Scheduling method and system for operation optimization in cooperative medical system

Abstract

The invention discloses a scheduling method and system for operation optimization in a cooperative medical system, and relates to the technical field of medical systems, and the method comprises the steps: obtaining a demand attribute of a to-be-implemented operation; acquiring use state information of medical resources from the intelligent cooperative medical system; screening out the medical resources in an idle state from the obtained medical resources to obtain to-be-scheduled medical resources; according to the demand attribute of the to-be-implemented operation, scheduling the to-be-scheduled medical resources to obtain medical resource scheduling information for the to-be-implemented operation; and uploading the medical resource scheduling information for the to-be-implemented operation to the intelligent cooperative medical system so as to update the use state information of the medical resources in the intelligent cooperative medical system. Therefore, the scheduling efficiency of the medical resources to be subjected to the operation in the cooperative medical system can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of medical systems, and in particular to a scheduling method and system for optimizing surgery in a collaborative medical system. Background Art

[0002] With the rapid development of economy in recent years, the medical service industry is facing market competition pressure. Choosing scientific scheduling methods to efficiently manage medical resources is one of the important ways to improve the competitiveness of medical service institutions and patient satisfaction.

[0003] In the current medical service industry, doctors and hospital beds are usually allocated manually based on the needs of the surgery to be performed. However, this method of scheduling medical resources is inefficient.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present application provide a scheduling method and system for optimizing surgery in a cooperative medical system to solve the above-mentioned technical problems.

[0006] The present application provides a scheduling method for optimizing surgery in a cooperative medical system, comprising:

[0007] Obtaining the demand attributes of the surgery to be performed; wherein the demand attributes of the surgery to be performed include surgery duration, surgery date, surgical room type, specialist type, resource demand data, patient preferences, and surgical care quality demand data;

[0008] Obtaining usage status information of medical resources from the smart cooperative medical system; wherein the medical resources include operating rooms, doctors, medical equipment, medical consumables, and hospital beds;

[0009] Filter out idle medical resources from the acquired medical resources to obtain medical resources to be scheduled;

[0010] Scheduling the medical resources to be scheduled according to the demand attributes of the surgery to be performed, and obtaining medical resource scheduling information for the surgery to be performed;

[0011] The medical resource scheduling information for the operation to be performed is uploaded to the smart cooperative medical system to update the usage status information of the medical resources in the smart cooperative medical system.

[0012] Furthermore, the medical resources to be scheduled are scheduled according to the demand attributes of the surgery to be performed, and the medical resource scheduling information for the surgery to be performed is obtained, including:

[0013] Determine a resource scheduling scenario according to resource demand data included in the demand attributes of the surgery to be performed; wherein the resource demand data includes equipment resource demand data, material resource demand data, and technical resource demand data;

[0014] Generate resource demand features using an automated tool according to the resource scheduling scenario and the demand attributes of the surgery to be performed; wherein the automated tool is used to explore and generate the resource demand features from the demand attributes of the surgery to be performed by a first deep feature synthesis method;

[0015] According to the resource scheduling scenario and the medical resources to be scheduled, the automated tool is used to generate resource scheduling features; wherein the automated tool is further used to explore and generate the resource scheduling features from the medical resources to be scheduled by a second deep feature synthesis method;

[0016] Based on the resource demand characteristics and the resource scheduling characteristics, medical resource scheduling information for the surgery to be performed is determined.

[0017] Furthermore, the determining of the medical resource scheduling information for the operation to be performed based on the resource demand characteristics and the resource scheduling characteristics includes:

[0018] Determine a first graph structure corresponding to the surgery to be performed based on the resource demand characteristics;

[0019] For each node in the first graph structure, determine the edge associated with the node; determine the characteristic information of the node based on the edge associated with the node; based on the characteristic information of each node, divide each node into a first node set or a second node set, wherein the data information in the first node set is associated with the operation duration, operation date, operation room type, specialist type and resource demand data, and the data information in the second node set is not associated with the operation duration, operation date, operation room type, specialist type and resource demand data;

[0020] Predicting a first resource requirement for the surgery to be performed using a first deep learning neural network based on the data information in the first node set;

[0021] According to the data information in the second node set, a second resource requirement for the operation to be performed is predicted using a second deep learning neural network,

[0022] Assigning weights to the first resource requirement predicted for the operation to be performed and the second resource requirement predicted for the operation to be performed, respectively, to obtain a simulated resource requirement for the operation to be performed;

[0023] Based on the simulated resource demand for the operation to be performed and the characteristics of the resources to be scheduled, medical resource scheduling information for the operation to be performed is determined.

[0024] Furthermore, predicting a first resource requirement for the surgery to be performed using a first deep learning neural network based on the data information in the first node set includes:

[0025] Constructing a first distributed data set according to the data information in the first node set;

[0026] Using an adaptive learning rate method to adjust the learning rate of each node in the first node set;

[0027] The learning state of the first deep neural network is used to predict a first resource requirement for the surgery to be performed.

[0028] Furthermore, the predicting of the second resource requirement for the surgery to be performed using a second deep learning neural network according to the data information in the second node set includes:

[0029] Constructing a second distributed data set according to the data information in the second node set;

[0030] Using an adaptive learning rate method to adjust the learning rate of each node in the second node set;

[0031] The learning state of the second deep neural network is used to predict a second resource requirement for the surgery to be performed.

[0032] Furthermore, the determining of the medical resource scheduling information for the surgery to be performed based on the simulated resource demand for the surgery to be performed and the resource scheduling characteristics includes:

[0033] Normalizing the simulated resource demand for the surgery to be performed and the resource scheduling characteristics;

[0034] The simulated resource demand and the resource scheduling characteristics after normalization are used as the input layer, and the medical resource scheduling information for the operation to be performed is used as the output layer, and a deep neural network is used for training to predict the medical resource scheduling information for the operation to be performed;

[0035] The deep neural network includes the input layer, the hidden layer and the output layer; the hidden layer includes multiple layers, wherein the number of nodes in the first hidden layer is equal to three times the number of units in the input layer, and the number of nodes in each subsequent hidden layer gradually decreases; the activation function used in the hidden layer is the sigmoid function;

[0036] Furthermore, the surgical care quality requirement data includes preoperative preparation quality requirement data, intraoperative monitoring quality requirement data and postoperative care quality requirement data.

[0037] The present application provides a scheduling system for optimizing surgery in a cooperative medical system, including a demand attribute acquisition unit, a medical resource status acquisition unit, a medical resource screening unit to be scheduled, a medical resource scheduling unit, and a medical resource status update unit; wherein,

[0038] The demand attribute acquisition unit is used to acquire the demand attributes of the surgery to be performed; wherein the demand attributes of the surgery to be performed include surgery duration, surgery date, surgical room type, specialist type, resource demand data, patient preferences, and surgical care quality demand data;

[0039] The medical resource status acquisition unit is used to acquire the usage status information of medical resources from the smart cooperative medical system; wherein the medical resources include operating rooms, doctors, medical equipment, medical consumables, and hospital beds;

[0040] The to-be-scheduled medical resource screening unit is used to screen out idle medical resources from the acquired medical resources to obtain the to-be-scheduled medical resources;

[0041] The medical resource scheduling unit is used to schedule the medical resources to be scheduled according to the demand attributes of the surgery to be performed, and obtain medical resource scheduling information for the surgery to be performed;

[0042] The medical resource status updating unit is used to upload the medical resource scheduling information for the operation to be performed to the smart cooperative medical system to update the usage status information of the medical resources in the smart cooperative medical system.

[0043] Furthermore, the medical resources to be scheduled are scheduled according to the demand attributes of the surgery to be performed, and the medical resource scheduling information for the surgery to be performed is obtained, including:

[0044] Determine a resource scheduling scenario according to resource demand data included in the demand attributes of the surgery to be performed; wherein the resource demand data includes equipment resource demand data, material resource demand data, and technical resource demand data;

[0045] Generate resource demand features using an automated tool according to the resource scheduling scenario and the demand attributes of the surgery to be performed; wherein the automated tool is used to explore and generate the resource demand features from the demand attributes of the surgery to be performed by a first deep feature synthesis method;

[0046] According to the resource scheduling scenario and the medical resources to be scheduled, the automated tool is used to generate resource scheduling features; wherein the automated tool is further used to explore and generate the resource scheduling features from the medical resources to be scheduled by a second deep feature synthesis method;

[0047] Based on the resource demand characteristics and the resource scheduling characteristics, medical resource scheduling information for the surgery to be performed is determined.

[0048] Furthermore, the determining of the medical resource scheduling information for the operation to be performed based on the resource demand characteristics and the resource scheduling characteristics includes:

[0049] Determine a first graph structure corresponding to the surgery to be performed based on the resource demand characteristics;

[0050] For each node in the first graph structure, determine the edge associated with the node; determine the characteristic information of the node based on the edge associated with the node; based on the characteristic information of each node, divide each node into a first node set or a second node set, wherein the data information in the first node set is associated with the operation duration, operation date, operation room type, specialist type and resource demand data, and the data information in the second node set is not associated with the operation duration, operation date, operation room type, specialist type and resource demand data;

[0051] Predicting a first resource requirement for the surgery to be performed using a first deep learning neural network based on the data information in the first node set;

[0052] According to the data information in the second node set, a second resource requirement for the operation to be performed is predicted using a second deep learning neural network,

[0053] Assigning weights to the first resource requirement predicted for the operation to be performed and the second resource requirement predicted for the operation to be performed, respectively, to obtain a simulated resource requirement for the operation to be performed;

[0054] Based on the simulated resource demand for the operation to be performed and the characteristics of the resources to be scheduled, medical resource scheduling information for the operation to be performed is determined.

[0055] Based on the embodiments provided by the present application, the demand attributes of the operation to be performed are obtained; wherein the demand attributes of the operation to be performed include the operation duration, operation date, operation room type, specialty type, resource demand data, patient preference, and operation care quality demand data; the use status information of medical resources is obtained from the smart cooperative medical system; wherein medical resources include operating rooms, doctors, medical equipment, medical consumables, and beds; medical resources in idle state are screened out from the obtained medical resources to obtain medical resources to be scheduled; according to the demand attributes of the operation to be performed, the medical resources to be scheduled are scheduled to obtain the medical resource scheduling information for the operation to be performed; the medical resource scheduling information for the operation to be performed is uploaded to the smart cooperative medical system to update the use status information of medical resources in the smart cooperative medical system. Thereby, the scheduling efficiency of medical resources for the operation to be performed in the cooperative medical system can be improved. Specifically, it has the following beneficial effects: obtaining the demand attributes of the surgery to be performed can ensure the comprehensiveness and personalization of the surgical plan and meet the detailed needs of the specific surgery; it helps to prepare and allocate necessary medical resources in advance; obtaining the use status information of medical resources from the smart cooperative medical system can monitor the availability of medical resources in real time, improve resource utilization, avoid resource conflicts and duplicate appointments, and ensure the feasibility of surgical arrangements; screening out idle medical resources can optimize resource allocation, ensure that the surgery can be performed at the right time and place, reduce surgical waiting time, and improve patient satisfaction; scheduling the medical resources to be scheduled can reasonably allocate resources according to the specific needs of the surgery, ensure the smooth progress of the surgery, improve the coordination of resources such as operating rooms, doctors, and equipment, and reduce surgical risks; uploading medical resource scheduling information to the smart cooperative medical system can realize real-time updates of the use status of medical resources, provide accurate resource information for other surgeries or medical services, enhance the transparency of the system, and facilitate medical management personnel to supervise and make decisions; updating the use status information of medical resources in the smart cooperative medical system can ensure that all relevant personnel have access to the latest resource usage, improve work efficiency, and avoid waste of resources or surgical delays due to outdated information.

[0056] Overall, this application helps improve the quality and efficiency of medical services, ensures that patients receive timely and appropriate treatment, and optimizes the management and use of medical resources. Through the smart cooperative medical system, the optimal allocation of medical resources can be achieved, and the overall coordination and response speed of medical services can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The drawings described herein are used to provide a further understanding of the embodiments of the present invention and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0058] Figure 1 A flowchart of an optional method for scheduling surgery optimization in a cooperative medical system according to an embodiment of the present application;

[0059] Figure 2 This is a structural diagram of an optional surgery optimization scheduling system in a cooperative medical system according to an embodiment of the present application.

[0060] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0061] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0062] Alternatively, if Figure 1 As shown, the present application provides a scheduling method for optimizing surgery in a collaborative medical system, comprising:

[0063] S101, obtaining demand attributes of the surgery to be performed; wherein the demand attributes of the surgery to be performed include surgery duration, surgery date, surgical room type, specialist type, resource demand data, patient preference, and surgical nursing quality demand data;

[0064] S102, obtaining usage status information of medical resources from the smart cooperative medical system; wherein the medical resources include operating rooms, doctors, medical equipment, medical consumables, and hospital beds;

[0065] S103, screening out idle medical resources from the acquired medical resources to obtain medical resources to be scheduled;

[0066] S104, scheduling the medical resources to be scheduled according to the demand attributes of the surgery to be performed, and obtaining the medical resource scheduling information for the surgery to be performed;

[0067] S105, uploading the medical resource scheduling information for the surgery to be performed to the smart cooperative medical system to update the usage status information of the medical resources in the smart cooperative medical system.

[0068] Based on the embodiments provided by the present application, the demand attributes of the operation to be performed are obtained; wherein the demand attributes of the operation to be performed include the operation duration, operation date, operation room type, specialty type, resource demand data, patient preference, and operation care quality demand data; the use status information of medical resources is obtained from the smart cooperative medical system; wherein medical resources include operating rooms, doctors, medical equipment, medical consumables, and beds; medical resources in idle state are screened out from the obtained medical resources to obtain medical resources to be scheduled; according to the demand attributes of the operation to be performed, the medical resources to be scheduled are scheduled to obtain the medical resource scheduling information for the operation to be performed; the medical resource scheduling information for the operation to be performed is uploaded to the smart cooperative medical system to update the use status information of medical resources in the smart cooperative medical system. Thereby, the scheduling efficiency of medical resources for the operation to be performed in the cooperative medical system can be improved. Specifically, it has the following beneficial effects: obtaining the demand attributes of the surgery to be performed can ensure the comprehensiveness and personalization of the surgical plan and meet the detailed needs of the specific surgery; it helps to prepare and allocate necessary medical resources in advance; obtaining the use status information of medical resources from the smart cooperative medical system can monitor the availability of medical resources in real time, improve resource utilization, avoid resource conflicts and duplicate appointments, and ensure the feasibility of surgical arrangements; screening out idle medical resources can optimize resource allocation, ensure that the surgery can be performed at the right time and place, reduce surgical waiting time, and improve patient satisfaction; scheduling the medical resources to be scheduled can reasonably allocate resources according to the specific needs of the surgery, ensure the smooth progress of the surgery, improve the coordination of resources such as operating rooms, doctors, and equipment, and reduce surgical risks; uploading medical resource scheduling information to the smart cooperative medical system can realize real-time updates of the use status of medical resources, provide accurate resource information for other surgeries or medical services, enhance the transparency of the system, and facilitate medical management personnel to supervise and make decisions; updating the use status information of medical resources in the smart cooperative medical system can ensure that all relevant personnel have access to the latest resource usage, improve work efficiency, and avoid waste of resources or surgical delays due to outdated information.

[0069] Overall, this application helps improve the quality and efficiency of medical services, ensures that patients receive timely and appropriate treatment, and optimizes the management and use of medical resources. Through the smart cooperative medical system, the optimal allocation of medical resources can be achieved, and the overall coordination and response speed of medical services can be improved.

[0070] Furthermore, according to the demand attributes of the surgery to be performed, the medical resources to be scheduled are scheduled to obtain the medical resource scheduling information for the surgery to be performed, including:

[0071] Determine a resource scheduling scenario according to resource demand data included in the demand attributes of the surgery to be performed; wherein the resource demand data includes equipment resource demand data, material resource demand data, and technical resource demand data;

[0072] Generate resource demand features using an automated tool based on the resource scheduling scenario and the demand attributes of the surgery to be performed; wherein the automated tool is used to explore and generate resource demand features from the demand attributes of the surgery to be performed using a first deep feature synthesis method;

[0073] According to the resource scheduling scenario and the medical resources to be scheduled, using an automated tool to generate features of the resources to be scheduled; wherein the automated tool is also used to explore and generate features of the resources to be scheduled from the medical resources to be scheduled by a second deep feature synthesis method;

[0074] Based on the resource demand characteristics and the resource scheduling characteristics, determine the medical resource scheduling information for the surgery to be performed.

[0075] Based on the embodiments provided in this application, the following beneficial effects are achieved: Optimize resource allocation: By considering demand attributes such as operation duration, operation date, and operation room type, medical resources such as operating rooms, doctors, and medical equipment can be matched more accurately, thereby improving resource utilization; Improve surgical efficiency: Determine resource scheduling scenarios and use automated tools to generate resource demand characteristics, which helps to quickly respond to surgical needs, reduce surgical waiting time, and speed up surgical procedures; Enhance the quality of medical services: The resource demand characteristics explored and generated by automated tools can better meet patient preferences and surgical care quality requirements, improve patient satisfaction and the overall quality of medical services; Flexibly respond to resource changes: The use of automated tools allows the system to dynamically adjust according to real-time data and resource status to ensure effective scheduling in resource-constrained or unexpected situations; Support decision making: The generated medical resources Scheduling information provides important decision-making support for hospital management, helping them monitor and optimize surgical arrangements and achieve more efficient resource planning and risk management; promotes the rational flow of medical resources: by considering doctors' multi-point practice, it is possible to balance medical resources in different regions, effectively restrain patients from blindly rushing into large urban hospitals, and achieve scientific allocation of medical resources; improves the flexibility and efficiency of the medical network: collaborative scheduling of operating rooms in multiple hospitals can integrate medical network resources, reduce dependence on single hospital resources, and improve the flexibility and efficiency of the entire medical network; achieves intelligent optimization: the use of intelligent optimization technologies, such as mixed integer programming and stochastic programming, can solve complex medical resource scheduling problems and achieve intelligent optimal allocation of resources; improves the utilization rate of surgical resources: through surgical disease grouping and stochastic programming models, it helps to improve the utilization rate of surgical resources within the hospital group and improve the level of medical services.

[0076] Furthermore, based on the resource demand characteristics and the resource to be scheduled characteristics, the medical resource scheduling information for the operation to be performed is determined, including:

[0077] Determine a first graph structure corresponding to the surgery to be performed based on the resource demand characteristics;

[0078] For each node in the first graph structure, determine the edge associated with the node; determine the characteristic information of the node based on the edge associated with the node; based on the characteristic information of each node, divide each node into a first node set or a second node set, wherein the data information in the first node set is associated with the operation duration, the operation date, the type of the operating room, the type of the specialist, and the resource demand data, and the data information in the second node set is not associated with the operation duration, the operation date, the type of the operating room, the type of the specialist, and the resource demand data;

[0079] Predicting a first resource requirement for a surgery to be performed using a first deep learning neural network based on data information in the first node set;

[0080] According to the data information in the second node set, a second resource requirement for the surgery to be performed is predicted using a second deep learning neural network,

[0081] Assigning weights to the predicted first resource demand for the surgery to be performed and the predicted second resource demand for the surgery to be performed, respectively, to obtain a simulated resource demand for the surgery to be performed;

[0082] Based on the simulated resource demand for the surgery to be performed and the characteristics of the resources to be scheduled, the medical resource scheduling information for the surgery to be performed is determined.

[0083] Based on the embodiments provided by the present application, the following beneficial effects are achieved: Accurately predict resource requirements: Using deep learning neural networks, such as the first and second neural networks, the amount of resources required for surgery, including manpower, equipment, and supplies, can be accurately predicted based on historical data and related features; Optimize resource allocation: By analyzing the data information of the first and second node sets, the resource requirements of different surgeries can be more accurately predicted, thereby optimizing the allocation and scheduling of resources; Improve surgical efficiency: Based on the predicted simulated resource requirements, surgical plans can be reasonably arranged, surgical waiting time can be reduced, and the efficiency of operating room use can be improved; Enhance emergency response capabilities: Rapidly assess medical resource requirements and conduct effective scheduling to better respond to emergencies and ensure the stable operation of the medical system; Improve patient satisfaction: By ensuring the timely availability of surgical resources, Reduce patient waiting time and improve the quality of medical services, thereby increasing patient satisfaction; Reduce medical costs: Reasonable prediction and scheduling of resources can reduce resource waste, reduce unnecessary costs, and achieve economical use of medical resources; Support decision-making: Provide data support and decision-making basis for hospital management to help them formulate more scientific and reasonable resource allocation strategies; Promote the rational flow of medical resources: Through reasonable prediction and scheduling, the allocation of medical resources between different regions and hospitals can be balanced, and the balanced layout of resources can be promoted; Improve the overall quality of medical services: Through the above steps, the response speed and quality of medical services can be improved to ensure that patients receive timely and effective treatment; Realize personalized medical services: Deep learning models can make personalized resource demand predictions based on the specific circumstances of different patients and surgeries to achieve precision medicine.

[0084] Further, based on the data information in the first node set, a first resource requirement for the surgery to be performed is predicted using a first deep learning neural network, including:

[0085] Constructing a first distributed data set according to the data information in the first node set;

[0086] Using an adaptive learning rate method to adjust the learning rate of each node in the first node set;

[0087]

[0088] Among them, V1 i，j is the learning rate of the i-th node in the first node set at the j-th iteration; W i is the data information of the i-th node in the first node set; u i is the adaptive learning efficiency gradient value of the i-th node in the first node set; k is the learning factor;

[0089] A first resource requirement for a surgery to be performed is predicted using a learning state of the first deep neural network.

[0090] Based on the embodiments provided in this application, the following beneficial effects are achieved: personalized learning rate adjustment: using an adaptive learning rate method, the learning rate can be adjusted according to the specific situation of each node, thereby improving learning efficiency and the convergence speed of the model; optimizing resource allocation: by accurately predicting the first resource demand required for surgery, the hospital can more effectively allocate and utilize limited resources and reduce resource waste; improving the accuracy of surgical scheduling: constructing a first distributed data set, various factors affecting resource demand can be more comprehensively considered, and the accuracy and efficiency of surgical scheduling can be improved; dynamically adjusting learning ability: using an adaptive learning efficiency gradient value, the model can dynamically adjust the learning ability according to data characteristics, thereby enhancing the model's adaptability to complex data; improving prediction accuracy: using First, the learning state of the deep neural network can make more accurate predictions about the resources required for surgery, thereby improving the success rate of surgical preparation and execution; support complex decision-making: through the prediction of the deep learning model, hospital management can better understand the resource demand pattern and support more complex decision-making processes; the use of adaptive learning rates and distributed data sets helps to improve the generalization ability of the model, so that it can adapt to different types of surgeries and resource demand scenarios; improve surgical safety: by ensuring the timely and appropriate supply of surgical resources, the surgical risks caused by insufficient resources can be reduced and patient safety can be improved; promote the rational flow of medical resources: reasonable prediction and scheduling can balance the allocation of medical resources between different regions and hospitals, and promote the balanced layout of resources.

[0091] Further, based on the data information in the second node set, a second deep learning neural network is used to predict a second resource requirement for the surgery to be performed, including:

[0092] Constructing a second distributed data set according to the data information in the second node set;

[0093] Adopting an adaptive learning rate method to adjust the learning rate of each node in the second node set;

[0094]

[0095] Among them, V2 i，j is the learning rate of the i-th node in the second node set at the j-th iteration; W i is the data information of the i-th node in the second node set; u i is the adaptive learning efficiency gradient value of the i-th node in the second node set; k is the learning factor;

[0096] The learning state of the second deep neural network is used to predict a second resource requirement for the surgery to be performed.

[0097] Furthermore, based on the simulated resource demand for the surgery to be performed and the resource scheduling characteristics, the medical resource scheduling information for the surgery to be performed is determined, including:

[0098] Normalizing the simulated resource demand and resource scheduling characteristics for the surgery to be performed;

[0099] The normalized simulated resource demand and resource scheduling features are used as the input layer, and the medical resource scheduling information for the surgery to be performed is used as the output layer. A deep neural network is used for training to predict the medical resource scheduling information for the surgery to be performed.

[0100] The deep neural network includes an input layer, a hidden layer and an output layer; the hidden layer includes multiple layers, wherein the number of nodes in the first hidden layer is equal to three times the number of units in the input layer, and the number of nodes in each subsequent hidden layer gradually decreases; the activation function used in the hidden layer is the sigmoid function; wherein the formula of the sigmoid function is as follows:

[0101]

[0102] In the formula, l i is the category index value, and the j specific indicators corresponding to the i-th category layer indicator are fused through the sigmoid average formula; y1, y2, ..., y j is the index value that needs to be fused by the sigmoid formula, 1≤j≤k; f -1 () is the inverse function of f().

[0103] Furthermore, the surgical care quality requirement data includes preoperative preparation quality requirement data, intraoperative monitoring quality requirement data and postoperative care quality requirement data.

[0104] Alternatively, if Figure 2 As shown, the present application provides a scheduling system for optimizing surgery in a cooperative medical system, including a demand attribute acquisition unit 201, a medical resource status acquisition unit 202, a medical resource screening unit 203 to be scheduled, a medical resource scheduling unit 204, and a medical resource status updating unit 205; wherein,

[0105] The demand attribute acquisition unit 201 is used to acquire the demand attributes of the surgery to be performed; wherein the demand attributes of the surgery to be performed include surgery duration, surgery date, surgical room type, specialist type, resource demand data, patient preference, and surgical nursing quality demand data;

[0106] The medical resource status acquisition unit 202 is used to acquire the usage status information of medical resources from the smart cooperative medical system; wherein the medical resources include operating rooms, doctors, medical equipment, medical consumables, and beds;

[0107] The to-be-scheduled medical resource screening unit 203 is used to screen out idle medical resources from the acquired medical resources to obtain the to-be-scheduled medical resources;

[0108] The medical resource scheduling unit 204 is used to schedule the medical resources to be scheduled according to the demand attributes of the surgery to be performed, and obtain the medical resource scheduling information for the surgery to be performed;

[0109] The medical resource status updating unit 205 is used to upload the medical resource scheduling information for the operation to be performed to the smart cooperative medical system to update the usage status information of the medical resources in the smart cooperative medical system.

[0110] Furthermore, according to the demand attributes of the surgery to be performed, the medical resources to be scheduled are scheduled to obtain the medical resource scheduling information for the surgery to be performed, including:

[0111] Determine a resource scheduling scenario according to resource demand data included in the demand attributes of the surgery to be performed; wherein the resource demand data includes equipment resource demand data, material resource demand data, and technical resource demand data;

[0112] Generate resource demand features using an automated tool based on the resource scheduling scenario and the demand attributes of the surgery to be performed; wherein the automated tool is used to explore and generate resource demand features from the demand attributes of the surgery to be performed using a first deep feature synthesis method;

[0113] According to the resource scheduling scenario and the medical resources to be scheduled, using an automated tool to generate features of the resources to be scheduled; wherein the automated tool is also used to explore and generate features of the resources to be scheduled from the medical resources to be scheduled by a second deep feature synthesis method;

[0114] Based on the resource demand characteristics and the resource scheduling characteristics, determine the medical resource scheduling information for the surgery to be performed.

[0115] Furthermore, based on the resource demand characteristics and the resource to be scheduled characteristics, the medical resource scheduling information for the operation to be performed is determined, including:

[0116] Determine a first graph structure corresponding to the surgery to be performed based on the resource demand characteristics;

[0117] For each node in the first graph structure, determine the edge associated with the node; determine the characteristic information of the node based on the edge associated with the node; based on the characteristic information of each node, divide each node into a first node set or a second node set, wherein the data information in the first node set is associated with the operation duration, the operation date, the type of the operating room, the type of the specialist, and the resource demand data, and the data information in the second node set is not associated with the operation duration, the operation date, the type of the operating room, the type of the specialist, and the resource demand data;

[0118] Predicting a first resource requirement for a surgery to be performed using a first deep learning neural network based on data information in the first node set;

[0119] According to the data information in the second node set, a second resource requirement for the surgery to be performed is predicted using a second deep learning neural network,

[0120] Assigning weights to the predicted first resource demand for the surgery to be performed and the predicted second resource demand for the surgery to be performed, respectively, to obtain a simulated resource demand for the surgery to be performed;

[0121] Based on the simulated resource demand for the surgery to be performed and the characteristics of the resources to be scheduled, the medical resource scheduling information for the surgery to be performed is determined.

[0122] It should be noted that the embodiments implemented by the scheduling system side for surgery optimization in the cooperative medical system provided in this application can refer to the embodiments implemented by the scheduling method side for surgery optimization in the cooperative medical system, and this application will not go into details.

[0123] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A scheduling method for optimizing surgery in a cooperative medical system, characterized in that: include: Obtaining the demand attributes of the surgery to be performed; wherein the demand attributes of the surgery to be performed include surgery duration, surgery date, surgical room type, specialist type, resource demand data, patient preferences, and surgical care quality demand data; Obtaining usage status information of medical resources from the smart cooperative medical system; wherein the medical resources include operating rooms, doctors, medical equipment, medical consumables, and hospital beds; Filter out idle medical resources from the acquired medical resources to obtain medical resources to be scheduled; Scheduling the medical resources to be scheduled according to the demand attributes of the surgery to be performed, and obtaining medical resource scheduling information for the surgery to be performed; The medical resource scheduling information for the operation to be performed is uploaded to the smart cooperative medical system to update the usage status information of the medical resources in the smart cooperative medical system.

2. The method for scheduling surgery optimization in a cooperative medical system according to claim 1, characterized in that: The step of scheduling the medical resources to be scheduled according to the demand attributes of the surgery to be performed, and obtaining the medical resource scheduling information for the surgery to be performed, includes: Determine a resource scheduling scenario according to resource demand data included in the demand attributes of the surgery to be performed; wherein the resource demand data includes equipment resource demand data, material resource demand data, and technical resource demand data; Generate resource demand features using an automated tool according to the resource scheduling scenario and the demand attributes of the surgery to be performed; wherein the automated tool is used to explore and generate the resource demand features from the demand attributes of the surgery to be performed by a first deep feature synthesis method; According to the resource scheduling scenario and the medical resources to be scheduled, the automated tool is used to generate resource scheduling features; wherein the automated tool is further used to explore and generate the resource scheduling features from the medical resources to be scheduled by a second deep feature synthesis method; Based on the resource demand characteristics and the resource scheduling characteristics, medical resource scheduling information for the surgery to be performed is determined.

3. The method for scheduling surgery optimization in a cooperative medical system according to claim 2, characterized in that: The determining of the medical resource scheduling information for the operation to be performed based on the resource demand characteristics and the resource scheduling characteristics includes: Determine a first graph structure corresponding to the surgery to be performed based on the resource demand characteristics; For each node in the first graph structure, determine the edge associated with the node; determine the characteristic information of the node based on the edge associated with the node; based on the characteristic information of each node, divide each node into a first node set or a second node set, wherein the data information in the first node set is associated with the operation duration, operation date, operation room type, specialist type and resource demand data, and the data information in the second node set is not associated with the operation duration, operation date, operation room type, specialist type and resource demand data; Predicting a first resource requirement for the surgery to be performed using a first deep learning neural network based on the data information in the first node set; According to the data information in the second node set, a second resource requirement for the operation to be performed is predicted using a second deep learning neural network, Assigning weights to the first resource requirement predicted for the operation to be performed and the second resource requirement predicted for the operation to be performed, respectively, to obtain a simulated resource requirement for the operation to be performed; Based on the simulated resource demand for the operation to be performed and the characteristics of the resources to be scheduled, medical resource scheduling information for the operation to be performed is determined.

4. The method for scheduling surgery optimization in a cooperative medical system according to claim 3, characterized in that: The method of predicting a first resource requirement for the surgery to be performed using a first deep learning neural network according to the data information in the first node set includes: Constructing a first distributed data set according to the data information in the first node set; Using an adaptive learning rate method to adjust the learning rate of each node in the first node set; The learning state of the first deep neural network is used to predict a first resource requirement for the surgery to be performed.

5. The method for scheduling surgery optimization in a cooperative medical system according to claim 3, characterized in that: The method of predicting a second resource requirement for the surgery to be performed using a second deep learning neural network according to the data information in the second node set includes: Constructing a second distributed data set according to the data information in the second node set; Using an adaptive learning rate method to adjust the learning rate of each node in the second node set; The learning state of the second deep neural network is used to predict a second resource requirement for the surgery to be performed.

6. The method for scheduling surgery optimization in a cooperative medical system according to claim 3, characterized in that: The determining of the medical resource scheduling information for the surgery to be performed based on the simulated resource demand for the surgery to be performed and the resource scheduling characteristics includes: Normalizing the simulated resource demand for the surgery to be performed and the resource scheduling characteristics; The simulated resource demand and the resource scheduling characteristics after normalization are used as the input layer, and the medical resource scheduling information for the operation to be performed is used as the output layer, and a deep neural network is used for training to predict the medical resource scheduling information for the operation to be performed; Among them, the deep neural network includes the input layer, the hidden layer and the output layer; the hidden layer includes multiple layers, among which the number of nodes in the first hidden layer is equal to three times the number of units in the input layer, and the number of nodes in each subsequent hidden layer gradually decreases; the activation function used by the hidden layer is the sigmoid function.

7. The method for scheduling surgery optimization in a cooperative medical system according to claim 1, characterized in that: The surgical care quality requirement data includes preoperative preparation quality requirement data, intraoperative monitoring quality requirement data and postoperative care quality requirement data.

8. A scheduling system for optimizing surgery in a cooperative medical system, characterized in that: It includes a demand attribute acquisition unit, a medical resource status acquisition unit, a medical resource screening unit to be scheduled, a medical resource scheduling unit and a medical resource status update unit; wherein, The demand attribute acquisition unit is used to acquire the demand attributes of the surgery to be performed; wherein the demand attributes of the surgery to be performed include surgery duration, surgery date, surgical room type, specialist type, resource demand data, patient preferences, and surgical care quality demand data; The medical resource status acquisition unit is used to acquire the usage status information of medical resources from the smart cooperative medical system; wherein the medical resources include operating rooms, doctors, medical equipment, medical consumables, and hospital beds; The to-be-scheduled medical resource screening unit is used to screen out idle medical resources from the acquired medical resources to obtain the to-be-scheduled medical resources; The medical resource scheduling unit is used to schedule the medical resources to be scheduled according to the demand attributes of the surgery to be performed, and obtain medical resource scheduling information for the surgery to be performed; The medical resource status updating unit is used to upload the medical resource scheduling information for the operation to be performed to the smart cooperative medical system to update the usage status information of the medical resources in the smart cooperative medical system.

9. The operation optimization scheduling system in the cooperative medical system according to claim 8, characterized in that: The step of scheduling the medical resources to be scheduled according to the demand attributes of the surgery to be performed, and obtaining the medical resource scheduling information for the surgery to be performed, includes: Determine a resource scheduling scenario according to resource demand data included in the demand attributes of the surgery to be performed; wherein the resource demand data includes equipment resource demand data, material resource demand data, and technical resource demand data; Generate resource demand features using an automated tool according to the resource scheduling scenario and the demand attributes of the surgery to be performed; wherein the automated tool is used to explore and generate the resource demand features from the demand attributes of the surgery to be performed by a first deep feature synthesis method; According to the resource scheduling scenario and the medical resources to be scheduled, the automated tool is used to generate resource scheduling features; wherein the automated tool is further used to explore and generate the resource scheduling features from the medical resources to be scheduled by a second deep feature synthesis method; Based on the resource demand characteristics and the resource scheduling characteristics, medical resource scheduling information for the surgery to be performed is determined.

10. The operation optimization scheduling system in the cooperative medical system according to claim 8, characterized in that: The determining of the medical resource scheduling information for the operation to be performed based on the resource demand characteristics and the resource scheduling characteristics includes: Determine a first graph structure corresponding to the surgery to be performed based on the resource demand characteristics; For each node in the first graph structure, determine the edge associated with the node; determine the characteristic information of the node based on the edge associated with the node; based on the characteristic information of each node, divide each node into a first node set or a second node set, wherein the data information in the first node set is associated with the operation duration, operation date, operation room type, specialist type and resource demand data, and the data information in the second node set is not associated with the operation duration, operation date, operation room type, specialist type and resource demand data; Predicting a first resource requirement for the surgery to be performed using a first deep learning neural network based on the data information in the first node set; According to the data information in the second node set, a second resource requirement for the operation to be performed is predicted using a second deep learning neural network, Assigning weights to the first resource requirement predicted for the operation to be performed and the second resource requirement predicted for the operation to be performed, respectively, to obtain a simulated resource requirement for the operation to be performed; Based on the simulated resource demand for the operation to be performed and the characteristics of the resources to be scheduled, medical resource scheduling information for the operation to be performed is determined.

Images