Urban dangerous case medical demand dynamic prediction and resource scheduling method and system

Abstract

The invention discloses an urban dangerous case medical demand dynamic prediction and resource scheduling method and system, and relates to the technical field of scheduling optimization. Comprising the steps of obtaining current data and historical dangerous case data of a target area, adopting a support vector machine regression method to construct an urban casualty population prediction model, performing training based on the historical dangerous case data to obtain the trained urban casualty population prediction model, inputting the current data to obtain the number of current casualties, and predicting the number of the current casualties. The method comprises the following steps: determining health rescue strength and medical material requirements, decomposing the rescue strength to form a plurality of rescue units, determining a rescue priority based on current data, distributing the rescue units according to the rescue priority, associating the rescue units with the medical material requirements, constructing a rescue process, obtaining a real-time rescue result, and dynamically adjusting the rescue priority. According to the invention, accurate prediction of urban dangerous case medical demands and efficient scheduling of medical resources can be realized, and the response speed and rescue effect of urban emergency medical rescue are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of scheduling optimization, in particular to a city danger medical demand dynamic prediction and resource scheduling method and system. BACKGROUND

[0002] City emergencies (such as natural disasters, accidents, public health events) have the characteristics of strong suddenness, great destructiveness and wide influence, and often produce a large number of casualties in a very short time, posing a serious challenge to the medical rescue system. The traditional rescue mode relying on experience and static plan is difficult to cope with the complex and variable on-site situation, often leading to resource mismatch, response delay, and ultimately affecting the rescue effect.

[0003] Therefore, a city danger medical demand dynamic prediction and resource scheduling method and system are proposed to solve the problems existing in the prior art, which is a problem that needs to be solved by those skilled in the art. SUMMARY

[0004] Therefore, the present application provides a city danger medical demand dynamic prediction and resource scheduling method and system, which realizes accurate prediction of city danger medical demand and efficient scheduling of medical resources, and improves the response speed and rescue effect of city emergency medical rescue.

[0005] In order to achieve the above purpose, the present application adopts the following technical scheme: A city danger medical demand dynamic prediction and resource scheduling method, comprising the following steps: Obtaining current data and historical danger data of a target area; Using a support vector machine regression method to construct a city casualty population prediction model, training based on historical danger data to obtain a trained city casualty population prediction model, inputting current data to obtain current casualty number, and determining health rescue force and medical material demand; Decomposing the rescue force to form a plurality of rescue units, determining the rescue priority based on the current data, and distributing the rescue units according to the rescue priority; Associating the rescue units with the medical material demand, constructing a treatment process, obtaining real-time rescue results, and dynamically adjusting the rescue priority.

[0006] Optionally, the city casualty population prediction model comprises: generating training data based on historical danger data, constructing a non-linear relationship between internal data to be predicted vectors and support vectors, and predicting the to-be-predicted vectors of the test data.

[0007] Optionally, decomposing the rescue force comprises: determining the rescue force according to the target area and the current casualty number, constructing a scheduling system according to the rescue force, and the scheduling system comprises: The main control unit, a plurality of sub-control units, a plurality of doctor units and a plurality of nurse units, each sub-control unit corresponds to a plurality of doctor units and a plurality of nurse units, the main control unit is used for target area grid division and grid labeling, and one or more sub-control units are allocated to different grids based on rescue forces, the sub-control unit sends a position signal to the doctor unit and the nurse unit after receiving the main control unit signal, and the doctor unit and the nurse unit determine the grid area to go to rescue according to the position signal.

[0008] Optionally, the doctor unit is divided into idle state and diagnosis state, and the nurse unit is divided into idle state and nursing state, when there are people to be rescued in the area, the sub-control unit dispatches the idle state doctor unit to rescue, the doctor unit judges the personnel state, the personnel state is divided into emergency, serious and general, the rescue priority is determined according to the personnel state, the weight is allocated to different personnel states to generate area index, the rescue priority is determined according to the area index, and the main control unit allocates a plurality of sub-control units to the area with high rescue priority.

[0009] Optionally, the construction of the treatment process includes: Traverse the treatment technology used by the doctor unit and the nurse unit for the different states of the people to be rescued, configure the health consumption resources required for the treatment technology, obtain the corresponding medical supplies under different personnel states, allocate the medical supplies according to the different grid data of the target area, determine the medical supply allocation path and the emergency personnel transfer path, and summarize the treatment process.

[0010] Optionally, when the personnel state is emergency, the sub-control unit directly allocates the doctor unit and the nurse unit, the doctor unit performs emergency treatment on the person to be rescued, and the nurse unit transfers the person treated to the ambulance, and the ambulance transports the person to the rear for treatment; When the personnel state is serious, the sub-control unit allocates the idle state doctor unit, if there is no idle state doctor unit, the information is sent to the doctor unit with general priority for the current patient; When the personnel state is general, the sub-control unit allocates the idle state doctor unit, if there is no idle state doctor unit, it waits until there is an idle state doctor unit, and the doctor unit deletes the information of the person to be rescued in the main control unit after completing the treatment of the person to be rescued; Set an interval time, the target area determines the area index of the target area according to the interval time and the current number of people to be rescued, and the rescue priority is determined again according to the area index.

[0011] A city danger medical demand dynamic prediction and resource scheduling system is used to realize any one of the above city danger medical demand dynamic prediction and resource scheduling methods, comprising a data acquisition module, a demand prediction module, a resource scheduling module and a data feedback module connected in turn: Data acquisition module: acquire current data and historical hazard data of the target area, Demand prediction module: build and train the current city casualty population prediction model to determine the demand for health rescue forces and medical supplies; Resource scheduling module: determine the rescue priority and schedule the rescue forces based on the priority; Data feedback module: associate health rescue forces and medical supply demand, build a treatment process, obtain real-time rescue results, and dynamically adjust the priority.

[0012] According to the above technical solution, compared with the prior art, the present application provides a city hazard medical demand dynamic prediction and resource scheduling method and system, which has the following beneficial effects: the present application can quickly and accurately determine the rescue demand, realize accurate prediction of city hazard medical demand and efficient scheduling of medical resources, and improve the response speed and rescue effect of city emergency medical rescue. BRIEF DESCRIPTION OF DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to the provided drawings without creative labor.

[0014] Figure 1 A city hazard medical demand dynamic prediction and resource scheduling method flow chart is provided for the present application. Figure 2 A city hazard medical demand dynamic prediction and resource scheduling system structure block diagram is provided for the present application. DETAILED DESCRIPTION

[0015] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0016] Referring to Figure 1 The present application discloses a city hazard medical demand dynamic prediction and resource scheduling method, comprising the following steps: Acquire current data and historical hazard data of the target area; A support vector machine regression method is used to construct an urban casualty population prediction model. The model is trained based on historical disaster data to obtain a well-trained urban casualty population prediction model. The current number of casualties is obtained by inputting the current data, and the needs of health rescue forces and medical supplies are determined. The rescue forces are broken down into multiple rescue units, rescue priorities are determined based on current data, and rescue units are allocated according to the rescue priorities. By linking rescue units with medical supply needs, a treatment process can be established to obtain real-time rescue results and dynamically adjust rescue priorities.

[0017] Furthermore, current data and historical risk data, including regional population information, medical institution information, and geographic information, are used to generate data samples, which then form a multivariate time series and undergo data cleaning and preprocessing.

[0018] Specifically, regional population information data includes information such as the total population of the target area, population age structure, gender ratio, and population density; The medical institution information data includes the number, type, number of beds, number of medical staff, medical equipment, and drug reserves of various types of medical institutions within the target area; Geographic information data includes the topography, road network distribution, building distribution, and location of important infrastructure in the target area.

[0019] Furthermore, the urban casualty population prediction model includes: generating training data based on historical hazard data, constructing a nonlinear relationship between the vector to be predicted and the support vector within the data, and predicting the vector to be predicted in the test data.

[0020] Specifically, the Support Vector Machine (SVM) regression method introduces a kernel function to map the nonlinear problem in the input space to a high-dimensional feature space, thereby constructing a linear regression model in the high-dimensional space to describe the nonlinear relationship between the vector to be predicted and the support vectors. Commonly used kernel functions include linear kernel functions, polynomial kernel functions, and radial basis function kernel functions. After the model is trained, test data is used to evaluate its performance. The test data is also selected from historical incident data and is independent of the training data. The input portion of the test data is fed into the trained model to obtain the predicted number of casualties, which is then compared with the actual number of casualties. The model's prediction accuracy is evaluated by calculating indicators such as error. If the model's prediction accuracy meets the requirements, it can be used for actual predictions; if it does not meet the requirements, the model parameters need to be readjusted or a different kernel function needs to be selected, and the model needs to be retrained and evaluated until it meets the prediction requirements.

[0021] Furthermore, the allocation of rescue forces includes: determining rescue forces based on the target area and the current number of casualties, and constructing a dispatch system based on these rescue forces. The dispatch system includes: The system consists of a main control unit, multiple sub-control units, multiple doctor units, and multiple nurse units. Each sub-control unit corresponds to multiple doctor units and multiple nurse units. The main control unit is used to divide the target area into grids and mark the grids. Based on the rescue force, one or more sub-control units are assigned to different grids. After receiving the signal from the main control unit, the sub-control unit sends a location signal to the doctor units and nurse units. The doctor units and nurse units determine the grid area based on the location signal and go to the rescue.

[0022] Furthermore, the doctor unit is divided into idle state and treatment state, and the nurse unit is divided into idle state and nursing state. When there are people in need of rescue in the area, the sub-control unit dispatches the idle doctor unit to provide assistance. The doctor unit judges the person's status, which is divided into emergency, serious and general. The rescue priority is determined according to the person's status. Weights are assigned to different person statuses to generate regional indicators. The rescue priority is determined according to the regional indicators. The main control unit allocates multiple sub-control units to areas with high rescue priority.

[0023] Furthermore, the construction of the treatment process includes: The system iterates through the medical and nursing units to identify the treatment techniques used to assist individuals in different states, allocates the necessary health resources to complete the treatment, obtains the medical supplies corresponding to different individuals' states, distributes medical supplies based on different grid data in the target area, determines the medical supply distribution path and the emergency personnel transfer path, and summarizes the treatment process.

[0024] Specifically, a standardized medical treatment technology database will be established, clearly defining the required standard medical resource packages for each treatment technology. This will map different injury states to the set of treatment technologies most likely to be needed, and then link them to the expected spectrum of medical supply needs. For example, patients in the emergency room are likely to require control of massive bleeding, airway management, and establishment of intravenous access; therefore, the emergency room state will be associated with a large amount of dressings, hemostatic agents, airway equipment, and infusion kits. In severe cases, fracture immobilization, wound suturing, and pain relief are likely required, thus involving splints, suture packs, and painkillers. In general, the main needs are cleaning and bandaging, so a small amount of disinfectant and bandages are needed.

[0025] Furthermore, when a person's status is emergency, the sub-control unit directly assigns a doctor unit and a nurse unit. The doctor unit provides emergency treatment to the person being rescued, and the nurse unit transfers the person after emergency treatment to the ambulance. The ambulance then transports the person to the rear for further treatment. When the patient's condition is critical, the sub-control unit assigns an idle doctor unit. If there is no idle doctor unit, the information is sent to the doctor unit currently handling the patient with the priority of normal. When the personnel status is normal, the sub-control unit assigns an idle doctor unit. If there is no idle doctor unit, it waits until an idle doctor unit becomes available. After the doctor unit finishes processing the person to be rescued, the information of the person to be rescued is deleted from the main control unit. Set an interval time, and determine the regional indicators of the target area based on the interval time and the current number of people in need of rescue. Then, redetermine the rescue priority based on the regional indicators.

[0026] Furthermore, when specific events are sent, such as significant changes in the situation, availability of resources, or completion of high-priority tasks, the system automatically triggers an update cycle.

[0027] A system for dynamic prediction and resource scheduling of medical needs in urban emergencies, and a method for dynamic prediction and resource scheduling of medical needs in urban emergencies, as described above, referencing... Figure 2 As shown, it includes a data acquisition module, a demand forecasting module, a resource scheduling module, and a data feedback module connected in sequence: Data acquisition module: Acquires current data and historical hazard data for the target area. Demand forecasting module: Builds and trains a current urban casualty population prediction model to determine the demand for health relief forces and medical supplies; Resource scheduling module: Determines rescue priorities and schedules rescue forces based on these priorities; Data feedback module: Links health rescue forces with medical supply needs, constructs treatment processes, obtains real-time rescue results, and dynamically adjusts priorities.

[0028] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for dynamic prediction and resource allocation of medical needs in urban emergencies, characterized in that, Includes the following steps: Obtain current data and historical hazard data for the target area; A support vector machine regression method is used to construct an urban casualty population prediction model. The model is trained based on historical disaster data to obtain a well-trained urban casualty population prediction model. The current number of casualties is obtained by inputting the current data, and the needs of health rescue forces and medical supplies are determined. The rescue forces are broken down into multiple rescue units, rescue priorities are determined based on current data, and rescue units are allocated according to the rescue priorities. By linking rescue units with medical supply needs, a treatment process can be established to obtain real-time rescue results and dynamically adjust rescue priorities.

2. The method for dynamic prediction and resource scheduling of urban emergency medical needs according to claim 1, characterized in that, The urban casualty population prediction model includes: generating training data based on historical hazard data, constructing a nonlinear relationship between the vector to be predicted and the support vector within the data, and predicting the vector to be predicted in the test data.

3. The method for dynamic prediction and resource scheduling of urban emergency medical needs according to claim 1, characterized in that, Decomposing rescue forces includes: determining rescue forces based on the target area and the current number of casualties; and constructing a dispatch system based on these rescue forces. The dispatch system includes: The system consists of a main control unit, multiple sub-control units, multiple doctor units, and multiple nurse units. Each sub-control unit corresponds to multiple doctor units and multiple nurse units. The main control unit is used to divide the target area into grids and mark the grids. Based on the rescue force, one or more sub-control units are assigned to different grids. After receiving the signal from the main control unit, the sub-control unit sends a location signal to the doctor units and nurse units. The doctor units and nurse units determine the grid area based on the location signal and go to the rescue.

4. The method for dynamic prediction and resource scheduling of urban emergency medical needs according to claim 3, characterized in that, The doctor unit is divided into an idle state and a treatment state, and the nurse unit is divided into an idle state and a nursing state. When there are people in need of rescue in the area, the sub-control unit dispatches the doctor unit in the idle state to provide assistance. The doctor unit judges the status of the person, which is divided into emergency, serious and general. The rescue priority is determined according to the status of the person. Weights are assigned to different statuses to generate regional indicators. The rescue priority is determined according to the regional indicators. The main control unit allocates multiple sub-control units to areas with high rescue priority.

5. The method for dynamic prediction and resource scheduling of urban emergency medical needs according to claim 4, characterized in that, The establishment of the treatment process includes: The system iterates through the medical and nursing units to identify the treatment techniques used to assist individuals in different states, allocates the necessary health resources to complete the treatment, obtains the medical supplies corresponding to different individuals' states, distributes medical supplies based on different grid data in the target area, determines the medical supply distribution path and the emergency personnel transfer path, and summarizes the treatment process.

6. The method for dynamic prediction and resource scheduling of urban emergency medical needs according to claim 5, characterized in that, Dynamically adjusting rescue priorities includes: When a person's status is emergency, the sub-control unit directly assigns a doctor unit and a nurse unit. The doctor unit provides emergency treatment to the person being rescued, and the nurse unit transfers the person after emergency treatment to the ambulance. The ambulance then transports the person to the rear for further treatment. When the patient's condition is critical, the sub-control unit assigns an idle doctor unit. If there is no idle doctor unit, the information is sent to the doctor unit currently handling the patient with the priority of normal. When the personnel status is normal, the sub-control unit assigns an idle doctor unit. If there is no idle doctor unit, it waits until an idle doctor unit becomes available. After the doctor unit finishes processing the person to be rescued, the information of the person to be rescued is deleted from the main control unit. Set an interval time, and determine the regional indicators of the target area based on the interval time and the current number of people in need of rescue. Then, redetermine the rescue priority based on the regional indicators.

7. A dynamic prediction and resource scheduling system for urban emergency medical needs, used to implement the dynamic prediction and resource scheduling method for urban emergency medical needs as described in any one of claims 1-6, characterized in that, It includes a data acquisition module, a demand forecasting module, a resource scheduling module, and a data feedback module, which are connected in sequence: Data acquisition module: Acquires current data and historical hazard data for the target area. Demand forecasting module: Builds and trains a current urban casualty population prediction model to determine the demand for health relief forces and medical supplies; Resource scheduling module: Determines rescue priorities and schedules rescue forces based on these priorities; Data feedback module: Links health rescue forces with medical supply needs, constructs treatment processes, obtains real-time rescue results, and dynamically adjusts priorities.

Images