Big data health medical management system

Abstract

The invention is suitable for the technical field of big data health management, and particularly relates to a big data health medical management system, which comprises a monitoring point location determination module used for determining a monitoring point location corresponding to a recorded public camera in a regional map, and determining a correction coefficient of the monitoring point location based on a boundary line and a regional mark; the video acquisition and identification module is used for receiving the video acquired by the public camera, identifying the video and calculating to obtain the exercise amount in a preset time period; the health degree calculation module is used for calculating the total exercise amount of each sub-region according to the correction coefficient and the exercise amount, and calculating the health degree of the sub-region according to the total exercise amount and the number of people in the sub-region; the system almost does not involve manpower cost, construction workers do not need to invest too much energy, the data acquisition process is enriched completely on the basis of existing facilities, and the convenience is extremely high.

Description

Technical Field

[0001] The present invention relates to the field of big data health management technology, and in particular to a big data health care management system. Background Art

[0002] As people's material living standards gradually improve, there have been great improvements in all aspects of food, clothing, housing and transportation. While this has improved people's sense of happiness, it has also brought some small troubles. Some groups lack exercise and are in a sub-healthy state. In order to solve this problem, it is necessary to provide some health management measures based on the health status of residents. For example, building outdoor sports venues such as parks or medical service venues such as hospitals; the existing construction plans are all completed manually, including the early data collection process. The more complete the data collection, the better the construction plan obtained. Therefore, how to assist construction personnel in the early data collection work to obtain a better construction plan is the technical problem that the technical solution of the present invention wants to solve. Summary of the Invention

[0003] The purpose of the present invention is to provide a big data health care management system to solve the problems raised in the above background technology.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A big data health care management system, comprising:

[0006] A regional map creation module is used to obtain regional information based on preset permissions and create a regional map containing virtual boundaries based on the regional information; the virtual boundaries are used to divide the regional map into sub-regions;

[0007] A monitoring point determination module is used to determine the monitoring points corresponding to the registered public cameras in the regional map and determine the correction coefficients of the monitoring points based on the boundary lines and regional markers;

[0008] The video acquisition and recognition module is used to receive videos collected by public cameras, identify the videos, and calculate the amount of exercise within a preset time period;

[0009] a health calculation module, configured to calculate the total amount of exercise in each sub-area based on the correction coefficient and the amount of exercise, and calculate the health of the sub-area based on the total amount of exercise and the number of people in the sub-area;

[0010] The reference plan determination module is used to determine a reference plan for health facilities according to the healthiness of the sub-area and send the plan to the planning end; the reference plan contains the locations of different types of health facilities.

[0011] Furthermore, the regional map creation module includes:

[0012] A reference map construction unit, configured to read the boundaries of an area and construct a reference map based on the boundaries;

[0013] A region segmentation unit is used to query the land use planning information of the region and segment the reference map according to the land use planning information to obtain sub-regions;

[0014] A tag query unit is used to query the regional tags of each sub-region and establish a regional map; the regional tags include commercial and service land, comprehensive land, industrial land, residential land and green land;

[0015] A regional map updating unit, configured to periodically generate acquisition instructions, randomly acquire a preset number of overhead images containing coordinates, and update the regional map based on the overhead images;

[0016] Among them, the main sources of aerial view images include drones and remote sensing satellites.

[0017] Furthermore, the monitoring point determination module includes:

[0018] A location query unit, used to query the installation location of public cameras in the record library based on the pre-acquired permissions;

[0019] Point query unit, used to query the monitoring points corresponding to the installation location in the regional map according to the same scale;

[0020] An influence value calculation unit is used to traverse all monitoring points, calculate the distance between the monitoring point and each sub-area, and query the influence value corresponding to the area mark of each sub-area;

[0021] The influence value statistical unit is used to calculate the influence value based on the distance and determine the correction coefficient of each monitoring point.

[0022] Furthermore, the video acquisition and recognition module includes:

[0023] A video recognition unit is used to receive videos collected by public cameras, identify the videos, and determine the dynamic contours, movement speed, and movement distance;

[0024] a first calculation unit, configured to determine an outline identity based on the dynamic outline and its motion speed, and query a unit motion amount based on the outline identity;

[0025] A second calculation unit is used to calculate the video motion amount with the time span of the video as a label according to the unit motion amount and the motion distance;

[0026] The motion amount statistics unit is used to receive the time period input by the management party, and to count the video motion amount corresponding to the public camera based on the time period to obtain the motion amount within the time period.

[0027] Furthermore, the health calculation module includes:

[0028] A first query unit is configured to query the amount of motion within the time period corresponding to each public camera;

[0029] The second query unit is used to query the correction coefficient of the monitoring point corresponding to each public camera;

[0030] An accumulation unit, used for accumulating the movement amount according to the correction coefficient to obtain the total movement amount;

[0031] The third calculation unit is used to query the number of people in the sub-area and calculate the health level of the sub-area according to the total amount of exercise and the number of people in the sub-area.

[0032] Furthermore, the reference solution determination module includes:

[0033] The third query unit is used to query the facility type and the number of health facilities;

[0034] an alternative plot determination unit, for determining an alternative plot for each facility type in a regional map;

[0035] An alternative plot selection unit is used to select the number of alternative plots for each facility type from among the alternative plots;

[0036] The solution generation unit is used to collect statistics on the selection results of all facility types and obtain a reference solution;

[0037] A scheme evaluation unit is used to evaluate the reference scheme based on the sub-area health and determine the final scheme;

[0038] The solution sending unit is used to send the final solution to the planning end.

[0039] Furthermore, the process of evaluating the reference solution based on the sub-area health and determining the final solution includes:

[0040] Traverse each plot in the reference plan, query the facility type of the plot, and query the service key health corresponding to the facility type;

[0041] Query the sub-area health within a preset range centered on the plot;

[0042] Obtain the mean of the sub-area health, calculate the difference between the service health and the mean, and determine the assessment score of each plot based on the inverse ratio of the absolute value of the difference;

[0043] The assessment scores of all plots are accumulated, and the reference plan with the largest assessment score is selected as the final plan.

[0044] Furthermore, the process of selecting candidate plots for each facility type from candidate plots for each facility type includes:

[0045] Query the traffic convenience of each candidate plot; the traffic convenience is determined by road condition information and site information, and is a value predetermined during the plot planning process;

[0046] Query the distance between each candidate plot and all selected candidate plots, and select the minimum distance;

[0047] Determining the selection utility value of each candidate plot based on the traffic convenience and the minimum distance;

[0048] The number of candidate plots with facilities is selected in descending order of the selected utility values.

[0049] Furthermore, the system's work content also includes:

[0050] Based on pre-acquired permissions, query and count the number of sports entries within a preset time period in real time in the social app;

[0051] Constructing a training set and a test set based on the number of sports terms and the sub-area health, training a neural network model based on the training set, and calculating the accuracy of the neural network model based on the test set;

[0052] Regularly updating the test set based on the number of newly acquired sports terms and sub-area health, and extracting data from the test set into the training set; wherein the test set is a queue structure, and its data storage capacity is a preset value;

[0053] When the accuracy reaches a preset accuracy threshold, the sub-area healthiness is calculated based on the trained neural network model and the number of collected motion terms.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] The present invention obtains the amount of motion based on the cameras in the area, and then adjusts the amount of motion based on the position of the cameras. For each sub-area, the adjusted amount of motion of all the cameras therein is obtained, and the health level of each sub-area is determined. This is used as reference data for the construction plan, with almost no labor cost involved. Construction workers do not need to invest too much energy, and it is completely based on existing facilities, enriching the data collection process and being extremely convenient. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention.

[0057] Figure 1This is a structural block diagram of the big data health care management system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0058] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below with reference to 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.

[0059] Figure 1 The following is a block diagram of the composition of a big data health and medical management system. In an embodiment of the present invention, a big data health and medical management system is provided. The system 10 includes:

[0060] The regional map creation module 11 is used to obtain regional information based on preset permissions and create a regional map containing virtual boundaries based on the regional information; the virtual boundaries are used to divide the regional map into sub-regions;

[0061] The technical solution of the present invention is used to manage an area. There are different plots of land in the area. The types and scopes of different plots of land are different, collectively referred to as regional information. The regional information is obtained according to preset permissions, and the regional information is analyzed and converted into a map form to obtain a map containing virtual boundaries, called a regional map; the virtual boundaries are the outlines of each plot of land, which are used to divide the regional map into sub-areas; specifically, the types of plots include commercial and service land, comprehensive land, residential land, industrial land and other land.

[0062] A monitoring point determination module 12 is used to determine the monitoring points corresponding to the registered public cameras in the regional map, and determine the correction coefficients of the monitoring points based on the boundary lines and regional markers;

[0063] There will be multiple public cameras set up in the area, most of which are usually on the roads. If the authority is sufficient, the internal monitoring information of many public areas can be obtained. It should be noted that the monitoring images obtained must be public images, otherwise the subsequent process cannot be carried out.

[0064] In the established regional map, the points corresponding to public cameras are queried, which are called monitoring points. Based on the location of the monitoring points, the influence of each sub-region on the monitoring points can be calculated. In addition, the influence of each sub-region mark has different magnitudes. By calculating the influence of each sub-region on each monitoring point, the correction coefficient of each monitoring point can be obtained.

[0065] Furthermore, regarding the physical meaning of the above-mentioned correction coefficient, the purpose of the technical solution of the present invention is to calculate the amount of exercise in the entire area based on the amount of exercise near each monitoring point. This is a summation process; if the monitoring point is close to industrial land, then the ratio of its amount of exercise to health level will be very low (it may even be a negative value). Accordingly, the amount of exercise calculated by the monitoring point needs to be multiplied by a smaller coefficient in the summation process of the health level. This coefficient is the above-mentioned correction coefficient.

[0066] From the above content, it can be seen that the correction coefficient is related to the surrounding area. The process of regional influence correction coefficient is based on two parameters, one is distance and the other is regional mark. Different regional marks have different impacts on the monitoring points. According to the ratio of the impact amplitude to the distance or the value determined by the distance, the correction coefficient inversely proportional to the distance can be determined.

[0067] The video acquisition and recognition module 13 is used to receive videos collected by public cameras, recognize the videos, and calculate the amount of exercise within a preset time period;

[0068] Establish a connection channel with a public camera, receive the video captured by the public camera, use the existing recognition algorithm to locate the moving subject in the video, determine the identity of the moving subject, which includes pedestrians and cyclists, obtain the moving distance of the moving subject, and then calculate the amount of exercise; the amount of exercise involved in this application is pedestrians and cyclists, and the exercise methods include walking, running and cycling.

[0069] a health degree calculation module 14, configured to calculate the total amount of exercise in each sub-area based on the correction coefficient and the amount of exercise, and calculate the health degree of the sub-area based on the total amount of exercise and the number of people in the sub-area;

[0070] By analyzing each surveillance video, we can obtain the corresponding amount of exercise in each sub-area. Combined with its corresponding correction coefficient, we can calculate the health level of the residents in the sub-area, which is called the sub-area health level.

[0071] A reference plan determining module 15 is configured to determine a reference plan for health facilities based on the health level of the sub-area and send the plan to the planning terminal; the reference plan includes locations of different types of health facilities;

[0072] After the sub-area health calculation is completed, the health levels of people in different sub-areas in the entire area have been quantified, which can be used as a reference for the installation of health facilities and sent to the planning end; in the above content, based on the feedback of health levels, the present invention will also generate some plans according to requirements to provide richer reference content.

[0073] As a preferred embodiment of the technical solution of the present invention, the working ideas of the technical solution of the present invention include:

[0074] The environmental conditions of each monitoring point are determined according to the status of each area, the athlete is located according to the monitoring video, the exercise process of the athlete is identified, and the amount of exercise is calculated; the amount of exercise is adjusted in combination with the environmental status (in areas with poor environment, the greater the amount of exercise, the slower the rate of health growth, or even a negative value), and the amount of exercise obtained by all monitoring videos in the sub-area is accumulated to obtain the total amount of exercise in the sub-area. The total amount of exercise is adjusted to obtain the health of the sub-area; wherein, the relationship between the total amount of exercise and the health of the sub-area is predetermined by the staff and is a functional relationship.

[0075] As a preferred embodiment of the technical solution of the present invention, the regional map establishment module 11 includes:

[0076] A reference map construction unit, configured to read the boundaries of an area and construct a reference map based on the boundaries;

[0077] A region segmentation unit is used to query the land use planning information of the region and segment the reference map according to the land use planning information to obtain sub-regions;

[0078] A tag query unit is used to query the regional tags of each sub-region and establish a regional map; the regional tags include commercial and service land, comprehensive land, industrial land, residential land and green land;

[0079] A regional map updating unit, configured to periodically generate acquisition instructions, randomly acquire a preset number of overhead images containing coordinates, and update the regional map based on the overhead images;

[0080] Among them, the main sources of aerial view images include drones and remote sensing satellites.

[0081] The above content limits the construction process of the regional map. First, the regional boundary is read, and a range can be determined at a preset scale, which is called a baseline map; then, the land use planning information of the area is queried (with the help of a map or map service, which has default permissions), and the baseline map is divided into regions to obtain multiple sub-regions, and the regional mark of each sub-region can be determined. The regional mark is used to characterize the purpose of each sub-region, and the regional map can be obtained; further, the present invention also opens a sub-region map update interface, so that staff can adjust the generated sub-region map.

[0082] As a preferred embodiment of the technical solution of the present invention, the monitoring point determination module 12 includes:

[0083] A location query unit, used to query the installation location of public cameras in the record library based on the pre-acquired permissions;

[0084] Point query unit, used to query the monitoring points corresponding to the installation location in the regional map according to the same scale;

[0085] An influence value calculation unit is used to traverse all monitoring points, calculate the distance between the monitoring point and each sub-area, and query the influence value corresponding to the area mark of each sub-area;

[0086] The influence value statistical unit is used to calculate the influence value based on the distance and determine the correction coefficient of each monitoring point.

[0087] The core process of the correction coefficient calculation process is to superimpose the influence of each sub-area on it. The influence value of each sub-area is fixed. The farther the distance, the smaller the influence on the monitoring point. By superimposing the influence values ​​of all areas according to the distance, the total influence value of each monitoring point can be obtained; the total influence value of each monitoring point is summed up, and then the ratio of each total influence value is calculated to obtain the correction coefficient of each monitoring point.

[0088] Specifically, the mathematical form of the correction coefficient calculation process is as follows:

[0089] The calculation process of the correction coefficient is:

[0090] Where, α i is the correction coefficient of the i-th monitoring point, B i is the comprehensive impact value of the i-th monitoring point, N is the total number of monitoring points, Y j is the impact value corresponding to the j-th sub-region, dis(q j ,w i ) is the distance between the center point of the jth sub-area and the i-th monitoring point, q j is the center point of the jth sub-region, w i is the i-th monitoring point, M is the total number of sub-areas

[0091] As a preferred embodiment of the technical solution of the present invention, the video acquisition and recognition module 13 includes:

[0092] A video recognition unit is used to receive videos collected by public cameras, identify the videos, and determine the dynamic contours, movement speed, and movement distance;

[0093] a first calculation unit, configured to determine an outline identity based on the dynamic outline and its motion speed, and query a unit motion amount based on the outline identity;

[0094] A second calculation unit is used to calculate the video motion amount with the time span of the video as a label according to the unit motion amount and the motion distance;

[0095] The motion amount statistics unit is used to receive the time period input by the management party, and to count the video motion amount corresponding to the public camera based on the time period to obtain the motion amount within the time period.

[0096] By establishing a connection channel with a public camera, receiving the video captured by the public camera, and identifying the video, the position of the dynamic contour can be located. By analyzing the position, the movement speed and movement distance can be calculated. By identifying the dynamic contour, the identity of the contour can be determined, that is, whether the contour is a pedestrian or a cyclist. Simultaneously, the identity of the contour can also be determined based on the movement speed. The speed of a pedestrian and the speed of a cyclist are different. The identity determination process based on the dynamic contour and the identity determination process based on the movement speed are performed independently, and the results are compared with each other to ensure the accuracy of the contour identity.

[0097] According to the contour identity, query the motion amount corresponding to the unit distance, read the motion distance corresponding to each dynamic contour, multiply the motion distance by the motion amount corresponding to the unit distance, and you can get the motion amount corresponding to each video; it should be noted that a video is a collection of images within a time period, which contains time period information, and the motion amount is the motion amount of that time period.

[0098] The staff inputs a time period, such as a day, and merges or intercepts the movement volume of each time period based on the time period to obtain the movement volume of each public camera within the time period.

[0099] As a preferred embodiment of the technical solution of the present invention, the health calculation module 14 includes:

[0100] A first query unit is configured to query the amount of motion within the time period corresponding to each public camera;

[0101] The second query unit is used to query the correction coefficient of the monitoring point corresponding to each public camera;

[0102] An accumulation unit, used for accumulating the movement amount according to the correction coefficient to obtain the total movement amount;

[0103] The third calculation unit is used to query the number of people in the sub-area and calculate the health level of the sub-area according to the total amount of exercise and the number of people in the sub-area.

[0104] The amount of motion within the time period corresponding to each public camera is queried, and the correction coefficient of the monitoring point corresponding to each public camera is queried. The correction coefficient is multiplied by the motion amount and accumulated to obtain the total amount of motion corresponding to each public camera. On this basis, for any sub-area, the monitoring points within the sub-area are queried, and the motion amount of each monitoring point is queried to calculate the total amount of motion of the sub-area. Combined with the number of people in the sub-area, the health of the sub-area can be calculated. The calculation process of the sub-area health can be as follows:

[0105] K is the health of the sub-area, β is the preset adjustment constant, S i is the amount of movement corresponding to the i-th monitoring point, and R is the number of people in the sub-area.

[0106] The above content is to calculate the ratio of the total amount of exercise to the number of registered people in the sub-area. It should be noted that since the unit of the total amount of exercise and the unit of the number of people are different, when calculating the ratio, the result has a unit. For this, a unit for balance is introduced in β (the inverse of the unit of the result), so that the health of the sub-area becomes a dimensionless data.

[0107] It should be noted that the technical solution of the present invention is actually to analyze the entire area first and determine the correction coefficients of different monitoring points. The correction coefficient is proportional to the impact value and represents the comprehensive impact. It is also related to the regional mark of each sub-area. The healthier the regional mark, the greater its impact value. For example, the impact value of green land is greater than that of industrial land. Therefore, the correction coefficient of the monitoring point in the area closer to the green land is greater.

[0108] Furthermore, the correction coefficient actually reflects a kind of effectiveness. For example, the amount of exercise monitored by a certain monitoring point is very large, but it is close to industrial land, and the corresponding correction coefficient is very small. The technical solution of the present invention believes that the effectiveness of these exercise amounts in improving health is very small. Accordingly, the total exercise amount calculated based on the correction coefficient and exercise amount will be smaller. Finally, the total exercise amount of all monitoring points in each sub-area is accumulated to calculate the health of the sub-area.

[0109] As a preferred embodiment of the technical solution of the present invention, the reference solution determination module 15 includes:

[0110] The third query unit is used to query the facility type and the number of health facilities;

[0111] an alternative plot determination unit, for determining an alternative plot for each facility type in a regional map;

[0112] An alternative plot selection unit is used to select the number of alternative plots for each facility type from among the alternative plots;

[0113] The solution generation unit is used to collect statistics on the selection results of all facility types and obtain a reference solution;

[0114] A scheme evaluation unit is used to evaluate the reference scheme based on the sub-area health and determine the final scheme;

[0115] The solution sending unit is used to send the final solution to the planning end.

[0116] In an example of the technical solution of the present invention, a specific reference solution generation process is provided to query the facility types and facility quantities of health facilities. The facility types of health facilities include hospitals of different levels, service units, and fitness facilities, etc., which are specifically determined by staff based on the budget, and the facility quantity of each facility type is also preset.

[0117] In the process of selecting the reference plan, the alternative plots for each facility type are determined in the regional map. The plots on which each facility type can be installed are determined by the regional marks of the plots. The number of alternative plots for each facility type is selected. The selection results of all facility types are counted to obtain a reference plan. The reference plan is evaluated based on the health of the sub-areas of the sub-areas, and the final plan is determined and sent to the planning end. This process is actually a process of selecting and then optimizing, which can quickly obtain a better plan.

[0118] Furthermore, the process of evaluating the reference solution based on the sub-area health and determining the final solution includes:

[0119] Traverse each plot in the reference plan, query the facility type of the plot, and query the service key health corresponding to the facility type;

[0120] Query the sub-area health within a preset range centered on the plot;

[0121] Obtain the mean of the sub-area health, calculate the difference between the service health and the mean, and determine the assessment score of each plot based on the inverse ratio of the absolute value of the difference;

[0122] The assessment scores of all plots are accumulated, and the reference plan with the largest assessment score is selected as the final plan.

[0123] For the evaluation process, traverse each plot in the reference plan, query the facility type of the plot, and query the service key health corresponding to the facility type. The relationship between the facility type and the service health is a preset value, which indicates how much health it can provide. Different facility types have different service capabilities and service health. Query the sub-area health of the sub-area within the preset range centered on the plot, calculate the mean, and the preset range corresponds to the facility type. Calculate the difference between the service health and the mean. The smaller the absolute value of the difference, the more suitable the facility installation is, and it can provide services without wasting service resources. Correspondingly, the higher the evaluation score. There are multiple plots in a reference plan with facilities installed, corresponding to multiple evaluation scores. Accumulate the evaluation scores of all plots, and select the reference plan with the largest evaluation score as the final plan.

[0124] As a preferred embodiment of the technical solution of the present invention, the process of selecting candidate plots for each facility type as many as the number of facilities from the candidate plots includes:

[0125] Query the traffic convenience of each candidate plot; the traffic convenience is determined by road condition information and site information, and is a value predetermined during the plot planning process;

[0126] Query the distance between each candidate plot and all selected candidate plots, and select the minimum distance;

[0127] Determining the selection utility value of each candidate plot based on the traffic convenience and the minimum distance;

[0128] The number of candidate plots with facilities is selected in descending order of the selected utility values.

[0129] In the process of selecting alternative plots, traffic convenience is also taken into consideration. The traffic convenience of each alternative plot is queried. The traffic convenience is a value predetermined in the plot planning process. The distance between each alternative plot and all selected alternative plots is queried, and the minimum distance is selected. The selection utility value of each alternative plot is determined based on the traffic convenience and the minimum distance. The selection utility value is directly proportional to the traffic convenience and inversely proportional to the minimum distance. Then, the number of alternative plots with facilities is selected in descending order based on the selection utility value. This can make the alternative plots with more convenient traffic and farther distance from the selected alternative plots more likely to be selected.

[0130] As a preferred embodiment of the technical solution of the present invention, the working content of the system 10 also includes:

[0131] Based on pre-acquired permissions, query and count the number of sports entries within a preset time period in real time in the social app;

[0132] Constructing a training set and a test set based on the number of sports terms and the sub-area health, training a neural network model based on the training set, and calculating the accuracy of the neural network model based on the test set;

[0133] Regularly updating the test set based on the number of newly acquired sports terms and sub-area health, and extracting data from the test set into the training set; wherein the test set is a queue structure, and its data storage capacity is a preset value;

[0134] When the accuracy reaches a preset accuracy threshold, the sub-area healthiness is calculated based on the trained neural network model and the number of collected motion terms.

[0135] In the technical solution of the present invention, a quick calculation scheme for sub-area health is also provided to reduce the execution frequency of steps S100 to S400. The principle is that, based on the calculated sub-area health, the number of sports-related entries is queried in the social app. These data are statistical data and require certain permissions to obtain. If the permissions are low, the search box of the social app is used to retrieve the number of entries related to the preset keywords as the number of sports entries. This method can be completed after registering an account.

[0136] By training the neural network model based on the acquired number of motion terms and the calculated sub-area health, a mapping relationship between the number of motion terms and the sub-area health can be obtained; when the accuracy of the neural network model becomes higher and higher, the execution frequency of steps S100 to S400 can be gradually reduced, and finally a complementary effect is achieved, that is, steps S100 to S400 serve as a judgment scheme that takes a longer time but has a higher accuracy, and the neural network model serves as a judgment scheme that takes a shorter time but has a slightly lower accuracy. The accuracy of the latter is continuously calculated by the former, which can ensure the judgment accuracy on the basis of improving the judgment speed.

[0137] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A big data health and medical management system, characterized in that: The system comprises: A regional map creation module is used to obtain regional information based on preset permissions and create a regional map containing virtual boundaries based on the regional information; the virtual boundaries are used to divide the regional map into sub-regions; A monitoring point determination module is used to determine the monitoring points corresponding to the registered public cameras in the regional map and determine the correction coefficients of the monitoring points based on the boundary lines and regional markers; The video acquisition and recognition module is used to receive videos collected by public cameras, identify the videos, and calculate the amount of exercise within a preset time period; a health calculation module, configured to calculate the total amount of exercise in each sub-area based on the correction coefficient and the amount of exercise, and calculate the health of the sub-area based on the total amount of exercise and the number of people in the sub-area; The reference plan determination module is used to determine a reference plan for health facilities according to the healthiness of the sub-area and send the plan to the planning end; the reference plan contains the locations of different types of health facilities.

2. The big data health and medical management system according to claim 1, characterized in that: The regional map building module includes: A reference map construction unit, configured to read the boundaries of an area and construct a reference map based on the boundaries; A region segmentation unit is used to query the land use planning information of the region and segment the reference map according to the land use planning information to obtain sub-regions; A tag query unit is used to query the regional tags of each sub-region and establish a regional map; the regional tags include commercial and service land, comprehensive land, industrial land, residential land and green land; A regional map updating unit, configured to periodically generate acquisition instructions, randomly acquire a preset number of overhead images containing coordinates, and update the regional map based on the overhead images; Among them, the main sources of aerial view images include drones and remote sensing satellites.

3. The big data health and medical management system according to claim 1, characterized in that: The monitoring point determination module includes: A location query unit, used to query the installation location of public cameras in the record library based on the pre-acquired permissions; Point query unit, used to query the monitoring points corresponding to the installation location in the regional map according to the same scale; An influence value calculation unit is used to traverse all monitoring points, calculate the distance between the monitoring point and each sub-area, and query the influence value corresponding to the area mark of each sub-area; The influence value statistical unit is used to calculate the influence value based on the distance and determine the correction coefficient of each monitoring point.

4. The big data health and medical management system according to claim 1, characterized in that: The video acquisition and recognition module includes: A video recognition unit is used to receive videos collected by public cameras, identify the videos, and determine the dynamic contours, movement speed, and movement distance; a first calculation unit, configured to determine an outline identity based on the dynamic outline and its motion speed, and query a unit motion amount based on the outline identity; A second calculation unit is used to calculate the video motion amount with the time span of the video as a label according to the unit motion amount and the motion distance; The motion amount statistics unit is used to receive the time period input by the management party, and to count the video motion amount corresponding to the public camera based on the time period to obtain the motion amount within the time period.

5. The big data health and medical management system according to claim 1, characterized in that: The health calculation module includes: A first query unit is configured to query the amount of motion within the time period corresponding to each public camera; The second query unit is used to query the correction coefficient of the monitoring point corresponding to each public camera; an accumulation unit, for accumulating the movement amount according to the correction coefficient to obtain the total movement amount; The third calculation unit is used to query the number of people in the sub-area and calculate the health level of the sub-area according to the total amount of exercise and the number of people in the sub-area.

6. The big data health and medical management system according to claim 1, characterized in that: The reference solution determination module includes: The third query unit is used to query the facility type and the number of health facilities; an alternative plot determination unit, configured to determine an alternative plot for each facility type in a regional map; An alternative plot selection unit is used to select the number of alternative plots for each facility type from among the alternative plots; The solution generation unit is used to collect statistics on the selection results of all facility types and obtain a reference solution; A scheme evaluation unit is used to evaluate the reference scheme based on the sub-area health and determine the final scheme; The solution sending unit is used to send the final solution to the planning end.

7. The big data health and medical management system according to claim 6, characterized in that: The process of evaluating the reference solution based on the sub-area health and determining the final solution includes: Traverse each plot in the reference plan, query the facility type of the plot, and query the service key health corresponding to the facility type; Query the sub-area health within a preset range centered on the plot; Obtain the mean of the sub-area health, calculate the difference between the service health and the mean, and determine the assessment score of each plot based on the inverse ratio of the absolute value of the difference; The assessment scores of all plots are accumulated, and the reference plan with the largest assessment score is selected as the final plan.

8. The big data health and medical management system according to claim 6, characterized in that: The process of selecting candidate plots for each facility type, the number of candidate plots for each facility type, includes: Query the traffic convenience of each candidate plot; the traffic convenience is determined by road condition information and site information, and is a value predetermined during the plot planning process; Query the distance between each candidate plot and all selected candidate plots, and select the minimum distance; Determining the selection utility value of each candidate plot based on the traffic convenience and the minimum distance; The number of candidate plots with facilities is selected in descending order of the selected utility values.

9. The big data health and medical management system according to claim 1, characterized in that: The system's work also includes: Based on pre-acquired permissions, query and count the number of sports entries within a preset time period in real time in the social app; Constructing a training set and a test set based on the number of sports terms and the sub-area health, training a neural network model based on the training set, and calculating the accuracy of the neural network model based on the test set; Regularly updating the test set based on the number of newly acquired sports terms and sub-area health, and extracting data from the test set into the training set; wherein the test set is a queue structure, and its data storage capacity is a preset value; When the accuracy reaches a preset accuracy threshold, the sub-area healthiness is calculated based on the trained neural network model and the number of collected motion terms.

Images