A dynamic route planning method for emergency medical system

Abstract

The present invention provides a dynamic route planning method for an emergency medical system, comprising obtaining an emergency medical request data set, including patient vital signs, location coordinates, and the real-time location of an emergency medical vehicle; real-time collection of dynamic traffic data, including traffic speed, traffic control area, accident point coordinates, and severity level; and obtaining medical institution status data, including reception capacity, emergency channel occupancy status, and resource matching parameters. Based on the above data, an initial path set is calculated using an improved dynamic modulation factor, and the paths are prioritized using a three-dimensional demodulation matrix. The final navigation path is generated through multi-level logical judgment, including fuel quantity judgment, accident point impact update, and medical institution status calibration. Finally, the dynamic modulation factor is corrected according to the path execution time deviation. The present invention can improve the efficiency and success rate of emergency medical treatment, and gain precious treatment time for patients.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent transportation and medical emergency, and more particularly to a dynamic route planning method for an emergency system. Background Art

[0002] In modern cities, the efficient operation of emergency medical systems is crucial to saving lives. Existing emergency route planning methods primarily rely on static map information and simple shortest path algorithms. While these methods can meet basic navigation needs to a certain extent, they fail to fully consider dynamic factors such as real-time traffic conditions, accident risks, the status of medical institution resources, and patient vital signs. This single-minded planning approach often leads to extended emergency vehicle travel times and mismatched resources when faced with complex urban traffic environments and urgent medical needs, thus compromising emergency response efficiency and success rates.

[0003] With the development of intelligent transportation technology, the collection and processing of dynamic traffic information has gradually matured, providing the potential for optimizing emergency route planning. However, existing dynamic route planning methods mostly focus solely on real-time updates of traffic conditions, ignoring key factors such as the urgency of the patient's condition, the safety risks at the incident site, and the capacity of medical institutions. These omissions prevent existing systems from achieving truly intelligent emergency route planning.

[0004] There are at least the following problems or defects in the existing technology: the existing emergency route planning method is unable to integrate multi-dimensional data such as dynamic traffic data, accident risk information, medical institution resource status, and patient vital signs in real time, resulting in insufficient path planning accuracy and inability to effectively respond to complex and changeable emergency scenarios, thereby affecting emergency efficiency and patient treatment success rate. Summary of the Invention

[0005] The present invention provides a dynamic route planning method for an emergency system, comprising:

[0006] S1. Obtain an emergency request data set, which includes patient vital sign parameters G p , patient position coordinates (X p , Y p ), the real-time position coordinates of the emergency vehicle (X v , Y v );

[0007] S2. Real-time collection of dynamic traffic data sets in the target area, including the traffic speed v of each road section k , traffic control area coordinate set (X c , Y c ), real-time accident point coordinate queue (X a , Y a) and its accident severity level s a ;

[0008] S3. Obtain the medical institution status dataset, including the emergency department admission capacity C h , Emergency channel occupied status O h , medical resource matching parameter R m ;

[0009] S4. Based on the emergency request data set (X p , Y p )、(X v , Y v ), v in the dynamic traffic dataset k 、(X a , Y a ), and O in the medical institution status dataset h 、R m , calculate the initial path set P through the improved dynamic modulation factor λ(t) initial , where λ(t) includes the time dimension weight coefficient α and the space dimension weight coefficient β;

[0010] S5. Using the three-dimensional demodulation matrix M 3d For the initial path set P initial Prioritize the three-dimensional demodulation matrix M 3d The dimensions include: path safety parameter S calculated based on real-time accident point data p , based on the road segment speed v k The timeliness parameter T p , based on the medical resource matching parameter R m and emergency department admission capacity C h Resource matching parameter R p ;

[0011] S6. Execute multi-level logical judgment to generate the final navigation path P final , specifically including:

[0012] S61. Based on the fuel quantity Q of the emergency vehicle v With threshold Q min The comparison result triggers path recalculation;

[0013] S62. Based on real-time accident point queue (X a , Y a ) in a Update the road section speed v′ k ;

[0014] S63. Combine C in the medical institution status dataset h and O h Calibrated path score Pscore ;

[0015] S7. Modify the dynamic modulation factor λ(t) according to the path execution time deviation Δτ.

[0016] Furthermore, the improved dynamic modulation factor calculation in step S4 includes:

[0017] S41. Constructing space-time coupling function:

[0018] λ(t)=α·F(t)+β·S(t)+γ·W(t),

[0019] in, represents the traffic flow change rate calculated based on the dynamic traffic dataset, represents the spatial complexity of the calculation based on the road topology structure, d i is the node distance, d0 is the regional feature distance, W(t)=1-exp(-w rain ·R w ) represents the weather impact factor calculated based on meteorological data, R w is the rainfall intensity, α, β, and γ are normalized weight coefficients;

[0020] S42. Calculate the dynamic weight of the road segment:

[0021] W ij =exp(-λ(t)·d ij / v k )+μ·O h , where d ij is the actual distance from node i to node j, μ is the medical resource impact coefficient defined based on the medical institution status dataset, O h The emergency channel is occupied, v k is the original road section speed;

[0022] S43. Generate dynamic adjacency matrix A(t)=[W ij ·δ(t)], where is the accident point attenuation factor, represents the impact attenuation of the mth accident point, τ is the time attenuation constant, t m is the occurrence time of the accident point m.

[0023] Furthermore, the three-dimensional demodulation matrix construction in step S5 includes:

[0024] S51. Calculate path security dimension parameters:

[0025] Among them, ω k is the safety weight of road section k calculated based on historical accident data, is the aggregate impact of the accident point, M k is the set of accident points associated with road section k;

[0026] S52. Calculate the timeliness dimension parameters:

[0027] T p =θ / (v a vg·(1+Δv / v a vg)), where θ is the total path length, Based on the dynamic traffic dataset v k Calculated weighted average speed, l k is the length of road section k, is the velocity fluctuation;

[0028] S53. Calculate resource matching dimension parameters:

[0029] R p =σ·R m ·exp(-|C h -C need | / C0), where σ is the specialty matching degree calculated based on the patient's symptoms, Medical resources required for the patient's condition, w s is the weight of symptom s, c s To correspond to resource demand, C0 is the capacity benchmark constant.

[0030] Furthermore, step S61 includes:

[0031] S611. When Q v <Q min When the emergency vehicle real-time location (X v , Y v ) and the gas station coordinates in the dynamic traffic dataset (X g , Y g ), generate a set of alternative paths

[0032] S612. According to the scoring model P alt reorder;

[0033] S613. Select the one that satisfies min(T p ) and S p >S th The path as P final , where S th The preset safety threshold.

[0034] Furthermore, step S62 includes:

[0035] S621. For each accident point (X a, Y a ), based on its severity level a Calculate the influence radius r a =r0·(1+0.5·s a ), where sa∈[1,3] comes from the real-time accident point queue data;

[0036] S622. Update road section speed:

[0037] Among them, d ka is the shortest distance between road section k and accident point a, A k is the set of accident points affecting road section k;

[0038] S623. When there is v′ k <v min When , the corresponding road segment is deleted and a new adjacency matrix A′(t) is generated.

[0039] Furthermore, step S63 includes:

[0040] S631. Based on the O in the medical institution status data set h and C h , calculate the load factor L h =O h / +0.2·(C h -C need ) / C h ;

[0041] S632. Dynamically adjust resource matching weight: ξ R =1 / (1+exp(-5·(L h -0.8))), where ξ R ∈[0, 1];

[0042] S633. Generate calibrated path score: P score =0.5·T p +0.3·S p +0.2·ξ R ·R p .

[0043] Furthermore, step S7 includes:

[0044] S71. Record the execution time deviation of each path

[0045] S72. Calculate the modulation factor correction:

[0046] Where σ is the standard deviation of the deviation distribution;

[0047] S73. Update dynamic modulation factor: λ′(t)=λ(t)+Δλ·tanh(∑|Δτ j |τ0), τ0 is the preset time base constant.

[0048] Furthermore, the medical resource matching parameter R m The calculation includes:

[0049] S81. Construct disease-resource mapping matrix D = [d ij ] m×n , where d ij =1 means disease i requires resource j, d ij =0 means that disease i does not require resource j;

[0050] S82. Based on the patient's vital sign parameters G p Generate symptom vector S p =[s1,...,s n ],s k ∈[0, 1] represents the severity of symptom k;

[0051] S83. Based on matrix D and vector S p Generate matching parameters:

[0052] Among them, C hj is the capacity of resource j, O hj is the occupancy of resource j.

[0053] Furthermore, the safety weight ω k The calculation includes:

[0054] S91. Obtain historical accident frequency of road section k N k (t) is the number of accidents during period t;

[0055] S92. Calculate road condition coefficient ρ k =0.6·w width +0.4·w light , w width ∈[0, 1] is the lane width score, w light ∈[0, 1] is the lighting score;

[0056] S93. Generate dynamic security weight: ω k =(1-f k )·ρ k +0.1·exp(-v k / v max ), v max Speed limit for the road section.

[0057] Furthermore, the calculation of the specialty matching degree σ includes:

[0058] S101. Extract the patient's main symptoms max =argmax(S p );

[0059] S102. Query the mapping table to obtain σ0=D(s max , h current ), h current Provide specialized equipment for medical institutions;

[0060] S103. Calculate the dynamic matching degree: σ=σ0·[1-0.5·exp(-t delay / t h )],t delay is the delay time, t h is the disease half-life parameter.

[0061] The above-described embodiments of the present invention have at least the following beneficial effects: The present invention's dynamic route planning method for emergency medical systems comprehensively considers multiple factors, including patient vital signs, real-time traffic conditions, accident risks, and the availability of medical institution resources. It dynamically optimizes and prioritizes routes using an improved dynamic modulation factor and a three-dimensional demodulation matrix. This method dynamically adjusts route planning based on real-time data, ensuring that emergency vehicles choose the optimal route in complex urban traffic environments, thereby effectively shortening emergency response time and improving emergency efficiency.

[0062] Furthermore, the present invention utilizes a multi-level logic judgment mechanism to calibrate path scores and modify dynamic modulation factors in real time, further enhancing the adaptability and accuracy of path planning. Combining medical institution status data with patient needs, this method enables precise resource matching, ensuring patients are transported to the most appropriate medical institution in the shortest possible time, thereby improving both the success rate of emergency treatment and the quality of patient care. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily apparent by reading the following detailed description with reference to the accompanying drawings, in which several embodiments of the present invention are shown by way of example and not limitation, in which:

[0064] Figure 1 A flowchart of a dynamic route planning method for an emergency medical system provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0065] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided solely to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. Rather, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0066] Those skilled in the art will appreciate that the embodiments of the present invention may be implemented as a system, apparatus, device, method, or computer program product. Therefore, the present invention may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software.

[0067] It should be noted that any number of elements in the drawings is for illustration only and not for limitation, and any naming is only for distinction and does not have any limiting meaning.

[0068] Reference below Figure 1 , Figure 1 This is a flow chart of a dynamic route planning method for an emergency system provided by an embodiment of the present invention. Figure 1 As shown, a dynamic route planning method for an emergency system includes:

[0069] S1. Obtain an emergency request data set, which includes patient vital sign parameters G p , patient position coordinates (X p , Y p ), the real-time position coordinates of the emergency vehicle (X v , Y v );

[0070] S2. Real-time collection of dynamic traffic data sets in the target area, including the traffic speed v of each road section k Traffic control area coordinate set (X c , Y c ), real-time accident point coordinate queue (X a , Y a ) and its accident severity level s a ;

[0071] S3. Obtain the medical institution status dataset, including the emergency department admission capacity C h , Emergency channel occupied status O h , medical resource matching parameter R m ;

[0072] S4. Based on the emergency request data set (X p , Y p )、(X v , Yv ), v in the dynamic traffic dataset k 、(X a , Y a ), and O in the medical institution status dataset h 、R m , calculate the initial path set P through the improved dynamic modulation factor λ(t) initial , where λ(t) includes the time dimension weight coefficient α and the space dimension weight coefficient β;

[0073] S5. Using the three-dimensional demodulation matrix M 3d P initial Prioritize and sort the three-dimensional demodulation matrix M 3d The dimensions include: path safety parameter S calculated based on real-time accident point data p , based on the road segment speed v k The timeliness parameter T p , based on R m and C h Resource matching parameter R p ;

[0074] S6. Execute multi-level logical judgment to generate the final navigation path P final , specifically including:

[0075] S61. Based on the fuel quantity Q of the emergency vehicle v With threshold Q min The comparison result triggers path recalculation;

[0076] S62. Based on real-time accident point queue (X a , Y a ) in a Update the road section speed v′ k ;

[0077] S63. Combine C in the medical institution status dataset h and O h Calibrated path score P score ;

[0078] S7. Modify the dynamic modulation factor λ(t) according to the path execution time deviation Δτ.

[0079] It should be noted that the dynamic route planning method for the emergency system of the present invention obtains an emergency request data set, a dynamic traffic data set, and a medical institution status data set, and optimizes and sorts the path in combination with an improved dynamic modulation factor and a three-dimensional demodulation matrix. Among them, the emergency request data set includes the patient's vital signs parameters, the patient's location coordinates, and the real-time location coordinates of the emergency vehicle. These data are the basic information for path planning. The dynamic traffic data set covers the traffic speed of each road section, the traffic control area coordinate set, the real-time accident point coordinate queue and its accident severity level. These data can reflect the dynamic changes in the current traffic conditions. The medical institution status data set includes the emergency department's reception capacity, the occupancy status of the emergency channel, and the medical resource matching parameters. These data are used to evaluate the reception capacity of the target medical institution. Through the comprehensive analysis of these data, dynamic planning of emergency routes can be achieved, ensuring that emergency vehicles can quickly and safely transport patients to the most suitable medical institution.

[0080] Specifically, patient vital sign parameters in the emergency request dataset refer to indicators of the patient's current health status, such as heart rate, blood pressure, and respiratory rate. These parameters can reflect the urgency of the patient's condition. The patient's location coordinates and the real-time location coordinates of the emergency vehicle are obtained through a GPS positioning system to determine the relative position between the emergency vehicle and the patient, facilitating a rapid response. Traffic speeds in the dynamic traffic dataset can be obtained in real time from traffic sensors or vehicle driving data. Traffic control area coordinates are derived from control information released by traffic management authorities. Real-time accident point coordinates and their severity levels are obtained from traffic monitoring systems or accident alarm systems. Emergency department capacity in the medical institution status dataset refers to the number of patients a medical institution can accept within a certain timeframe. Emergency channel occupancy status is used to determine whether emergency vehicles can successfully enter the medical institution. Medical resource matching parameters are calculated based on the patient's condition and the medical institution's resource allocation. The specific settings of these parameters can be adjusted based on actual conditions. For example, capacity can be set based on the size and departmental configuration of the medical institution, while medical resource matching parameters can be calculated based on the patient's primary symptoms and the institution's specialty configuration.

[0081] Preferably, in order to further optimize the path planning process, the collection of road construction information can be increased when obtaining the dynamic traffic data set to more comprehensively reflect the traffic conditions. When calculating the improved dynamic modulation factor, meteorological data, such as rainfall intensity, can be introduced to evaluate the impact of weather on traffic and emergency tasks. In addition, when generating the initial path set, the paths can be prioritized according to the urgency of the patient's condition to ensure that critically ill patients can get priority access to emergency resources. In the medical institution status data set, the calculation method of the medical resource matching parameters can be further refined, for example, according to the patient's specific symptoms and the number of specialists, equipment resources, etc. of the medical institution for more accurate matching. Through these refinement and optimization measures, the efficiency and reliability of the emergency system can be further improved to ensure that patients receive effective treatment in the shortest time.

[0082] In some embodiments, the improved dynamic modulation factor calculation in step S4 includes:

[0083] S41. Construct the spatiotemporal coupling function: λ(t) = α·F(t) + β·S(t) + γ·W(t) where, represents the traffic flow change rate calculated based on the dynamic traffic dataset, represents the spatial complexity of the calculation based on the road topology structure, d i is the node distance, d0 is the regional feature distance, W(t)=1-exp(-w rain ·R w ) represents the weather impact factor calculated based on meteorological data, R w is the rainfall intensity, α, β, and γ are normalized weight coefficients;

[0084] s42. Calculate the dynamic weight of the road section: W ij =exp(-λ(t)·d ij / v k )+μ·O h Among them, d ij is the actual distance from node i to node j, μ is the medical resource impact coefficient defined based on the medical institution status dataset, O h The emergency channel is occupied;

[0085] S43. Generate dynamic adjacency matrix A(t)=[W ij ·δ(t)], where is the accident point attenuation factor, represents the impact attenuation of the mth accident point, τ is the time attenuation constant, t m is the occurrence time of the accident point m.

[0086] It should be noted that the calculation of the improved dynamic modulation factor in the present invention is a key link in realizing dynamic route planning. By constructing a spatiotemporal coupling function and combining the traffic flow change rate, spatial complexity and weather influencing factors, the influence of time and space factors on path planning can be comprehensively considered. Among them, the traffic flow change rate reflects the dynamic changes in traffic flow on each road section in the dynamic traffic data set; the spatial complexity is calculated based on the road topology structure and reflects the complexity of the road network; the weather influencing factor takes into account the impact of meteorological conditions on the travel of emergency vehicles. Through the comprehensive calculation of these factors, a more adaptive dynamic modulation factor can be obtained, thereby providing more accurate weight guidance for path planning.

[0087] Specifically, the traffic flow change rate is obtained by differentially calculating the flow data of each road section in the dynamic traffic dataset, which reflects the changing trend of traffic flow over time. Spatial complexity is calculated by the node spacing and regional characteristic distance in the road topology structure, where the node spacing represents the distance between adjacent nodes in the road network, and the regional characteristic distance is a reference value set according to the scale of the entire target area and the road distribution. The weather impact factor takes into account meteorological parameters such as rainfall intensity, and calculates its influence on path planning through an exponential decay function. When calculating the dynamic weight of a road section, the actual distance between nodes, the medical resource impact coefficient, and the occupancy status of the emergency channel are combined. These parameters jointly determine the priority of the road section. The generation of the dynamic adjacency matrix takes into account the accident point attenuation factor, which is used to evaluate the impact of the accident on the surrounding road sections, thereby providing a more accurate adjacency relationship for path planning.

[0088] Preferably, when constructing the spatiotemporal coupling function, the normalized weight coefficient can be adjusted according to the actual application scenario to balance the influence of the time dimension and the space dimension. For example, in areas with severe traffic congestion, the weight of the traffic flow change rate can be appropriately increased; in complex urban road networks, the weight of spatial complexity can be increased. In addition, for weather influencing factors, in addition to rainfall intensity, other meteorological parameters such as visibility or wind speed can be introduced to more comprehensively reflect the impact of meteorological conditions on emergency tasks. When calculating the dynamic weight of the road section, the calculation method of the medical resource impact coefficient can be further refined, for example, dynamic adjustment can be made according to the patient's specific condition and the type of resources required. Through these refinement and optimization measures, the adaptability of the dynamic modulation factor and the accuracy of path planning can be further improved.

[0089] In some embodiments, the three-dimensional demodulation matrix construction in step S5 includes:

[0090] S51. Calculate path security dimension parameters: Among them, ω k is the safety weight of road section k calculated based on historical accident data, is the aggregate impact of the accident point, M k is the set of accident points associated with road section k;

[0091] S52. Calculate the timeliness dimension parameter: T p =θ / (v a vg·(1+Δv / v a vg)) where θ is the total path length, Based on the dynamic traffic dataset v k Calculated weighted average speed, l k is the length of road section k, is the velocity fluctuation;

[0092] S53. Calculate resource matching dimension parameters:

[0093] R p =σ·R m ·exp(-|C h -C need | / C0) where σ is the specialty matching degree calculated based on the patient's symptoms, Medical resources required for the patient's condition, w s is the weight of symptom S, c s To correspond to resource demand, C0 is the capacity benchmark constant.

[0094] It should be noted that the construction of the three-dimensional demodulation matrix in the present invention is an important step in achieving path priority sorting. By calculating the parameters of the three dimensions of path safety, timeliness and resource matching, the initial path set can be comprehensively evaluated and sorted. Among them, the path safety parameter reflects the level of accident risk on the path; the timeliness parameter takes into account the path's travel speed and speed fluctuations; and the resource matching parameter evaluates the degree of match between the resources of the medical institution and the patient's needs. Through comprehensive consideration of these three dimensions, the optimal path can be selected for the emergency vehicle to ensure that the patient is sent to the most suitable medical institution in the shortest time.

[0095] Specifically, the calculation of path safety dimension parameters is based on historical accident data and real-time accident point information. The road section safety weight is calculated based on the historical accident frequency and road condition coefficient, reflecting the safety level of the road section under normal circumstances. The accident point aggregation impact takes into account the impact of real-time accident points on the path, and calculates its dynamic impact on surrounding sections through the accident point attenuation function. The calculation of timeliness dimension parameters involves the total length of the path, the weighted average speed and the speed fluctuation. The weighted average speed reflects the actual traffic efficiency of each section on the path, and the speed fluctuation is used to evaluate the stability of the path. The resource matching dimension parameters combine the medical resources required for the patient's condition and the resource status of the medical institution, and reflect the availability of resources by dynamically adjusting the matching degree. The specific settings of these parameters can be adjusted according to actual traffic and medical data to adapt to different application scenarios.

[0096] Preferably, when calculating the path safety parameters, the accident point attenuation function can be further refined, and more factors (such as accident type, accident handling progress, etc.) can be introduced to more accurately evaluate the impact of the accident on the path. For timeliness parameters, it is possible to consider introducing real-time traffic flow data and dynamically adjusting the calculation method of the weighted average speed to more accurately reflect the traffic efficiency of the path. In the calculation of resource matching parameters, in addition to considering the patient's condition and the resource status of the medical institution, the time factor can also be introduced, such as dynamically adjusting the resource matching weight according to the urgency of the patient's condition and the expected arrival time. In addition, for the specialty matching degree in the resource matching dimension parameters, a more detailed calculation can be performed in combination with the patient's main symptoms and the specialty configuration of the medical institution, such as by introducing a disease-resource mapping matrix to achieve a more accurate match. Through these refinement and optimization measures, the accuracy and practicality of the three-dimensional demodulation matrix can be further improved, thereby providing a more reliable basis for emergency path planning.

[0097] In some embodiments, step S61 includes:

[0098] S611. When Q v <Q min When the emergency vehicle real-time location (X v , Y v ) and the gas station coordinates in the dynamic traffic dataset (X g , Y g ), generate a set of alternative paths

[0099] S612. According to the scoring model P alt reorder;

[0100] S613. Select the one that satisfies min(T p ) and S p >Sth The path as P final , where S th The preset safety threshold.

[0101] It should be noted that the present invention incorporates a fuel level determination mechanism into the route planning process to ensure that emergency vehicles are not interrupted due to fuel shortages while performing their missions. When the emergency vehicle's fuel level falls below a preset threshold, the system generates a set of alternative routes based on the vehicle's current location and dynamic traffic data. These routes will guide the vehicle to the nearest gas station. A scoring model is used to sort the alternative routes, and a path that meets both safety requirements and efficiency is selected as the final navigation path. This mechanism effectively avoids delays caused by fuel shortages and ensures the continuity and reliability of emergency missions.

[0102] Specifically, the core of the fuel quantity judgment mechanism lies in comparing the actual fuel quantity of the emergency vehicle with the preset safety threshold. When the fuel quantity is lower than the threshold, the system will start the path recalculation process. The generation of the alternative path set is based on the real-time location of the emergency vehicle and the coordinates of the gas station in the dynamic traffic data. The alternative path set is constructed by calculating the reachable path between the current location of the vehicle and the gas station. The scoring model comprehensively considers the safety and timeliness of the path, with the safety weight being 0.7 and the timeliness weight being 0.3. This weight distribution strategy reflects the principle of prioritizing path safety in emergency situations. The setting of the safety threshold is based on the estimation of the vehicle's fuel consumption rate and the task completion time to ensure that the vehicle has enough fuel to maintain operation before arriving at the gas station.

[0103] Preferably, when generating a set of alternative routes, the real-time operating status of the gas station can be further considered, for example, by connecting with the gas station's management system to obtain information on whether it is open for business, thereby avoiding directing vehicles to stations that cannot refuel. In addition, the weights in the scoring model can be adjusted according to actual needs. For example, in some special cases, the importance of timeliness may be higher than safety. In this case, the weight of timeliness can be appropriately increased. At the same time, in order to improve the flexibility of route planning, consideration of backup gas stations can be added to the set of alternative routes. When the nearest gas station cannot meet the demand, the system can automatically switch to the suboptimal route. Through these refinement and optimization measures, the practicality and reliability of the fuel quantity judgment mechanism can be further improved, ensuring that emergency vehicles can successfully complete their tasks under any circumstances.

[0104] In some embodiments, step S62 includes:

[0105] S621. For each accident point (X a , Y a ), based on its severity level a Calculate the influence radius r a=r0·(1+0.5·s a ), where s a ∈[1, 3] comes from real-time accident point queue data;

[0106] S622. Update road speed:

[0107] Among them, d ka is the shortest distance between road section k and accident point a, A k is the set of accident points affecting road section k;

[0108] S623. When there is v′ k <v min When , the corresponding road segment is deleted and a new adjacency matrix A′(t) is generated.

[0109] It should be noted that this invention addresses the impact of real-time incidents by dynamically updating road speeds, ensuring accurate and timely route planning. Specifically, the system calculates the impact radius based on the severity of the incident and adjusts the speed of the affected road section accordingly. This process involves calculating the distance between the incident and the road section and dynamically adjusting the speed. This fully accounts for the impact of incidents on traffic flow in route planning, preventing delays in emergency response missions caused by traffic congestion.

[0110] Specifically, the severity level of the accident point is divided according to real-time accident data, usually divided into levels 1 to 3, where level 1 indicates a minor accident and level 3 indicates a serious accident. Based on the severity level of the accident, the system will calculate the impact radius of the accident point, that is, the potential impact range of the accident on the traffic capacity of surrounding roads. The update of the traffic speed is achieved by considering the closest distance between the accident point and the road section, combined with the impact attenuation function. The attenuation function reflects the impact of the accident on sections of different distances. The closer the section is to the accident point, the greater the adjustment of the traffic speed. When the updated section traffic speed is lower than the preset minimum threshold, the system will remove the section from the path planning and regenerate the adjacency matrix to ensure that the path planning avoids severely congested areas.

[0111] Preferably, in order to more accurately evaluate the impact of accidents on traffic speed, more accident characteristic parameters can be introduced, such as accident type (such as collision, rollover, etc.) and accident handling progress. These parameters can further refine the calculation of the impact radius and attenuation function. In addition, for the update of traffic speed, the parameters of the attenuation function can be dynamically adjusted in combination with real-time traffic flow data to make it closer to the actual traffic conditions. For example, during peak traffic hours, the impact of accidents on traffic speed may be more significant, and the attenuation coefficient can be appropriately increased. At the same time, the system can also introduce historical accident data to model the impact of different types of accidents, so that the traffic speed can be adjusted more quickly and accurately when facing new accidents. Through these optimization measures, the response capability of path planning to accidents can be further improved, ensuring that emergency vehicles can avoid congestion and reach their destination quickly.

[0112] In some embodiments, step S63 includes:

[0113] S631. Based on the O in the medical institution status data set h and C h , calculate the load factor L h =O h / +0.2·(C h -C need ) / C h ;

[0114] S632. Dynamically adjust resource matching weight: ξ R =1 / (1+exp(-5·(L h -0.8))), where ξ R ∈[0, 1];

[0115] S633. Generate calibrated path score: P score =0.5·T p +0.3·S p +0.2·ξ R ·R p .

[0116] It should be noted that the present invention calibrates the path score by combining medical institution status data to ensure that path planning not only takes into account traffic conditions and accident risks, but also fully integrates the actual reception capacity of the medical institution. Specifically, the system dynamically adjusts the resource matching weight according to the load of the medical institution and generates a calibrated path score accordingly. This process involves calculating the load factor of the medical institution and dynamically adjusting the resource matching weight, so that medical institutions that can quickly receive and treat patients are given priority in path planning, further improving the overall efficiency of the emergency system.

[0117] Specifically, the load factor in the medical institution status data is calculated by comprehensively considering the emergency department's admission capacity and the emergency channel occupancy status, and is used to reflect the current reception capacity of the medical institution. In the calculation formula of the load factor, the admission capacity indicates the number of patients that the medical institution can receive within a certain period of time, and the emergency channel occupancy status reflects the difficulty of emergency vehicles entering the hospital. The dynamic adjustment of the resource matching weight is based on the size of the load factor and is achieved by introducing a nonlinear function (such as an exponential decay function). When the load factor is high, it means that the medical institution is close to saturation, and the resource matching weight will be reduced accordingly, thereby reducing the priority of the medical institution in the path score. The calibrated path score comprehensively considers the safety, timeliness and resource matching weight of the path, and obtains the final score through weighted summation to guide emergency vehicles to select the optimal path.

[0118] Preferably, when calculating the load factor, more status parameters of medical institutions can be introduced, such as operating room occupancy rate, intensive care unit (ICU) bed utilization rate, etc. These parameters can more comprehensively reflect the reception capacity of medical institutions. At the same time, the adjustment function of the resource matching weight can be fitted in combination with actual data. For example, by analyzing the relationship between the success rate of historical emergency missions and the load of medical institutions, the parameters of the weight adjustment function can be optimized. In addition, the time factor can be introduced to update the load factor and resource matching weight in real time according to the estimated arrival time of the emergency vehicle and the dynamic changes of the medical institution. For example, if the estimated arrival time is long, the weight of the load factor can be appropriately reduced because the medical institution may release some resources during this period. Through these refinement and optimization measures, the accuracy and practicality of the path score can be further improved, ensuring that emergency vehicles can quickly and efficiently transport patients to the most suitable medical institution.

[0119] In some embodiments, step S7 includes:

[0120] S71. Record the execution time deviation of each path

[0121] S72. Calculate the modulation factor correction:

[0122] Where σ is the standard deviation of the deviation distribution;

[0123] S73. Update dynamic modulation factor: λ′(t)=λ(t)+Δλ·tanh(∑|Δτ j |τ0), τ0 is the preset time base constant.

[0124] It should be noted that the present invention achieves adaptive optimization of path planning by recording path execution time deviations and correcting the dynamic modulation factor. Path execution time deviation refers to the difference between actual travel time and planned time. This deviation reflects the degree of mismatch between path planning and actual traffic conditions. The system uses this deviation to correct the dynamic modulation factor, a key parameter in path planning that adjusts path weights to better match actual traffic conditions. By correcting the dynamic modulation factor, the system can continuously learn and adapt to changes in the traffic environment, thereby improving the accuracy and reliability of path planning.

[0125] Specifically, the path execution time deviation is recorded by comparing the actual arrival time of the emergency vehicle with the estimated arrival time in the path planning. The standard deviation of the deviation distribution is used to measure the degree of dispersion of the deviation, which reflects the fluctuation of the path execution time deviation. The correction amount of the dynamic modulation factor is calculated based on these deviation data. By introducing the standard deviation of the deviation distribution and the preset time reference constant, the system can quantify the impact of the deviation on the modulation factor. The corrected dynamic modulation factor will be adjusted according to the size and direction of the deviation. For example, if the actual driving time is greater than the planned time, the modulation factor will be adjusted in a more conservative direction to reduce the risk weight of the path; otherwise, it will be adjusted in a more radical direction to increase the efficiency weight of the path.

[0126] Preferably, in order to further improve the accuracy of the dynamic modulation factor correction, more dimensional data can be introduced when recording the path execution time deviation, such as deviation data in different time periods, deviation data in different road sections, etc., so as to more comprehensively reflect the changes in the traffic environment. In addition, for the calculation of the standard deviation of the deviation distribution, a sliding window method can be used to only consider the deviation data in the most recent period to improve the real-time performance of the system. When correcting the dynamic modulation factor, a dynamic adjustment mechanism of the learning rate coefficient can be introduced to dynamically adjust the learning rate according to the size of the deviation. For example, when the deviation is large, the learning rate is increased to quickly correct it, and when the deviation is small, the learning rate is reduced to avoid over-correction. In addition, historical data analysis can be introduced, and the deviation data can be modeled through machine learning algorithms to more accurately predict and correct the dynamic modulation factor. Through these refinement and optimization measures, the adaptability and reliability of the path planning system can be further improved.

[0127] In some embodiments, the medical resource matching parameter R m The calculation includes:

[0128] S81. Construct disease-resource mapping matrix D = [d ij ] m×n , where d ij =1 means disease i requires resource j, d ij=0 means that disease i does not require resource j;

[0129] S82. Based on the patient's vital sign parameters G p Generate symptom vector S p =[s1,...,s n ],s k ∈[0, 1] represents the severity of symptom k;

[0130] S83. Based on matrix D and vector S p Generate matching parameters:

[0131] Among them, C hj is the capacity of resource j, O hj is the occupancy of resource j.

[0132] It should be noted that the present invention realizes the accurate calculation of medical resource matching parameters by constructing a disease-resource mapping matrix and generating symptom vectors based on the patient's vital signs parameters. This process is an important link in resource matching in emergency route planning, and aims to quickly match the most suitable medical resources according to the patient's specific condition. Among them, the disease-resource mapping matrix is used to clarify the medical resources required for different diseases, while the symptom vector reflects the severity of the patient's condition and specific needs. Through the combination of the two, the system can dynamically evaluate the matching degree of medical resources, thereby providing an important basis for emergency vehicles to select target medical institutions.

[0133] Specifically, the disease-resource mapping matrix is a two-dimensional matrix whose rows represent disease types and columns represent medical resource types. The elements in the matrix indicate whether a certain disease requires a certain resource, with a value of 1 indicating yes and a value of 0 indicating no. This matrix can be pre-constructed based on medical knowledge and clinical experience and updated according to actual conditions. The symptom vector is generated based on the patient's vital signs, including key indicators such as heart rate, blood pressure, and respiratory rate. After normalization, the value of each indicator forms a vector reflecting the severity of the patient's condition. The calculation of the medical resource matching parameter combines the symptom vector with the disease-resource mapping matrix, taking into account the resource capacity and occupancy of the medical institution, and finally obtains a quantitative value to evaluate whether the medical institution can meet the needs of the patient.

[0134] Preferably, in order to improve the accuracy and practicality of the disease-resource mapping matrix, the opinions of multidisciplinary experts can be introduced, and dynamic updates can be performed in combination with clinical guidelines and actual case data. For example, for certain complex diseases, a detailed description of the number of specialists and equipment resources can be added. When generating symptom vectors, vital sign parameters can be weighted according to the characteristics of different diseases. For example, for cardiovascular diseases, the weights of heart rate and blood pressure can be appropriately increased. In addition, the time factor can be introduced to dynamically adjust the calculation method of the resource matching parameters according to the urgency of the patient's condition. For example, for patients with critical conditions, the system can give priority to medical institutions that are closer and have sufficient resources. Through these refinement and optimization measures, the accuracy and practicality of medical resource matching parameters can be further improved, providing more reliable decision support for emergency path planning.

[0135] In some embodiments, the security weight ω k The calculation includes:

[0136] S91. Obtain historical accident frequency of road section k N k (t) is the number of accidents during period t;

[0137] S92. Calculate road condition coefficient ρ k =0.6·w width +0.4·w light , w width ∈[0, 1] is the lane width score, w light ∈[0, 1] is the lighting score;

[0138] S93. Generate dynamic security weight: ω k =(1-f k )·ρ k +0.1·exp(-v k / v max ), v max Speed limit for the road section.

[0139] It should be noted that the present invention provides an important safety assessment basis for emergency route planning by calculating the safety weight of the road section. The calculation of the safety weight comprehensively considers factors such as the historical accident frequency of the road section, the road condition coefficient and the speed limit, and can dynamically reflect the safety of the road section. Among them, the historical accident frequency is used to assess the accident risk level of the road section, the road condition coefficient reflects the impact of the physical characteristics of the road on safety, and the speed limit is used as a reference factor to adjust the dynamic changes of the safety weight. In this way, the system can give priority to road sections with higher safety in route planning, thereby reducing the risk of accidents during the emergency treatment process.

[0140] Specifically, the historical accident frequency of a road section is obtained by counting the number of accidents on that road section within a certain period of time, reflecting the accident risk level of the road section under normal traffic conditions. The road condition coefficient is composed of a lane width score and a lighting score, which respectively reflect the road's traffic capacity and nighttime driving safety. The lane width score is evaluated based on the actual width of the lane; the wider the width, the higher the score; the lighting score is evaluated based on the completeness of the road lighting facilities; the better the lighting conditions, the higher the score. In the safety weight calculation formula, the weight of the historical accident frequency is low, while the weight of the road condition coefficient is high, which reflects the importance of the physical conditions of the road in safety assessment. In addition, the speed limit is used as a regulating factor to fine-tune the safety weight through an exponential decay function, further reflecting the impact of speed on safety.

[0141] Preferably, when calculating the safety weight, more parameters related to road safety can be introduced, such as road slope, curve radius, etc. These parameters can more comprehensively reflect the impact of the physical characteristics of the road on safety. For example, for road sections with larger slopes, their safety weights can be appropriately reduced; for road sections with smaller curve radii, the weights can also be adjusted to reflect their higher accident risks. In addition, the statistics of historical accident frequencies can be further refined into different time periods (such as daytime and nighttime) and different seasons to more accurately reflect the safety changes of road sections. At the same time, machine learning algorithms can be introduced to automatically adjust the weights of various parameters through analysis of historical accident data, thereby achieving more accurate safety weight calculations. Through these refinement and optimization measures, the accuracy and practicality of road section safety weights can be further improved, providing a more reliable safety assessment basis for emergency route planning.

[0142] In some embodiments, the calculation of the specialty matching degree σ includes:

[0143] S101. Extract the patient's main symptoms max =argmax(S p );

[0144] S102. Query the mapping table to obtain σ0=D(s max , h current ), h current Provide specialized configuration for medical institutions;

[0145] S103. Calculate the dynamic matching degree: σ=σ0·[1-0.5·exp(-t delay / t h )],t delay is the delay time, t h is the disease half-life parameter.

[0146] It should be noted that the present invention achieves an accurate match between the specialist capabilities of medical institutions and the patient's condition requirements by calculating the specialist matching degree. The calculation of the specialist matching degree is based on factors such as the patient's main symptoms, the specialist configuration of the medical institution, and the delay time, and can dynamically reflect the medical institution's reception capacity under specific conditions. Among them, the patient's main symptoms are determined by analyzing the patient's vital signs and medical history, the specialist configuration of the medical institution reflects the hospital's medical resources and professional capabilities in specific fields, and the delay time takes into account the impact of the time it takes for the emergency vehicle to arrive at the hospital on the patient's condition. In this way, the system can give priority to medical institutions with high specialist matching degrees in route planning, thereby improving the success rate of first aid.

[0147] Specifically, a patient's primary symptom refers to the most prominent symptom of their current condition, such as chest pain or dyspnea. These symptoms are determined through the initial diagnosis of emergency medical personnel or the patient's self-report. A medical institution's specialty configuration refers to the hospital's specialized offerings in specific disease areas, such as cardiovascular surgery or neurosurgery. This information can be obtained through the hospital's public data or through integration with the hospital's information system. The specialty match calculation first determines a baseline match by querying a mapping table, which is pre-set based on the hospital's specialty configuration and common disease types. The baseline match is then dynamically adjusted based on the delay time and disease half-life parameters. The delay time reflects the estimated time it takes for the emergency vehicle to arrive at the hospital, while the disease half-life parameter indicates the rate at which the patient's condition deteriorates over time. In this way, the specialty match takes into account both the urgency of the patient's condition and the medical institution's capacity.

[0148] Preferably, in order to further improve the accuracy of specialist matching, more parameters related to the patient's condition can be introduced in the calculation process, such as the patient's age, past medical history, etc. These parameters can more comprehensively reflect the complexity of the patient's condition. At the same time, the setting of the disease half-life parameter can be dynamically adjusted in combination with clinical data. For example, for certain acute diseases, the half-life parameter can be set shorter to reflect the rapid deterioration of the condition. In addition, an expert system or machine learning algorithm can be introduced to automatically optimize the calculation model of specialist matching by learning from a large number of historical emergency cases. For example, the system can automatically adjust the basic matching weights in the mapping table based on the success rate of specialist matching for different diseases. Through these refinement and optimization measures, the accuracy and practicality of specialist matching can be further improved, providing more reliable decision support for emergency path planning.

[0149] The aforementioned embodiments of the present invention have the following beneficial effects: The dynamic route planning method for an emergency medical system comprehensively considers multiple factors, including patient vital signs, real-time traffic conditions, accident risks, and the status of medical institution resources. It dynamically optimizes and prioritizes routes using an improved dynamic modulation factor and a three-dimensional demodulation matrix. This method dynamically adjusts route planning based on real-time data, ensuring that emergency vehicles select the optimal route in complex urban traffic environments, thereby effectively shortening emergency response time and improving emergency efficiency. Furthermore, a multi-level logical judgment mechanism calibrates route scores and corrects dynamic modulation factors in real time, further enhancing the adaptability and accuracy of route planning. Combining medical institution status data with patient medical needs, this method accurately matches resources, ensuring that patients are transported to the most appropriate medical institution in the shortest possible time, significantly improving the success rate of emergency medical treatment and the quality of patient care. Furthermore, the present invention further optimizes route selection and resource allocation by calculating dynamic safety weights and specialty matching, thereby improving the overall performance and reliability of the emergency medical system.

[0150] Furthermore, the storage medium of the embodiment of the present application stores program instructions that can implement all the above methods, wherein the program instructions can be stored in the above storage medium in the form of a software product, including a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or a terminal device such as a computer, a server, a mobile phone, or a tablet.

[0151] The above descriptions are merely some preferred embodiments of the present invention and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present invention is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also encompass other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned inventive concept. For example, a technical solution formed by mutually replacing the above-mentioned features with (but not limited to) technical features having similar functions disclosed in the embodiments of the present invention.

Claims

1. A dynamic route planning method for an emergency system, characterized in that: The following steps are involved: S1. Obtain an emergency request data set, which includes patient vital sign parameters G p , patient position coordinates (X p ,Y p ), the real-time position coordinates of the emergency vehicle (X v ,Y v ); S2. Real-time collection of dynamic traffic data sets in the target area, including the traffic speed v of each road section k , traffic control area coordinate set (X c ,Y c ), real-time accident point coordinate queue (X a ,Y a ) and its accident severity level s a ; S3. Obtain the medical institution status dataset, including the emergency department admission capacity C h , Emergency channel occupied status O h , medical resource matching parameter R m ;The medical resource matching parameter is calculated based on the disease-resource mapping matrix and the patient's symptom vector; S4. Calculate the initial path set P based on the emergency request dataset, dynamic traffic dataset, and medical institution status dataset using the improved dynamic modulation factor λ(t) initial ; S5. Using the three-dimensional demodulation matrix M 3d For the initial path set P initial Prioritize the three-dimensional demodulation matrix M 3d The dimensions include: path safety parameter S calculated based on real-time accident point data p , based on the road segment speed v k The timeliness parameter T p , based on the medical resource matching parameter R m and emergency department admission capacity C h Resource matching parameter R p ; S6. Execute multi-level logical judgment to generate the final navigation path P final ; Specifically include: S61. Based on the fuel quantity Q of the emergency vehicle v With threshold Q min The comparison result triggers path recalculation; S62. Based on real-time accident point queue (X a ,Y a ) in a Update the road section speed v k '; S63. Combine C in the medical institution status dataset h and O h Calibrated path score P score ; S7. Modify the dynamic modulation factor λ(t) according to the path execution time deviation Δτ; The improved dynamic modulation factor calculation in step S4 includes: S41. Constructing space-time coupling function: λ(t)=α·F(t)+β·S(t)+γ·W(t) Where F(t) is the sum of the speed change rates calculated based on the dynamic traffic data set, S(t) is the spatial complexity calculated based on the road topology, W(t) is the weather impact factor calculated based on meteorological data, and α, β, and γ are normalized weight coefficients. S42. Calculate the dynamic weight of the road segment: W ij =exp(-λ(t)·d ij / v k )+μ·O h Among them, d ij is the actual distance from node i to node j, μ is the medical resource impact coefficient defined based on the medical institution status dataset, O h The emergency channel is occupied; v k is the original road section speed; S43. Generate dynamic adjacency matrix A(t)=[W ij ·δ(t)], where δ(t) is the attenuation factor of the accident point, is the impact attenuation of the mth accident point, τ is the time attenuation constant, t m is the occurrence time of the accident point m.

2. The method according to claim 1, characterized in that The construction of the three-dimensional demodulation matrix in step S5 includes: S51. Calculate path security parameters: Among them, ω k is the safety weight of road section k calculated based on historical accident data, δ k is the aggregated impact of the accident point, M k is the set of accident points associated with road section k; S52. Calculate timeliness parameters: T p =θ / (v avg ·(1+Δv / v avg )) Where θ is the total path length, l k is the length of road section k, v k is the traffic speed of section k, S53. Calculate resource matching parameters: R p =σ·R m ·exp(-|C h -C need | / C0) in, σ is the specialty matching degree calculated based on the patient's symptoms, w s is the weight of symptom s, c s for Corresponding to resource demand, C0 is the capacity benchmark constant, C h is the emergency department admission capacity obtained from the medical institution status dataset, C need is the total amount of medical resources required for the patient’s condition, R p Match parameters for resources; The calculation of the specialty matching degree σ is shown in the following formula: σ=σ0·[1-0.5·exp(-t delay / t h )], Among them, t delay is the delay time, t h is the disease half-life parameter, is the rate at which the patient's condition worsens over time, and σ0 is the basic specialty matching degree.

3. The method according to claim 1, characterized in that Step S61 includes: S611. When Q v min When the emergency vehicle real-time location (X v ,Y v ) and the gas station coordinates in the dynamic traffic dataset (X g ,Y g ), generate a set of alternative paths:​ S612. According to the scoring model For the set of alternative paths P alt reorder; S613. Select the reordered candidate path set that satisfies min(T p ) and S p >S th The path is used as the final navigation path P final , where S th The preset safety threshold.

4. The method according to claim 1, wherein Step S62 includes: S621. For each accident point (X a ,Y a ), based on its severity level a Calculate the influence radius r a ; S622. Update the road segment speed, as shown in the following formula: Among them, d ka is the shortest distance between road section k and accident point a, A k is the set of accident points affecting road section k; S623. When there is v′ k <v min When , the corresponding road segment is deleted and a new adjacency matrix A′(t) is generated.

5. The method according to claim 3, characterized in that Step S63 includes: S631. Based on the O in the medical institution status data set h and C h , calculate the load factor S632. Dynamically adjust resource matching weight: ξ R =1 / (1+exp(-5·(L h -0.8))), where ξ R ∈[0,1]; S633. Generate calibrated path score: P score =0.5·T p +0.3·S p +0.2·ξ R ·R p .

6. The method according to claim 5, characterized in that Step S7 includes: S71. Record the execution time deviation of each path S72. Calculate the modulation factor correction: Among them, σ τ is the standard deviation of the deviation distribution; S73. Update dynamic modulation factor: λ′(t)=λ(t)+Δλ·tanh(∑|Δτ j′ |τ0), τ0 is the preset time base constant.

7. The method according to claim 6, characterized in that The medical resource matching parameter R m The calculation includes: S81. Construct disease-resource mapping matrix D; S82. Based on the patient's vital sign parameters G p Generate symptom vector S v =[s1,...,s n ],s1,...,s n Indicates the severity of symptoms 1,...,n; S83. Based on matrix D and vector S v Generate matching parameters: Among them, C hj” is the capacity of resource j”, O hj” is the occupancy of resource j”, and m is the total number of medical resource categories.

8. The method according to claim 7, characterized in that The safety weight ω k The calculation includes: S91. Obtain historical accident frequency f of road section k k ; S92. Calculate road condition coefficient ρ k ρ k =0.6·w width +0.4·w light , w width ∈[0,1] is the lane width score, w light ∈[0,1] is the lighting score; S93. Based on historical accident frequency f k and road condition coefficient ρ k Generate a dynamic security weight as shown in the following formula: ω k =(1-f k )·ρ k +0.1·exp(-v k / v max ), Among them, v max Set speed limits for the road section.

Images