Emergency nursing resource optimal distribution system

The emergency nursing resource optimization system addresses dynamic demand challenges by analyzing resource interactions and predicting needs, optimizing allocation to enhance response speed and treatment quality.

CN119092074AInactive Publication Date: 2024-12-06SHIJIAZHUANG THIRD HOSPITAL
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411206710.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-30
Publication Date
2024-12-06
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing resource management systems in emergency departments lack flexibility and adaptability to dynamic demand changes, leading to improper allocation of medical equipment and human resources, causing treatment delays and increased costs.

Method used

An emergency nursing resource optimization allocation system that analyzes resource interactions, predicts demand, and dynamically adjusts resource allocation using spatiotemporal analysis and real-time monitoring to optimize resource distribution.

Benefits of technology

Improves response speed and treatment quality by accurately mapping resource utilization and predicting needs, reducing patient waiting times and enhancing overall system adaptability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119092074A_ABST
    Figure CN119092074A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of resource management, in particular to an emergency nursing resource optimal distribution system, which comprises a resource association analysis module, a resource allocation module, a resource allocation module, a resource allocation module, a resource allocation module and a resource allocation module, wherein the resource association analysis module is used for analyzing relationships among medical equipment, medical personnel and medicines, counting interaction frequencies among various resources, and summarizing resource flow modes according to geographic positions and time parameters; and calculating the interaction strength between the nodes to obtain a resource dependency strength table. According to the method and the device, the interaction modes and the dependency relationships of various medical resources are comprehensively analyzed, the dynamic interaction of the resources in the emergency treatment event is accurately mapped, the accuracy of resource utilization is improved, each resource can be efficiently configured according to actual requirements, the response speed and the processing quality of the emergency treatment event are greatly improved, and in addition, the method and the device have good application prospects. Through deep mining of historical data and real-time event monitoring, the prediction model can accurately predict the resource demand of each time-space node, which not only enhances the adaptability of the system to changes, but also optimizes the prospective allocation of resources.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of resource management, and in particular to an emergency nursing resource optimization allocation system. Background Art

[0002] The field of resource management technology involves the efficient allocation and use of limited resources to maximize their utility and productivity. In healthcare systems, this typically includes the allocation of medical equipment, pharmaceuticals, financial, and human resources (such as doctors and nurses). Optimizing the management of these resources is critical, especially in environments where demand is constantly changing, such as emergency departments. Technology plays a key role in this area by using advanced data analytics, artificial intelligence algorithms, and real-time monitoring systems to predict resource needs and optimize resource allocation. This management approach not only improves the efficient use of resources, but also improves patient treatment outcomes and overall satisfaction.

[0003] Among them, the emergency care resource optimization allocation system refers to the use of technical tools and methods to manage and allocate key resources in the emergency room to improve response efficiency and treatment quality. This system can analyze the data of admitted patients in real time, predict resource requirements, and optimize the allocation of medical staff, equipment and drugs accordingly. Its main purpose is to ensure that in emergency situations, necessary medical services can be provided to patients quickly and effectively, reduce waiting time, improve patient satisfaction and treatment effectiveness, and also help reduce medical costs and improve overall operational efficiency.

[0004] Existing technologies usually rely on experience and fixed rules in resource management, resulting in a lack of necessary flexibility and adaptability in a rapidly changing medical environment. For example, static methods of resource allocation cannot effectively cope with the dynamic demands during peak emergency periods, often leading to improper resource allocation, such as idle or over-concentrated medical equipment and human resources. This phenomenon is particularly evident when resources are tight or demand surges, often causing treatment delays, affecting patient treatment quality and satisfaction, and increasing medical costs. The lack of in-depth analysis of resource dependencies and flow patterns also often makes it impossible to achieve optimal resource allocation, reducing the overall operating efficiency of the medical system. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose an emergency nursing resource optimization allocation system.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: an emergency nursing resource optimization allocation system comprises:

[0007] The resource association analysis module analyzes the relationship between medical equipment, medical staff and drugs, counts the interaction frequency between multiple resources, summarizes the resource flow pattern according to geographical location and time parameters, calculates the interaction intensity between nodes, and obtains the resource dependency intensity table;

[0008] The resource demand prediction module calculates the resource demand at different time nodes and geographical locations based on the resource dependency intensity table, combined with the emergency event type and historical traffic data, and generates a predicted resource demand table;

[0009] The spatiotemporal prediction adjustment module uses the resource dependency intensity table and the predicted resource demand table to analyze the sensitivity of resources at differentiated times and locations, adjusts the distribution of personnel and equipment according to the resource usage frequency and the geographical frequency of emergency events, updates resource allocation, and generates a resource allocation optimization plan;

[0010] The dynamic deployment execution module adopts the resource allocation optimization solution, monitors emergency event response and equipment usage, adjusts medical staff configuration and equipment location, updates configuration data in real time, and generates implementation deployment results.

[0011] As a further solution of the present invention, the step of obtaining the resource dependency intensity table is specifically as follows:

[0012] Through the medical system data interface, the interaction data between medical equipment, medical staff and drugs is automatically collected, using the formula:

[0013] F=[f ij ]

[0014] Get the interaction frequency matrix F;

[0015] Among them, i represents a certain type of medical resources including target medical equipment, j represents other types of resources including medical staff or drugs, and f ij Represents the number of interactions between resource i and resource j;

[0016] The interaction frequency matrix is ​​combined with the geographic information system and time management system data to construct a location-time dependency matrix using the formula:

[0017]

[0018] Generate resource flow pattern R;

[0019] Among them, L represents the geographical location influence matrix, and T represents the time influence matrix;

[0020] The resource flow pattern is used to calculate the interaction strength between nodes. The interaction strength is calculated for each pair of nodes i and j using the covariance formula, using the formula:

[0021]

[0022] Get the interaction strength s between nodes ij ;

[0023] Among them, r ik 、r jk They represent the flow intensity of resource i and resource j at the kth time and place, denote the average flow intensity of resource i and resource j respectively, and n denotes the total number of observations;

[0024] Using the interaction strength between the nodes, a weighted formula is applied to calculate the resource dependency strength, using the formula:

[0025]

[0026] Generate resource dependency intensity table D;

[0027] Among them, w ij represents the interaction importance weight between resources i and j, and the square root indicates the nonlinear influence of the weight.

[0028] As a further solution of the present invention, the step of obtaining the predicted resource demand table is specifically as follows:

[0029] Based on the resource dependency intensity table, time series data and event type data are extracted from the emergency event database and the historical traffic system, using the formula:

[0030]

[0031] Calculate preliminary resource requirements R based on time and event type t ;

[0032] Among them, t represents the time series, e represents the event type, and f q (e) Function representing event type, α q represents the adjustment factor;

[0033] Combined with the above preliminary resource requirements, a geographical location matrix is ​​constructed using the formula:

[0034] R t,l =R t ·L 1 / 2

[0035] Generate adjusted resource requirements R t,l ;

[0036] Where L represents the geographical location adjustment matrix;

[0037] Based on the adjusted resource requirements, according to the urgency of emergency events and historical data on resource flows, the formula is used:

[0038]

[0039] Generate forecast resource requirement table R final ;

[0040] Among them, β q represents the response intensity coefficient, δ q represents the time adjustment factor, t 0 Represents the time offset parameter.

[0041] As a further solution of the present invention, the steps of obtaining the resource allocation optimization solution are specifically as follows:

[0042] Analyze the resource dependency intensity table and the predicted resource demand table to determine the sensitivity of resources at differentiated times and locations, using the formula:

[0043]

[0044] Calculate the sensitivity of resources and generate sensitivity analysis results S td ;

[0045] Among them, c w represents the adjustment factor, h w Represents the impact of historical data;

[0046] According to the frequency of resource use and the geographical frequency of emergency events, the distribution of personnel and equipment is adjusted using the formula:

[0047]

[0048] Generate updated resource distribution D new ;

[0049] Where F represents the frequency of resource use, G represents the geographical frequency of emergency events, and k w represents the smoothing coefficient;

[0050] Integrating the sensitivity analysis results and the updated resource distribution, the formula is used:

[0051]

[0052] Generate resource configuration optimization plan P opt ;

[0053] Among them, m w Represents the adjustment offset.

[0054] As a further solution of the present invention, the step of obtaining the implementation result of the deployment is specifically as follows:

[0055] Monitor emergency event response and equipment usage, use the resource allocation optimization solution, combine real-time event response data, and use the formula:

[0056]

[0057] Generate current resource usage analysisA current ;

[0058] Among them, E r represents the weighted real-time incident response data, α r represents the adjustment coefficient, t r represents the time variable;

[0059] Based on the current resource usage analysis and historical configuration data, adjust the medical staff configuration and equipment location using the formula:

[0060]

[0061] Update the configuration data and generate the adjusted configuration data C adjust ;

[0062] Among them, F r represents the adjusted frequency data, H represents the historical configuration data, and k r represents the adjustment factor;

[0063] Integrate the adjusted configuration data, using the formula:

[0064]

[0065] Generate implementation deployment results U final ;

[0066] Among them, m r Represents adjustment of offset parameters.

[0067] Compared with the prior art, the advantages and positive effects of the present invention are:

[0068] In the present invention, by comprehensively analyzing the interaction patterns and dependencies of various medical resources, the dynamic interaction of resources in emergency events is accurately mapped, the accuracy of resource utilization is improved, and each resource can be efficiently configured according to actual needs, which greatly improves the response speed and processing quality of emergency events. In addition, through deep mining of historical data and real-time event monitoring, the prediction model can accurately predict the resource requirements of each time and space node, which not only enhances the system's adaptability to changes, but also optimizes the forward-looking allocation of resources. Dynamic allocation execution enables continuous optimization of resource allocation, greatly reduces patient waiting time, and improves treatment effects and patient satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 is a system flow chart of the present invention;

[0070] Figure 2 A flowchart of the steps for obtaining the resource dependency intensity table of the present invention;

[0071] Figure 3 A flowchart of the steps for obtaining a resource demand forecast table according to the present invention;

[0072] Figure 4 A flowchart of the steps for obtaining the resource allocation optimization solution of the present invention;

[0073] Figure 5 The present invention is a flowchart of the steps for obtaining the blending results. DETAILED DESCRIPTION

[0074] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0075] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0076] Embodiment 1

[0077] See also Figure 1 , an emergency nursing resource optimization allocation system includes:

[0078] The resource association analysis module analyzes the relationship between medical equipment, medical staff and drugs, counts the interaction frequency between multiple resources, summarizes the resource flow pattern according to geographical location and time parameters, calculates the interaction intensity between nodes, and obtains the resource dependency intensity table;

[0079] The resource demand forecasting module calculates the resource demand at different time nodes and geographical locations based on the resource dependency intensity table, combined with the emergency event type and historical traffic data, and generates a forecast resource demand table;

[0080] The spatiotemporal prediction adjustment module uses the resource dependency intensity table and the predicted resource demand table to analyze the sensitivity of resources at different times and locations, adjusts the distribution of personnel and equipment, updates resource allocation, and generates a resource allocation optimization plan based on the resource usage frequency and the geographical frequency of emergency events;

[0081] The dynamic deployment execution module adopts a resource allocation optimization solution, monitors emergency event response and equipment usage, adjusts medical staff configuration and equipment location, updates configuration data in real time, and generates implementation deployment results.

[0082] The resource dependency intensity table includes medical equipment dependency, medical staff dependency, and drug dependency. The predicted resource demand table includes time node requirements, geographical location requirements, and resource quantity requirements. The resource allocation optimization plan includes sensitivity analysis, usage frequency analysis, and geographical frequency analysis. The implementation deployment results include actual response status, real-time equipment location, and configuration update data.

[0083] See also Figure 2 ,The specific steps for obtaining the resource dependency intensity table are:

[0084] Through the medical system data interface, the interaction data between medical equipment, medical staff and drugs is automatically collected, using the formula:

[0085] F=[f ij ]

[0086] Get the interaction frequency matrix F;

[0087] Among them, i represents a certain type of medical resources including target medical equipment, j represents other types of resources including medical staff or drugs, and f ij Represents the number of interactions between resource i and resource j;

[0088] The interaction frequency matrix is ​​combined with the geographic information system and time management system data to construct the location-time dependency matrix using the formula:

[0089]

[0090] Generate resource flow pattern R;

[0091] Among them, L represents the geographical location influence matrix, and T represents the time influence matrix;

[0092] The resource flow pattern is used to calculate the interaction strength between nodes. The covariance formula is used to calculate the interaction strength for each pair of nodes i and j. The formula is:

[0093]

[0094] Get the interaction strength s between nodes ij ;

[0095] Among them, r ik 、r jk They represent the flow intensity of resource i and resource j at the kth time and place, denote the average flow intensity of resource i and resource j respectively, and n denotes the total number of observations;

[0096] Using the interaction strength between nodes, apply the weighted formula to calculate the resource dependency strength, using the formula:

[0097]

[0098] Generate resource dependency intensity table D;

[0099] Among them, w ij represents the interaction importance weight between resources i and j, and the square root indicates the nonlinear influence of the weight.

[0100] formula:

[0101] F=[f ij

[0102] in:

[0103] f ij : The number of interactions between resource i and resource j within a given time window.

[0104] i, j: index of resources, such as i for medical equipment and j for medical staff.

[0105] Derivation of example

[0106] Set up the data:

[0107] Medical device 1 and medical staff 2 interacted 5 times in one week.

[0108] Medical device 1 and medical staff 3 interacted 3 times in the same week.

[0109] Calculation process:

[0110] Construct a 2x2 matrix where Indicates the number of interactions between device 1 and persons 2 and 3 respectively.

[0111] formula:

[0112]

[0113] in:

[0114] L, T: Geographical and temporal factors impact matrix.

[0115] Derivation of example

[0116] Set up the data:

[0117] Geographical location influence coefficient L = [1 0.5]

[0118] Time influence coefficient

[0119] Using the above results, F

[0120] Calculation process:

[0121]

[0122] formula:

[0123]

[0124] in:

[0125] r ik 、r jk : The flow intensity of resource i and resource j at the kth time-place.

[0126] The average flow intensity of resource i and resource j.

[0127] n: total number of observations.

[0128] Derivation of example

[0129] Set up the data:

[0130] For the flow intensity r of resources i and j at three time points i =[2,3,2.5], r j =[1,1.5,1]

[0131]

[0132] Calculation process:

[0133]

[0134] formula:

[0135]

[0136] in:

[0137] s ij : Interaction strength between nodes.

[0138] w ij : The interaction importance weight between resources i and j.

[0139] Derivation of example

[0140] Set up the data:

[0141] Set the weight w ij = 1 for all node pairs.

[0142] Using s from the above results ij

[0143] Calculation process:

[0144]

[0145] See also Figure 3 , the specific steps for obtaining the forecast resource demand table are:

[0146] Based on the resource dependency intensity table, time series data and event type data are extracted from the emergency event database and historical traffic system using the formula:

[0147]

[0148] Calculate preliminary resource requirements R based on time and event type t ;

[0149] Among them, t represents the time series, e represents the event type, and f q (e) Function representing event type, α q represents the adjustment factor;

[0150] Combined with the initial resource requirements, a geographical location matrix is ​​constructed using the formula:

[0151] R t,l =R t ·L 1 / 2

[0152] Generate adjusted resource requirements R t,l ;

[0153] Where L represents the geographical location adjustment matrix;

[0154] Based on the adjusted resource requirements, according to the urgency of emergency events and historical data on resource flows, the formula is used:

[0155]

[0156] Generate forecast resource requirement table R final ;

[0157] Among them, β q represents the response intensity coefficient, δ q represents the time adjustment factor, t 0 Represents the time offset parameter.

[0158] formula:

[0159]

[0160] Parameter details and how to obtain them:

[0161] t: time series, including hours or days, which can be obtained from historical data. For example, if analyzing a week's data, t can be an integer from 1 to 7.

[0162] e: Event type, the variable depends on the classification of the emergency event, such as heart attack, accident, and each type corresponds to a code.

[0163] D: Resource dependency intensity table, which is a matrix whose values ​​are obtained through historical data analysis and reflects the dependency relationship between differentiated resources.

[0164] α q : Adjustment coefficient, obtained through statistical analysis of historical data, represents the intensity of resource demand adjustment for differentiated event types.

[0165] f q (e): Function of event type, providing the quantitative impact of each type of event on resource requirements, based on the frequency of past events.

[0166] Calculation example:

[0167] Assume that a heart attack event (e=1, assuming f q (1) = 3), resource dependency matrix D = 0.5, adjustment coefficient α q =0.3, the calculation formula is:

[0168]

[0169] This means that on that day, the corresponding resource demand index is 1.0196, reflecting the resource demand impact of the heart attack event.

[0170] formula:

[0171]

[0172] Parameter details and how to obtain them:

[0173] L: Geographic location adjustment matrix, obtained through geographic information system analysis, each location factor l ij Indicates the degree of influence of geographical location on resource demand.

[0174] R t : Preliminary resource requirements.

[0175] Calculation example:

[0176] Set the geographic location factor L = 1.1 (indicating that the resource demand of the location is 10% higher than the average level), then:

[0177] This means that at the geographic location, the resource demand index is 1.0696.

[0178] formula:

[0179]

[0180] Parameter details and how to obtain them:

[0181] β q : Response intensity coefficient, obtained through analysis of historical emergency response data.

[0182] δ q ,t 0 : The time adjustment coefficient and time offset parameter are obtained by fitting the event response time in historical data.

[0183] Calculation example:

[0184] Setting up beta q =0.1,δ q =0.5, t 0 =1, time t=1:

[0185]

[0186] This indicates a resource requirement index of 1.1048, which is used to predict the amount of resources required at the target time and location.

[0187] See also Figure 4 , the specific steps for obtaining the resource allocation optimization plan are:

[0188] Analyze the resource dependency intensity table and the forecast resource demand table to determine the sensitivity of resources at differentiated times and locations, using the formula:

[0189]

[0190] Calculate the sensitivity of resources and generate sensitivity analysis results S td ;

[0191] Among them, c w represents the adjustment factor, h w Represents the impact of historical data;

[0192] According to the frequency of resource use and the geographical frequency of emergency events, the distribution of personnel and equipment is adjusted using the formula:

[0193]

[0194] Generate updated resource distribution D new ;

[0195] Where F represents the frequency of resource use, G represents the geographical frequency of emergency events, and k w represents the smoothing coefficient;

[0196] Integrating the sensitivity analysis results and the updated resource distribution, the formula is used:

[0197]

[0198] Generate resource allocation optimization plan P opt ;

[0199] Among them, m w Represents the adjustment offset.

[0200] formula:

[0201]

[0202] in:

[0203] D is the resource dependence intensity table, which reflects the degree of dependence on differentiated resources.

[0204] R final It is a forecast resource demand table that predicts future demand based on historical data.

[0205] c w is the adjustment coefficient, which is set to 0.5 and represents the weight of the impact on historical data during sensitivity analysis.

[0206] h w is the historical data impact index, which is set to 4 and represents the impact of historical events on current resource demand.

[0207] Set up the study:

[0208] Set D = 0.8 (indicating high resource dependence), R final =100 (predicting that 100 units of resources will be needed in the future).

[0209] Calculation process:

[0210] Calculate D·R final =0.8×100=80

[0211] calculate

[0212] Final result td =80+1=81

[0213] The result 81 represents the sensitivity assessment value of the resource at the target time and location.

[0214] formula:

[0215]

[0216] in:

[0217] S td It is a sensitivity result.

[0218] F represents the resource usage frequency, which is set to 2 times per day.

[0219] G is the geographic frequency of emergency events, set to 5 times per day.

[0220] k w is the smoothing factor, set to 1 to adjust for the effect of geographic frequency.

[0221] Example calculation:

[0222] Set F=2, G=5

[0223] calculate

[0224] calculate

[0225] Final result D new =81×2×0.912=147.744

[0226] The result 147.744 represents the new resource distribution index adjusted for sensitivity and usage frequency.

[0227] formula:

[0228]

[0229] in:

[0230] D new is the new resource distribution index.

[0231] m w It is to adjust the offset, set to 0.1, to fine-tune the response function.

[0232] Example calculation:

[0233] Using D new =147.744,m w =0.1

[0234] calculate (very close to 0, because the exponential term is very small)

[0235] Final Result

[0236] Result 1 means that under given parameters, resource allocation has reached the optimal state.

[0237] See also Figure 5 , the specific steps for obtaining the deployment results are:

[0238] Monitor emergency incident response and equipment usage, use resource allocation optimization solutions, combine real-time incident response data, and use the formula:

[0239]

[0240] Generate current resource usage analysisA current ;

[0241] Among them, E r represents the weighted real-time incident response data, α r represents the adjustment coefficient, t r represents the time variable;

[0242] According to the current resource usage analysis and historical configuration data, adjust the medical staff configuration and equipment location, using the formula:

[0243]

[0244] Update the configuration data and generate the adjusted configuration data C adjust ;

[0245] Among them, F r represents the adjusted frequency data, H represents the historical configuration data, and k r represents the adjustment factor;

[0246] Integrate the adjusted configuration data using the formula:

[0247]

[0248] Generate implementation deployment results U final ;

[0249] Among them, m r Represents the adjustment offset parameter.

[0250] formula:

[0251]

[0252] Analysis:

[0253] P opt : Resource allocation optimization plan, set as an adjustment coefficient, calculated based on historical data and efficiency model.

[0254] E r: Weighted real-time incident response data, collected in real time from the monitoring system.

[0255] α r : Adjustment coefficient, obtained by analyzing historical response data.

[0256] t r : Time variable, indicating the time from the start of the event to the present (in hours).

[0257] Calculation process:

[0258] set up:

[0259] P opt =0.8 (assumed to be based on the response efficiency of similar events in the past)

[0260] E r =50 (Real-time event data shows that there are currently 50 events that require urgent response)

[0261] α r =0.5 (based on analysis of past data)

[0262] t r =4 (4 hours have passed since the incident)

[0263] calculate:

[0264]

[0265] A current =40+1=41

[0266] Analysis of calculation results:

[0267] A current =41 means the current resource usage status is 41, which is a comprehensive score of resource utilization efficiency or response level.

[0268] formula:

[0269]

[0270] Analysis:

[0271] F r : Frequency adjustment parameter, representing the adjusted resource allocation frequency.

[0272] H: Historical configuration data.

[0273] k r : Smoothing adjustment coefficient, used to adjust the frequency.

[0274] Calculation process:

[0275] set up:

[0276] F r =10 (equipment dispatch frequency is 10 times per hour)

[0277] H = 100 (the historical average response time is 100 times per hour)

[0278] k r =20 (increased smoothing factor)

[0279] calculate:

[0280]

[0281] Analysis of calculation results:

[0282] C adjust =37.44 represents the adjusted allocation level, and a higher value indicates enhanced resource allocation efficiency.

[0283] formula:

[0284]

[0285] Analysis:

[0286] m r : Model adjustment parameters used to optimize model prediction accuracy.

[0287] Calculation process:

[0288] set up:

[0289] m r =2 (parameters obtained based on model optimization)

[0290] calculate:

[0291]

[0292] Analysis of calculation results:

[0293] U final ≈1 means that the adjusted configuration almost completely matches the current demand and is close to the ideal state.

[0294] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. An emergency nursing resource optimization allocation system, characterized in that: The system comprises: The resource association analysis module analyzes the relationship between medical equipment, medical staff and drugs, counts the interaction frequency between multiple resources, summarizes the resource flow pattern according to geographical location and time parameters, calculates the interaction intensity between nodes, and obtains the resource dependency intensity table; The resource demand prediction module calculates the resource demand at different time nodes and geographical locations based on the resource dependency intensity table, combined with the emergency event type and historical traffic data, and generates a predicted resource demand table; The spatiotemporal prediction adjustment module uses the resource dependency intensity table and the predicted resource demand table to analyze the sensitivity of resources at differentiated times and locations, adjusts the distribution of personnel and equipment according to the resource usage frequency and the geographical frequency of emergency events, updates resource allocation, and generates a resource allocation optimization plan; The dynamic deployment execution module adopts the resource allocation optimization solution, monitors emergency event response and equipment usage, adjusts medical staff configuration and equipment location, updates configuration data in real time, and generates implementation deployment results.

2. The emergency nursing resource optimization allocation system according to claim 1, characterized in that: The steps for obtaining the resource dependency intensity table are specifically as follows: Through the medical system data interface, the interaction data between medical equipment, medical staff and drugs is automatically collected, using the formula: F=[f ij ] Get the interaction frequency matrix F; Among them, i represents a certain type of medical resources including target medical equipment, j represents other types of resources including medical staff or drugs, and f ij Represents the number of interactions between resource i and resource j; The interaction frequency matrix is ​​combined with the geographic information system and time management system data to construct a location-time dependency matrix using the formula: Generate resource flow pattern R; Among them, L represents the geographical location influence matrix, and T represents the time influence matrix; The resource flow pattern is used to calculate the interaction strength between nodes. The interaction strength is calculated for each pair of nodes i and j using the covariance formula, using the formula: Get the interaction strength s between nodes ij ; Among them, r ik 、r jk They represent the flow intensity of resource i and resource j at the kth time and place, denote the average flow intensity of resource i and resource j respectively, and n denotes the total number of observations; Using the interaction strength between the nodes, a weighted formula is applied to calculate the resource dependency strength, using the formula: Generate resource dependency intensity table D; Among them, w ij represents the interaction importance weight between resources i and j, and the square root indicates the nonlinear influence of the weight.

3. The emergency nursing resource optimization allocation system according to claim 2, characterized in that: The steps for obtaining the predicted resource demand table are specifically as follows: Based on the resource dependency intensity table, time series data and event type data are extracted from the emergency event database and the historical traffic system, using the formula: Calculate preliminary resource requirements R based on time and event type t ; Among them, t represents the time series, e represents the event type, and f q (e) Function representing event type, α q represents the adjustment factor; Combined with the above preliminary resource requirements, a geographical location matrix is ​​constructed using the formula: R t,l =R t ·L 1 / 2 Generate adjusted resource requirements R t,l ; Where L represents the geographical location adjustment matrix; Based on the adjusted resource requirements, according to the urgency of emergency events and historical data on resource flows, the formula is used: Generate forecast resource requirement table R final ; Among them, β q represents the response intensity coefficient, δ q represents the time adjustment coefficient, and t0 represents the time offset parameter.

4. The emergency nursing resource optimization allocation system according to claim 3 is characterized in that: The steps for obtaining the resource configuration optimization solution are specifically as follows: Analyze the resource dependency intensity table and the predicted resource demand table to determine the sensitivity of resources at differentiated times and locations, using the formula: Calculate the sensitivity of resources and generate sensitivity analysis results S td ; Among them, c w represents the adjustment factor, h w Represents the impact of historical data; According to the frequency of resource use and the geographical frequency of emergency events, the distribution of personnel and equipment is adjusted using the formula: Generate updated resource distribution D new ; Where F represents the frequency of resource use, G represents the geographical frequency of emergency events, and k w represents the smoothing coefficient; Integrating the sensitivity analysis results and the updated resource distribution, the formula is used: Generate resource configuration optimization plan P opt ; Among them, m w Represents the adjustment offset.

5. The emergency nursing resource optimization allocation system according to claim 4, characterized in that: The steps for obtaining the deployment result are specifically as follows: Monitor emergency event response and equipment usage, use the resource allocation optimization solution, combine real-time event response data, and use the formula: Generate current resource usage analysisA current ; Among them, E r represents the weighted real-time incident response data, α r represents the adjustment coefficient, t r represents the time variable; Based on the current resource usage analysis and historical configuration data, adjust the medical staff configuration and equipment location using the formula: Update the configuration data and generate the adjusted configuration data C adjust ; Among them, F r represents the adjusted frequency data, H represents the historical configuration data, and k r represents the adjustment factor; Integrate the adjusted configuration data, using the formula: Generate implementation deployment results U final ; Among them, m r Represents adjustment of offset parameters.

Citation Information

Cited By

  • Emergency medical material dynamic replenishment method and system

    CN120412944A