A Big Data-Based Urban Medical Resource Service Data Analysis System and Method

Abstract

This invention discloses a data analysis system and method for urban medical resource services based on big data, belonging to the field of medical resource analysis technology. The invention collects road condition data, hospital bed data, and population data; establishes a correlation between driving distance and accessibility baseline score; calculates accessibility resistance factors by combining the number of turns and turn density; introduces the proportion of congestion time to obtain the final superimposed resistance at different times; and generates a gain offset value based on the number of route choices; integrates parameters to calculate accessibility scores and classifies them into levels; delineates the effective coverage area of ​​hospitals according to the levels; and determines the effective number of hospital beds needed by statistically analyzing the total population within the coverage area; calculates the theoretical bed demand by combining the required bed occupancy rate; compares the real-time available bed numbers to obtain the supply-demand gap value and supplements beds accordingly.

Description

Technical Field

[0001] This invention relates to the field of medical resource analysis technology, specifically to a data analysis system and method for urban medical resource services based on big data. Background Technology

[0002] In the field of optimizing the allocation of urban medical resources, accessibility assessment and hospital bed resource planning are core components for improving the efficiency of medical services. With the application of big data technology in the medical field, related data analysis methods have become a research hotspot. However, existing technologies still have many limitations in practical applications and are difficult to meet the needs of precise allocation of medical resources.

[0003] In assessing accessibility to healthcare, existing technologies often rely on single or limited-dimensional data analysis, lacking systematic coupling of multi-dimensional data and generally ignoring the offsetting effects of other parameters. This results in biased assessments that fail to accurately reflect actual accessibility. Furthermore, existing technologies are largely static analyses, neglecting traffic flow characteristics at different times. They frequently use fixed parameters for calculations, failing to differentiate between dynamic changes in road conditions at different times, thus failing to generate time-specific assessments and becoming disconnected from real-world scenarios. In the planning of medical bed resources, existing technologies suffer from inaccurate demand estimations and strong subjectivity in decision-making. Traditional methods often directly estimate demand based on the total population of the region, failing to define reasonable service areas based on accessibility, leading to significant discrepancies in the statistical analysis of effective demand. Additionally, the addition of existing beds often relies on experience-based judgments, lacking quantitative calculations, which can easily result in resource underutilization or insufficient service capacity, affecting the scientific and rational allocation of medical resources. Summary of the Invention

[0004] The purpose of this invention is to provide a data analysis system and method for urban medical resource services based on big data, so as to solve the problems raised in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: In a first aspect, the present invention provides a data analysis method for urban medical resource services based on big data, including: Collect traffic data, hospital bed data, and population data. The traffic data includes the distance residents travel to the hospital, the number of turns, the number of route choices, and the percentage of congestion time. Establish the correlation between driving distance and basic accessibility score; convert the number of turns into an initial accessibility resistance factor, and combine it with the turn density to obtain the accessibility resistance factor; Introducing the congestion duration percentage and combining it with the accessibility resistance factor, the final superimposed resistance for different time periods is calculated; the number of route choices is converted into an accessibility gain factor, forming a gain offset value for the final superimposed resistance for different time periods; By integrating the basic accessibility score, the final superimposed resistance and gain offset value, the accessibility score is calculated and the accessibility level is divided; the effective coverage area of ​​the hospital is defined according to the accessibility level, and the effective demand for the hospital is determined by combining the collected population data with the total population within the coverage area. The theoretical bed demand is calculated based on the number of people in the hospital with effective demand. The bed supply and demand gap is calculated by combining the hospital bed data. Beds are then added according to the bed supply and demand gap.

[0006] In conjunction with the first aspect, in the first implementation of the first aspect of this application, the collection of road condition data, hospital bed data, and population data includes: The hospital bed data includes the total number of beds, the number of beds available in real time, and the required bed occupancy rate based on historical experience; the population data includes the spatial coordinates of residential areas and the number of permanent residents in the corresponding areas.

[0007] In conjunction with the first aspect, in the second implementation of the first aspect of this application, the establishment of the correlation between driving distance and accessibility baseline score includes: Based on the needs of urban medical service layout and combined with the collected driving distances, a distance benchmark value and an accessibility basic score scoring system are set. When the driving distance is less than or equal to the distance benchmark value, the accessibility basic score is full. When the driving distance is greater than the distance benchmark value, the difference between the driving distance and the distance benchmark value is multiplied by a preset linear deduction coefficient to obtain the accessibility basic score deduction. The difference between the full accessibility basic score and the accessibility basic score deduction is calculated to obtain the accessibility basic score.

[0008] In conjunction with the first aspect, in the third implementation of the first aspect of this application, the step of converting the number of turns into an initial reachability resistance factor, and combining the turn density to obtain the reachability resistance factor, includes: Based on the distance reference value, when the driving distance is less than or equal to the distance reference value, the preset linear resistance coefficient is multiplied by the number of turns to obtain the initial accessibility resistance factor; when the driving distance is greater than the distance reference value, the preset quadratic resistance coefficient is multiplied by the square of the number of turns to obtain the initial accessibility resistance factor. The turning density is obtained by the ratio of the number of turns to the driving distance. When the turning density is greater than the preset turning density threshold, the sum of 1 and the preset turning coefficient is calculated to obtain the turning coefficient correction value. The turning coefficient correction value is multiplied by the initial accessibility resistance factor to obtain the accessibility resistance factor.

[0009] In conjunction with the first aspect, in the fourth implementation of the first aspect of this application, the introduction of congestion duration percentage and the calculation of the final superimposed resistance for different time periods in conjunction with the accessibility resistance factor includes: Based on historical experience and urban traffic tidal patterns, the system is divided into several time periods, and a congestion weighting coefficient is set for each time period. Combining the distance benchmark, turning density, and calculated accessibility resistance factor, the congestion impact weight is determined as follows: when the driving distance is less than or equal to the distance benchmark, the congestion impact weight is the product of a preset basic weight and the corresponding time period congestion weight coefficient; when the driving distance is greater than the distance benchmark and the turning density is less than or equal to a preset turning density threshold, the congestion impact weight is the product of a preset medium weight and the corresponding time period congestion weight coefficient; when the driving distance is greater than the distance benchmark and the turning density is greater than the preset turning density threshold, the congestion impact weight is the product of a preset high weight and the corresponding time period congestion weight coefficient. Based on the determined congestion impact weight and the proportion of congestion duration collected in different time periods, combined with the accessibility resistance factor, the final superimposed resistance for the corresponding time period is calculated. Specifically, the product of the congestion impact weight and the proportion of congestion duration is calculated, and the sum of the product and 1 is the congestion correction coefficient. The congestion correction coefficient is then multiplied by the accessibility resistance factor to obtain the final superimposed resistance for different time periods.

[0010] In conjunction with the first aspect, in the fifth implementation of the first aspect of this application, the step of converting the number of route selections into reachability gain factors to form gain offset values ​​for the final superimposed resistance at different time periods includes: Based on the divided time periods, set the detour threshold and gain conversion factor for the corresponding time periods; Extract all candidate routes from the selected routes. Combine the collected driving distance with the driving distance of the candidate routes to calculate the route repetition rate for each candidate route. Specifically, calculate the difference between the driving distance of the candidate route and the collected driving distance, and divide the difference by the collected driving distance to obtain the route repetition rate. When the route repetition rate is less than or equal to the detour threshold for the corresponding time period, it is determined to be a valid route. The number of effective routes is counted, and the number of effective routes is multiplied by the gain conversion factor for the corresponding time period to obtain the accessibility gain factor. Based on the calculated final superimposed resistance for different time periods, the gain cancellation value is taken as the minimum value of the final superimposed resistance and the reachability gain factor for the corresponding time period.

[0011] In conjunction with the first aspect, in the sixth implementation of the first aspect of this application, the integration of the basic accessibility score, the final superimposed resistance, and the gain offset value to calculate the accessibility score and classify accessibility levels includes: Based on the time period division criteria, the calculation data is integrated for each time period, and the difference between the final superimposed resistance and the gain offset value of the corresponding time period is calculated. The accessibility base score is subtracted from the difference, and the result is adjusted by boundary to obtain the accessibility score of the corresponding time period. Based on the planning needs of urban medical resources and historical travel data, three accessibility levels (high, medium, and low) are set with score thresholds. The accessibility scores for the corresponding time periods are compared with the score thresholds for the accessibility levels to classify them into different accessibility levels.

[0012] In conjunction with the first aspect, in the seventh implementation of the first aspect of this application, the step of defining the effective coverage area of ​​the hospital based on the accessibility level, and determining the effective demand for hospital personnel by combining the total population within the statistical range of the collected population data, includes: Based on the accessibility levels, different hospital coverage radii are set; using a geographic information system, the effective coverage area boundary of the hospital is drawn with the target hospital as the center and the hospital coverage radius corresponding to the accessibility level as the radius; the collected population data is retrieved to obtain the total population within the effective coverage area of ​​the hospital, which is taken as the effective number of people needed by the hospital.

[0013] In conjunction with the first aspect, in the eighth implementation of the first aspect of this application, the step of calculating the theoretical bed demand based on the effective number of hospital staff, calculating the bed supply-demand gap value based on hospital bed data, and increasing the number of beds according to the bed supply-demand gap value includes: Based on the determined effective demand for hospital beds, the required bed occupancy rate obtained from historical experience in the collected hospital bed data is retrieved, and the theoretical bed occupancy rate is obtained by multiplying the effective demand for hospital beds by the required bed occupancy rate. The system retrieves the total number of beds and the number of beds available in real time from the collected hospital bed data. The difference between the theoretical bed demand and the number of beds available in real time is used as the bed supply and demand gap value. When the bed supply and demand gap value is positive, it is determined that the bed supply is insufficient, and the number of beds is increased according to the bed supply and demand gap value.

[0014] Secondly, this invention provides a big data-based urban medical resource service data analysis system, including: Basic data acquisition module: includes multi-dimensional data acquisition unit; the multi-dimensional data acquisition unit collects traffic data, hospital bed data, and population data; The accessibility calculation and classification module includes an accessibility base score calculation unit, a resistance and gain factor calculation unit, a time-segment final superimposed resistance calculation unit, and an accessibility score and classification unit. Specifically, the accessibility base score calculation unit calculates the accessibility base score through linear deduction based on the relationship between driving distance and a baseline value; the resistance and gain factor calculation unit calculates and corrects the accessibility resistance factor, determines valid routes, and generates accessibility gain factors and gain offset values; the time-segment final superimposed resistance calculation unit calculates the final superimposed resistance for different time periods; and the accessibility score and classification unit calculates the time-segment accessibility score, corrects the boundaries, and classifies accessibility levels. The module for determining the effective number of hospital residents in need includes a coverage area delineation unit and a demand area statistics unit. The coverage area delineation unit sets the hospital coverage radius according to the accessibility level and draws the boundary of the hospital's effective coverage area. The demand area statistics unit counts the total population within the effective coverage area as the hospital's effective demand area. The bed supply and demand gap analysis module includes a theoretical bed demand calculation unit and a supply and demand gap and bed increase determination unit. The theoretical bed demand calculation unit multiplies the effective demand of the hospital by the required bed rate to obtain the theoretical bed demand. The supply and demand gap and bed increase determination unit calculates the difference between the theoretical bed demand and the real-time available bed number, and increases the number of beds when the gap value is positive.

[0015] Compared with the prior art, the beneficial effects of the present invention are: 1. This invention couples multi-dimensional traffic data and considers the offsetting effects of the number of route selections on the number of turns, turn density, and congestion duration, forming a gain offsetting value for the final superimposed resistance.

[0016] 2. This invention integrates the characteristics of different time periods to calculate the final superimposed resistance, gain cancellation value, and accessibility score under the influence of different time periods.

[0017] 3. This invention defines the effective coverage area of ​​hospitals based on accessibility levels, counts the effective number of people in need of hospitals, and quantifies the theoretical bed demand and supply-demand gap accordingly to supplement beds. Attached Figure Description

[0018] Figure 1 This is a schematic diagram illustrating the steps of the big data-based urban medical resource service data analysis method of the present invention; Figure 2 This is a flowchart of the data analysis method for urban medical resource services based on big data according to the present invention. Figure 3 This is a system architecture diagram of the big data-based urban medical resource service data analysis system of the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Example: Figures 1-3 As shown, the present invention provides a technical solution. like Figure 1The schematic diagram illustrates the steps of a big data-based urban medical resource service data analysis method. This invention provides a big data-based urban medical resource service data analysis method, including: Step S100: Collect road condition data, hospital bed data, and population data; Specifically, the hospital bed data includes the total number of beds, the number of beds available in real time, and the required bed occupancy rate based on historical experience; the population data includes the spatial coordinates of residential areas and the number of permanent residents in the corresponding areas.

[0021] In one specific embodiment, a general hospital in a certain urban area is used as the analysis object. Multi-dimensional data of the past 30 days are collected. The traffic data includes the average driving distance of 2.1 kilometers, the average number of turns of 3, the number of route choices of 8 residents within 3 kilometers of the hospital, and the proportion of congestion time during the morning peak of 7:00-9:00 (35%), the evening peak of 17:00-19:00 (42%), and the off-peak congestion time (12%). The hospital bed data shows a total of 500 beds and 120 beds available at real time. The required bed occupancy rate is 0.2% based on the inpatient data of the past year. The population data includes the spatial coordinates of 5 residential points within the radiation range, corresponding to a total permanent population of 126,000 in the area, with permanent populations of 28,000, 32,000, 21,000, 25,000, and 20,000 for each residential point, respectively.

[0022] Step S200: Establish the correlation between driving distance and basic accessibility score; convert the number of turns into an initial accessibility resistance factor, and combine it with the turn density to obtain the accessibility resistance factor; Specifically, based on the needs of urban medical service layout and combined with the collected driving distances, a distance benchmark value and an accessibility basic score scoring system are set. When the driving distance is less than or equal to the distance benchmark value, the accessibility basic score is full. When the driving distance is greater than the distance benchmark value, the difference between the driving distance and the distance benchmark value is multiplied by a preset linear deduction coefficient to obtain the accessibility basic score deduction. The difference between the full accessibility basic score and the accessibility basic score deduction is calculated to obtain the accessibility basic score.

[0023] Based on the distance reference value, when the driving distance is less than or equal to the distance reference value, the preset linear resistance coefficient is multiplied by the number of turns to obtain the initial accessibility resistance factor; when the driving distance is greater than the distance reference value, the preset quadratic resistance coefficient is multiplied by the square of the number of turns to obtain the initial accessibility resistance factor. The turning density is obtained by the ratio of the number of turns to the driving distance. When the turning density is greater than the preset turning density threshold, the sum of 1 and the preset turning coefficient is calculated to obtain the turning coefficient correction value. The turning coefficient correction value is multiplied by the initial accessibility resistance factor to obtain the accessibility resistance factor.

[0024] In one specific embodiment, a distance baseline of 2 kilometers is set, the maximum accessibility score is 100 points, and a preset linear deduction coefficient of 5 points / kilometer is set. Based on the collected average driving distance of 2.1 kilometers, which exceeds the baseline, a deduction of 0.5 points is calculated, resulting in a final accessibility baseline score of 99.5 points. Simultaneously, a preset linear resistance coefficient of 0.8 and a preset quadratic resistance coefficient of 0.05 are set. Since the driving distance exceeds the baseline, the initial accessibility resistance factor is 0.45. Then, based on the number of turns (3) and the driving distance of 2.1 kilometers, a turning density of approximately 1.43 times / kilometer is calculated. A preset turning density threshold of 0.8 times / kilometer and a preset turning coefficient of 0.2 are set. Since the turning density exceeds the threshold, the turning coefficient is corrected to 1.2, resulting in a final accessibility resistance factor of 0.54.

[0025] Step S300: Introduce the congestion duration percentage and calculate the final superimposed resistance for different time periods by combining it with the accessibility resistance factor; convert the number of route selections into an accessibility gain factor to form a gain offset value for the final superimposed resistance for different time periods. Specifically, based on historical experience and urban traffic tidal patterns, the city is divided into several time periods, and a congestion weighting coefficient is set for each time period. Combining the distance benchmark, turning density, and calculated accessibility resistance factor, the congestion impact weight is determined as follows: when the driving distance is less than or equal to the distance benchmark, the congestion impact weight is the product of a preset basic weight and the corresponding time period congestion weight coefficient; when the driving distance is greater than the distance benchmark and the turning density is less than or equal to a preset turning density threshold, the congestion impact weight is the product of a preset medium weight and the corresponding time period congestion weight coefficient; when the driving distance is greater than the distance benchmark and the turning density is greater than the preset turning density threshold, the congestion impact weight is the product of a preset high weight and the corresponding time period congestion weight coefficient. Based on the determined congestion impact weight and the proportion of congestion duration collected in different time periods, combined with the accessibility resistance factor, the final superimposed resistance for the corresponding time period is calculated. Specifically, the product of the congestion impact weight and the proportion of congestion duration is calculated, and the sum of the product and 1 is the congestion correction coefficient. The congestion correction coefficient is then multiplied by the accessibility resistance factor to obtain the final superimposed resistance for different time periods.

[0026] Based on the divided time periods, set the detour threshold and gain conversion factor for the corresponding time periods; Extract all candidate routes from the selected routes. Combine the collected driving distance with the driving distance of the candidate routes to calculate the route repetition rate for each candidate route. Specifically, calculate the difference between the driving distance of the candidate route and the collected driving distance, and divide the difference by the collected driving distance to obtain the route repetition rate. When the route repetition rate is less than or equal to the detour threshold for the corresponding time period, it is determined to be a valid route. The number of effective routes is counted, and the number of effective routes is multiplied by the gain conversion factor for the corresponding time period to obtain the accessibility gain factor. Based on the calculated final superimposed resistance for different time periods, the gain cancellation value is taken as the minimum value of the final superimposed resistance and the reachability gain factor for the corresponding time period.

[0027] In one specific embodiment, the system is divided into three time periods: morning peak (7:00-9:00), evening peak (17:00-19:00), and off-peak. The congestion weight coefficients for these time periods are set to 1.2, 1.3, and 0.9, respectively, with a preset high weight of 0.6. Thus, the congestion impact weights for each time period are 0.72, 0.78, and 0.54, respectively. Based on the congestion duration percentages of 35%, 42%, and 12% for each time period, the congestion correction coefficients are calculated to be 1.252, 1.328, and 1.065, respectively, corresponding to final superimposed resistance values ​​of 0.676, 0.717, and 0.575. Simultaneously, a detour threshold of 10% is set for each time period, a gain conversion coefficient of 0.1 is set, 6 out of 8 alternative routes have a detour rate ≤10%, the number of effective routes is 6, and the accessibility gain factor is 0.6. Finally, the gain offset values ​​for each time period are the minimum values ​​of the corresponding final superimposed resistance and 0.6, i.e., 0.6, 0.6, and 0.575.

[0028] Step S400: Integrate the basic accessibility score, the final superimposed resistance and gain offset value, calculate the accessibility score, and classify the accessibility level; delineate the effective coverage area of ​​the hospital based on the accessibility level, and determine the effective number of people needed by the hospital by combining the collected population data with the total population within the coverage area. Specifically, based on the time period division criteria, the calculation data is integrated for each time period, and the difference between the final superimposed resistance and the gain offset value of the corresponding time period is calculated. The accessibility base score is subtracted from the difference, and the result is adjusted by boundary to obtain the accessibility score of the corresponding time period. Based on the planning needs of urban medical resources and historical travel data, three accessibility levels (high, medium, and low) are set with score thresholds. The accessibility scores for the corresponding time periods are compared with the score thresholds for the accessibility levels to classify them into different accessibility levels.

[0029] Based on the accessibility levels, different hospital coverage radii are set; using a geographic information system, the effective coverage area boundary of the hospital is drawn with the target hospital as the center and the hospital coverage radius corresponding to the accessibility level as the radius; the collected population data is retrieved to obtain the total population within the effective coverage area of ​​the hospital, which is taken as the effective number of people needed by the hospital.

[0030] In one specific embodiment, calculations are performed separately for morning and evening peak hours and off-peak hours. The difference between the final superimposed resistance and gain offset value is 0.076 for the morning peak, 0.117 for the evening peak, and 0 for the off-peak. The above differences are subtracted from the basic accessibility score of 99.5 points. After boundary correction, the accessibility scores for each time period are 99.42 points, 99.38 points, and 99.5 points, respectively. Thresholds are set for high level ≥99 points, medium level 85-98 points, and low level <85 points. All three time periods are classified as high accessibility level, and a hospital coverage radius of 3 kilometers is set accordingly. Based on the geographic information system, a 3-kilometer boundary is drawn with the target hospital as the center. Data is retrieved to count the total population of 126,000 in 5 residential areas within this range, which is taken as the effective demand for the hospital.

[0031] Step S500: Calculate the theoretical bed demand based on the number of people in effective demand at the hospital, calculate the bed supply-demand gap value in combination with hospital bed data, and increase the number of beds according to the bed supply-demand gap value.

[0032] Specifically, based on the determined effective demand for hospital beds, the required bed occupancy rate obtained from historical experience in the collected hospital bed data is retrieved, and the theoretical bed demand is obtained by multiplying the effective demand for hospital beds by the required bed occupancy rate. The system retrieves the total number of beds and the number of beds available in real time from the collected hospital bed data. The difference between the theoretical bed demand and the number of beds available in real time is used as the bed supply and demand gap value. When the bed supply and demand gap value is positive, it is determined that the bed supply is insufficient, and the number of beds is increased according to the bed supply and demand gap value.

[0033] In one specific embodiment, based on the determined effective demand of 126,000 people in the hospital, the required bed occupancy rate of 0.2% is retrieved, and the theoretical bed demand is calculated to be 252 beds. Then, the number of available beds in the hospital in real time is retrieved to be 120. The difference between the theoretical bed demand and the number of available beds in real time is taken as the bed supply and demand gap value, which is 132 beds. Since the gap value is positive, it is determined that the bed supply is insufficient, and 132 beds are added according to the gap value.

[0034] like Figure 2 The flowchart of the data analysis method for urban medical resource services based on big data is shown in this invention. The invention provides a data analysis method for urban medical resource services based on big data, including: After the process begins, data is collected to obtain three basic data: road conditions, hospital beds, and population. The process is then divided into parallel computing branches: one branch establishes the correlation between driving distance and accessibility basic score and calculates the score, while the other branch converts the number of turns and turn density into accessibility resistance factor. Next, the process enters the fusion calculation stage, which introduces the proportion of congestion time in each period and combines it with the obtained resistance factors to calculate the final superimposed resistance in different periods. At the same time, the number of route selections is converted into accessibility gain factors. The process is then integrated into the integrated evaluation stage, which integrates the basic score, superimposed resistance and gain offset value to calculate the accessibility score for each period and classify it into high, medium and low levels. Based on the classification levels, differentiated hospital coverage radii are set according to the levels to define the effective coverage area, and the total population within the area is counted as the effective demand number. Finally, the theoretical bed demand is calculated using the effective demand number and the historical bed demand rate. By comparing it with the real-time available bed number, the supply and demand gap is determined, and the number of beds is increased.

[0035] like Figure 3 The system architecture diagram of the big data-based urban medical resource service data analysis system is shown in the figure. This invention provides a big data-based urban medical resource service data analysis system, including: Basic data acquisition module: includes multi-dimensional data acquisition unit; the multi-dimensional data acquisition unit collects traffic data, hospital bed data, and population data; The accessibility calculation and classification module includes an accessibility base score calculation unit, a resistance and gain factor calculation unit, a time-segment final superimposed resistance calculation unit, and an accessibility score and classification unit. Specifically, the accessibility base score calculation unit calculates the accessibility base score through linear deduction based on the relationship between driving distance and a baseline value; the resistance and gain factor calculation unit calculates and corrects the accessibility resistance factor, determines valid routes, and generates accessibility gain factors and gain offset values; the time-segment final superimposed resistance calculation unit calculates the final superimposed resistance for different time periods; and the accessibility score and classification unit calculates the time-segment accessibility score, corrects the boundaries, and classifies accessibility levels. The module for determining the effective number of hospital residents in need includes a coverage area delineation unit and a demand area statistics unit. The coverage area delineation unit sets the hospital coverage radius according to the accessibility level and draws the boundary of the hospital's effective coverage area. The demand area statistics unit counts the total population within the effective coverage area as the hospital's effective demand area. The bed supply and demand gap analysis module includes a theoretical bed demand calculation unit and a supply and demand gap and bed increase determination unit. The theoretical bed demand calculation unit multiplies the effective demand of the hospital by the required bed rate to obtain the theoretical bed demand. The supply and demand gap and bed increase determination unit calculates the difference between the theoretical bed demand and the real-time available bed number, and increases the number of beds when the gap value is positive.

[0036] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A data analysis method for urban medical resource services based on big data, characterized in that, include: Collect traffic data, hospital bed data, and population data. The traffic data includes the distance residents travel to the hospital, the number of turns, the number of route choices, and the percentage of congestion time. Establish the correlation between driving distance and basic accessibility score; The number of turns is converted into an initial accessibility resistance factor, and the accessibility resistance factor is obtained by combining the turn density. By introducing the proportion of congestion time and combining it with the accessibility resistance factor, the final superimposed resistance for different time periods is calculated; The number of route choices is converted into an accessibility gain factor, which forms a gain offset value for the final superimposed resistance at different time periods; By integrating the basic accessibility score, the final superimposed resistance, and the gain offset value, an accessibility score is calculated, and accessibility levels are classified. The effective coverage area of ​​the hospital is defined based on the accessibility level, and the total population within the scope of the statistical data is combined with the collected population data to determine the effective number of people needed by the hospital. The theoretical bed demand is calculated based on the number of people in the hospital with effective demand. The bed supply and demand gap is calculated by combining the hospital bed data. Beds are then added according to the bed supply and demand gap.

2. The data analysis method for urban medical resource services based on big data according to claim 1, characterized in that, The collected road condition data, hospital bed data, and population data include: The hospital bed data includes the total number of beds, the number of beds available in real time, and the required bed occupancy rate based on historical experience; the population data includes the spatial coordinates of residential areas and the number of permanent residents in the corresponding areas.

3. The data analysis method for urban medical resource services based on big data according to claim 1, characterized in that, The establishment of the correlation between driving distance and basic accessibility score includes: Based on the needs of urban medical service layout and combined with the collected driving distances, a distance benchmark value and an accessibility basic score scoring system are set. When the driving distance is less than or equal to the distance benchmark value, the accessibility basic score is full. When the driving distance is greater than the distance benchmark value, the difference between the driving distance and the distance benchmark value is multiplied by a preset linear deduction coefficient to obtain the accessibility basic score deduction. The difference between the full accessibility basic score and the accessibility basic score deduction is calculated to obtain the accessibility basic score.

4. The method for analyzing urban medical resource service data based on big data according to claim 1, characterized in that, The process of converting the number of turns into an initial reachability resistance factor, and combining this with the turn density to obtain the reachability resistance factor, includes: Based on the distance reference value, when the driving distance is less than or equal to the distance reference value, the preset linear resistance coefficient is multiplied by the number of turns to obtain the initial accessibility resistance factor; when the driving distance is greater than the distance reference value, the preset quadratic resistance coefficient is multiplied by the square of the number of turns to obtain the initial accessibility resistance factor. The turning density is obtained by the ratio of the number of turns to the driving distance. When the turning density is greater than the preset turning density threshold, the sum of 1 and the preset turning coefficient is calculated to obtain the turning coefficient correction value. The turning coefficient correction value is multiplied by the initial accessibility resistance factor to obtain the accessibility resistance factor.

5. The method for analyzing urban medical resource service data based on big data according to claim 1, characterized in that, The introduction of congestion duration percentage, combined with accessibility resistance factors, to calculate the final cumulative resistance for different time periods includes: Based on historical experience and urban traffic tidal patterns, the system is divided into several time periods, and a congestion weighting coefficient is set for each time period. Combining the distance benchmark, turning density, and calculated accessibility resistance factor, the congestion impact weight is determined as follows: when the driving distance is less than or equal to the distance benchmark, the congestion impact weight is the product of a preset basic weight and the corresponding time period congestion weight coefficient; when the driving distance is greater than the distance benchmark and the turning density is less than or equal to a preset turning density threshold, the congestion impact weight is the product of a preset medium weight and the corresponding time period congestion weight coefficient; when the driving distance is greater than the distance benchmark and the turning density is greater than the preset turning density threshold, the congestion impact weight is the product of a preset high weight and the corresponding time period congestion weight coefficient. Based on the determined congestion impact weight and the proportion of congestion duration collected in different time periods, combined with the accessibility resistance factor, the final superimposed resistance for the corresponding time period is calculated. Specifically, the product of the congestion impact weight and the proportion of congestion duration is calculated, and the sum of the product and 1 is the congestion correction coefficient. The congestion correction coefficient is then multiplied by the accessibility resistance factor to obtain the final superimposed resistance for different time periods.

6. The method for analyzing urban medical resource service data based on big data according to claim 1, characterized in that, The process of converting the number of route choices into an accessibility gain factor to form a gain offset value for the final superimposed resistance at different time periods includes: Based on the divided time periods, set the detour threshold and gain conversion factor for the corresponding time periods; Extract all candidate routes from the selected routes. Combine the collected driving distance with the driving distance of the candidate routes to calculate the route repetition rate for each candidate route. Specifically, calculate the difference between the driving distance of the candidate route and the collected driving distance, and divide the difference by the collected driving distance to obtain the route repetition rate. When the route repetition rate is less than or equal to the detour threshold for the corresponding time period, it is determined to be a valid route. The number of effective routes is counted, and the number of effective routes is multiplied by the gain conversion factor for the corresponding time period to obtain the accessibility gain factor. Based on the calculated final superimposed resistance for different time periods, the gain cancellation value is taken as the minimum value of the final superimposed resistance and the reachability gain factor for the corresponding time period.

7. The method for analyzing urban medical resource service data based on big data according to claim 1, characterized in that, The integrated accessibility baseline score, final superimposed resistance, and gain offset value are used to calculate the accessibility score and classify accessibility levels, including: Based on the time period division criteria, the calculation data is integrated for each time period, and the difference between the final superimposed resistance and the gain offset value of the corresponding time period is calculated. The accessibility base score is subtracted from the difference, and the result is adjusted by boundary to obtain the accessibility score of the corresponding time period. Based on the planning needs of urban medical resources and historical travel data, three accessibility levels (high, medium, and low) are set with score thresholds. The accessibility scores for the corresponding time periods are compared with the score thresholds for the accessibility levels to classify them into different accessibility levels.

8. The method for analyzing urban medical resource service data based on big data according to claim 1, characterized in that, The process of defining the effective coverage area of ​​the hospital based on accessibility levels, and determining the effective demand for hospital personnel by combining the collected population data with the total population within the coverage area, includes: Based on the accessibility levels, different hospital coverage radii are set; using a geographic information system, the effective coverage area boundary of the hospital is drawn with the target hospital as the center and the hospital coverage radius corresponding to the accessibility level as the radius; the collected population data is retrieved to obtain the total population within the effective coverage area of ​​the hospital, which is taken as the effective number of people needed by the hospital.

9. The method for analyzing urban medical resource service data based on big data according to claim 1, characterized in that, The process of calculating the theoretical bed demand based on the effective number of hospital applicants, calculating the bed supply-demand gap value based on hospital bed data, and increasing the number of beds according to the bed supply-demand gap value includes: Based on the determined effective demand for hospital beds, the required bed occupancy rate obtained from historical experience in the collected hospital bed data is retrieved, and the theoretical bed occupancy rate is obtained by multiplying the effective demand for hospital beds by the required bed occupancy rate. The system retrieves the total number of beds and the number of beds available in real time from the collected hospital bed data. The difference between the theoretical bed demand and the number of beds available in real time is used as the bed supply and demand gap value. When the bed supply and demand gap value is positive, it is determined that the bed supply is insufficient, and the number of beds is increased according to the bed supply and demand gap value.

10. A big data-based urban medical resource service data analysis system, using the big data-based urban medical resource service data analysis method according to any one of claims 1-9, characterized in that, include: Basic data acquisition module: includes multi-dimensional data acquisition units; The multi-dimensional data acquisition unit collects road condition data, hospital bed data, and population data; The accessibility calculation and classification module includes an accessibility base score calculation unit, a resistance and gain factor calculation unit, a time-segment final superimposed resistance calculation unit, and an accessibility score and classification unit. Specifically, the accessibility base score calculation unit calculates the accessibility base score through linear deduction based on the relationship between driving distance and a baseline value; the resistance and gain factor calculation unit calculates and corrects the accessibility resistance factor, determines valid routes, and generates accessibility gain factors and gain offset values; the time-segment final superimposed resistance calculation unit calculates the final superimposed resistance for different time periods; and the accessibility score and classification unit calculates the time-segment accessibility score, corrects the boundaries, and classifies accessibility levels. The module for determining the effective number of hospital residents in need includes a coverage area delineation unit and a demand area statistics unit. The coverage area delineation unit sets the hospital coverage radius according to the accessibility level and draws the boundary of the hospital's effective coverage area. The demand area statistics unit counts the total population within the effective coverage area as the hospital's effective demand area. The bed supply and demand gap analysis module includes a theoretical bed demand calculation unit and a supply and demand gap and bed increase determination unit. The theoretical bed demand calculation unit multiplies the effective demand of the hospital by the required bed rate to obtain the theoretical bed demand. The supply and demand gap and bed increase determination unit calculates the difference between the theoretical bed demand and the real-time available bed number, and increases the number of beds when the gap value is positive.

Images