted value of the work order processing satisfaction corresponding to the mth element in the certain individual, η m represents the predicted value of the resource utilization rate corresponding to the mth element in the certain individual.

[0085] S34. Determine whether the current iteration number T has reached the maximum iteration number T max , if so, select the individual corresponding to the highest fitness from the current population as the optimal work order allocation plan, otherwise increment the current iteration number T by 1, and then execute step S35.

[0086] After the step S33, if the current highest fitness exceeds the preset fitness threshold, the individual corresponding to the current highest fitness can also be directly used as the optimal work order allocation plan, and the process can be ended in advance.

[0087] S35. According to each of the individuals and the fitness of each of the individuals, through the selection operation, crossover operation, and mutation operation in the genetic optimization algorithm, N new individuals that respectively meet the constraint conditions of the allocation scheme are obtained to form a new population, and then return to execute step S33.

[0088] In step S35, the selection operation, the crossover operation, and the mutation operation (i.e., randomly changing some gene positions in the chromosome at a certain mutation rate to increase the diversity of the population), etc. are all conventional operations in the existing genetic optimization algorithm. For example, the selection operation can adopt roulette wheel selection or tournament selection, etc., and the crossover operation can adopt single-point crossover or two-point crossover, etc. Specific details are not elaborated here.

[0089] S4. According to the optimal work order allocation scheme, dispatch each of the hospital logistics operation and maintenance work orders to the hospital logistics operation and maintenance resource objects corresponding to the vector elements with the corresponding serial numbers.

[0090] In step S4, for example, if M takes the value of 7, The value is 5, and the optimal work order allocation plan is expressed as [0, 0, 5, 4, 3, 2, 1]. Then, no work orders are assigned to the first two of the M hospital logistics operation and maintenance resource objects. The hospital logistics operation and maintenance work order with serial number 5 is assigned to the third hospital logistics operation and maintenance resource object among the M hospital logistics operation and maintenance resource objects, the hospital logistics operation and maintenance work order with serial number 4 is assigned to the fourth hospital logistics operation and maintenance resource object among the M hospital logistics operation and maintenance resource objects, the hospital logistics operation and maintenance work order with serial number 3 is assigned to the fifth hospital logistics operation and maintenance resource object among the M hospital logistics operation and maintenance resource objects, the hospital logistics operation and maintenance work order with serial number 2 is assigned to the sixth hospital logistics operation and maintenance resource object among the M hospital logistics operation and maintenance resource objects, and the hospital logistics operation and maintenance work order with serial number 1 is assigned to the seventh hospital logistics operation and maintenance resource object among the M hospital logistics operation and maintenance resource objects. In addition, in order to adaptively optimize the intelligent work order allocation plan for the entire hospital logistics operation and maintenance, preferably, after the respective hospital logistics operation and maintenance work orders are respectively assigned to the hospital logistics operation and maintenance resource objects corresponding to the vector elements with corresponding serial numbers, the method further includes but is not limited to: according to the processing result feedback data of the respective hospital logistics operation and maintenance work orders, adjusting the function design of the fitness and / or the algorithm parameters of the genetic optimization algorithm; the specific details of the foregoing adjustment of the function design of the fitness may include but are not limited to adjusting the weight coefficients in the dimensions of the work order processing duration, the work order processing satisfaction degree, and the resource utilization rate. The foregoing algorithm parameters further include but are not limited to the model hyperparameters of the work order processing duration prediction model, the work order processing satisfaction degree prediction model, and the resource utilization rate prediction model.

[0091] Based on the hospital logistics operation and maintenance intelligent work order allocation method described in the foregoing steps S1 to S4, a new solution for combining positioning technology with big data analysis technology for hospital logistics operation and maintenance intelligent work order allocation is provided, that is, first, real-time receive the location status collection data from all hospital logistics operation and maintenance resource objects, and then when receiving the hospital logistics operation and maintenance work orders from the hospital logistics management system, select M hospital logistics operation and maintenance resource objects whose current status is the to-be-allocated status according to the collection data. Then, apply the work order location and work order feature information, as well as the object's current location and object feature information, and optimize the work order allocation plan based on the genetic optimization algorithm to obtain the optimal work order allocation plan with the highest fitness. Finally, complete the work order allocation according to the optimal work order allocation plan. In this way, the intelligent allocation and precise scheduling of hospital logistics operation and maintenance tasks can be realized, significantly improving the management efficiency, optimizing the resource allocation, ensuring the timeliness, efficiency, and precision of the logistics service, thus strongly supporting the improvement of the overall medical service quality of the hospital, enhancing the core competitiveness of the hospital in the medical market competition, and facilitating practical application and promotion.

[0092] As Figure 4 shown, in the second aspect of this embodiment, a virtual device for implementing the hospital logistics operation and maintenance intelligent dispatching method described in the first aspect is provided, including a collected data receiving unit, a resource object selection unit, a distribution plan optimization unit, and a work order dispatching execution unit;

[0093] The collected data receiving unit is used to receive in real time the location status collected data from all hospital logistics operation and maintenance resource objects, where the hospital logistics operation and maintenance resource objects refer to hospital logistics operation and maintenance personnel or hospital logistics operation and maintenance equipment, and the location status collected data includes the current location and current status of the corresponding object;

[0094] The resource object selection unit is communicatively connected to the collected data receiving unit and is used for, when receiving hospital logistics operation and maintenance work orders from the hospital logistics management system, selecting M hospital logistics operation and maintenance resource objects whose current status is the to-be-allocated status from all the hospital logistics operation and maintenance resource objects according to the location status collected data of all the hospital logistics operation and maintenance resource objects, where represents a positive integer, and M represents a positive integer greater than or equal to ;

[0095] The distribution plan optimization unit is respectively communicatively connected to the collected data receiving unit and the resource object selection unit and is used for applying the work order location and work order feature information in each of the hospital logistics operation and maintenance work orders and the current location and object feature information in each of the M hospital logistics operation and maintenance resource objects, and optimizing the work order distribution plan for allocating the hospital logistics operation and maintenance work orders to the M hospital logistics operation and maintenance resource objects based on the genetic optimization algorithm to obtain an optimal work order distribution plan with the highest fitness, where the work order distribution plan is represented by an M-dimensional vector corresponding one-to-one to the M hospital logistics operation and maintenance resource objects. When any element in the M-dimensional vector is a zero value, it means that the hospital logistics operation and maintenance resource object corresponding to the any element is not allocated with the hospital logistics operation and maintenance work order, and when any element in the M-dimensional vector is a positive integer, it means that the hospital logistics operation and maintenance resource object corresponding to the any element is allocated with a certain hospital logistics operation and maintenance work order and the serial number of the certain hospital logistics operation and maintenance work order in the hospital logistics operation and maintenance work orders is the positive integer, and the fitness function is designed based on the work order processing duration dimension, the work order processing satisfaction dimension, and the resource utilization rate dimension in the work order processing process;

[0096] The work order dispatching execution unit, communicatively connected to the allocation scheme optimization unit, is configured to dispatch each hospital logistics operation and maintenance work order to the hospital logistics operation and maintenance resource object corresponding to the vector element with the corresponding serial number according to the optimal work order allocation scheme.

[0097] For the working process, working details and technical effects of the foregoing device provided in the second aspect of this embodiment, reference may be made to the hospital logistics operation and maintenance intelligent dispatching method described in the first aspect, which will not be elaborated herein.

[0098] As Figure 5 shown, a computer device for executing the hospital logistics operation and maintenance intelligent dispatching method described in the first aspect is provided in the third aspect of this embodiment, including a memory, a processor, and a transceiver communicatively connected in sequence. Among them, the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the hospital logistics operation and maintenance intelligent dispatching method described in the first aspect. Specifically, for example, the memory may include, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a flash memory, a first input first output (FIFO), and / or a first input last output (FILO), etc.; the processor may include, but is not limited to, a microprocessor of the STM32F105 series. In addition, the computer device may further include, but is not limited to, a power module, a display screen, and other necessary components.

[0099] For the working process, working details and technical effects of the foregoing computer device provided in the third aspect of this embodiment, reference may be made to the hospital logistics operation and maintenance intelligent dispatching method described in the first aspect, which will not be elaborated herein.

[0100] A computer-readable storage medium storing instructions including the hospital logistics operation and maintenance intelligent dispatching method described in the first aspect is provided in the fourth aspect of this embodiment, that is, instructions are stored on the computer-readable storage medium, and when the instructions run on a computer, the hospital logistics operation and maintenance intelligent dispatching method described in the first aspect is executed. Among them, the computer-readable storage medium refers to a carrier for storing data, and may include, but is not limited to, a floppy disk, an optical disk, a hard disk, a flash memory, a USB flash drive, and / or a memory stick, etc. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0101] For the working process, working details and technical effects of the foregoing computer-readable storage medium provided in the fourth aspect of this embodiment, reference may be made to the hospital logistics operation and maintenance intelligent dispatching method described in the first aspect, which will not be elaborated herein.

[0102] In the fifth aspect of this embodiment, a computer program product is provided, including a computer program or instruction, and when the computer program or the instruction is executed by a computer, the hospital logistics operation and maintenance intelligent dispatching method described in the first aspect is implemented. Among them, the computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices.

[0103] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not intended to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A hospital logistics operation and maintenance intelligent dispatching method, characterized in that: include: Receive location status collection data from all hospital logistics operation and maintenance resource objects in real time, wherein the hospital logistics operation and maintenance resource objects refer to hospital logistics operation and maintenance personnel or hospital logistics operation and maintenance equipment, and the location status collection data contains the current location and current status of the corresponding object; Upon receiving the When a hospital logistics operation and maintenance work order is issued, data is collected according to the position status of all hospital logistics operation and maintenance resource objects, and M hospital logistics operation and maintenance resource objects whose current status is to be distributed are selected from all hospital logistics operation and maintenance resource objects, where: Represents a positive integer, M represents greater than or equal to A positive integer of ; Application in the The work order location and work order feature information of each hospital logistics operation and maintenance work order in the M hospital logistics operation and maintenance work orders and the current location and object feature information of each hospital logistics operation and maintenance resource object in the M hospital logistics operation and maintenance resource objects are used to convert the The work order allocation scheme of the hospital logistics operation and maintenance work orders allocated to the M hospital logistics operation and maintenance resource objects is optimized to obtain the optimal work order allocation scheme with the highest fitness, wherein the work order allocation scheme is represented by an M-dimensional vector corresponding to the M hospital logistics operation and maintenance resource objects one by one, and when any element in the M-dimensional vector is a zero value, it means that the hospital logistics operation and maintenance resource object corresponding to any element is not allocated with the hospital logistics operation and maintenance work order, and when any element in the M-dimensional vector is a positive integer, it means that the hospital logistics operation and maintenance resource object corresponding to any element is allocated with a certain hospital logistics operation and maintenance work order and the certain hospital logistics operation work order is allocated in the The serial number in the logistics operation and maintenance work order of a hospital is the positive integer, and the fitness function is designed based on the work order processing time dimension, the work order processing satisfaction dimension and the resource utilization dimension in the work order processing process; According to the optimal work order allocation scheme, each of the hospital logistics operation and maintenance work orders is respectively dispatched to the hospital logistics operation and maintenance resource objects corresponding to the vector elements with corresponding serial numbers.

2. The hospital logistics operation and maintenance intelligent dispatching method according to claim 1 is characterized in that: The work order characteristic information includes work order type, urgency level and / or complexity level; And / or, the object characteristic information includes operation and maintenance skill level, historical processing time of various work orders, historical service scores of various work orders, workload in the current assessment period and / or order distribution uniformity index value in the current assessment period.

3. The hospital logistics operation and maintenance intelligent dispatching method according to claim 1 is characterized in that: Application in the The work order location and work order feature information of each hospital logistics operation and maintenance work order in the M hospital logistics operation and maintenance work orders and the current location and object feature information of each hospital logistics operation and maintenance resource object in the M hospital logistics operation and maintenance resource objects are used to convert the The work order allocation scheme of the M hospital logistics operation and maintenance work orders allocated to the M hospital logistics operation and maintenance resource objects is optimized to obtain the optimal work order allocation scheme with the highest fitness, including the following steps S31-S35: S31. Initialize the genetic optimization algorithm and include the population size N and the maximum number of iterations T max The algorithm parameters are set, and the current number of iterations T is initialized to 0, and then step S32 is executed; S32. Randomly generate the allocation scheme constraints and the The N work order allocation schemes for allocating hospital logistics and maintenance work orders to the M hospital logistics and maintenance resource objects are used, and the N work order allocation schemes are used one-to-one as N individuals to form an initial population, and then step S33 is executed, wherein the work order allocation scheme is represented by an M-dimensional vector corresponding one-to-one to the M hospital logistics and maintenance resource objects, and when any element in the M-dimensional vector is a zero value, it means that the hospital logistics and maintenance resource object corresponding to any element is not allocated with the hospital logistics and maintenance work order, and when any element in the M-dimensional vector is a positive integer, it means that the hospital logistics and maintenance resource object corresponding to any element is allocated with a certain hospital logistics and maintenance work order and the certain hospital logistics and operation work order is allocated in the The serial number in the logistics operation and maintenance work order of a hospital is the positive integer, and the constraints of the allocation scheme include the following: each element in the M-dimensional vector belongs to the interval [0, M] and any two elements in the M-dimensional vector are not equal; S33. For each individual in the current population, apply The work order position and work order feature information of each hospital logistics operation and maintenance work order in the M hospital logistics operation and maintenance work orders and the current position and object feature information of each hospital logistics operation and maintenance resource object in the M hospital logistics operation and maintenance resource objects are calculated based on the artificial intelligence algorithm to obtain the corresponding fitness, and then step S34 is executed, wherein the fitness function is designed based on the work order processing time dimension, the work order processing satisfaction dimension, and the resource utilization dimension in the work order processing process; S34. Determine whether the current number of iterations T has reached the maximum number of iterations T max If yes, then select the individual corresponding to the highest fitness from the current population as the optimal work order allocation solution, otherwise, increment the current iteration number T by 1, and then execute step S35; S35. According to the individuals and their fitness, through the selection operation, crossover operation and mutation operation in the genetic optimization algorithm, N new individuals that respectively meet the constraints of the allocation scheme are obtained to form a new population, and then return to execute step S33.

4. The hospital logistics operation and maintenance intelligent dispatching method according to claim 3 is characterized in that: For each individual in the current population, apply the The work order location and work order feature information of each hospital logistics operation and maintenance work order in the M hospital logistics operation and maintenance work orders and the current location and object feature information of each hospital logistics operation and maintenance resource object in the M hospital logistics operation and maintenance resource objects are calculated based on the artificial intelligence algorithm to obtain the corresponding fitness, including: For an individual in the current population, apply Based on the work order location and work order feature information of each hospital logistics operation and maintenance work order in the M hospital logistics operation and maintenance work orders and the current location and object feature information of each hospital logistics operation and maintenance resource object in the M hospital logistics operation and maintenance resource objects, the predicted value of each work order processing time, the predicted value of each work order processing satisfaction and the predicted value of each resource utilization rate in the work order processing process, which correspond one-to-one to each element in the corresponding individual, are calculated based on the artificial intelligence algorithm; The fitness F of the individual is calculated according to the following formula: Where m is a positive integer less than or equal to M, w1 is the preset weight coefficient in the dimension of work order processing time, w2 is the preset weight coefficient in the dimension of work order processing satisfaction, w3 is the preset weight coefficient in the dimension of resource utilization, t m represents the predicted value of the work order processing time corresponding to the mth element in the individual, p m represents the predicted value of the work order processing satisfaction corresponding to the mth element in the individual, η m represents the resource utilization prediction value corresponding to the mth element in the certain individual.

5. The hospital logistics operation and maintenance intelligent dispatching method according to claim 4 is characterized in that: For an individual in the current population, apply The work order location and work order feature information of each hospital logistics operation and maintenance work order in the M hospital logistics operation and maintenance work orders and the current location and object feature information of each hospital logistics operation and maintenance resource object in the M hospital logistics operation and maintenance resource objects are calculated based on the artificial intelligence algorithm to obtain the predicted values ​​of each work order processing time, each work order processing satisfaction predicted value and each resource utilization rate predicted value in the work order processing process, which correspond to each element in the corresponding individual one by one, including: For a certain individual in the current population, read each element in the corresponding individual; For a certain element in the certain individual, if the corresponding element is zero, the corresponding work order processing time prediction value is directly infinite, the corresponding work order processing satisfaction prediction value is zero, and the corresponding resource utilization prediction value is infinite. Otherwise, according to the current position of the corresponding hospital logistics operation and maintenance resource object and the work order position of the hospital logistics operation and maintenance work order whose serial number is the corresponding element, the corresponding shortest path length between the current position and the work order position is obtained; The shortest path length corresponding to the certain element, the operation and maintenance skill level and the historical processing time of similar work orders in the object feature information of the hospital logistics operation and maintenance resource object corresponding to the certain element, and the work order type and urgency level in the work order feature information of the hospital logistics operation and maintenance work order with the serial number of the certain element are imported into the work order processing time prediction model obtained by pre-training based on the first artificial intelligence algorithm, and the work order processing time prediction value corresponding to the certain element is output, wherein the similar work order refers to a work order of the type of the work order type in the work order feature information of the hospital logistics operation and maintenance work order with the serial number of the certain element; Import the predicted value of the work order processing time corresponding to the certain element, the historical service score of the same type of work order in the object feature information of the hospital logistics operation and maintenance resource object corresponding to the certain element, and the complexity level in the work order feature information of the hospital logistics operation and maintenance work order with the serial number of the certain element into the work order processing satisfaction prediction model obtained by pre-training based on the second artificial intelligence algorithm, and output the predicted value of the work order processing satisfaction corresponding to the certain element; The workload in the current assessment period and the order distribution uniformity index value in the current assessment period in the object characteristic information of the hospital logistics and maintenance resource object corresponding to the certain element, as well as the work order type in the work order characteristic information of the hospital logistics and maintenance work order with the serial number of the certain element, are imported into the resource utilization prediction model obtained by pre-training based on the third artificial intelligence algorithm, and the resource utilization prediction value corresponding to the certain element is output.

6. The hospital logistics operation and maintenance intelligent dispatching method according to claim 1 is characterized in that: After the hospital logistics operation and maintenance work orders are respectively dispatched to the hospital logistics operation and maintenance resource objects corresponding to the vector elements with corresponding serial numbers, the method further includes: According to the feedback data of the processing results of the logistics operation and maintenance work orders of each hospital, the function design of the fitness and / or the algorithm parameters of the genetic optimization algorithm are adjusted.

7. A hospital logistics operation and maintenance intelligent dispatching device, characterized in that: It includes a data collection receiving unit, a resource object selection unit, an allocation plan optimization unit and a work order dispatching execution unit; The collected data receiving unit is used to receive the location status collected data from all hospital logistics operation and maintenance resource objects in real time, wherein the hospital logistics operation and maintenance resource objects refer to hospital logistics operation and maintenance personnel or hospital logistics operation and maintenance equipment, and the location status collected data contains the current location and current status of the corresponding object; The resource object selection unit is communicatively connected to the data collection receiving unit, and is used to receive the data from the hospital logistics management system. When a hospital logistics operation and maintenance work order is issued, data is collected according to the position status of all hospital logistics operation and maintenance resource objects, and M hospital logistics operation and maintenance resource objects whose current status is to be distributed are selected from all hospital logistics operation and maintenance resource objects, where: Represents a positive integer, M represents greater than or equal to A positive integer of ; The allocation scheme optimization unit is respectively connected to the acquisition data receiving unit and the resource object selection unit for application in the The work order location and work order feature information of each hospital logistics operation and maintenance work order in the M hospital logistics operation and maintenance work orders and the current location and object feature information of each hospital logistics operation and maintenance resource object in the M hospital logistics operation and maintenance resource objects are used to convert the The work order allocation scheme of the hospital logistics operation and maintenance work orders allocated to the M hospital logistics operation and maintenance resource objects is optimized to obtain the optimal work order allocation scheme with the highest fitness, wherein the work order allocation scheme is represented by an M-dimensional vector corresponding to the M hospital logistics operation and maintenance resource objects one by one, and when any element in the M-dimensional vector is a zero value, it means that the hospital logistics operation and maintenance resource object corresponding to any element is not allocated with the hospital logistics operation and maintenance work order, and when any element in the M-dimensional vector is a positive integer, it means that the hospital logistics operation and maintenance resource object corresponding to any element is allocated with a certain hospital logistics operation and maintenance work order and the certain hospital logistics operation work order is allocated in the The serial number in the logistics operation and maintenance work order of a hospital is the positive integer, and the fitness function is designed based on the work order processing time dimension, the work order processing satisfaction dimension and the resource utilization dimension in the work order processing process; The work order dispatching execution unit is communicatively connected to the allocation scheme optimization unit, and is used to dispatch each of the hospital logistics operation and maintenance work orders to the hospital logistics operation and maintenance resource objects corresponding to the vector elements with corresponding serial numbers according to the optimal work order allocation scheme.

8. A computer device, characterized in that: It includes a memory, a processor and a transceiver which are communicatively connected in sequence, wherein the memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the hospital logistics operation and maintenance intelligent dispatching method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed on the computer, the hospital logistics operation and maintenance intelligent dispatching method as described in any one of claims 1 to 6 is executed.

10. A computer program product comprising a computer program or instructions, characterized in that When executed by a computer, the computer program or the instruction implements the intelligent dispatching method for hospital logistics operation and maintenance as described in any one of claims 1 to 6.

Images