Detailed description of the preferred embodiments
The invention provides an infectious disease simulation early warning method and system based on big data, and solves the technical problems that the influence of an initial infection position on the actual transmission of an infectious disease is not considered when the infectious disease is predicted and early warned in the prior art, so that the accuracy of infectious disease prediction is not enough, and the reliability of infectious disease early warning and the infectious disease prevention and control effect are finally influenced. By carrying out difference analysis and simulation of different initial infection positions on the types of the infectious diseases to be simulated, the technical goal of providing refined reference data for infectious disease prevention and control is achieved, the infectious disease early warning reliability is improved, and the technical effect of infectious disease prevention and control effect is further improved.
In the technical scheme of the invention, the data acquisition, storage, use, processing and the like all conform to relevant regulations of national laws and regulations.
In the following, the technical solutions in the present invention will be clearly and completely described with reference to the accompanying drawings, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments of the present invention, and it should be understood that the present invention is not limited by the example embodiments described herein. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention. It should be further noted that, for the convenience of description, only some but not all of the elements associated with the present invention are shown in the drawings.
Examples
Referring to fig. 1, the present invention provides an infectious disease simulation early warning method based on big data, wherein the method is applied to an infectious disease simulation early warning system based on big data, and the method specifically comprises the following steps:
step S100: constructing a plurality of propagation paths;
further, as shown in fig. 2, step S100 of the present invention further includes:
step S110: setting an infection-susceptible element as a first node, a latent element as a second node, an infected element as a third node, and a rehabilitation element as a fourth node;
step S120: generating a first propagation path according to the first node and the third node;
step S130: generating a second propagation path according to the first node and the second node;
step S140: generating a third propagation path according to the second node and the third node;
step S150: generating a fourth propagation path according to the second node and the fourth node;
step S160: generating a fifth propagation path according to the third node and the fourth node;
step S170: adding the first propagation path, the second propagation path, the third propagation path, the fourth propagation path, and the fifth propagation path to the plurality of propagation paths.
Specifically, the infectious disease simulation early warning method based on big data is applied to the infectious disease simulation early warning system based on big data, and can realize the purposes of providing refined reference data for infectious disease prevention and control and further improving the early warning accuracy of infectious disease transmission by performing difference analysis and simulation on different initial infection positions of types of infectious diseases to be simulated. The multiple transmission paths refer to multiple transmission paths of the infectious disease determined after analysis based on the transmission characteristics of the infectious disease.
First, a susceptible element, which is a healthy person without infection and a region where no infection case occurs, is set as a first node. Next, a second node is defined as a latent element, which is a person or region thereof that is currently infected with an infectious disease but has not been diagnosed or does not show symptoms of the infection due to factors such as the characteristics of the infectious disease. Next, an infection factor, which is a person who has been identified to be infected with an infectious disease and a regional route in which the person moves, is set as a third node. Finally, a rehabilitation factor is set as the fourth node, wherein the rehabilitation factor refers to a crowd who has been confirmed to be infected with an infectious disease but has been completely cured at present and an area in which the crowd has moved. In addition, when each node determines the region where the corresponding node crowd is located, screening determination is carried out according to comparative analysis of the interval duration and a preset duration threshold. Further, a first propagation path is generated according to the first node and the third node; that is, the situation in which the healthy people are determined to be infected with the infectious disease in the healthy area is the first transmission route situation. Generating a second propagation path according to the first node and the second node; that is, the second transmission path is a case where the healthy person is infected with an infectious disease in a healthy area but does not show the infection characteristics. Generating a third propagation path according to the second node and the third node; that is, the third transmission pathway is the case when the population that has already been infected with the infectious disease but has not yet exhibited the infectious disease characteristic, i.e., the population that has developed the infectious disease characteristic changes from a non-dominant characteristic to a dominant one. Generating a fourth propagation path according to the second node and the fourth node; that is, the population infected with the infectious disease but with the disease characteristics not yet revealed is cured by treatment or the like, that is, the recovered condition is the fourth transmission pathway condition. Generating a fifth propagation path according to the third node and the fourth node; that is, it is determined that the person infected with the infectious disease is cured, i.e., recovered, by the treatment or the like, and that the fifth transmission route is the case. Finally, the first propagation path, the second propagation path, the third propagation path, the fourth propagation path, and the fifth propagation path are added to the plurality of propagation paths.
Through constructing a plurality of propagation paths after sequential classification analysis, the propagation classification target of nodes in different stages of infectious diseases is realized, refined basic data are provided for subsequent simulation, and the simulation reliability and the technical effect close to the actual condition are improved.
Step S200: traversing the plurality of propagation paths to perform big data analysis according to the type of the infectious disease to be simulated to generate a plurality of groups of propagation probabilities;
further, as shown in fig. 3, step S200 of the present invention further includes:
step S210: traversing the plurality of propagation paths, and acquiring a plurality of groups of propagation sample data according to the type of the infectious disease to be simulated;
step S220: carrying out time sequence clustering on any one group of sample data of the multiple groups of propagation sample data according to the path trigger duration to generate a plurality of sample clustering sequences;
step S230: constructing a plurality of infection probability-time change curves according to the plurality of sample clustering sequences;
step S240: and generating the plurality of groups of propagation probabilities according to the plurality of infection probability-time change curves.
Specifically, the type of the infectious disease to be simulated refers to the infectious disease to be subjected to intelligent simulation and early warning analysis of the infectious disease by using the infectious disease simulation early warning system. And traversing in the plurality of propagation paths by combining the actual situation of the infectious disease type to be simulated, so as to obtain a plurality of groups of propagation sample data of the infectious disease type to be simulated. And then, carrying out time sequence clustering on any one group of sample data of the multiple groups of propagation sample data according to the path trigger time length to generate a plurality of sample clustering sequences. And finally, analyzing the plurality of sample clustering sequences, constructing a plurality of infection probability-time change curves, and generating the plurality of groups of propagation probabilities according to the plurality of infection probability-time change curves. The method has the advantages that the transmission probability of the infectious disease type to be simulated is obtained after cluster analysis by collecting the transmission sample data of the infectious disease type to be simulated, and the technical effect of improving the accuracy of infectious disease transmission probability analysis is achieved.
Step S300: acquiring a scene simulation static element and a scene simulation dynamic element;
step S400: constructing a scene simulation environment according to the scene simulation static element and the scene simulation dynamic element;
further, as shown in fig. 4, step S400 of the present invention further includes:
step S410: the scene simulation static elements comprise meteorological simulation elements, traffic layout simulation elements and facility layout simulation elements;
step S420: the scene simulation dynamic element comprises a traffic vehicle simulation element and a virtual character simulation element;
step S430: traversing the meteorological simulation element, the traffic layout simulation element and the facility layout simulation element, and extracting static big data information from an area to be simulated;
step S440: traversing the traffic vehicle simulation element and the virtual character simulation element, and extracting dynamic big data information from the area to be simulated;
step S450: and constructing the scene simulation environment according to the static big data information and the dynamic big data information.
Further, the invention also comprises the following steps:
step S451: setting a vehicle random activity constraint track and a character random activity constraint track for the traffic vehicle simulation element and the virtual character simulation element according to the dynamic big data information;
step S452: and constructing the scene simulation environment according to the vehicle random activity constraint track, the figure random activity constraint track and the static big data information.
Specifically, before the scene simulation environment of the infectious disease type to be simulated is constructed, the scene simulation elements of the infectious disease type to be simulated are collected, wherein the scene simulation elements comprise scene simulation static elements and scene simulation dynamic elements. The scene simulation static elements comprise meteorological simulation elements, traffic layout simulation elements and facility layout simulation elements. Exemplary static scene elements of a certain area include area division, building distribution in the area, weather in the area, road planning, and the like. The scene simulation dynamic elements comprise traffic vehicle simulation elements and virtual character simulation elements. Exemplarily, there are element information of motion change in a certain area, and the running track and speed of the vehicle on the road.
Further, traversing the meteorological simulation element, the traffic layout simulation element and the facility layout simulation element, and extracting static big data information from the area to be simulated, and simultaneously traversing the traffic vehicle simulation element and the virtual character simulation element, and extracting dynamic big data information from the area to be simulated. And then, according to the dynamic big data information, setting a vehicle random activity constraint track and a character random activity constraint track for the traffic vehicle simulation element and the virtual character simulation element. And finally, constructing the scene simulation environment according to the vehicle random activity constraint track, the figure random activity constraint track and the static big data information.
The scene simulation environment is constructed by sequentially collecting the dynamic scene elements and the static scene elements in the region to be simulated and adding the dynamic scene elements into the static scene elements as scene construction constraints, so that a reliable and real environment basis is provided for subsequent simulation analysis of infectious disease types to be simulated, and the simulation quality is improved.
Step S500: randomly generating a preset number of initial infection positions and a preset propagation time in the scene simulation environment, and performing propagation prediction based on the multiple groups of propagation probabilities to generate a propagation range expansion speed;
further, step S500 of the present invention further includes:
step S510: determining an initial infection path node according to the initial infection position;
step S520: generating a track tracking network according to the preset propagation time and the initial infection path node;
step S530: performing diffusion simulation based on the plurality of groups of propagation probabilities according to the trajectory tracking network and the preset propagation time to generate an infection trajectory diffusion area;
further, step S530 of the present invention further includes:
step S531: constructing a probability distribution network according to the plurality of groups of propagation probabilities and the trajectory tracking network;
step S532: generating a plurality of infection track diffusion areas and a plurality of diffusion area distribution probabilities based on a Bayesian algorithm according to the probability distribution network;
step S533: judging whether any one of the distribution probabilities of the diffusion regions meets a preset distribution probability;
step S534: adding any one of the plurality of diffusion region distribution probabilities that satisfies the preset distribution probability into the infection trajectory diffusion region.
Step S540: and calculating the propagation range expansion speed according to the infection track diffusion area.
Specifically, after the scene simulation environment is constructed, a preset number of initial infection positions and a preset propagation time are randomly generated by the system, and then, the propagation prediction of the infectious diseases at each initial infection position is sequentially performed based on the plurality of sets of propagation probabilities, so that the propagation range expansion speed is generated.
Firstly, the initial infection position preset by the system is used as an initial infection path node, and a track tracking network is generated by combining the preset propagation time. And then according to the track tracking network and the preset transmission time, combining the multiple groups of transmission probabilities to carry out diffusion simulation on the transmission track of the infectious disease, thereby generating an infection track diffusion area. Namely, a probability distribution network of the type of the infectious disease to be simulated is constructed according to the multiple groups of propagation probabilities and the trajectory tracking network, and the probability distribution network is calculated and analyzed by using the Bayesian algorithm principle, so that a plurality of infection trajectory diffusion areas and a plurality of diffusion area distribution probabilities are generated. And then, judging whether any diffusion region distribution probability of the diffusion region distribution probabilities meets a preset distribution probability, and if the any diffusion region distribution probability meets the preset distribution probability, adding the any diffusion region distribution probability into the infection track diffusion region. The preset distribution probability is determined after comprehensive analysis by related professional technicians and is stored in the infectious disease simulation early warning system in advance. And finally, calculating the spreading speed of the spreading range according to the infection track spreading area.
Step S600: judging whether the propagation range expansion speed meets an expansion speed threshold or not;
step S700: and if so, carrying out risk early warning on the type of the infectious disease to be simulated based on the initial infection position and the preset propagation time.
Specifically, after the spread range expansion speed is calculated and obtained based on the infection track spread area, the system intelligently judges whether the spread range expansion speed meets an expansion speed threshold, and if the spread range expansion speed meets the expansion speed threshold, risk early warning is carried out on the type of the infectious disease to be simulated by the initial infection position and the preset spread time. By constructing a plurality of propagation paths, the goal of carrying out propagation classification on nodes in different stages on infectious diseases is realized. And then traversing and analyzing by combining the characteristics of the types of the infectious diseases to be simulated to obtain a plurality of groups of transmission probabilities, thereby achieving the technical effect of providing a prediction basis for the subsequent infectious disease simulation. Then, a scene simulation environment is constructed by collecting scene simulation elements, and an initial infection position and propagation time are preset, so that a foundation is provided for simulation of the type of the infectious disease to be simulated, and the technical effect of improving the early warning reliability of the type of the infectious disease to be simulated is achieved.
In summary, the infectious disease simulation early warning method based on big data provided by the invention has the following technical effects:
by constructing a plurality of propagation paths; traversing the plurality of propagation paths to perform big data analysis according to the type of the infectious disease to be simulated to generate a plurality of groups of propagation probabilities; acquiring a scene simulation static element and a scene simulation dynamic element; constructing a scene simulation environment according to the scene simulation static element and the scene simulation dynamic element; randomly generating a preset number of initial infection positions and a preset propagation time in the scene simulation environment, and performing propagation prediction based on the multiple groups of propagation probabilities to generate a propagation range expansion speed; judging whether the propagation range expansion speed meets an expansion speed threshold or not; and if so, carrying out risk early warning on the type of the infectious disease to be simulated based on the initial infection position and the preset propagation time. By constructing a plurality of propagation paths, the goal of carrying out propagation classification on nodes in different stages on infectious diseases is realized. And then traversing and analyzing by combining the characteristics of the types of the infectious diseases to be simulated to obtain a plurality of groups of transmission probabilities, thereby achieving the technical effect of providing a prediction basis for the subsequent infectious disease simulation. Then, a scene simulation environment is constructed by collecting scene simulation elements, and an initial infection position and propagation time are preset, so that a foundation is provided for simulation of the type of the infectious disease to be simulated, and the technical effect of improving the early warning reliability of the type of the infectious disease to be simulated is achieved. By carrying out difference analysis and simulation of different initial infection positions on the types of the infectious diseases to be simulated, the technical goal of providing refined reference data for infectious disease prevention and control is achieved, the infectious disease early warning reliability is improved, and the technical effect of infectious disease prevention and control effect is further improved.
Examples
Based on the same inventive concept as the infectious disease simulation early warning method based on big data in the foregoing embodiment, the present invention further provides an infectious disease simulation early warning system based on big data, please refer to fig. 5, where the system includes:
a first building block M100, said first building block M100 being adapted to build a plurality of propagation paths;
the first generation module M200 is used for traversing the plurality of propagation paths to perform big data analysis according to the type of the infectious disease to be simulated to generate a plurality of groups of propagation probabilities;
an obtaining module M300, where the obtaining module M300 is configured to obtain a scene simulation static element and a scene simulation dynamic element;
a second constructing module M400, wherein the second constructing module M400 is used for constructing a scene simulation environment according to the scene simulation static element and the scene simulation dynamic element;
a second generating module M500, where the second generating module M500 is configured to randomly generate a preset number of initial infection positions and preset propagation times in the scene simulation environment, perform propagation prediction based on the multiple groups of propagation probabilities, and generate a propagation range expansion speed;
a judging module M600, where the judging module M600 is configured to judge whether the propagation range expansion speed meets an expansion speed threshold;
and the execution module M700 is used for performing risk early warning on the type of the infectious disease to be simulated based on the initial infection position and the preset propagation time if the type of the infectious disease to be simulated is met.
Further, the first building block M100 in the system is further configured to:
setting an infection-susceptible element as a first node, a latent element as a second node, an infected element as a third node, and a rehabilitation element as a fourth node;
generating a first propagation path according to the first node and the third node;
generating a second propagation path according to the first node and the second node;
generating a third propagation path according to the second node and the third node;
generating a fourth propagation path according to the second node and the fourth node;
generating a fifth propagation path according to the third node and the fourth node;
adding the first propagation path, the second propagation path, the third propagation path, the fourth propagation path, and the fifth propagation path to the plurality of propagation paths.
Further, the first generating module M200 in the system is further configured to:
traversing the plurality of propagation paths, and acquiring a plurality of groups of propagation sample data according to the type of the infectious disease to be simulated;
carrying out time sequence clustering on any one group of sample data of the multiple groups of propagation sample data according to the path trigger duration to generate a plurality of sample clustering sequences;
constructing a plurality of infection probability-time change curves according to the plurality of sample clustering sequences;
and generating the plurality of groups of propagation probabilities according to the plurality of infection probability-time change curves.
Further, the second building module M400 in the system is further configured to:
the scene simulation static elements comprise meteorological simulation elements, traffic layout simulation elements and facility layout simulation elements;
the scene simulation dynamic elements comprise traffic vehicle simulation elements and virtual character simulation elements;
traversing the meteorological simulation element, the traffic layout simulation element and the facility layout simulation element, and extracting static big data information from an area to be simulated;
traversing the traffic vehicle simulation element and the virtual character simulation element, and extracting dynamic big data information from the area to be simulated;
and constructing the scene simulation environment according to the static big data information and the dynamic big data information.
Further, the second building module M400 in the system is further configured to:
setting a vehicle random activity constraint track and a character random activity constraint track for the traffic vehicle simulation element and the virtual character simulation element according to the dynamic big data information;
and constructing the scene simulation environment according to the vehicle random activity constraint track, the figure random activity constraint track and the static big data information.
Further, the second generating module M500 in the system is further configured to:
determining an initial infection path node according to the initial infection position;
generating a track tracking network according to the preset propagation time and the initial infection path node;
performing diffusion simulation based on the plurality of groups of propagation probabilities according to the trajectory tracking network and the preset propagation time to generate an infection trajectory diffusion area;
and calculating the propagation range expansion speed according to the infection track diffusion area.
Further, the second generating module M500 in the system is further configured to:
constructing a probability distribution network according to the plurality of groups of propagation probabilities and the trajectory tracking network;
generating a plurality of infection track diffusion areas and a plurality of diffusion area distribution probabilities based on a Bayesian algorithm according to the probability distribution network;
judging whether any one of the distribution probabilities of the plurality of diffusion regions meets a preset distribution probability;
adding any one of the plurality of diffusion region distribution probabilities that satisfies the preset distribution probability into the infection trajectory diffusion region.
In the present specification, each embodiment is described in a progressive manner, and the emphasis of each embodiment is on the difference from other embodiments, and the above-mentioned infectious disease simulation and early warning method based on big data in the first embodiment in fig. 1 and the specific example are also applicable to the infectious disease simulation and early warning system based on big data in the present embodiment. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the present invention and its equivalent technology, it is intended that the present invention also include such modifications and variations.