An intelligent analysis and processing system and method for disease risk based on epidemic big data

Abstract

The present invention discloses an intelligent analysis and processing system and method for disease risk based on epidemic big data, belonging to the field of epidemic big data technology. A climate disease archive is established to store climate disease medical records; based on the data cluster of the time when the pathological early symptoms are generated and the data cluster of the time when the pathological late symptoms are generated, the climate disease medical records are locked, and the type of disease and meteorological induction factors are captured retroactively to generate feature-driven labels; the pathological early sample set and the pathological late sample set are respectively mapped to the pathological early feature matrix and the pathological late feature matrix, respectively, to obtain the pathological early feature matrix and the pathological late feature matrix with time node marks; the time correlation coefficient between the pathological early stage and the pathological late stage is analyzed to evaluate whether there is a disease risk relationship between the pathological early stage and the pathological late stage; further, the correlation between early blight and late blight can be monitored for a long time, and time prediction assistance can be provided for the disease risk of late blight.

Description

Technical Field

[0001] The present invention relates to the technical field of epidemic big data, and specifically to a system and method for intelligent analysis and processing of disease hidden dangers based on epidemic big data. Background Art

[0002] Climate diseases refer to plant diseases that are directly or indirectly caused by changes in climate conditions. The occurrence, development and spread of these diseases are often closely related to specific climate conditions, such as temperature, humidity, light, precipitation, wind speed, etc.

[0003] For the early pathological characteristics of climate-related diseases, existing technologies have conducted many relevant studies on the origin of the pathogen, changes in population genetic structure, infection mechanism, monitoring and early warning, as well as prevention and control methods; however, intelligent and accurate early warning and precise prevention and control of late blight have not been achieved; for example, for a long time, the monitoring and early warning of potato late blight mainly relied on manual field surveys, and early warning information was issued after identifying the early symptoms of potato late blight in the field. However, this method not only consumes a lot of manpower and material resources, but also has low accuracy in early warning, which often leads to delays in prevention and control time and affects the prevention and control effect. Summary of the invention

[0004] The purpose of the present invention is to provide a system and method for intelligent analysis and processing of disease hidden dangers based on epidemic big data to solve the problems raised in the above-mentioned background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] An intelligent analysis and processing system for disease risk based on epidemic big data, the system includes: a climate disease archive module, a driving analysis module, a driving feature matrix carrier module and a disease risk assessment and analysis module;

[0007] The climatic disease archive module is used to establish a climatic disease archive to store climatic disease medical records, wherein the climatic disease medical records record pathological characteristic information of plants, wherein the pathological characteristic information includes the type of disease, the meteorological induction factor of the disease, the time when the initial pathological symptoms occur, and the time when the late pathological symptoms occur, and generates a data cluster of the type of disease, a data cluster of the meteorological induction factor, a data cluster of the time when the initial pathological symptoms occur, and a data cluster of the time when the late pathological symptoms occur;

[0008] The driving analysis module locks the medical records of climatic diseases based on the data clusters of the time when the pathological early symptoms occur and the data clusters of the time when the pathological late symptoms occur, and traces back to capture the types of disease occurrence and meteorological induction factors to generate feature driving labels, and generates the pathological early sample set and the pathological late sample set;

[0009] The driving feature matrix carrier module is used to establish an early pathology feature matrix and a late pathology feature matrix, and map the early pathology sample set and the late pathology sample set to the early pathology feature matrix and the late pathology feature matrix in sequence, respectively, to obtain the early pathology feature matrix and the late pathology feature matrix with time node marks, respectively;

[0010] The disease risk assessment and analysis module analyzes the time correlation coefficient between the early pathology stage and the late pathology stage based on the early pathology feature matrix and the late pathology feature matrix with time node marks, and assesses whether there is a disease risk relationship between the early pathology stage and the late pathology stage.

[0011] Further, the climate disease archive module includes a climate disease medical record unit and a pathological characteristic data cluster unit;

[0012] The climatic disease medical record unit is used to establish a climatic disease archive, in which a plurality of climatic disease medical records are stored, and the climatic disease medical records have a unique coding attribute;

[0013] The pathological characteristic data cluster unit is used to uniformly number each pathological characteristic information in sequence and generate disease type data clusters respectively. , meteorological induction factor data cluster , pathological initial symptom occurrence time data cluster and pathological late stage symptom generation time data cluster ,in, represents the hth climatic disease record, Indicates the history of climatic diseases The nth type of disease recorded in ,and , N represents the total number of types of disease, Indicates the history of climatic diseases The i-th meteorological induction factor recorded in ,and , I represents the total number of types of meteorological induction factors, Indicates the history of climatic diseases The rth time point when the initial symptoms of the pathology were recorded ,and , by initializing the minimum time unit scale k to record the time node of the initial pathological symptoms, R represents the current time node number, Indicates the history of climatic diseases The time point when the symptoms of late pathology occurred was recorded in , ,and Indicates the time point when the initial symptoms of the pathology occur Delay g initialization delay length of minimum time unit scale k.

[0014] Further, the driving analysis module includes a driving feature generation unit and a driving sample library unit;

[0015] The driving feature generating unit generates a time data cluster FTD based on the pathological early stage symptom generation time data cluster STD based on the pathological late stage symptom generation time data cluster at the time node Identify the time point when the initial symptoms of the pathology occur And lock the medical records of climate-related diseases , identify the time point when symptoms of late pathology occur And lock the medical records of climate-related diseases ;

[0016] Based on the disease type data cluster AD and the meteorological induction factor data cluster FD, the locked climatic disease records , respectively capture the type of disease and meteorological factors , and the history of climatic diseases Additional feature driver tags, denoted as If we can capture the type of disease and meteorological factors , then let the feature drive label , otherwise let the feature drive the label ;

[0017] The driving sample library unit, based on the capture behavior, at the time node Under the following conditions, the pathological early stage sample sets are generated respectively and pathological late stage sample set , specifically including:

[0018] If we identify the time point when the initial symptoms of the pathology occur And locked climate disease records , then the feature-driven label Recorded in the early pathology sample set In; if by identifying the time point when the symptoms of late pathology occur And locked climate disease records , then the feature-driven label Enter the pathology late sample set middle.

[0019] Furthermore, the driving feature matrix carrier module includes an epidemic big data model matrix unit and a matrix mapping unit;

[0020] The disease big data model matrix unit is used to establish the disease big data model matrix, which is recorded as RR(N×I), where N×I means that the disease big data model matrix has N rows and I columns, and the feature-driven label As the matrix element corresponding to the nth row and the ith column; based on the epidemic big data model matrix, the early pathology feature matrix FS[RR(N×I)] and the late pathology feature matrix SS[RR(N×I)] are established respectively;

[0021] The matrix mapping unit is used to respectively map the pathological early stage sample set and pathological late stage sample set Mapped to the pathological early stage feature matrix FS[RR(N×I)] and the pathological late stage feature matrix SS[RR(N×I)] in sequence, the attached time nodes are obtained respectively Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix :SS[RR(N×I)].

[0022] Furthermore, the disease risk assessment and analysis module includes a correlation coefficient analysis unit and a risk warning unit;

[0023] The correlation coefficient analysis unit is based on the time node Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix : SS[RR(N×I)], evaluates the temporal correlation coefficient between the early and late stages of pathology, as follows:

[0024] ;

[0025] In the formula, Indicates at time node When the time correlation coefficient between the early stage of pathology and the late stage of pathology is Indicates the attached time node Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix : The number of 1s contained in the result of the Boolean intersection operation between SS[RR(N×I)], Indicates the attached time node Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix : The number of 1s contained in the result of the Boolean union operation between SS[RR(N×I)];

[0026] The hidden danger warning unit presets a correlation coefficient threshold value. If the time correlation coefficient If it is greater than or equal to the correlation coefficient threshold, it means that at the time node There is a relationship between the early and late stages of pathology and the potential risk of disease progression at the time node. Issue an early warning prompt.

[0027] A method for intelligent analysis and processing of disease risk based on epidemic big data, the method comprising the following steps:

[0028] Step S1: Establish a climate disease archive to store climate disease medical records, wherein the climate disease medical records record pathological characteristic information of plants, wherein the pathological characteristic information includes the type of disease, the meteorological induction factor of the disease, the time when the pathological initial symptoms occur, and the time when the pathological late symptoms occur, and generate a data cluster of the type of disease, a data cluster of the meteorological induction factor, a data cluster of the time when the pathological initial symptoms occur, and a data cluster of the time when the pathological late symptoms occur;

[0029] Step S2: Based on the data clusters of the time when the pathological early symptoms occurred and the data clusters of the time when the pathological late symptoms occurred, the medical records of climatic diseases are locked, and the types of disease occurrence and meteorological induction factors are retroactively captured to generate feature-driven labels, and the pathological early sample set and the pathological late sample set are generated;

[0030] Step S3: Establishing an early pathology feature matrix and a late pathology feature matrix, mapping the early pathology sample set and the late pathology sample set to the early pathology feature matrix and the late pathology feature matrix in sequence, respectively, to obtain the early pathology feature matrix and the late pathology feature matrix with time node marks, respectively;

[0031] Step S4: Based on the early pathology feature matrix and the late pathology feature matrix with time node marks, the time correlation coefficient between the early pathology stage and the late pathology stage is analyzed to evaluate whether there is a potential disease risk relationship between the early pathology stage and the late pathology stage.

[0032] Furthermore, the specific implementation process of step S1 includes:

[0033] Establishing a climate disease archive, wherein the climate disease archive stores a plurality of climate disease medical records, wherein the climate disease medical records have a unique coding attribute;

[0034] Uniformly number each pathological feature information in turn, and generate disease type data clusters respectively , meteorological induction factor data cluster , pathological initial symptom occurrence time data cluster and pathological late stage symptom generation time data cluster ,in, represents the hth climatic disease record, Indicates the history of climatic diseases The nth type of disease recorded in ,and , N represents the total number of types of disease, Indicates the history of climatic diseases The i-th meteorological induction factor recorded in ,and , I represents the total number of types of meteorological induction factors, Indicates the history of climatic diseases The rth time point when the initial symptoms of the pathology were recorded ,and , by initializing the minimum time unit scale k to record the time node of the initial pathological symptoms, R represents the current time node number, Indicates the history of climatic diseases The time point when the symptoms of late pathology occurred was recorded in , ,and Indicates the time point when the initial symptoms of the pathology occur Delay g initialization delay length of minimum time unit scale k.

[0035] Furthermore, the specific implementation process of step S2 includes:

[0036] Based on the FTD data cluster of the time when the pathological early symptoms occur and the STD data cluster of the time when the pathological late symptoms occur, at the time node Identify the time point when the initial symptoms of the pathology occur And lock the medical records of climate-related diseases , identify the time point when symptoms of late pathology occur And lock the medical records of climate-related diseases ;

[0037] Based on the disease type data cluster AD and the meteorological induction factor data cluster FD, the locked climatic disease records , respectively capture the type of disease and meteorological factors , and the history of climatic diseases Additional feature driver tags, denoted as If we can capture the type of disease and meteorological factors , then let the feature drive label , otherwise let the feature drive the label ;

[0038] Based on the capture behavior, at the time node Under the following conditions, the pathological early stage sample sets are generated respectively and pathological late stage sample set , specifically including:

[0039] If we identify the time point when the initial symptoms of the pathology occur And locked climate disease records , then the feature-driven label Recorded in the early pathology sample set In; if by identifying the time point when the symptoms of late pathology occur And locked climate disease records , then the feature-driven label Enter the pathology late sample set middle.

[0040] Furthermore, the specific implementation process of step S3 includes:

[0041] Establish an epidemic big data model matrix, denoted as RR(N×I), where N×I means that the epidemic big data model matrix has N rows and I columns, and the feature-driven label As the matrix element corresponding to the nth row and the ith column;

[0042] Based on the disease big data model matrix, the pathological early stage feature matrix FS[RR(N×I)] and the pathological late stage feature matrix SS[RR(N×I)] were established respectively;

[0043] The early pathological sample set and pathological late stage sample set Mapped to the pathological early stage feature matrix FS[RR(N×I)] and the pathological late stage feature matrix SS[RR(N×I)] in sequence, the attached time nodes are obtained respectively Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix :SS[RR(N×I)].

[0044] Furthermore, the specific implementation process of step S4 includes:

[0045] Based on time nodes Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix : SS[RR(N×I)], evaluates the temporal correlation coefficient between the early and late stages of pathology, as follows:

[0046] ;

[0047] In the formula, Indicates at time node When the time correlation coefficient between the early stage of pathology and the late stage of pathology is Indicates the attached time node Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix : The number of 1s contained in the result of the Boolean intersection operation between SS[RR(N×I)], Indicates the attached time node Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix : The number of 1s contained in the result of the Boolean union operation between SS[RR(N×I)];

[0048] Preset correlation coefficient threshold, if the time correlation coefficient If it is greater than or equal to the correlation coefficient threshold, it means that at the time node There is a relationship between the early and late stages of pathology and the potential risk of disease progression at the time node. Issue an early warning prompt.

[0049] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: in an intelligent analysis and processing system and method for disease hazard based on epidemic big data provided by the present invention, a climate disease archive is established to store climate disease medical records; based on the time data clusters of the generation of early pathological symptoms and the time data clusters of the generation of late pathological symptoms, the climate disease medical records are locked, and the types of disease and meteorological induction factors are traced and captured to generate feature-driven labels; the early pathological sample set and the late pathological sample set are respectively mapped to the early pathological feature matrix and the late pathological feature matrix in turn, and the early pathological feature matrix and the late pathological feature matrix with time node marks are obtained respectively; the time correlation coefficient between the early pathological stage and the late pathological stage is analyzed, and it is evaluated whether there is a disease hazard relationship between the early pathological stage and the late pathological stage; further, the correlation between early blight and late blight can be monitored for a long time, and time prediction assistance can be provided for the disease hazard of late blight. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0051] Figure 1 It is a structural schematic diagram of an intelligent analysis and processing system for disease hidden dangers based on epidemic big data of the present invention;

[0052] Figure 2 It is a schematic diagram of the steps of a method for intelligent analysis and processing of disease hidden dangers based on epidemic big data of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] See also Figure 1 In the first embodiment of the present invention, a disease risk intelligent analysis and processing system based on disease big data is provided, the system comprising: a climatic disease archive module, a driving analysis module, a driving characteristic matrix carrier module and a disease risk assessment and analysis module;

[0055] The climatic disease archive module is used to establish a climatic disease archive to store climatic disease medical records, wherein the climatic disease medical records record pathological characteristic information of plants, wherein the pathological characteristic information includes the type of disease, the meteorological induction factor of the disease, the time when the initial pathological symptoms occur, and the time when the late pathological symptoms occur, and generates a data cluster of the type of disease, a data cluster of the meteorological induction factor, a data cluster of the time when the initial pathological symptoms occur, and a data cluster of the time when the late pathological symptoms occur;

[0056] Preferably, the climate disease archive module includes a climate disease medical record unit and a pathological characteristic data cluster unit;

[0057] The climatic disease medical record unit is used to establish a climatic disease archive, in which a plurality of climatic disease medical records are stored, and the climatic disease medical records have a unique coding attribute;

[0058] The pathological characteristic data cluster unit is used to uniformly number each pathological characteristic information in sequence and generate disease type data clusters respectively. , meteorological induction factor data cluster , pathological initial symptom occurrence time data cluster and pathological late stage symptom generation time data cluster ,in, represents the hth climatic disease record, Indicates the history of climatic diseases The nth type of disease recorded in ,and , N represents the total number of types of disease, Indicates the history of climatic diseases The i-th meteorological induction factor recorded in ,and , I represents the total number of types of meteorological induction factors, Indicates the history of climatic diseases The rth time point when the initial symptoms of the pathology were recorded ,and , by initializing the minimum time unit scale k to record the time node of the initial pathological symptoms, R represents the current time node number, Indicates the history of climatic diseases The time point when the symptoms of late pathology occurred was recorded in , ,and Indicates the time point when the initial symptoms of the pathology occur Delay g initialization minimum time unit scale k delay extension;

[0059] The driving analysis module locks the medical records of climatic diseases based on the data clusters of the time when the pathological early symptoms occur and the data clusters of the time when the pathological late symptoms occur, and traces back to capture the types of disease occurrence and meteorological induction factors to generate feature driving labels, and generates the pathological early sample set and the pathological late sample set;

[0060] Preferably, the driving analysis module includes a driving feature generation unit and a driving sample library unit;

[0061] The driving feature generating unit generates a time data cluster FTD based on the pathological early stage symptom generation time data cluster STD based on the pathological late stage symptom generation time data cluster at the time node Identify the time point when the initial symptoms of the pathology occur And lock the medical records of climate-related diseases , identify the time point when symptoms of late pathology occur And lock the medical records of climate-related diseases ;

[0062] Based on the disease type data cluster AD and the meteorological induction factor data cluster FD, the locked climatic disease records , respectively capture the type of disease and meteorological factors , and the history of climatic diseases Additional feature driver tags, denoted as If we can capture the type of disease and meteorological factors , then let the feature drive label , otherwise let the feature drive the label ;

[0063] The driving sample library unit, based on the capture behavior, at the time node Under the following conditions, the pathological early stage sample sets are generated respectively and pathological late stage sample set , specifically including:

[0064] If we identify the time point when the initial symptoms of the pathology occur And locked climate disease records , then the feature-driven label Recorded in the early pathology sample set In; if by identifying the time point when the symptoms of late pathology occur And locked climate disease records , then the feature-driven label Enter the pathology late sample set middle;

[0065] The driving feature matrix carrier module is used to establish an early pathology feature matrix and a late pathology feature matrix, and map the early pathology sample set and the late pathology sample set to the early pathology feature matrix and the late pathology feature matrix in sequence, respectively, to obtain the early pathology feature matrix and the late pathology feature matrix with time node marks, respectively;

[0066] Preferably, the driving characteristic matrix carrier module includes an epidemic big data model matrix unit and a matrix mapping unit;

[0067] The disease big data model matrix unit is used to establish the disease big data model matrix, which is recorded as RR(N×I), where N×I means that the disease big data model matrix has N rows and I columns, and the feature-driven label As the matrix element corresponding to the nth row and the ith column; based on the epidemic big data model matrix, the early pathology feature matrix FS[RR(N×I)] and the late pathology feature matrix SS[RR(N×I)] are established respectively;

[0068] The matrix mapping unit is used to respectively map the pathological early stage sample set and pathological late stage sample set Mapped to the pathological early stage feature matrix FS[RR(N×I)] and the pathological late stage feature matrix SS[RR(N×I)] in sequence, the attached time nodes are obtained respectively Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix : SS[RR(N×I)];

[0069] The morbidity risk assessment and analysis module analyzes the time correlation coefficient between the early pathology stage and the late pathology stage based on the early pathology feature matrix and the late pathology feature matrix with time node marks, and assesses whether there is a morbidity risk relationship between the early pathology stage and the late pathology stage;

[0070] Preferably, the disease risk assessment and analysis module includes a correlation coefficient analysis unit and a risk warning unit;

[0071] The correlation coefficient analysis unit is based on the time node Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix : SS[RR(N×I)], evaluates the temporal correlation coefficient between the early and late stages of pathology, as follows:

[0072] ;

[0073] In the formula, Indicates at time node When the time correlation coefficient between the early stage of pathology and the late stage of pathology is Indicates the attached time node Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix : The number of 1s contained in the result of the Boolean intersection operation between SS[RR(N×I)], Indicates the attached time node Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix : The number of 1s contained in the result of the Boolean union operation between SS[RR(N×I)];

[0074] The hidden danger warning unit presets a correlation coefficient threshold value. If the time correlation coefficient If it is greater than or equal to the correlation coefficient threshold, it means that at the time node There is a relationship between the early and late stages of pathology and the potential risk of disease progression at the time node. Issue an early warning prompt.

[0075] See also Figure 2 In the second embodiment, a method for intelligent analysis and processing of disease risk based on epidemic big data is provided, and the method comprises the following steps:

[0076] Step S1: Establish a climate disease archive to store climate disease medical records, wherein the climate disease medical records record pathological characteristic information of plants, wherein the pathological characteristic information includes the type of disease, the meteorological induction factor of the disease, the time when the pathological initial symptoms occur, and the time when the pathological late symptoms occur, and generate a data cluster of the type of disease, a data cluster of the meteorological induction factor, a data cluster of the time when the pathological initial symptoms occur, and a data cluster of the time when the pathological late symptoms occur;

[0077] Exemplarily, a climate disease archive is established, wherein a plurality of climate disease medical records are stored in the climate disease archive, and the climate disease medical records have a unique coding attribute;

[0078] Uniformly number each pathological feature information in turn, and generate disease type data clusters respectively , meteorological induction factor data cluster , pathological initial symptom occurrence time data cluster and pathological late stage symptom generation time data cluster ,in, represents the hth climatic disease record, Indicates the history of climatic diseases The nth type of disease recorded in ,and , N represents the total number of types of disease, Indicates the history of climatic diseases The i-th meteorological induction factor recorded in ,and , I represents the total number of types of meteorological induction factors, Indicates the history of climatic diseases The rth time point when the initial symptoms of the pathology were recorded ,and , by initializing the minimum time unit scale k to record the time node of the initial pathological symptoms, R represents the current time node number, Indicates the history of climatic diseases The time point when the symptoms of late pathology occurred was recorded in , ,and Indicates the time point when the initial symptoms of the pathology occur Delay g initialization minimum time unit scale k delay extension;

[0079] Step S2: Based on the data clusters of the time when the pathological early symptoms occurred and the data clusters of the time when the pathological late symptoms occurred, the medical records of climatic diseases are locked, and the types of disease occurrence and meteorological induction factors are retroactively captured to generate feature-driven labels, and the pathological early sample set and the pathological late sample set are generated;

[0080] For example, based on the pathological early stage symptom generation time data cluster FTD and the pathological late stage symptom generation time data cluster STD, at the time node Identify the time point when the initial symptoms of the pathology occur And lock the medical records of climate-related diseases , identify the time point when symptoms of late pathology occur And lock the medical records of climate-related diseases ;

[0081] Based on the disease type data cluster AD and the meteorological induction factor data cluster FD, the locked climatic disease records , respectively capture the type of disease and meteorological factors , and the history of climatic diseases Additional feature driver tags, denoted as If we can capture the type of disease and meteorological factors , then let the feature drive label , otherwise let the feature drive the label ;

[0082] Based on the capture behavior, at the time node Under the following conditions, the pathological early stage sample sets are generated respectively and pathological late stage sample set , specifically including:

[0083] If we identify the time point when the initial symptoms of the pathology occur And locked climate disease records , then the feature-driven label Recorded in the early pathology sample set In; if by identifying the time point when the symptoms of late pathology occur And locked climate disease records , then the feature-driven label Enter the pathology late sample set middle;

[0084] Step S3: Establishing an early pathology feature matrix and a late pathology feature matrix, mapping the early pathology sample set and the late pathology sample set to the early pathology feature matrix and the late pathology feature matrix in sequence, respectively, to obtain the early pathology feature matrix and the late pathology feature matrix with time node marks, respectively;

[0085] For example, a disease big data model matrix is ​​established, which is recorded as RR(N×I), where N×I indicates that the disease big data model matrix has N rows and I columns, and the feature-driven label As the matrix element corresponding to the nth row and the ith column;

[0086] Based on the disease big data model matrix, the pathological early stage feature matrix FS[RR(N×I)] and the pathological late stage feature matrix SS[RR(N×I)] were established respectively;

[0087] The early pathological sample set and pathological late stage sample set Mapped to the pathological early stage feature matrix FS[RR(N×I)] and the pathological late stage feature matrix SS[RR(N×I)] in sequence, the attached time nodes are obtained respectively Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix : SS[RR(N×I)];

[0088] Step S4: Based on the pathological early stage feature matrix and the pathological late stage feature matrix with time node marks, the time correlation coefficient between the pathological early stage and the pathological late stage is analyzed to evaluate whether there is a relationship of potential disease risk between the pathological early stage and the pathological late stage;

[0089] Exemplary, based on time nodes Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix : SS[RR(N×I)], evaluates the temporal correlation coefficient between the early and late stages of pathology, as follows:

[0090] ;

[0091] In the formula, Indicates at time node When the time correlation coefficient between the early stage of pathology and the late stage of pathology is Indicates the attached time node Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix : The number of 1s contained in the result of the Boolean intersection operation between SS[RR(N×I)], Indicates the attached time node Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix : The number of 1s contained in the result of the Boolean union operation between SS[RR(N×I)];

[0092] Preset correlation coefficient threshold, if the time correlation coefficient If it is greater than or equal to the correlation coefficient threshold, it means that at the time node There is a relationship between the early and late stages of pathology and the potential risk of disease progression at the time node. Issue an early warning prompt.

[0093] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0094] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for intelligent analysis and processing of disease risk based on epidemic big data, characterized in that: The method comprises the following steps: Step S1: Establish a climate disease archive to store climate disease medical records, wherein the climate disease medical records record pathological characteristic information of plants, wherein the pathological characteristic information includes the type of disease, the meteorological induction factor of the disease, the time when the pathological initial symptoms occur, and the time when the pathological late symptoms occur, and generate a data cluster of the type of disease, a data cluster of the meteorological induction factor, a data cluster of the time when the pathological initial symptoms occur, and a data cluster of the time when the pathological late symptoms occur; Step S2: Based on the data clusters of the time when the pathological early symptoms occurred and the data clusters of the time when the pathological late symptoms occurred, the medical records of climatic diseases are locked, and the types of disease occurrence and meteorological induction factors are retroactively captured to generate feature-driven labels, and the pathological early sample set and the pathological late sample set are generated; Step S3: Establishing an early pathology feature matrix and a late pathology feature matrix, mapping the early pathology sample set and the late pathology sample set to the early pathology feature matrix and the late pathology feature matrix in sequence, respectively, to obtain the early pathology feature matrix and the late pathology feature matrix with time node marks, respectively; Step S4: Based on the pathological early stage feature matrix and the pathological late stage feature matrix with time node marks, the time correlation coefficient between the pathological early stage and the pathological late stage is analyzed to evaluate whether there is a relationship of potential disease risk between the pathological early stage and the pathological late stage; The specific implementation process of step S1 includes: Establishing a climate disease archive, wherein the climate disease archive stores a plurality of climate disease medical records, wherein the climate disease medical records have a unique coding attribute; Uniformly number each pathological feature information in turn, and generate disease type data clusters respectively , meteorological induction factor data cluster , pathological initial symptom occurrence time data cluster and pathological late stage symptom generation time data cluster ,in, represents the hth climatic disease record, Indicates the history of climatic diseases The nth type of disease recorded in ,and , N represents the total number of types of disease occurrence, Indicates the history of climatic diseases The i-th meteorological induction factor recorded in ,and , I represents the total number of types of meteorological induction factors, Indicates the history of climatic diseases The rth time point when the initial symptoms of the pathology were recorded ,and , by initializing the minimum time unit scale k to record the time node of the initial pathological symptoms, R represents the current time node number, Indicates the history of climatic diseases The time point when the symptoms of late pathology occurred was recorded in , ,and Indicates the time point when the initial symptoms of the pathology occur Delay g initialization minimum time unit scale k delay extension; The specific implementation process of step S2 includes: Based on the FTD data cluster of the time when the pathological early symptoms occur and the STD data cluster of the time when the pathological late symptoms occur, at the time node Identify the time point when the initial symptoms of the pathology occur And lock the medical records of climate-related diseases , identify the time point when symptoms of late pathology occur And lock the medical records of climate-related diseases ; Based on the disease type data cluster AD and the meteorological induction factor data cluster FD, the locked climatic disease records , respectively capture the type of disease and meteorological factors , and the history of climatic diseases Additional feature driver tags, denoted as If we can capture the type of disease and meteorological factors , then let the feature drive label , otherwise let the feature drive the label ; Based on the capture behavior, at the time node Under the following conditions, the pathological early stage sample sets are generated respectively and pathological late stage sample set , including: If we identify the time point when the initial symptoms of the pathology occur And locked climate disease records , then the feature-driven label Recorded in the early pathology sample set In; if by identifying the time point when the symptoms of late pathology occur And locked climate disease records , then the feature-driven label Included in the pathology late stage sample set middle; The specific implementation process of step S3 includes: Establish an epidemic big data model matrix, denoted as RR(N×I), where N×I means that the epidemic big data model matrix has N rows and I columns, and the feature-driven label As the matrix element corresponding to the nth row and the ith column; Based on the disease big data model matrix, the pathological early stage feature matrix FS[RR(N×I)] and the pathological late stage feature matrix SS[RR(N×I)] were established respectively; The early pathological sample set and pathological late stage sample set Mapped to the pathological early stage feature matrix FS[RR(N×I)] and the pathological late stage feature matrix SS[RR(N×I)] in sequence, the attached time nodes are obtained respectively Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix : SS[RR(N×I)]; The specific implementation process of step S4 includes: Based on time nodes Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix : SS[RR(N×I)], evaluates the temporal correlation coefficient between the early and late stages of pathology, as follows: ； In the formula, Indicates at time node When the time correlation coefficient between the early stage of pathology and the late stage of pathology is Indicates the attached time node Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix : The number of 1s contained in the result of the Boolean intersection operation between SS[RR(N×I)], Indicates the attached time node Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix : The number of 1s contained in the result of the Boolean union operation between SS[RR(N×I)]; Preset correlation coefficient threshold, if the time correlation coefficient If it is greater than or equal to the correlation coefficient threshold, it means that at the time node There is a relationship between the early and late stages of pathology and the potential risk of disease progression at the time node. Issue an early warning prompt.

2. A system for intelligent analysis and processing of disease risk based on epidemic big data, which executes the method for intelligent analysis and processing of disease risk based on epidemic big data as claimed in claim 1, characterized in that: The system includes: a climatic disease archive module, a driving analysis module, a driving characteristic matrix carrier module and a disease risk assessment and analysis module; The climatic disease archive module is used to establish a climatic disease archive to store climatic disease medical records, wherein the climatic disease medical records record pathological characteristic information of plants, wherein the pathological characteristic information includes the type of disease, the meteorological induction factor of the disease, the time when the initial pathological symptoms occur, and the time when the late pathological symptoms occur, and generates a data cluster of the type of disease, a data cluster of the meteorological induction factor, a data cluster of the time when the initial pathological symptoms occur, and a data cluster of the time when the late pathological symptoms occur; The driving analysis module locks the medical records of climatic diseases based on the data clusters of the time when the pathological early symptoms occur and the data clusters of the time when the pathological late symptoms occur, and traces back to capture the types of disease occurrence and meteorological induction factors to generate feature driving labels, and generates the pathological early sample set and the pathological late sample set; The driving feature matrix carrier module is used to establish an early pathology feature matrix and a late pathology feature matrix, and map the early pathology sample set and the late pathology sample set to the early pathology feature matrix and the late pathology feature matrix in sequence, respectively, to obtain the early pathology feature matrix and the late pathology feature matrix with time node marks, respectively; The disease risk assessment and analysis module analyzes the time correlation coefficient between the early pathology stage and the late pathology stage based on the early pathology feature matrix and the late pathology feature matrix with time node marks, and assesses whether there is a disease risk relationship between the early pathology stage and the late pathology stage.

3. The intelligent analysis and processing system for disease risk based on epidemic big data according to claim 2 is characterized by: The climate disease archive module includes a climate disease medical record unit and a pathological characteristic data cluster unit; The climatic disease medical record unit is used to establish a climatic disease archive, in which a plurality of climatic disease medical records are stored, and the climatic disease medical records have a unique coding attribute; The pathological characteristic data cluster unit is used to uniformly number each pathological characteristic information in sequence and generate disease type data clusters respectively. , meteorological induction factor data cluster , pathological initial symptom occurrence time data cluster and pathological late stage symptom generation time data cluster ,in, represents the hth climatic disease record, Indicates the history of climatic diseases The nth type of disease recorded in ,and , N represents the total number of types of disease occurrence, Indicates the history of climatic diseases The i-th meteorological induction factor recorded in ,and , I represents the total number of types of meteorological induction factors, Indicates the history of climatic diseases The rth time point when the initial symptoms of the pathology were recorded ,and , by initializing the minimum time unit scale k to record the time node of the initial pathological symptoms, R represents the current time node number, Indicates the history of climatic diseases The time point when the symptoms of late pathology occurred was recorded in , ,and Indicates the time point when the initial symptoms of the pathology occur Delay g initialization delay length of minimum time unit scale k.

4. The intelligent analysis and processing system for potential disease risks based on epidemic big data according to claim 3 is characterized by: The driving analysis module includes a driving feature generation unit and a driving sample library unit; The driving feature generating unit generates a time data cluster FTD based on the pathological early stage symptom generation time data cluster STD based on the pathological late stage symptom generation time data cluster at the time node Identify the time point when the initial symptoms of the pathology occur And lock the medical records of climate-related diseases , identify the time point when symptoms of late pathology occur And lock the medical records of climate-related diseases ; Based on the disease type data cluster AD and the meteorological induction factor data cluster FD, the locked climatic disease records , respectively capture the type of disease and meteorological factors , and the history of climatic diseases Additional feature driver tags, denoted as If we can capture the type of disease and meteorological factors , then let the feature drive label , otherwise let the feature drive the label ; The driving sample library unit, based on the capture behavior, at the time node Under the following conditions, the pathological early stage sample sets are generated respectively and pathological late stage sample set , including: If we identify the time point when the initial symptoms of the pathology occur And locked climate disease records , then the feature-driven label Recorded in the early pathology sample set In; if by identifying the time point when the symptoms of late pathology occur And locked climate disease records , then the feature-driven label Included in the pathology late stage sample set middle.

5. The intelligent analysis and processing system for potential disease risks based on epidemic big data according to claim 4 is characterized by: The driving feature matrix carrier module includes an epidemic big data model matrix unit and a matrix mapping unit; The disease big data model matrix unit is used to establish the disease big data model matrix, which is recorded as RR(N×I), where N×I means that the disease big data model matrix has N rows and I columns, and the feature-driven label As the matrix element corresponding to the nth row and the ith column; based on the epidemic big data model matrix, the early pathology feature matrix FS[RR(N×I)] and the late pathology feature matrix SS[RR(N×I)] are established respectively; The matrix mapping unit is used to respectively map the pathological early stage sample set and pathological late stage sample set Mapped to the pathological early stage feature matrix FS[RR(N×I)] and the pathological late stage feature matrix SS[RR(N×I)] in sequence, the attached time nodes are obtained respectively Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix :SS[RR(N×I)].

6. The intelligent analysis and processing system for disease risk based on epidemic big data according to claim 5 is characterized by: The disease risk assessment and analysis module includes a correlation coefficient analysis unit and a risk warning unit; The correlation coefficient analysis unit is based on the time node Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix : SS[RR(N×I)], evaluates the temporal correlation coefficient between the early and late stages of pathology, as follows: ； In the formula, Indicates at time node When the time correlation coefficient between the early stage of pathology and the late stage of pathology is Indicates the attached time node Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix : The number of 1s contained in the result of the Boolean intersection operation between SS[RR(N×I)], Indicates the attached time node Matrix of marked pathological early features :FS[RR(N×I)] and pathological late stage feature matrix : The number of 1s contained in the result of the Boolean union operation between SS[RR(N×I)]; The hidden danger warning unit presets a correlation coefficient threshold value. If the time correlation coefficient If it is greater than or equal to the correlation coefficient threshold, it means that at the time node There is a relationship between the early and late stages of pathology and the potential risk of disease progression at the time node. Issue an early warning prompt.

Images