CN112669984A - Infectious disease cooperative progressive monitoring and early warning coping method based on big data artificial intelligence - Google Patents
Infectious disease cooperative progressive monitoring and early warning coping method based on big data artificial intelligence Download PDFInfo
- Publication number
- CN112669984A CN112669984A CN202011627022.2A CN202011627022A CN112669984A CN 112669984 A CN112669984 A CN 112669984A CN 202011627022 A CN202011627022 A CN 202011627022A CN 112669984 A CN112669984 A CN 112669984A
- Authority
- CN
- China
- Prior art keywords
- early warning
- platform
- infectious disease
- data
- monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 208000035473 Communicable disease Diseases 0.000 title claims abstract description 213
- 208000015181 infectious disease Diseases 0.000 title claims abstract description 190
- 238000012544 monitoring process Methods 0.000 title claims abstract description 179
- 238000000034 method Methods 0.000 title claims abstract description 52
- 230000000750 progressive effect Effects 0.000 title claims abstract description 33
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 24
- 230000010485 coping Effects 0.000 title claims description 59
- 238000012549 training Methods 0.000 claims abstract description 74
- 230000004044 response Effects 0.000 claims abstract description 29
- 238000012790 confirmation Methods 0.000 claims description 32
- 238000003062 neural network model Methods 0.000 claims description 27
- 230000008859 change Effects 0.000 claims description 25
- 238000005065 mining Methods 0.000 claims description 23
- 238000005728 strengthening Methods 0.000 claims description 23
- 238000013135 deep learning Methods 0.000 claims description 12
- 238000010801 machine learning Methods 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 10
- 230000036541 health Effects 0.000 claims description 9
- 230000008520 organization Effects 0.000 claims description 9
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 claims description 6
- 208000024891 symptom Diseases 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 230000002776 aggregation Effects 0.000 claims 2
- 238000004220 aggregation Methods 0.000 claims 2
- 238000013528 artificial neural network Methods 0.000 claims 1
- 238000007418 data mining Methods 0.000 claims 1
- 238000000605 extraction Methods 0.000 claims 1
- 238000007689 inspection Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 10
- 238000011161 development Methods 0.000 description 7
- 238000003745 diagnosis Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 4
- 230000002787 reinforcement Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000009024 positive feedback mechanism Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
基于大数据人工智能的传染病协同递进监测预警应对方法，包括：传染病获取步骤；传染病监测步骤；用户预警步骤；部门预警步骤；数据更新步骤；应对跟踪步骤；监测强化训练步骤；个人预警强化训练步骤；部门预警强化训练步骤。上述方法、系统和机器人，将监测平台、预警平台、应对平台之间的信息对接起来，使得相互之间可以互通有无，相互印证和促进，使得监测平台可以根据应对平台的结果反馈进行监测平台的预测模型的强化训练，来逐步提高监测平台的预测模型的预测准确率，同时，根据应对平台的结果反馈进行预警平台的预警模型的强化训练，来逐步提高预警的效果。
A collaborative progressive monitoring and early warning response method for infectious diseases based on big data artificial intelligence, including: infectious disease acquisition step; infectious disease monitoring step; user early warning step; department early warning step; data update step; response tracking step; monitoring intensive training step; individual Early warning intensive training steps; department early warning intensive training steps. The above methods, systems and robots connect the information between the monitoring platform, the early warning platform, and the response platform, so that they can communicate with each other, confirm and promote each other, so that the monitoring platform can monitor the platform according to the feedback of the response platform. To gradually improve the prediction accuracy of the prediction model of the monitoring platform, at the same time, according to the feedback of the results of the response platform, strengthen the training of the early warning model of the early warning platform to gradually improve the effect of the early warning.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an infectious disease cooperative progressive monitoring and early warning coping method based on big data artificial intelligence.
Background
In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art: in the prior art, the monitoring, early warning and coping of the new major infectious diseases are inseparable links, but in the practical operation process, particularly under the condition of serious illness state of the new major infectious diseases, the three links of monitoring, early warning and coping are always disconnected, and each department is easily disconnected with each other.
Accordingly, the prior art is yet to be improved and developed.
Disclosure of Invention
Based on the above, it is necessary to provide a cooperative progressive infectious disease monitoring and early warning coping method based on big data artificial intelligence to solve the problem that the three links of monitoring, early warning and coping are disjointed in the prior art, aiming at the defects or shortcomings in the prior art.
In a first aspect, an embodiment of the present invention provides an artificial intelligence method, where the method includes:
an infectious disease acquisition step: acquiring infectious diseases to be monitored through a monitoring platform to serve as target infectious diseases;
infectious disease monitoring: acquiring user information suspected of infecting the target infectious disease through a monitoring platform; the user information suspected of infecting the target infectious disease comprises the identity of the user or/and the severity of symptoms or/and the credibility of the monitoring result; sending user information suspected of being infected with the target infectious disease to an early warning platform;
a user early warning step: analyzing whether a user needs to be pre-warned or not according to the user information suspected to be infected with the target infectious disease through the pre-warning platform, and if the user needs to be pre-warned, sending pre-warning information through the pre-warning platform to suggest the user suspected to be infected with the target infectious disease to go to a hospital for examination;
department early warning step: analyzing whether a department needs to be early-warned or not according to the user information suspected to be infected with the target infectious disease through the early-warning platform, and if the department needs to be early-warned, sending early-warning information through the early-warning platform to inform the relevant department of the location of the user suspected to be infected with the target infectious disease to track;
and a data updating step: updating infectious disease monitoring statistical data of all levels of departments through the monitoring platform;
a coping tracking step: acquiring a corresponding result generated after the user and each level department take corresponding measures through the corresponding platform, and feeding the result back to the monitoring platform and the early warning platform;
monitoring and strengthening training: the monitoring platform performs reinforced training on a prediction model in the monitoring platform according to the result feedback of the corresponding platform;
the personal early warning strengthening training step: the early warning platform performs reinforced training on the personal early warning model in the early warning platform according to the result feedback of the response platform;
department early warning strengthening training: and the early warning platform performs reinforced training on the department early warning model in the early warning platform according to the result feedback of the response platform.
Preferably, the coping tracking step specifically includes:
the method comprises the steps that a result of a hospital examination of a user suspected to be infected with a target infectious disease is obtained through a corresponding platform, if the result is that the user suspected to be infected with the target infectious disease is diagnosed, confirmation information of a monitoring result of the user suspected to be infected with the target infectious disease is sent to a monitoring platform, and confirmation information of early warning of the user suspected to be infected with the target infectious disease is sent to an early warning platform; and if the result is that the target infectious disease is not infected, transmitting the denial information of the user monitoring result suspected to be infected with the target infectious disease to the monitoring platform, and transmitting the denial information of the early warning of the user suspected to be infected with the target infectious disease to the early warning platform.
Preferably, the monitoring reinforcement training step specifically includes:
the data of the user who confirms the diagnosis of the infection of the target infectious disease and the confirmation of the infection of the target infectious disease contained in the confirmation information are taken as input and expected output through the monitoring platform, and the infectious disease prediction model in the monitoring platform is subjected to supervised training; carrying out supervised training on an infectious disease prediction model in the monitoring platform by using the data of the user for confirming that the infectious disease is not infected and the data of the user for confirming that the infectious disease is not infected, which are contained in the denial information, as input and expected output through the monitoring platform; the infectious disease prediction model comprises a deep learning neural network model or a convolutional neural network model or other neural network models or machine learning models.
Preferably, the first and second electrodes are formed of a metal,
the personal early warning strengthening training steps specifically comprise: the data of the user who confirms the diagnosis of the target infectious disease and the data which confirm that the user needs to be early-warned are input and expected output through the early-warning platform, and the early-warning platform carries out supervised training on an infectious disease individual early-warning model in the early-warning platform; the early warning platform is used for carrying out supervised training on an infectious disease individual early warning model in the early warning platform by confirming the data of the user who confirms that the infectious disease target is not infected and contained in the denial information and confirming that the early warning of the user is not needed to be carried out as input and expected output; the infectious disease personal early warning model comprises a deep learning neural network model or a convolution neural network model or other neural network models or machine learning models;
the department early warning strengthening training step specifically comprises the following steps: if the early warning platform receives confirmation information of early warning of users suspected to be infected with the target infectious disease, which belong to the same department, and exceed a preset number in a preset continuous time, the data and the confirmation of the users suspected to be infected with the target infectious disease in the preset continuous time need to be used for early warning of the department as input and expected output to carry out supervised training on an infectious disease department early warning model in the early warning platform; if the early warning platform does not receive confirmation information of early warning of users suspected to be infected with the target infectious disease and belonging to the same department, wherein the number of the users suspected to be infected with the target infectious disease exceeds a preset number within a preset continuous time, the data and the confirmation of the users within the preset continuous time are not needed to be used for early warning of the department as input and expected output to carry out supervised training on an infectious disease department early warning model in the early warning platform; the early warning model of the department of infectious diseases comprises a deep learning neural network model or a convolutional neural network model or other neural network models or machine learning models.
Preferably, the method further comprises:
adjusting a medical early warning threshold value: acquiring information whether resources are in shortage in a coping process within a latest preset time length through the coping platform, and if so, improving a threshold value of personal medical warning of a user through the early warning platform; if not, reducing the threshold value of the individual medical early warning of the user through the early warning platform;
personalized early warning step: if the early warning is needed to be carried out on the user according to the analysis of the user information suspected to be infected with the target infectious disease through the early warning platform, but the medical early warning threshold value is not reached, the user is recommended to isolate at home or treat at home; if the early warning is needed to be carried out on the user according to the analysis of the user information suspected to be infected with the target infectious disease through the early warning platform and the medical early warning threshold value is reached, the user is recommended to go to a hospital for examination and treatment;
a data change detection step: and setting change mark fields on the monitoring platform, the early warning platform and the coping platform respectively, and detecting the change of data corresponding to the change mark fields by each platform through detecting the change mark fields of the platform and other platforms.
Preferably, the method further comprises:
step-by-step progressive monitoring: summarizing or updating data layer by layer upwards through a monitoring platform according to the hierarchical relationship and the jurisdiction range of individuals, family members and different departments, counting, summarizing, analyzing and excavating key feature data of each layer through a big data technology on each layer, and sending the key feature data to the individuals, the family members or all levels of departments corresponding to each layer;
and (3) carrying out progressive early warning step layer by layer: determining whether to send early warning information and the content of sending the early warning information to corresponding individuals, family members and all levels of departments according to the key characteristic data of the individuals, the family members and different departments through the early warning platform according to the hierarchical relationship and the jurisdiction range of the individuals and different departments;
step-by-step coping steps: recommending different coping suggestions to corresponding individuals and different departments through the coping platform according to the hierarchical relationship and the jurisdiction range of the individuals and different departments and according to key feature data of the individuals, family members and the different departments;
a local increment updating step: when monitoring data, early warning data and coping data are updated and data of individuals and different departments are changed, each layer only needs to send the changed part to a higher layer for updating.
Preferably, the step of layer-by-layer progressive monitoring specifically comprises:
by adopting a large data multilayer MAP-REDUCE mode to gather or update by a monitoring platform, firstly mining and extracting key characteristic data of user monitoring data, then gathering or updating each user monitoring data to a department or community where the user is located, mining and extracting key characteristic data of the department or community, then gathering or updating each department or community data to each city area, mining and extracting key characteristic data of the city area, gathering or updating each city area data to each city, mining and extracting key characteristic data of the city, then gathering or updating each city area data to each province, mining and extracting key characteristic data of the country, even summarizing or updating the data of each country to the international health organization, and mining and extracting the key characteristic data of the international health organization.
In a second aspect, an embodiment of the present invention provides an artificial intelligence system, where the system includes:
an infectious disease acquisition module: acquiring infectious diseases to be monitored through a monitoring platform to serve as target infectious diseases;
an infectious disease monitoring module: acquiring user information suspected of infecting the target infectious disease through a monitoring platform; the user information suspected of infecting the target infectious disease comprises the identity of the user or/and the severity of symptoms or/and the credibility of the monitoring result; sending user information suspected of being infected with the target infectious disease to an early warning platform;
the user early warning module: analyzing whether a user needs to be pre-warned or not according to the user information suspected to be infected with the target infectious disease through the pre-warning platform, and if the user needs to be pre-warned, sending pre-warning information through the pre-warning platform to suggest the user suspected to be infected with the target infectious disease to go to a hospital for examination;
department early warning module: analyzing whether a department needs to be early-warned or not according to the user information suspected to be infected with the target infectious disease through the early-warning platform, and if the department needs to be early-warned, sending early-warning information through the early-warning platform to inform the relevant department of the location of the user suspected to be infected with the target infectious disease to track;
a data updating module: updating infectious disease monitoring statistical data of all levels of departments through the monitoring platform;
a coping tracking module: acquiring a corresponding result generated after the user and each level department take corresponding measures through the corresponding platform, and feeding the result back to the monitoring platform and the early warning platform;
the monitoring and strengthening training module: the monitoring platform performs reinforced training on a prediction model in the monitoring platform according to the result feedback of the corresponding platform;
the personal early warning strengthening training module: the early warning platform performs reinforced training on the personal early warning model in the early warning platform according to the result feedback of the response platform;
department early warning strengthening training module: and the early warning platform performs reinforced training on the department early warning model in the early warning platform according to the result feedback of the response platform.
Preferably, the coping tracking module specifically includes:
the method comprises the steps that a result of a hospital examination of a user suspected to be infected with a target infectious disease is obtained through a corresponding platform, if the result is that the user suspected to be infected with the target infectious disease is diagnosed, confirmation information of a monitoring result of the user suspected to be infected with the target infectious disease is sent to a monitoring platform, and confirmation information of early warning of the user suspected to be infected with the target infectious disease is sent to an early warning platform; and if the result is that the target infectious disease is not infected, transmitting the denial information of the user monitoring result suspected to be infected with the target infectious disease to the monitoring platform, and transmitting the denial information of the early warning of the user suspected to be infected with the target infectious disease to the early warning platform.
Preferably, the monitoring reinforcement training module specifically includes:
the data of the user who confirms the diagnosis of the infection of the target infectious disease and the confirmation of the infection of the target infectious disease contained in the confirmation information are taken as input and expected output through the monitoring platform, and the infectious disease prediction model in the monitoring platform is subjected to supervised training; carrying out supervised training on an infectious disease prediction model in the monitoring platform by using the data of the user for confirming that the infectious disease is not infected and the data of the user for confirming that the infectious disease is not infected, which are contained in the denial information, as input and expected output through the monitoring platform; the infectious disease prediction model comprises a deep learning neural network model or a convolutional neural network model or other neural network models or machine learning models.
Preferably, the first and second electrodes are formed of a metal,
the personal early warning strengthening training module specifically comprises: the data of the user who confirms the diagnosis of the target infectious disease and the data which confirm that the user needs to be early-warned are input and expected output through the early-warning platform, and the early-warning platform carries out supervised training on an infectious disease individual early-warning model in the early-warning platform; the early warning platform is used for carrying out supervised training on an infectious disease individual early warning model in the early warning platform by confirming the data of the user who confirms that the infectious disease target is not infected and contained in the denial information and confirming that the early warning of the user is not needed to be carried out as input and expected output; the infectious disease personal early warning model comprises a deep learning neural network model or a convolution neural network model or other neural network models or machine learning models;
the department early warning strengthening training module specifically comprises: if the early warning platform receives confirmation information of early warning of users suspected to be infected with the target infectious disease, which belong to the same department, and exceed a preset number in a preset continuous time, the data and the confirmation of the users suspected to be infected with the target infectious disease in the preset continuous time need to be used for early warning of the department as input and expected output to carry out supervised training on an infectious disease department early warning model in the early warning platform; if the early warning platform does not receive confirmation information of early warning of users suspected to be infected with the target infectious disease and belonging to the same department, wherein the number of the users suspected to be infected with the target infectious disease exceeds a preset number within a preset continuous time, the data and the confirmation of the users within the preset continuous time are not needed to be used for early warning of the department as input and expected output to carry out supervised training on an infectious disease department early warning model in the early warning platform; the early warning model of the department of infectious diseases comprises a deep learning neural network model or a convolutional neural network model or other neural network models or machine learning models.
Preferably, the system further comprises:
hospitalizing early warning threshold value adjusting module: acquiring information whether resources are in shortage in a coping process within a latest preset time length through the coping platform, and if so, improving a threshold value of personal medical warning of a user through the early warning platform; if not, reducing the threshold value of the individual medical early warning of the user through the early warning platform;
individualized early warning module: if the early warning is needed to be carried out on the user according to the analysis of the user information suspected to be infected with the target infectious disease through the early warning platform, but the medical early warning threshold value is not reached, the user is recommended to isolate at home or treat at home; if the early warning is needed to be carried out on the user according to the analysis of the user information suspected to be infected with the target infectious disease through the early warning platform and the medical early warning threshold value is reached, the user is recommended to go to a hospital for examination and treatment;
a data change detection module: and setting change mark fields on the monitoring platform, the early warning platform and the coping platform respectively, and detecting the change of data corresponding to the change mark fields by each platform through detecting the change mark fields of the platform and other platforms.
Preferably, the system further comprises:
a layer-by-layer progressive monitoring module: summarizing or updating data layer by layer upwards through a monitoring platform according to the hierarchical relationship and the jurisdiction range of individuals, family members and different departments, counting, summarizing, analyzing and excavating key feature data of each layer through a big data technology on each layer, and sending the key feature data to the individuals, the family members or all levels of departments corresponding to each layer;
the layer-by-layer progressive early warning module: determining whether to send early warning information and the content of sending the early warning information to corresponding individuals, family members and all levels of departments according to the key characteristic data of the individuals, the family members and different departments through the early warning platform according to the hierarchical relationship and the jurisdiction range of the individuals and different departments;
the coping modules are gradually carried out layer by layer: recommending different coping suggestions to corresponding individuals and different departments through the coping platform according to the hierarchical relationship and the jurisdiction range of the individuals and different departments and according to key feature data of the individuals, family members and the different departments;
a local incremental update module: when monitoring data, early warning data and coping data are updated and data of individuals and different departments are changed, each layer only needs to send the changed part to a higher layer for updating.
Preferably, the layer-by-layer progressive monitoring module specifically includes:
by adopting a large data multilayer MAP-REDUCE mode to gather or update by a monitoring platform, firstly mining and extracting key characteristic data of user monitoring data, then gathering or updating each user monitoring data to a department or community where the user is located, mining and extracting key characteristic data of the department or community, then gathering or updating each department or community data to each city area, mining and extracting key characteristic data of the city area, gathering or updating each city area data to each city, mining and extracting key characteristic data of the city, then gathering or updating each city area data to each province, mining and extracting key characteristic data of the country, even summarizing or updating the data of each country to the international health organization, and mining and extracting the key characteristic data of the international health organization.
In a third aspect, an embodiment of the present invention provides an artificial intelligence apparatus, where the apparatus includes the modules of the system in any one of the embodiments of the second aspect.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method according to any one of the embodiments of the first aspect.
In a fifth aspect, an embodiment of the present invention provides a robot, including a memory, a processor, and an artificial intelligence robot program stored in the memory and executable on the processor, where the processor executes the program to implement the steps of the method according to any one of the embodiments of the first aspect.
The infectious disease collaborative progressive monitoring and early warning coping method based on big data artificial intelligence provided by the embodiment comprises the following steps: an infectious disease acquisition step; an infectious disease monitoring step; a user early warning step; a department early warning step; a data updating step; a coping tracking step; monitoring and strengthening training; a personal early warning strengthening training step; and (5) performing early warning and strengthening training by departments. According to the method, the system and the robot, information among the monitoring platform, the early warning platform and the corresponding platform is connected, so that the monitoring platform can be communicated with or not, verified and promoted mutually, the monitoring platform can perform reinforced training on the prediction model of the monitoring platform according to result feedback of the corresponding platform, the prediction accuracy of the prediction model of the monitoring platform is gradually improved, and meanwhile, the reinforced training on the early warning model of the early warning platform is performed according to the result feedback of the corresponding platform, and the early warning effect is gradually improved.
Drawings
FIG. 1 is a flow chart of an artificial intelligence method provided by an embodiment of the invention;
FIG. 2 is a flow chart of an artificial intelligence method provided by an embodiment of the invention;
FIG. 3 is a flow chart of an artificial intelligence method provided by an embodiment of the invention;
FIG. 4 is a schematic diagram illustrating the monitoring, pre-warning, and dialectical development of infectious diseases according to an embodiment of the present invention;
fig. 5 is a schematic diagram of layer-by-layer progressive monitoring, early warning and coping of infectious diseases based on big data according to an embodiment of the present invention.
Detailed Description
The technical solutions in the examples of the present invention are described in detail below with reference to the embodiments of the present invention.
Basic embodiment of the invention
One embodiment of the present invention provides an artificial intelligence method, as shown in fig. 1, the method including: an infectious disease acquisition step; an infectious disease monitoring step; a user early warning step; a department early warning step; a data updating step; a coping tracking step; monitoring and strengthening training; a personal early warning strengthening training step; and (5) performing early warning and strengthening training by departments. The technical effects are as follows: the method comprises the steps of butting information among a monitoring platform, an early warning platform and a corresponding platform, so that the monitoring platform can be communicated with each other, and the information is mutually verified and promoted, so that the monitoring platform can perform reinforced training on a prediction model of the monitoring platform according to result feedback of the corresponding platform, the prediction accuracy of the prediction model of the monitoring platform is gradually improved, and meanwhile, the reinforced training on the early warning model of the early warning platform is performed according to the result feedback of the corresponding platform, and the early warning effect is gradually improved.
Preferably, as shown in fig. 2, the method further comprises: adjusting a medical early warning threshold; personalized early warning; and a data change detection step. The technical effects are as follows: the method determines whether to isolate treatment at home or visit a hospital according to the early warning threshold value, so that the pressure of medical resources can be relieved.
Preferably, as shown in fig. 3, the method further comprises: monitoring layer by layer; carrying out early warning step by step; step of layer-by-layer progressive coping; and updating the local increment. The technical effects are as follows: according to the method, the monitoring, early warning and coping efficiency can be greatly improved in a layer-by-layer progressive mode, all levels of areas can be fully covered, each sub-area can be narrowed down, overall control can be achieved, incremental updating can be achieved, repeated calculation is avoided, calculation resources are saved, and the real-time performance and timeliness of monitoring, early warning and coping can be greatly improved.
PREFERRED EMBODIMENTS OF THE PRESENT INVENTION
An infectious disease acquisition step: acquiring infectious diseases to be monitored through a monitoring platform to serve as target infectious diseases;
infectious disease monitoring: acquiring user information suspected of infecting the target infectious disease through a monitoring platform; the user information suspected of infecting the target infectious disease comprises the identity of the user or/and the severity of symptoms or/and the credibility of the monitoring result; sending user information suspected of being infected with the target infectious disease to an early warning platform;
a user early warning step: analyzing whether a user needs to be pre-warned or not according to the user information suspected to be infected with the target infectious disease through the pre-warning platform, and if the user needs to be pre-warned, sending pre-warning information through the pre-warning platform to suggest the user suspected to be infected with the target infectious disease to go to a hospital for examination;
department early warning step: analyzing whether a department needs to be early-warned or not according to the user information suspected to be infected with the target infectious disease through the early-warning platform, and if the department needs to be early-warned, sending early-warning information through the early-warning platform to inform the relevant department of the location of the user suspected to be infected with the target infectious disease to track;
and a data updating step: updating infectious disease monitoring statistical data of all levels of departments through the monitoring platform;
a coping tracking step: acquiring a corresponding result generated after the user and each level department take corresponding measures through the corresponding platform, and feeding the result back to the monitoring platform and the early warning platform;
the coping tracking step specifically comprises: the method comprises the steps that a result of a hospital examination of a user suspected to be infected with a target infectious disease is obtained through a corresponding platform, if the result is that the user suspected to be infected with the target infectious disease is diagnosed, confirmation information of a monitoring result of the user suspected to be infected with the target infectious disease is sent to a monitoring platform, and confirmation information of early warning of the user suspected to be infected with the target infectious disease is sent to an early warning platform; if the result is that the target infectious disease is confirmed to be not infected, sending the denial information of the user monitoring result suspected to be infected with the target infectious disease to the monitoring platform, and sending the denial information of the early warning of the user suspected to be infected with the target infectious disease to the early warning platform;
monitoring and strengthening training: the monitoring platform performs reinforced training on a prediction model in the monitoring platform according to the result feedback of the corresponding platform;
the monitoring and strengthening training step specifically comprises the following steps: the data of the user who confirms the diagnosis of the infection of the target infectious disease and the confirmation of the infection of the target infectious disease contained in the confirmation information are taken as input and expected output through the monitoring platform, and the infectious disease prediction model in the monitoring platform is subjected to supervised training; carrying out supervised training on an infectious disease prediction model in the monitoring platform by using the data of the user for confirming that the infectious disease is not infected and the data of the user for confirming that the infectious disease is not infected, which are contained in the denial information, as input and expected output through the monitoring platform; the infectious disease prediction model comprises a deep learning neural network model or a convolution neural network model or other neural network models or machine learning models;
the personal early warning strengthening training step: the early warning platform performs reinforced training on the personal early warning model in the early warning platform according to the result feedback of the response platform;
department early warning strengthening training: the early warning platform performs reinforced training on a department early warning model in the early warning platform according to the result feedback of the response platform;
the personal early warning strengthening training steps specifically comprise: the data of the user who confirms the diagnosis of the target infectious disease and the data which confirm that the user needs to be early-warned are input and expected output through the early-warning platform, and the early-warning platform carries out supervised training on an infectious disease individual early-warning model in the early-warning platform; the early warning platform is used for carrying out supervised training on an infectious disease individual early warning model in the early warning platform by confirming the data of the user who confirms that the infectious disease target is not infected and contained in the denial information and confirming that the early warning of the user is not needed to be carried out as input and expected output; the infectious disease personal early warning model comprises a deep learning neural network model or a convolution neural network model or other neural network models or machine learning models;
the department early warning strengthening training step specifically comprises the following steps: if the early warning platform receives confirmation information of early warning of users suspected to be infected with the target infectious disease, which belong to the same department, and exceed a preset number in a preset continuous time, the data and the confirmation of the users suspected to be infected with the target infectious disease in the preset continuous time need to be used for early warning of the department as input and expected output to carry out supervised training on an infectious disease department early warning model in the early warning platform; if the early warning platform does not receive confirmation information of early warning of users suspected to be infected with the target infectious disease and belonging to the same department, wherein the number of the users suspected to be infected with the target infectious disease exceeds a preset number within a preset continuous time, the data and the confirmation of the users within the preset continuous time are not needed to be used for early warning of the department as input and expected output to carry out supervised training on an infectious disease department early warning model in the early warning platform; the early warning model of the infectious disease department comprises a deep learning neural network model or a convolutional neural network model or other neural network models or a machine learning model;
adjusting a medical early warning threshold value: acquiring information whether resources are in shortage in a coping process within a latest preset time length through the coping platform, and if so, improving a threshold value of personal medical warning of a user through the early warning platform; if not, reducing the threshold value of the individual medical early warning of the user through the early warning platform;
personalized early warning step: if the early warning is needed to be carried out on the user according to the analysis of the user information suspected to be infected with the target infectious disease through the early warning platform, but the medical early warning threshold value is not reached, the user is recommended to isolate at home or treat at home; if the early warning is needed to be carried out on the user according to the analysis of the user information suspected to be infected with the target infectious disease through the early warning platform and the medical early warning threshold value is reached, the user is recommended to go to a hospital for examination and treatment;
a data change detection step: and setting change mark fields on the monitoring platform, the early warning platform and the coping platform respectively, and detecting the change of data corresponding to the change mark fields by each platform through detecting the change mark fields of the platform and other platforms.
Step-by-step progressive monitoring: summarizing or updating data layer by layer upwards through a monitoring platform according to the hierarchical relationship and the jurisdiction range of individuals, family members and different departments, counting, summarizing, analyzing and excavating key feature data of each layer through a big data technology on each layer, and sending the key feature data to the individuals, the family members or all levels of departments corresponding to each layer;
the step of layer-by-layer progressive monitoring specifically comprises the following steps: by adopting a large data multilayer MAP-REDUCE mode to gather or update by a monitoring platform, firstly mining and extracting key characteristic data of user monitoring data, then gathering or updating each user monitoring data to a department or community where the user is located, mining and extracting key characteristic data of the department or community, then gathering or updating each department or community data to each city area, mining and extracting key characteristic data of the city area, gathering or updating each city area data to each city, mining and extracting key characteristic data of the city, then gathering or updating each city area data to each province, mining and extracting key characteristic data of the country, even summarizing or updating the data of each country to the international health organization, and mining and extracting key characteristic data of the international health organization;
and (3) carrying out progressive early warning step layer by layer: determining whether to send early warning information and the content of sending the early warning information to corresponding individuals, family members and all levels of departments according to the key characteristic data of the individuals, the family members and different departments through the early warning platform according to the hierarchical relationship and the jurisdiction range of the individuals and different departments;
step-by-step coping steps: different coping suggestions are recommended to corresponding individuals and different departments through the coping platform according to the hierarchical relationship and the jurisdiction range of the individuals and different departments and according to key feature data of the individuals, family members and the different departments.
A local increment updating step: when monitoring data, early warning data and coping data are updated and data of individuals and different departments are changed, each layer only needs to send the changed part to a higher layer for updating.
Other embodiments of the invention
The monitoring, early warning and coping of the new serious infectious diseases are inseparable links, but in the practical operation process, especially under the condition of serious infectious disease state shortage, the three links of monitoring, early warning and coping are easy to be disconnected, and each department is easy to be divided into political departments and disconnected with each other, how to prevent the disconnection? The three stages of dialectical development in philosophy are supposed to be utilized in the embodiment, and the three stages are mutually transformed, so that disjointing of the three stages can be avoided, and the three stages can be mutually used and mutually promoted. Meanwhile, according to the hierarchical relationship and the jurisdiction range of individuals and different departments, the various departments can perform their own functions and can be unified up and down through monitoring, early warning and coping layer by the big data technology.
Firstly, effective positive feedback and feedback are realized on the system level through a 'big data-based monitoring, early warning and dialectical development coordination mechanism for newly-discovered major infectious diseases', so that the system accuracy can be gradually improved along with the increase of big data, and a 'small week day' is opened. Then, the whole communication of 'monitoring, early warning and coping' is carried out layer by layer from three levels of time and space (time, space and user attributes) through a 'research scheme of layer by layer monitoring, early warning and coping of new major infectious diseases based on big data', and 'big day' is opened.
(1) Research scheme of' big data-based monitoring, early warning and dialectical development cooperative mechanism of new major infectious diseases
Monitoring, early warning and coping with dialectical development relations of three stages of newly-discovered major infectious diseases based on big data: the monitoring of new important infectious diseases based on big data belongs to the thinking stage of dialectical development, and the monitoring process is really a prediction without knowing whether infectious diseases exist at all, so the monitoring process belongs to the thinking stage. The monitoring result is used for early warning, and the early warning aims at demonstration and is prepared for response, so that the demonstration stage is entered. The early warning of the new major infectious disease based on the big data belongs to the demonstration stage of the new major infectious disease, and the demonstration stage is to remind a user and a related department to carry out demonstration and go to a hospital to check and see whether the infection is really caused, so that the user needs to deal with the infection and the user needs to enter the unified stage. The coping of the new major infectious disease based on the big data belongs to the unified stage of the new major infectious disease, and the final effect still needs to see whether the coping of the new major infectious disease based on the big data has the effect or not, so the stage is the stage of 'collecting officer', but the stage has poor effect and needs to be monitored by the monitoring stage, so the stage returns to the thinking stage. The three stages are mutually converted, so that the disjointing of the three stages can be avoided, and the three stages can be mutually used and mutually promoted. FIG. 4 shows the transformation scheme used.
The positive feedback and feedback mechanism among monitoring, early warning and coping of new major infectious diseases based on big data is as follows:
when a user is monitored to be possibly infected with a new major infectious disease, the early warning system suggests the user to go to a hospital for examination and informs local related departments to track, and meanwhile, the monitoring statistical data of the new major infectious disease of each level of department can be updated, so that each level of department can master the development condition of the new major infectious disease at any time, and the user and each level of department can generate a response result after taking response measures, for example, the user finds that the new major infectious disease is infected after going to the hospital for examination, the monitoring and early warning are correct, and the result needs to be fed back to the monitoring system and the early warning system to give a certain reward to the system for the reinforcement learning of a monitoring and early warning model; on the contrary, if the user finds that no new serious infectious disease is infected after going to the hospital for examination, the monitoring and early warning are wrong, and the bad result needs to be fed back to the monitoring system and the early warning system to give a certain penalty to the system for further reinforcement learning of the monitoring and early warning model.
Meanwhile, if the situation of resource shortage occurs in the process of coping with, the threshold value of early warning is also increased, so that medical resources and diagnosis and treatment capacity are balanced with the number of users receiving early warning, the increase of the threshold value of early warning does not mean that the early warning is not performed on the users, but means that personalized information of the early warning of the users is adjusted, for example, when the monitoring result is low risk, the users are originally recommended to go to a hospital, and the users are recommended to buy medicines for home treatment.
Monitoring, early warning, and coping with big data traffic and cooperation of new major infectious diseases: a big data-based monitoring system for the newly-sent major infectious disease, a big data-based early warning system for the newly-sent major infectious disease and a big data-based coping system for the newly-sent major infectious disease are developed based on an SPARK platform, compatible file systems, databases and knowledge base storage modes are provided, and mutual data transmission and result mutual use can be performed. Data related to other systems in one system can be provided with a change flag field, and other systems can detect the change of the system data by detecting the change flag field, so that the system pressure caused by frequent change detection can be greatly reduced for a large data system, and the data volume of the change detection is reduced. When the data cooperative processing and calculation of a plurality of systems are carried out, the data can be processed concurrently by adopting a MAP-REDUCE architecture, so that the processing speed is improved.
(2) Research scheme of' layer-by-layer progressive monitoring, early warning and coping for new major infectious diseases based on big data
The new major infectious disease is progressively monitored, early-warned and responded layer by layer based on big data: during early warning, monitoring information can not be sent to individuals or local departments, but key characteristic data are calculated, summarized, analyzed and mined out through a big data technology according to the hierarchical relationship and the administration range of the individuals and different departments and are sent to the individuals, the family members and all levels of departments in an individualized mode, namely, early warnings received by all levels of departments are different, and thousands of uniform early warning information cannot be received, and the thousands of uniform early warning information can cause all levels of departments to know the urgency of newly-developed serious infectious diseases in unclear administration ranges of the departments, so that the situation of newly-developed serious infectious diseases is disordered. After different early warnings are received by each layer of department and area, different corresponding measures can be taken layer by layer, and the well is well-ordered. Certainly, to realize layer-by-layer early warning, statistical data of regions and departments at each layer need to be obtained, so that layer-by-layer progressive monitoring needs to be carried out before layer-by-layer progressive early warning and coping. Fig. 5 shows a schematic diagram of layer-by-layer progressive monitoring, early warning and coping of new major infectious diseases based on big data.
The relationship of monitoring, early warning, monitoring and coping is gradually carried out layer by layer: the layer-by-layer progressive early warning of the new major infectious disease based on the big data is performed on the basis of the layer-by-layer progressive monitoring of the new major infectious disease, because if the layer-by-layer progressive monitoring of the new major infectious disease based on the big data is not available, the layer-by-layer progressive early warning of the new major infectious disease based on the big data is not provided. Similarly, the purpose of layer-by-layer early warning of the new serious infectious disease based on the big data is to cope with the new serious infectious disease based on the big data layer by layer, and the three are mutually dependent. Of course, the layer-by-layer progressive monitoring of new major infectious diseases based on big data is the key and core, and layer-by-layer early warning and layer-by-layer coping can be performed after the layer-by-layer monitoring result is obtained, so a layer-by-layer monitoring research scheme is specifically provided below.
Layer-by-layer progressive monitoring of newly-developed major infectious diseases based on big data: the method adopts a large data multi-layer MAP-REDUCE progressive summary analysis mode, firstly, the monitoring data of each user is summarized to the department or community where the user is located, then the data of each department or community is summarized to each city area, then the data of each city area is summarized to each city, then the data of each city is summarized to each province, then the data of each province is summarized to the country, and even the data of each country is summarized to the international health organization. The process can greatly accelerate the timeliness of big data processing, can enable the department to which the user belongs to obtain related big data analysis monitoring data in the first time, and can update the big data analysis result of each superior department in real time instead of reporting one time a day, but the real-time updating is carried out to each layer, even if a big data processing mode is adopted, the calculated amount is very huge, so that an incremental mode is necessary to carry out hierarchical progression, and the process of updating layer by layer can be rapidly completed.
Layer-by-layer incremental monitoring of newly-developed major infectious diseases based on big data: because the layer progression is incremental, not recalculation or statistical analysis every time, for example, as long as the monitoring data of a user in a province changes, the changed data will firstly affect the statistical data of the department or community where the user is located, and then affect the statistical data of each higher-level region, and the individual effect will be transmitted to higher-level departments and regions step by step, so that only the data of each level needs to be corrected according to the influence without performing big data statistics and analysis again, and the result is basically consistent. In order to improve the accuracy, all the data at each stage may be summarized again after a period of time, for example, one day, to be compared with the incrementally summarized data, so that on one hand, the correctness of the incrementally summarized result may be verified, and on the other hand, if the incrementally summarized data result has an input or an output, the correction may also be performed.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for those skilled in the art, various changes and modifications can be made without departing from the spirit of the present invention, and these changes and modifications are within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011627022.2A CN112669984B (en) | 2020-12-30 | 2020-12-30 | Infectious disease collaborative progressive monitoring and early warning response method based on big data artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011627022.2A CN112669984B (en) | 2020-12-30 | 2020-12-30 | Infectious disease collaborative progressive monitoring and early warning response method based on big data artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112669984A true CN112669984A (en) | 2021-04-16 |
| CN112669984B CN112669984B (en) | 2023-09-12 |
Family
ID=75412521
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011627022.2A Active CN112669984B (en) | 2020-12-30 | 2020-12-30 | Infectious disease collaborative progressive monitoring and early warning response method based on big data artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112669984B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113409952A (en) * | 2021-08-20 | 2021-09-17 | 苏州市疾病预防控制中心 | Infectious disease monitoring, prevention and control system and method under multi-point trigger view angle |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102202072A (en) * | 2010-03-23 | 2011-09-28 | 盛霆信息技术(上海)有限公司 | Unidirectional synchronization method of internet website data |
| CN105938492A (en) * | 2016-04-14 | 2016-09-14 | 北京思特奇信息技术股份有限公司 | Data synchronization increment tracking method and system |
| CN106355035A (en) * | 2016-09-28 | 2017-01-25 | 湖南老码信息科技有限责任公司 | Pneumonia prediction method and prediction system based on incremental neural network model |
| CN106933882A (en) * | 2015-12-31 | 2017-07-07 | 华为技术有限公司 | A kind of big data incremental calculation method and device |
| WO2019196281A1 (en) * | 2018-04-11 | 2019-10-17 | 平安科技（深圳）有限公司 | Epidemic grading and prediction method and apparatus, computer apparatus, and readable storage medium |
| CN111899893A (en) * | 2020-09-29 | 2020-11-06 | 南京汉卫公共卫生研究院有限公司 | Infectious disease early warning decision platform system |
| CN112000649A (en) * | 2020-07-07 | 2020-11-27 | 武汉达梦数据库有限公司 | Incremental data synchronization method and device based on map reduce |
| CN112115580A (en) * | 2020-08-12 | 2020-12-22 | 科技谷（厦门）信息技术有限公司 | Big data-based newly-released major infectious disease monitoring, early warning and coping system |
-
2020
- 2020-12-30 CN CN202011627022.2A patent/CN112669984B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102202072A (en) * | 2010-03-23 | 2011-09-28 | 盛霆信息技术(上海)有限公司 | Unidirectional synchronization method of internet website data |
| CN106933882A (en) * | 2015-12-31 | 2017-07-07 | 华为技术有限公司 | A kind of big data incremental calculation method and device |
| CN105938492A (en) * | 2016-04-14 | 2016-09-14 | 北京思特奇信息技术股份有限公司 | Data synchronization increment tracking method and system |
| CN106355035A (en) * | 2016-09-28 | 2017-01-25 | 湖南老码信息科技有限责任公司 | Pneumonia prediction method and prediction system based on incremental neural network model |
| WO2019196281A1 (en) * | 2018-04-11 | 2019-10-17 | 平安科技（深圳）有限公司 | Epidemic grading and prediction method and apparatus, computer apparatus, and readable storage medium |
| CN112000649A (en) * | 2020-07-07 | 2020-11-27 | 武汉达梦数据库有限公司 | Incremental data synchronization method and device based on map reduce |
| CN112115580A (en) * | 2020-08-12 | 2020-12-22 | 科技谷（厦门）信息技术有限公司 | Big data-based newly-released major infectious disease monitoring, early warning and coping system |
| CN111899893A (en) * | 2020-09-29 | 2020-11-06 | 南京汉卫公共卫生研究院有限公司 | Infectious disease early warning decision platform system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113409952A (en) * | 2021-08-20 | 2021-09-17 | 苏州市疾病预防控制中心 | Infectious disease monitoring, prevention and control system and method under multi-point trigger view angle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112669984B (en) | 2023-09-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Abdel-Basset et al. | RETRACTED: A novel and powerful framework based on neutrosophic sets to aid patients with cancer | |
| CN117457147B (en) | Personalized nursing planning method and system for rehabilitation patient | |
| CN106845147B (en) | Method for building up, the device of medical practice summary model | |
| CN105162880B (en) | The aid decision-making method of the collaborative treatment of a kind of ACS compartmentalization network | |
| CN116364299A (en) | A method and system for clustering disease diagnosis and treatment paths based on heterogeneous information network | |
| CN107463774A (en) | Analysis on the health status Forecasting Methodology and system based on big data | |
| CN112331349B (en) | Cerebral apoplexy relapse monitoring system | |
| CN117877763B (en) | Nursing communication system and method based on smart wristband | |
| CN113315752B (en) | Intelligent medical attack tracing method based on block chain and medical big data system | |
| CN118230977B (en) | Rehabilitation auxiliary management system in intelligent medical treatment | |
| KR102506643B1 (en) | Patient information based medication management device and method | |
| CN112669984A (en) | Infectious disease cooperative progressive monitoring and early warning coping method based on big data artificial intelligence | |
| CN113192586A (en) | Intelligent medical file sharing method based on block chain and medical big data system | |
| CN109657907B (en) | Quality control method and device for geographical national condition monitoring data and terminal equipment | |
| US20220005566A1 (en) | Medical scan labeling system with ontology-based autocomplete and methods for use therewith | |
| CN109192312B (en) | A system and method for intelligent management of adverse events in patients with heart failure | |
| CN118299063A (en) | Cardiovascular and cerebrovascular disease information management system for rehabilitation assistance | |
| CN118072930A (en) | Hospital operation management system and method based on digital twinning | |
| CN115714016B (en) | Brucellosis screening rate improving method based on machine learning | |
| CN117594246A (en) | An automatic ICD encoding method and system for medical text based on graph attention | |
| Dev et al. | IoT and fog computing based prediction and monitoring system for stroke disease | |
| CN116324830A (en) | Decentralized training method suitable for disparate training sets | |
| CN114068036A (en) | Infection propagation prediction method and system based on Internet of things perception | |
| CN112216400A (en) | Method and system for predicting food-borne disease pathogenic factors based on big data | |
| CN113782216B (en) | Disabling weight determining method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |