A public health data statistics and analysis system

Abstract

This invention relates to data statistical analysis, specifically to a public health data statistical and analysis system, including a control unit. The control unit collects regional characteristic data of sample cities and target cities through a data collection module, and outputs corresponding representation vectors based on the regional characteristic data using an encoder. The control unit decodes the representation vectors of the sample cities and target cities respectively through a decoder, and extracts common feature data of the regional characteristic data of the sample cities and target cities using a common feature extractor. The control unit classifies the target city based on the common feature data using a classifier. When the target city and the sample city are both in public health event outbreak areas, the control unit obtains basic characteristic data of the public health event through a data acquisition module. The technical solution provided by this invention can effectively overcome the shortcomings of existing technologies, such as inaccurate public health risk level classification and poor adaptability of emergency plans.

Description

Technical Field

[0001] This invention relates to data statistical analysis, specifically to a public health data statistical and analysis system. Background Technology

[0002] Public health emergencies are characterized by their suddenness, high transmissibility, and wide-ranging impact. Timely statistical analysis of public health data, risk level assessment, and matching of emergency response plans are crucial to improving urban public health prevention and control capabilities. Existing traditional public health analysis methods largely rely on manual statistics of single-dimensional population, medical, and basic transportation data, lacking systematic collection and in-depth analysis of multi-dimensional regional characteristics of cities, making it difficult to quantify the commonalities and correlations of regional characteristics among different cities.

[0003] Currently, conventional technologies struggle to vectorize and reconstruct urban regional characteristics through encoding and decoding, failing to accurately extract common features between sample and target cities. This results in only a rough assessment of public health risks in target cities, lacking refined methods based on binary classification models to eliminate discrepancies in the distribution of common features between cities. Furthermore, existing technologies lack a multi-dimensional quantitative calculation system for public health event spread indices, population impact indices, and resource reserve indices. The methods for delineating event spread areas are crude, failing to accurately delineate geographical boundaries by combining the initial location of the event with the diameter of the spread index interval.

[0004] Furthermore, existing public health emergency response plans rely heavily on experience, failing to construct a comprehensive evaluation coefficient that considers the characteristics of event spread, the degree of population impact, and the city's medical and material resource reserves. Consequently, they cannot automatically match the corresponding relief level and emergency plan based on the comprehensive evaluation coefficient. This results in problems such as delayed risk assessment, inaccurate delineation of the spread range, poor adaptability of emergency plans, and lack of data support for prevention and control decisions, making it difficult to meet the practical application needs of large-scale, intelligent public health data statistical analysis and precise emergency prevention and control. Summary of the Invention

[0005] (a) Technical problems to be solved

[0006] In view of the above-mentioned shortcomings of the existing technology, the present invention provides a public health data statistics and analysis system, which can effectively overcome the defects of the existing technology, such as inaccurate public health risk level classification and poor adaptability of emergency plans.

[0007] (II) Technical Solution

[0008] To achieve the above objectives, the present invention provides the following technical solution:

[0009] A public health data statistics and analysis system includes a control unit. The control unit collects regional feature data of sample cities and target cities through a data collection module, and outputs corresponding representation vectors based on the regional feature data using an encoder. The control unit decodes the representation vectors of sample cities and target cities respectively through a decoder, and extracts common feature data of the regional feature data of sample cities and target cities using a common feature extractor. The control unit classifies and determines the target city based on the common feature data using a classifier.

[0010] When the target city and the sample city are both located in the public health emergency outbreak area, the control unit obtains basic characteristic data of the public health emergency through the data acquisition module, and calculates the diffusion index of the public health emergency based on the basic characteristic data using the diffusion index calculation module. The control unit calculates the population impact index of the public health emergency based on the diffusion index using the population impact index calculation module, and calculates the medical resource reserve index and material resource reserve index of the target city using the resource reserve index calculation module. The control unit calculates the comprehensive evaluation coefficient of the public health emergency through the comprehensive evaluation coefficient calculation module, and matches the corresponding emergency plan based on the comprehensive evaluation coefficient using the emergency plan matching module.

[0011] Preferably, the data collection module collects regional characteristic data of the sample city and the target city, including:

[0012] Collect regional characteristic data, including surrounding infrastructure, regional population size, regional population age distribution, regional transportation, and regional population flow, for sample cities and target cities.

[0013] Preferably, the encoder outputs a corresponding representation vector based on the region feature data, including:

[0014] The regional feature data of the sample city and the target city are input into the encoder, and the encoder outputs the representation vectors of the sample city and the target city respectively after encoding.

[0015] Preferably, the decoder decodes the representation vectors of the sample city and the target city respectively, including:

[0016] The representation vector of the sample city is decoded using the sample city decoder, and the representation vector of the target city is decoded using the target city decoder.

[0017] Preferably, the classifier classifies the target city based on common feature data, including:

[0018] The classifier takes the common features of the regional feature data of the sample city and the target city as input, and combines them with the preset public health event risk labeling rules to classify and determine the public health risk level of the target city.

[0019] Preferably, the classifier constructs a binary classification model, using the common feature data of the regional feature data of the sample city and the target city as input, reducing the difference in the distribution offset of common features between the sample city and the target city, and outputting the public health event risk category determination result of the target city.

[0020] Preferably, the diffusion index calculation module calculates the diffusion index of a public health event based on basic characteristic data, including:

[0021] The spread index of a public health event is calculated based on the population growth rate assessment coefficient, the population recovery rate assessment coefficient, and the incubation period assessment coefficient.

[0022] Preferably, the population impact index calculation module calculates the population impact index of a public health event based on the diffusion index, including:

[0023] S1. Determine the area of ​​spread of the public health event;

[0024] S2. Calculate the total number of permanent residents in the diffusion area at the current monitoring time point, and obtain the area of ​​the diffusion area. At the same time, calculate the population density assessment coefficient of the diffusion area based on the preset population density of the diffusion area.

[0025] S3. Based on the nature of the public health event, the reference personnel impact rate of each type of public health event pre-stored in the data cloud platform is matched to obtain the reference personnel impact rate of the public health event, and then the personnel impact assessment coefficient of the diffusion area is calculated.

[0026] S4. Calculate the population impact index of public health events based on the population density assessment coefficient and population impact assessment coefficient of the diffusion area.

[0027] Preferably, determining the area of ​​spread of the public health event in S1 includes:

[0028] S11. Obtain a map of the area to which the public health event belongs and determine the initial location of the public health event;

[0029] S12. Geographically locate the initial location of the public health event on the regional map of the area to which the event occurred;

[0030] S13. Match the diffusion index of the public health event with the diffusion area reference division diameter corresponding to each diffusion index interval pre-stored in the data cloud platform to determine the diffusion area reference division diameter corresponding to the diffusion index of the public health event.

[0031] S14. Using the initial location of the public health event as the center of the diffusion area, and combining the diffusion area reference division diameter, delineate and divide the diffusion area of ​​the public health event on the map of the region, and mark and store the diffusion area.

[0032] Preferably, the emergency plan matching module matches the corresponding emergency plan based on a comprehensive evaluation coefficient, including:

[0033] The comprehensive evaluation coefficient of public health events is matched with the relief level of public health events of various types under each comprehensive evaluation coefficient range, which are pre-stored in the data cloud platform, to obtain the relief level of public health events.

[0034] The emergency response level for public health emergencies is matched with the pre-set emergency response plans for each level to construct the corresponding emergency response plan for public health emergencies and provide real-time data feedback and prompts.

[0035] (III) Beneficial Effects

[0036] Compared with the prior art, the public health data statistics and analysis system provided by the present invention has the following beneficial effects:

[0037] 1) Construct a feature-based intelligent analysis system to improve the accuracy of public health risk identification.

[0038] By collecting regional characteristic data such as urban infrastructure, population size, age distribution, transportation, and population flow from multiple dimensions, and relying on encoders and decoders to complete feature vector representation and reconstruction processing, and combining common feature extractors to mine the common features associated with sample cities and target cities, a binary classification model is constructed to reduce the differences in the distribution of common features between cities. Combined with pre-set public health event risk labeling rules, the public health risk level classification of target cities is completed. This breaks through the limitations of traditional manual single-dimensional assessment, realizes intelligent and refined assessment of urban public health risks, avoids errors caused by subjective experience judgments, and significantly improves the accuracy and foresight of potential public health event risk identification.

[0039] 2) Accurately delineate the scope of the event's spread and enhance the effectiveness of public health emergency prevention and control.

[0040] The spread index of public health events is quantified by multiple coefficients such as population growth rate, recovery rate, and incubation period. A population impact index assessment system is constructed by combining parameters such as regional resident population, land area, residential density, and population impact rate. At the same time, the spread area of ​​the event is accurately delineated and marked with the event location as the center by combining the initial location of the event, regional map positioning, and the spread index interval matching reference diameter pre-stored in the cloud platform. This changes the traditional extensive model of delineating the scope of prevention and control, realizes the scientific and visual division of the spread boundary of public health events, provides accurate data support for layered prevention and control, personnel management, and regional lockdown, and effectively improves the ability to prevent and control the spread of public health events at the source.

[0041] 3) Quantitatively evaluate and match contingency plans to optimize emergency resource allocation and response support.

[0042] By combining the diffusion index, population impact index, and urban medical and material resource reserve index, a comprehensive evaluation coefficient for public health emergencies is calculated. The system then uses a data cloud platform to match the level of assistance, automatically adapt to standardized emergency plans, and provide real-time data feedback. This approach eliminates the drawbacks of traditional emergency plans that rely on human experience and blindly allocate resources. Instead, it intelligently matches emergency strategies based on the severity of the event, the scope of population impact, and the city's resource endowment. This allows for precise allocation of emergency resources such as medical supplies and healthcare personnel, avoiding resource redundancy or insufficient reserves, and significantly improving the speed of emergency response, the standardization of handling, and the overall protection capacity of public health emergencies. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0044] Figure 1 This is a schematic diagram of the system of the present invention;

[0045] Figure 2 This is a schematic diagram of the process for calculating the population impact index of public health events in this invention. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0047] The following describes the specific functional modules of the public health data statistics and analysis system provided by this invention, using concrete examples (such as...). Figure 1 (As shown) and its technical effects. The system functional modules include: a control unit, which collects regional feature data of sample cities and target cities through a data collection module, and outputs corresponding representation vectors based on the regional feature data using an encoder; the control unit decodes the representation vectors of sample cities and target cities respectively through a decoder, and extracts common feature data of the regional feature data of sample cities and target cities using a common feature extractor; and the control unit classifies and determines the target city based on the common feature data using a classifier.

[0048] I. Data Collection Module

[0049] The data collection module collects regional characteristic data from sample cities and target cities, including:

[0050] Collect regional characteristic data, including surrounding infrastructure, regional population size, regional population age distribution, regional transportation, and regional population flow, for sample cities and target cities.

[0051] II. Encoder

[0052] The encoder outputs a corresponding representation vector based on the region feature data, including:

[0053] The regional feature data of the sample city and the target city are input into the encoder, and the encoder outputs the representation vectors of the sample city and the target city respectively after encoding.

[0054] III. Decoder

[0055] The decoder decodes the representation vectors of the sample city and the target city respectively, including:

[0056] The representation vector of the sample city is decoded using the sample city decoder, and the representation vector of the target city is decoded using the target city decoder.

[0057] IV. Classifier

[0058] The classifier classifies and determines the target city based on common feature data, including:

[0059] The classifier takes the common features of the regional feature data of the sample city and the target city as input, and combines them with the preset public health event risk labeling rules to classify and determine the public health risk level of the target city.

[0060] Specifically, the classifier constructs a binary classification model, using the common feature data of the regional feature data of the sample city and the target city as input, reducing the difference in the distribution offset of common features between the sample city and the target city, and outputting the public health event risk category determination result of the target city.

[0061] The aforementioned technical solution collects regional characteristic data such as urban infrastructure, population size, age distribution, transportation, and population flow from multiple dimensions. It relies on encoders and decoders to complete feature vector representation and reconstruction processing, and combines a common feature extractor to mine the common features associated with sample cities and target cities. At the same time, it reduces the difference in the distribution of common features between cities by constructing a binary classification model, and combines it with preset public health event risk labeling rules to complete the classification and determination of the public health risk level of the target city. This breaks through the limitations of traditional manual single-dimensional assessment, realizes intelligent and refined assessment of urban public health risks, avoids errors caused by subjective experience judgments, and significantly improves the accuracy and foresight of potential public health event risk identification.

[0062] When the target city and the sample city are both located in the public health emergency outbreak area, the control unit obtains basic characteristic data of the public health emergency through the data acquisition module, and calculates the diffusion index of the public health emergency based on the basic characteristic data using the diffusion index calculation module. The control unit calculates the population impact index of the public health emergency based on the diffusion index using the population impact index calculation module, and calculates the medical resource reserve index and material resource reserve index of the target city using the resource reserve index calculation module. The control unit calculates the comprehensive evaluation coefficient of the public health emergency through the comprehensive evaluation coefficient calculation module, and matches the corresponding emergency plan based on the comprehensive evaluation coefficient using the emergency plan matching module.

[0063] V. Diffusion Index Calculation Module

[0064] The diffusion index calculation module calculates the diffusion index of a public health event based on basic characteristic data, including:

[0065] The spread index of a public health event is calculated based on the population growth rate assessment coefficient, the population recovery rate assessment coefficient, and the incubation period assessment coefficient.

[0066] VI. Population Impact Index Calculation Module

[0067] The population impact index calculation module calculates the population impact index of public health events based on the diffusion index, such as... Figure 2 As shown, it includes:

[0068] S1. Determine the area of ​​spread of the public health event;

[0069] S2. Calculate the total number of permanent residents in the diffusion area at the current monitoring time point, and obtain the area of ​​the diffusion area. At the same time, calculate the population density assessment coefficient of the diffusion area based on the preset population density of the diffusion area.

[0070] S3. Based on the nature of the public health event, the reference personnel impact rate of each type of public health event pre-stored in the data cloud platform is matched to obtain the reference personnel impact rate of the public health event, and then the personnel impact assessment coefficient of the diffusion area is calculated.

[0071] S4. Calculate the population impact index of public health events based on the population density assessment coefficient and population impact assessment coefficient of the diffusion area.

[0072] Specifically, S1 identifies the areas of spread of public health events, such as... Figure 2 As shown, it includes:

[0073] S11. Obtain a map of the area to which the public health event belongs and determine the initial location of the public health event;

[0074] S12. Geographically locate the initial location of the public health event on the regional map of the area to which the event occurred;

[0075] S13. Match the diffusion index of the public health event with the diffusion area reference division diameter corresponding to each diffusion index interval pre-stored in the data cloud platform to determine the diffusion area reference division diameter corresponding to the diffusion index of the public health event.

[0076] S14. Using the initial location of the public health event as the center of the diffusion area, and combining the diffusion area reference division diameter, delineate and divide the diffusion area of ​​the public health event on the map of the region, and mark and store the diffusion area.

[0077] The aforementioned technical solution quantifies the spread index of public health events based on multiple coefficients such as population growth rate, recovery rate, and incubation period. It constructs a population impact index assessment system by combining parameters such as regional resident population, land area, residential density, and population impact rate. Simultaneously, it uses the initial location of the event, regional map positioning, and pre-stored spread index intervals in the cloud platform as a reference to define the diameter, accurately delineating and marking the event spread area with the event location as the center. This changes the traditional extensive model of delineating the scope of prevention and control, realizing the scientific and visual division of the boundaries of public health event spread. It provides precise data support for layered prevention and control, personnel management, and regional lockdown, effectively improving the ability to prevent and control the spread of public health events at their source.

[0078] VII. Emergency Response Plan Matching Module

[0079] The emergency response plan matching module matches corresponding emergency response plans based on a comprehensive evaluation coefficient, including:

[0080] The comprehensive evaluation coefficient of public health events is matched with the relief level of public health events of various types under each comprehensive evaluation coefficient range, which are pre-stored in the data cloud platform, to obtain the relief level of public health events.

[0081] The emergency response level for public health emergencies is matched with the pre-set emergency response plans for each level to construct the corresponding emergency response plan for public health emergencies and provide real-time data feedback and prompts.

[0082] The aforementioned technical solution calculates a comprehensive evaluation coefficient for public health emergencies by integrating diffusion index, population impact index, and urban medical and material resource reserve indexes. It then uses a data cloud platform to match the level of assistance, automatically adapts to standardized emergency plans, and provides real-time data feedback. This approach eliminates the drawbacks of traditional emergency plans that rely on human experience and blindly allocate resources. Instead, it intelligently matches emergency strategies based on the severity of the event, the scope of population impact, and the city's resource endowment, accurately allocating emergency resources such as medical supplies and medical personnel. This avoids resource redundancy and waste or insufficient reserves, significantly improving the speed of emergency response, the standardization of handling, and the overall protection capacity of public health emergencies.

[0083] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A public health data statistics and analysis system, characterized in that: The system includes a control unit, which collects regional feature data of sample cities and target cities through a data collection module, and outputs corresponding representation vectors based on the regional feature data using an encoder. The control unit decodes the representation vectors of sample cities and target cities respectively through a decoder, and extracts common feature data of the regional feature data of sample cities and target cities using a common feature extractor. The control unit classifies and determines the target city based on the common feature data using a classifier. When the target city and the sample city are both located in the public health emergency outbreak area, the control unit obtains basic characteristic data of the public health emergency through the data acquisition module, and calculates the diffusion index of the public health emergency based on the basic characteristic data using the diffusion index calculation module. The control unit calculates the population impact index of the public health emergency based on the diffusion index using the population impact index calculation module, and calculates the medical resource reserve index and material resource reserve index of the target city using the resource reserve index calculation module. The control unit calculates the comprehensive evaluation coefficient of the public health emergency through the comprehensive evaluation coefficient calculation module, and matches the corresponding emergency plan based on the comprehensive evaluation coefficient using the emergency plan matching module.

2. The public health data statistics and analysis system according to claim 1, characterized in that: The data collection module collects regional characteristic data of the sample city and the target city, including: Collect regional characteristic data, including surrounding infrastructure, regional population size, regional population age distribution, regional transportation, and regional population flow, for sample cities and target cities.

3. The public health data statistics and analysis system according to claim 2, characterized in that: The encoder outputs a corresponding representation vector based on the region feature data, including: The regional feature data of the sample city and the target city are input into the encoder, and the encoder outputs the representation vectors of the sample city and the target city respectively after encoding.

4. The public health data statistics and analysis system according to claim 3, characterized in that: The decoder decodes the representation vectors of the sample city and the target city respectively, including: The representation vector of the sample city is decoded using the sample city decoder, and the representation vector of the target city is decoded using the target city decoder.

5. The public health data statistics and analysis system according to claim 4, characterized in that: The classifier classifies the target city based on common feature data, including: The classifier takes the common features of the regional feature data of the sample city and the target city as input, and combines them with the preset public health event risk labeling rules to classify and determine the public health risk level of the target city.

6. The public health data statistics and analysis system according to claim 5, characterized in that: The classifier constructs a binary classification model, using the common feature data of regional feature data of sample cities and target cities as input, reducing the difference in the distribution offset of common features between sample cities and target cities, and outputting the public health event risk category determination result of the target city.

7. The public health data statistics and analysis system according to claim 1, characterized in that: The diffusion index calculation module calculates the diffusion index of a public health event based on basic characteristic data, including: The spread index of a public health event is calculated based on the population growth rate assessment coefficient, the population recovery rate assessment coefficient, and the incubation period assessment coefficient.

8. The public health data statistics and analysis system according to claim 7, characterized in that: The population impact index calculation module calculates the population impact index of public health events based on the diffusion index, including: S1. Determine the area of ​​spread of the public health event; S2. Calculate the total number of permanent residents in the diffusion area at the current monitoring time point, and obtain the area of ​​the diffusion area. At the same time, calculate the population density assessment coefficient of the diffusion area based on the preset population density of the diffusion area. S3. Based on the nature of the public health event, the reference personnel impact rate of each type of public health event pre-stored in the data cloud platform is matched to obtain the reference personnel impact rate of the public health event, and then the personnel impact assessment coefficient of the diffusion area is calculated. S4. Calculate the population impact index of public health events based on the population density assessment coefficient and population impact assessment coefficient of the diffusion area.

9. The public health data statistics and analysis system according to claim 8, characterized in that: S1 identifies the areas of spread of the public health event, including: S11. Obtain a map of the area to which the public health event belongs and determine the initial location of the public health event; S12. Geographically locate the initial location of the public health event on the regional map of the area to which the event occurred; S13. Match the diffusion index of the public health event with the diffusion area reference division diameter corresponding to each diffusion index interval pre-stored in the data cloud platform to determine the diffusion area reference division diameter corresponding to the diffusion index of the public health event. S14. Using the initial location of the public health event as the center of the diffusion area, and combining the diffusion area reference division diameter, delineate and divide the diffusion area of ​​the public health event on the map of the region, and mark and store the diffusion area.

10. The public health data statistics and analysis system according to claim 8, characterized in that: The emergency response plan matching module matches corresponding emergency response plans based on a comprehensive evaluation coefficient, including: The comprehensive evaluation coefficient of public health events is matched with the relief level of public health events of various types under each comprehensive evaluation coefficient range, which are pre-stored in the data cloud platform, to obtain the relief level of public health events. The emergency response level for public health emergencies is matched with the pre-set emergency response plans for each level to construct the corresponding emergency response plan for public health emergencies and provide real-time data feedback and prompts.

Images