CN112863685A - Infectious disease coping method based on big data artificial intelligence and robot - Google Patents

Infectious disease coping method based on big data artificial intelligence and robot Download PDF

Info

Publication number
CN112863685A
CN112863685A CN202011629860.3A CN202011629860A CN112863685A CN 112863685 A CN112863685 A CN 112863685A CN 202011629860 A CN202011629860 A CN 202011629860A CN 112863685 A CN112863685 A CN 112863685A
Authority
CN
China
Prior art keywords
user
infectious disease
region
early warning
target infectious
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
Application number
CN202011629860.3A
Other languages
Chinese (zh)
Other versions
CN112863685B (en
Inventor
朱定局
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
South China Normal University
Original Assignee
South China Normal University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by South China Normal University filed Critical South China Normal University
Priority to CN202011629860.3A priority Critical patent/CN112863685B/en
Publication of CN112863685A publication Critical patent/CN112863685A/en
Application granted granted Critical
Publication of CN112863685B publication Critical patent/CN112863685B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
    • 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

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Business, Economics & Management (AREA)
  • General Business, Economics & Management (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

Infectious disease coping method and robot based on big data artificial intelligence comprise the following steps: acquiring a target infectious disease; early warning and coping steps; an epidemic situation judgment step; a resource judgment step; judging the priority of the user; judging the state of the patient; cost handling steps; and (5) coping with an aging step. According to the method, the system and the robot, the early warning levels and the early warning threshold values of the regions and the users are carried out according to the conditions of the target infectious diseases, the medical resource conditions, the user priorities and the user conditions, so that personalized early warning can be adopted in different regions and different users, the coping cost is considered, coping schemes with different cost and different time effectiveness are adopted for early warning of different levels, and the coping schemes are more personalized and efficient.

Description

Infectious disease coping method based on big data artificial intelligence and robot
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an infectious disease coping method based on big data artificial intelligence and a robot.
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, in the aspect of dealing with new major infectious diseases, contradictions between protection resources such as masks, medical resources such as sickrooms and diagnosis and treatment requirements of people are difficult to solve.
Accordingly, the prior art is yet to be improved and developed.
Disclosure of Invention
Based on the above, it is necessary to provide an infectious disease coping method and a robot based on big data artificial intelligence to solve the problem in the prior art that the contradiction between the protection resources and the diagnosis and treatment requirements of people is difficult to solve, 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:
a step of acquiring a target infectious disease: acquiring infectious diseases to be dealt with as target infectious diseases;
early warning coping steps: acquiring the level of early warning, and determining the level of response according to the level of early warning;
an epidemic situation judging step: acquiring a target infectious disease condition of each region aiming at each region, setting the early warning level of each region as a preset higher level if the target infectious disease condition is serious, and adjusting the early warning threshold of each region to a preset lower threshold; if the target infectious disease condition is not serious, setting the early warning level of each region as a preset lower level, and adjusting the early warning threshold value of each region to a preset higher threshold value;
a resource judgment step: aiming at each region, acquiring the change of the medical resource condition of the target infectious disease of each region, and if the tension degree of the medical resource condition is increased, reducing the early warning level of each region and increasing the early warning threshold of each region; if the tension degree of the medical resource condition is reduced, improving the early warning level of each area, and reducing the early warning threshold value of each area;
a user priority judging step: acquiring information of each user aiming at each user, setting the early warning level of each user to be a preset higher level if the user bears important work tasks or belongs to a group with key cares, and adjusting the early warning threshold value of each user to be a preset lower threshold value; if the user does not undertake important work tasks and does not belong to the group of key careers, the early warning level of the area to which each user belongs is taken as the early warning level of each user, and the early warning threshold value of each user is adjusted to be the early warning threshold value of the area to which each user belongs; the people who pay special attention to the care include medical care personnel, pregnant women, the old and children;
judging the state of the patient: aiming at each user, acquiring the suspected infection target infectious disease degree of each user, if the suspected infection target infectious disease degree of each user is higher than a preset suspected degree threshold value, setting the early warning level of each user to be a preset higher level, and adjusting the early warning threshold value of each user to be a preset lower threshold value; if the suspected infection target infectious disease degree of the user is lower than a preset suspected degree threshold value, keeping the existing early warning level and early warning threshold value of each user;
cost coping steps: recommending coping schemes with different costs according to the early warning level;
the cost coping step specifically comprises the following steps: if the early warning level is high, recommending a coping scheme with high cost; if the early warning level is low, recommending a coping scheme with low cost;
and (3) coping aging step: recommending coping schemes with different timeliness according to the early warning level;
the aging treatment step specifically comprises: if the early warning level is higher, recommending a coping scheme with higher timeliness; and if the early warning level is low, recommending a coping scheme with low timeliness.
Preferably, the method further comprises:
the intelligent early warning coping step of the user: obtaining each user in a training sample, obtaining a target infectious disease state of an area to which each user belongs in the training sample, a change of a target infectious disease medical resource state of the area to which each user belongs in the training sample, information of each user in the training sample, and a suspected target infectious disease infection degree of each user in the training sample as input, obtaining an early warning suggestion and a coping suggestion corresponding to each user in the training sample as expected output, training a deep learning neural network model to obtain a user intelligent early warning coping deep learning neural network model, and taking the target infectious disease state of the area to which the user belongs, the change of the target infectious disease medical resource state of the area to which the user belongs, the information of the user, and the suspected target infectious disease infection degree of the user as input of the user intelligent early warning coping deep learning neural network model, the calculated output is an early warning suggestion and a corresponding suggestion corresponding to the user;
regional intelligent early warning coping steps: the method comprises the steps of obtaining each region in a training sample, obtaining a target infectious disease state of each region in the training sample and a change of a target infectious disease medical resource state of each region as input, obtaining an early warning suggestion and a response suggestion corresponding to each region in the training sample as expected output, training a deep learning neural network model to obtain a regional intelligent early warning response deep learning neural network model, using the target infectious disease state of each region and the change of the target infectious disease medical resource state of each region as input of the regional intelligent early warning response deep learning neural network model, and obtaining the calculated output which is the early warning suggestion and the response suggestion corresponding to each region.
Preferably, the first and second electrodes are formed of a metal,
the steps of acquiring a target infectious disease condition of a region specifically include: judging the stage of the target infectious disease of the region, wherein the stage of the target infectious disease comprises a peak period or a low peak period or a grade or a quantized value; judging whether the target infectious disease condition of the region is serious according to the stage of the target infectious disease of the region; if the stage of the target infectious disease of the region is in a peak period or high or the quantitative value exceeds a first preset value, the target infectious disease condition of the region is serious, otherwise, the target infectious disease condition of the region is not serious;
the step of judging the stage of the target infectious disease of the region specifically comprises the following steps: acquiring the number of newly-increased confirmed cases per day of an area, if the number of newly-increased confirmed cases per day of the area exceeds K1, the current stage of the area belongs to level 1, if the number of newly-increased confirmed cases per day of the area is K1-K2, the current stage of the area belongs to level 2, if the number of newly-increased confirmed cases per day of the area is K2-K3, the severity of the illness state of the area at the current stage belongs to level 3, and so on; wherein K1, K2 and K3 are natural numbers, and K1 is more than K2 and less than K3; or standardizing the number of newly-added confirmed cases in the area every day to be used as a quantitative value of the severity of the disease condition; standardizing the number of newly-added confirmed cases per day in the area comprises dividing the number of newly-added confirmed cases per day in the area by the number of the area population;
the steps for acquiring the change of the target infectious disease medical resource condition of the region specifically comprise: judging the current medical resource tension degree of the target infectious disease in the region, wherein the current medical resource tension degree of the target infectious disease comprises a grade or a quantized value; judging the change of the medical resource condition of the target infectious disease in each region according to the current medical resource tension degree of the target infectious disease in the region; if the level of the current medical resource tension degree of the target infectious disease in the region is increased or the increment of the quantitative value exceeds a second preset value, the current medical resource tension degree of the target infectious disease in the region is increased; if the level of the current medical resource tension degree of the target infectious disease in the region is not changed or the change of the quantitative value does not exceed a second preset value, the current medical resource tension degree of the target infectious disease in the region is not changed; if the level of the current medical resource tension degree of the target infectious disease in the region is reduced or the reduction value of the quantitative value exceeds a third preset value, the current medical resource tension degree of the target infectious disease in the region is reduced;
the step of judging the current medical resource tension degree of the target infectious disease in the region specifically comprises the following steps: acquiring the current medical resource occupancy rate of the target infectious disease of the region, wherein if the current medical resource occupancy rate of the target infectious disease of the region exceeds A1%, the current medical resource tension degree of the target infectious disease of the region belongs to grade 1, if the current medical resource occupancy rate of the target infectious disease of the region is A1% -A2%, the current medical resource tension degree of the target infectious disease of the region belongs to grade 2, and if the current medical resource occupancy rate of the target infectious disease of the region is A2% -A3%, the current medical resource tension degree of the target infectious disease of the region belongs to grade 3, and so on; wherein A1, A2, A3 are all non-negative numbers between 0 and 100 and A1< A2< A3; or taking the current medical resource occupancy rate of the target infectious disease of the area as a quantitative value of the current medical resource tension degree of the target infectious disease of the area.
Preferably, the first and second electrodes are formed of a metal,
the step of acquiring the information of the user specifically comprises: acquiring a head portrait of a user through a camera, automatically identifying an identity card number of the user, asking the user to confirm, and acquiring user information according to the identity card number if the user confirms the identified identity card number; if the user does not confirm or deny the identified identity card number, identifying the user information according to the head portrait of the user; the identification number and the user information of each user are stored in a user knowledge base in advance; the user information comprises age or/and occupation;
the step of acquiring the head portrait of the user through the camera and automatically identifying the identity card number of the user specifically comprises the following steps: acquiring a sample set of a user head portrait and an identity card number, acquiring the user head portrait through a camera, automatically identifying the identity card number of the user as input and expected output respectively, training a deep learning neural network model to obtain an identity recognition deep learning neural network model, inputting the head portrait of the user into the identity recognition deep learning neural network model, and calculating to obtain output as the identity card number of the user;
the step of identifying the user information according to the avatar of the user specifically includes: acquiring a user head portrait and a sample set of identity information, acquiring the user head portrait through a camera, automatically identifying the identity information of the user as input and expected output respectively, training a deep learning neural network model to obtain an identity information identification deep learning neural network model, inputting the head portrait of the user into the identity information identification deep learning neural network model, and calculating to obtain output as the identity information of the user.
In a second aspect, an embodiment of the present invention provides an artificial intelligence system, where the system includes:
a target infectious disease acquisition module: acquiring infectious diseases to be dealt with as target infectious diseases;
the early warning coping module: acquiring the level of early warning, and determining the level of response according to the level of early warning;
epidemic situation judging module: acquiring a target infectious disease condition of each region aiming at each region, setting the early warning level of each region as a preset higher level if the target infectious disease condition is serious, and adjusting the early warning threshold of each region to a preset lower threshold; if the target infectious disease condition is not serious, setting the early warning level of each region as a preset lower level, and adjusting the early warning threshold value of each region to a preset higher threshold value;
a resource judgment module: aiming at each region, acquiring the change of the medical resource condition of the target infectious disease of each region, and if the tension degree of the medical resource condition is increased, reducing the early warning level of each region and increasing the early warning threshold of each region; if the tension degree of the medical resource condition is reduced, improving the early warning level of each area, and reducing the early warning threshold value of each area;
a user priority judging module: acquiring information of each user aiming at each user, setting the early warning level of each user to be a preset higher level if the user bears important work tasks or belongs to a group with key cares, and adjusting the early warning threshold value of each user to be a preset lower threshold value; if the user does not undertake important work tasks and does not belong to the group of key careers, the early warning level of the area to which each user belongs is taken as the early warning level of each user, and the early warning threshold value of each user is adjusted to be the early warning threshold value of the area to which each user belongs; the people who pay special attention to the care include medical care personnel, pregnant women, the old and children;
the user state of an illness judging module: aiming at each user, acquiring the suspected infection target infectious disease degree of each user, if the suspected infection target infectious disease degree of each user is higher than a preset suspected degree threshold value, setting the early warning level of each user to be a preset higher level, and adjusting the early warning threshold value of each user to be a preset lower threshold value; if the suspected infection target infectious disease degree of the user is lower than a preset suspected degree threshold value, keeping the existing early warning level and early warning threshold value of each user;
a cost handling module: recommending coping schemes with different costs according to the early warning level;
the cost coping module specifically comprises: if the early warning level is high, recommending a coping scheme with high cost; if the early warning level is low, recommending a coping scheme with low cost;
the coping aging module: recommending coping schemes with different timeliness according to the early warning level;
the coping aging module specifically comprises: if the early warning level is higher, recommending a coping scheme with higher timeliness; and if the early warning level is low, recommending a coping scheme with low timeliness.
Preferably, the system further comprises:
user's intelligence early warning deals with the module: obtaining each user in a training sample, obtaining a target infectious disease state of an area to which each user belongs in the training sample, a change of a target infectious disease medical resource state of the area to which each user belongs in the training sample, information of each user in the training sample, and a suspected target infectious disease infection degree of each user in the training sample as input, obtaining an early warning suggestion and a coping suggestion corresponding to each user in the training sample as expected output, training a deep learning neural network model to obtain a user intelligent early warning coping deep learning neural network model, and taking the target infectious disease state of the area to which the user belongs, the change of the target infectious disease medical resource state of the area to which the user belongs, the information of the user, and the suspected target infectious disease infection degree of the user as input of the user intelligent early warning coping deep learning neural network model, the calculated output is an early warning suggestion and a corresponding suggestion corresponding to the user;
regional intelligent early warning reply module: the method comprises the steps of obtaining each region in a training sample, obtaining a target infectious disease state of each region in the training sample and a change of a target infectious disease medical resource state of each region as input, obtaining an early warning suggestion and a response suggestion corresponding to each region in the training sample as expected output, training a deep learning neural network model to obtain a regional intelligent early warning response deep learning neural network model, using the target infectious disease state of each region and the change of the target infectious disease medical resource state of each region as input of the regional intelligent early warning response deep learning neural network model, and obtaining the calculated output which is the early warning suggestion and the response suggestion corresponding to each region.
Preferably, the first and second electrodes are formed of a metal,
the module for acquiring the target infectious disease condition of the region specifically comprises the following modules: judging the stage of the target infectious disease of the region, wherein the stage of the target infectious disease comprises a peak period or a low peak period or a grade or a quantized value; judging whether the target infectious disease condition of the region is serious according to the stage of the target infectious disease of the region; if the stage of the target infectious disease of the region is in a peak period or high or the quantitative value exceeds a first preset value, the target infectious disease condition of the region is serious, otherwise, the target infectious disease condition of the region is not serious;
the module for judging the stage of the target infectious disease in the region specifically comprises: acquiring the number of newly-increased confirmed cases per day of an area, if the number of newly-increased confirmed cases per day of the area exceeds K1, the current stage of the area belongs to level 1, if the number of newly-increased confirmed cases per day of the area is K1-K2, the current stage of the area belongs to level 2, if the number of newly-increased confirmed cases per day of the area is K2-K3, the severity of the illness state of the area at the current stage belongs to level 3, and so on; wherein K1, K2 and K3 are natural numbers, and K1 is more than K2 and less than K3; or standardizing the number of newly-added confirmed cases in the area every day to be used as a quantitative value of the severity of the disease condition; standardizing the number of newly-added confirmed cases per day in the area comprises dividing the number of newly-added confirmed cases per day in the area by the number of the area population;
the module for acquiring the change of the target infectious disease medical resource condition of the region specifically comprises the following modules: judging the current medical resource tension degree of the target infectious disease in the region, wherein the current medical resource tension degree of the target infectious disease comprises a grade or a quantized value; judging the change of the medical resource condition of the target infectious disease in each region according to the current medical resource tension degree of the target infectious disease in the region; if the level of the current medical resource tension degree of the target infectious disease in the region is increased or the increment of the quantitative value exceeds a second preset value, the current medical resource tension degree of the target infectious disease in the region is increased; if the level of the current medical resource tension degree of the target infectious disease in the region is not changed or the change of the quantitative value does not exceed a second preset value, the current medical resource tension degree of the target infectious disease in the region is not changed; if the level of the current medical resource tension degree of the target infectious disease in the region is reduced or the reduction value of the quantitative value exceeds a third preset value, the current medical resource tension degree of the target infectious disease in the region is reduced;
the module for judging the current medical resource shortage degree of the target infectious disease in the region specifically comprises the following steps: acquiring the current medical resource occupancy rate of the target infectious disease of the region, wherein if the current medical resource occupancy rate of the target infectious disease of the region exceeds A1%, the current medical resource tension degree of the target infectious disease of the region belongs to grade 1, if the current medical resource occupancy rate of the target infectious disease of the region is A1% -A2%, the current medical resource tension degree of the target infectious disease of the region belongs to grade 2, and if the current medical resource occupancy rate of the target infectious disease of the region is A2% -A3%, the current medical resource tension degree of the target infectious disease of the region belongs to grade 3, and so on; wherein A1, A2, A3 are all non-negative numbers between 0 and 100 and A1< A2< A3; or taking the current medical resource occupancy rate of the target infectious disease of the area as a quantitative value of the current medical resource tension degree of the target infectious disease of the area.
Preferably, the first and second electrodes are formed of a metal,
the module for acquiring the information of the user specifically comprises: acquiring a head portrait of a user through a camera, automatically identifying an identity card number of the user, asking the user to confirm, and acquiring user information according to the identity card number if the user confirms the identified identity card number; if the user does not confirm or deny the identified identity card number, identifying the user information according to the head portrait of the user; the identification number and the user information of each user are stored in a user knowledge base in advance; the user information comprises age or/and occupation;
the module for acquiring the head portrait of the user and automatically identifying the identity card number of the user through the camera specifically comprises: acquiring a sample set of a user head portrait and an identity card number, acquiring the user head portrait through a camera, automatically identifying the identity card number of the user as input and expected output respectively, training a deep learning neural network model to obtain an identity recognition deep learning neural network model, inputting the head portrait of the user into the identity recognition deep learning neural network model, and calculating to obtain output as the identity card number of the user;
the module for identifying the user information according to the avatar of the user specifically includes: acquiring a user head portrait and a sample set of identity information, acquiring the user head portrait through a camera, automatically identifying the identity information of the user as input and expected output respectively, training a deep learning neural network model to obtain an identity information identification deep learning neural network model, inputting the head portrait of the user into the identity information identification deep learning neural network model, and calculating to obtain output as the identity information of the user.
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 coping method and the robot based on big data artificial intelligence provided by the embodiment comprise the following steps: acquiring a target infectious disease; early warning and coping steps; an epidemic situation judgment step; a resource judgment step; judging the priority of the user; judging the state of the patient; cost handling steps; and (5) coping with an aging step. According to the method, the system and the robot, the early warning levels and the early warning threshold values of the regions and the users are carried out according to the conditions of the target infectious diseases, the medical resource conditions, the user priorities and the user conditions, so that personalized early warning can be adopted in different regions and different users, the coping cost is considered, coping schemes with different cost and different time effectiveness are adopted for early warning of different levels, and the coping schemes are more personalized and efficient.
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 diagram of a dynamic personalized grading coping pattern of new major infectious diseases based on big data provided by the embodiment of the 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: acquiring a target infectious disease; early warning and coping steps; an epidemic situation judgment step; a resource judgment step; judging the priority of the user; judging the state of the patient; cost handling steps; and (5) coping with an aging step. The technical effects are as follows: according to the method, the early warning levels and the early warning threshold values of the regions and the users are carried out according to the target infectious disease conditions, the medical resource conditions, the user priorities and the user illness states of each region, so that personalized early warning can be adopted in different regions and different users, meanwhile, the coping cost is considered, coping schemes with different cost and different time effectiveness are adopted for early warning of different levels, and the coping schemes are more personalized and efficient.
In a preferred embodiment, as shown in fig. 2, the method further comprises: a user intelligent early warning response step; and (5) responding to regional intelligent early warning. The technical effects are as follows: the method carries out the training of the deep learning model through the target infectious disease state, the medical resource state, the user priority, the user illness state and the early warning suggestions and coping suggestions given by the existing experts, can fully utilize the judgment result of the existing experts, then carries out the early warning suggestions and the prediction of coping suggestions through the trained deep learning model, and can greatly save the labor cost of the experts needing to carry out the manual early warning decision and coping decision.
PREFERRED EMBODIMENTS OF THE PRESENT INVENTION
A step of acquiring a target infectious disease: acquiring infectious diseases to be dealt with as target infectious diseases;
early warning coping steps: acquiring the level of early warning, and determining the level of response according to the level of early warning;
an epidemic situation judging step: acquiring a target infectious disease condition of each region aiming at each region, setting the early warning level of each region as a preset higher level if the target infectious disease condition is serious, and adjusting the early warning threshold of each region to a preset lower threshold; if the target infectious disease condition is not serious, setting the early warning level of each region as a preset lower level, and adjusting the early warning threshold value of each region to a preset higher threshold value;
a resource judgment step: aiming at each region, acquiring the change of the medical resource condition of the target infectious disease of each region, and if the tension degree of the medical resource condition is increased, reducing the early warning level of each region and increasing the early warning threshold of each region; if the tension degree of the medical resource condition is reduced, improving the early warning level of each area, and reducing the early warning threshold value of each area;
a user priority judging step: acquiring information of each user aiming at each user, setting the early warning level of each user to be a preset higher level if the user bears important work tasks or belongs to a group with key cares, and adjusting the early warning threshold value of each user to be a preset lower threshold value; if the user does not undertake important work tasks and does not belong to the group of key careers, the early warning level of the area to which each user belongs is taken as the early warning level of each user, and the early warning threshold value of each user is adjusted to be the early warning threshold value of the area to which each user belongs; the people who pay special attention to the care include medical care personnel, pregnant women, the old and children;
judging the state of the patient: aiming at each user, acquiring the suspected infection target infectious disease degree of each user, if the suspected infection target infectious disease degree of each user is higher than a preset suspected degree threshold value, setting the early warning level of each user to be a preset higher level, and adjusting the early warning threshold value of each user to be a preset lower threshold value; if the suspected infection target infectious disease degree of the user is lower than a preset suspected degree threshold value, keeping the existing early warning level and early warning threshold value of each user;
cost coping steps: recommending coping schemes with different costs according to the early warning level;
the cost coping step specifically comprises the following steps: if the early warning level is high, recommending a coping scheme with high cost; and if the early warning level is low, recommending a response scheme with low cost.
And (3) coping aging step: recommending coping schemes with different timeliness according to the early warning level;
the aging treatment step specifically comprises: if the early warning level is higher, recommending a coping scheme with higher timeliness; and if the early warning level is low, recommending a coping scheme with low timeliness.
The intelligent early warning coping step of the user: obtaining each user in a training sample, obtaining a target infectious disease state of an area to which each user belongs in the training sample, a change of a target infectious disease medical resource state of the area to which each user belongs in the training sample, information of each user in the training sample, and a suspected target infectious disease infection degree of each user in the training sample as input, obtaining an early warning suggestion and a coping suggestion corresponding to each user in the training sample as expected output, training a deep learning neural network model to obtain a user intelligent early warning coping deep learning neural network model, and taking the target infectious disease state of the area to which the user belongs, the change of the target infectious disease medical resource state of the area to which the user belongs, the information of the user, and the suspected target infectious disease infection degree of the user as input of the user intelligent early warning coping deep learning neural network model, the calculated output is an early warning suggestion and a corresponding suggestion corresponding to the user;
regional intelligent early warning coping steps: acquiring each region in a training sample, acquiring a target infectious disease state of each region in the training sample and a change of a target infectious disease medical resource state of each region in the training sample as input, acquiring an early warning suggestion and a response suggestion corresponding to each region in the training sample as expected output, training a deep learning neural network model to obtain a regional intelligent early warning response deep learning neural network model, and taking the target infectious disease state of each region and the change of the target infectious disease medical resource state of each region as input of the regional intelligent early warning response deep learning neural network model, wherein the calculated output is the early warning suggestion and the response suggestion corresponding to each region;
the step of acquiring the target infectious disease condition of each region specifically comprises the following steps: judging the stage of the target infectious disease in each region, wherein the stage of the target infectious disease comprises a peak period or a low peak period or a grade or a quantized value; judging whether the target infectious disease condition of each region is serious according to the stage of the target infectious disease of each region; if the stage of the target infectious disease of each region is in a peak period or the high level or the quantitative value exceeds a first preset value, the target infectious disease condition of each region is serious, otherwise, the target infectious disease condition of each region is not serious;
the step of judging the stage of the target infectious disease in each region specifically comprises the following steps: acquiring the number of newly-added confirmed cases per day in each area, wherein if the number of newly-added confirmed cases per day in each area exceeds K1, the current stage of the area belongs to level 1, if the number of newly-added confirmed cases per day in each area is K1-K2, the current stage of the area belongs to level 2, and if the number of newly-added confirmed cases per day in each area is K2-K3, the severity of the illness state of the area in the current stage belongs to level 3, and so on; wherein K1, K2 and K3 are natural numbers, and K1 is more than K2 and less than K3; or standardizing the newly added diagnosis cases in each area every day to be used as a quantitative value of the severity of the disease; standardizing the number of newly-added confirmed cases per day in each area, wherein the standardization comprises dividing the number of newly-added confirmed cases per day in each area by the number of the population in each area;
the step of acquiring the change of the target infectious disease medical resource condition of each region specifically comprises the following steps: judging the current medical resource tension degree of the target infectious disease in each region, wherein the current medical resource tension degree of the target infectious disease comprises a grade or a quantized value; judging the change of the medical resource condition of the target infectious disease in each region according to the current medical resource tension degree of the target infectious disease in each region; if the level of the current medical resource tension degree of the target infectious disease in each area is increased or the increment of the quantitative value exceeds a second preset value, the current medical resource tension degree of the target infectious disease in each area is increased; if the level of the current medical resource tension degree of the target infectious disease in each area is not changed or the change of the quantitative value does not exceed a second preset value, the current medical resource tension degree of the target infectious disease in each area is not changed; if the level of the current medical resource tension degree of the target infectious disease in each region is reduced or the reduction value of the quantitative value exceeds a third preset value, the current medical resource tension degree of the target infectious disease in each region is reduced;
the step of judging the current medical resource shortage degree of the target infectious disease in each region specifically comprises the following steps: acquiring the current medical resource occupancy rate of the target infectious disease of each region, wherein if the current medical resource occupancy rate of the target infectious disease of each region exceeds A1%, the current medical resource tension degree of the target infectious disease of each region belongs to level 1, if the current medical resource occupancy rate of the target infectious disease of each region is A1% -A2%, the current medical resource tension degree of the target infectious disease of each region belongs to level 2, and if the current medical resource occupancy rate of the target infectious disease of each region is A2% -A3%, the current medical resource tension degree of the target infectious disease of each region belongs to level 3, and so on; wherein A1, A2, A3 are all non-negative numbers between 0 and 100 and A1< A2< A3; or taking the current medical resource occupancy rate of the target infectious disease of each region as a quantitative value of the current medical resource tension degree of the target infectious disease of each region;
the step of obtaining the information of the user: acquiring a head portrait of a user through a camera, automatically identifying an identity card number of the user, asking the user to confirm, and acquiring user information according to the identity card number if the user confirms the identified identity card number; if the user does not confirm or deny the identified identity card number, identifying the user information according to the head portrait of the user; the identification number and the user information of each user are stored in a user knowledge base in advance; the user information comprises age or/and occupation;
the step of acquiring the head portrait of the user through the camera and automatically identifying the identity card number of the user specifically comprises the following steps: acquiring a sample set of a user head portrait and an identity card number, acquiring the user head portrait through a camera, automatically identifying the identity card number of the user as input and expected output respectively, training a deep learning neural network model to obtain an identity recognition deep learning neural network model, inputting the head portrait of the user into the identity recognition deep learning neural network model, and calculating to obtain output as the identity card number of the user;
the step of identifying the user information according to the avatar of the user specifically includes: acquiring a user head portrait and a sample set of identity information, acquiring the user head portrait through a camera, automatically identifying the identity information of the user as input and expected output respectively, training a deep learning neural network model to obtain an identity information identification deep learning neural network model, inputting the head portrait of the user into the identity information identification deep learning neural network model, and calculating to obtain output as the identity information of the user.
Other embodiments of the invention
How to solve the contradiction between the shortage of protective resources such as masks and medical resources such as wards and the need of people for diagnosis and treatment in the response to new major infectious diseases? The method to be adopted by the embodiment is to adopt different levels of coping ways for different levels of early warning, and needs to adopt personalized early warning and coping mechanisms for different regions and different people, for example, if some regions are serious, emergency coping is adopted, some areas are slight, so that loose response is adopted, some people contact more people due to the working property or the places, for example, shop staff also need to adopt high-level coping, some people undertake important work tasks or belong to people who pay strong care, such as medical care personnel, pregnant women, old people and children, also need to adopt high-level coping, for the crowd or the area needing to adopt the high-level response, the early warning threshold value is properly reduced (as long as the early warning threshold value is greater than the early warning threshold value, the early warning threshold value is reduced, and therefore the user can meet the early warning condition and is early warned more easily).
Dynamic personalized grading of newly-discovered major infectious diseases based on big data:
and analyzing based on the big data to obtain data such as users, resources, regions, disease development time sequence characteristics and the like, and further adopting corresponding dynamic personalized hierarchical corresponding measures according to the knowledge base. The dynamic personalized grading coping needs to be carried out based on big data analysis, grading is carried out according to the monitoring data and the early warning data of each region and each time period, the attributes of each user and the conditions of each region resource, and the grading process can be realized by combining machine learning based on big data with an expert system.
It is very necessary to adopt dynamic personalized hierarchical coping, because if a high-cost coping method is adopted for all situations, although the safety degree is high, the protection resources such as masks and medical resources such as sickrooms are scarce and finally cannot be effectively coped, different levels of early warning are required to adopt coping methods of different levels, and personalized early warning and coping mechanisms are required to be adopted for different areas and different crowds, for example, some areas are serious, emergency coping is adopted, some areas are slight, loose coping is adopted, some crowds contact more people due to the working properties or places thereof, for example, shop staff, high-level coping is also adopted, some crowds undertake important work tasks or belong to important career groups, for example, medical staff, pregnant women, old people and children, high-level coping is also adopted, for the crowd or the area needing to adopt the high-level response, the early warning threshold value is properly reduced (as long as the early warning threshold value is greater than the early warning threshold value, the early warning threshold value is reduced, and therefore the user can meet the early warning condition and is early warned more easily). Fig. 3 shows a pattern diagram for dynamically personalized grading of newly developed major infectious diseases based on big data.
Obtaining statistical data required by coping with decision: firstly, in the monitoring stage, the identity card number of the user is automatically identified through the camera head portrait, and the user is asked to confirm, so that the user information such as age, occupation and the like can be obtained through the identity card number. If the user does not confirm, the age and the gender of the user are identified according to the head portrait of the user through a deep learning model. And then acquiring the disease condition monitoring statistical data and the medical resource monitoring statistical data of each time interval of each region of the new major infectious disease from the monitoring system, and preparing for personalized dynamic personalized grading treatment based on the big data.
The intelligent grading three-level early warning dealing rule base for the new major infectious diseases comprises the following steps:
and establishing a three-level early warning corresponding rule base according to the sequence from macro to micro, from global to local and from society to individual.
The primary rule base is mainly obtained by analyzing the disease state space-time big data of the new major infectious diseases, and mainly judges the stage, such as the peak stage or the low peak stage, of the current new major infectious diseases in each region, for example, if the number of newly-added confirmed cases per day in a certain region exceeds K1, the current stage of the region belongs to level 1, the number of newly-added confirmed cases per day in a certain region is K1-K2, the current stage of the region belongs to level 2, the number of newly-added confirmed cases per day in a certain region is K2-K3, the severity of the disease state in the current stage of the region belongs to level 3, and so on. The number of confirmed cases can also be normalized (e.g., divided by the number of population) to obtain a quantitative value of the severity of the disease. Thus, the disease severity level of each province and city is determined according to the primary rule base and big data.
The second-level rule base is mainly obtained by analyzing the medical resource space-time big data of the new major infectious disease, and mainly judges whether the medical resources of the current new major infectious disease in each region are loose or tense, for example, if the occupancy rate of the medical resources in a certain region exceeds A1%, the tension degree of the medical resources in the current stage of the region belongs to level 1, if the occupancy rate of the medical resources in a certain region is in the range of A1% -A2%, the tension degree of the medical resources in the current stage of the region belongs to level 2, if the occupancy rate of the medical resources in a certain region is in the range of A2% -A3%, the tension degree of the medical resources in the current stage of. The medical resource occupancy rate can also be used as a quantitative value of the medical resource tension degree. Thus, the data resource tension level of each province and city is determined according to the secondary rule base and big data.
The third-level rule base is mainly obtained by analyzing the user information of the newly-sent major infectious diseases and mainly judges the corresponding measures which should be taken by each user. The diagnosis and treatment priority of the user is firstly analyzed according to user attributes such as age, occupation and special conditions (such as pregnancy), and then the corresponding strategy of the user is determined according to the infection risk probability, the local disease level and the medical resource tension level of the user. For example, the infection risk probability of a certain user is P%, the priority level of the user attribute is 3, the severity of the illness state of the current stage of the region belongs to 2, the medical resource tension degree of the current stage of the region belongs to 3, and a decision tree or a deep learning model is input to obtain early warning and corresponding suggestions and send the early warning and corresponding suggestions to the user and relevant departments.
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)

1. An artificial intelligence method, the method comprising:
a step of acquiring a target infectious disease: acquiring infectious diseases to be dealt with as target infectious diseases;
early warning coping steps: acquiring the level of early warning, and determining the level of response according to the level of early warning;
an epidemic situation judging step: acquiring a target infectious disease condition of each region aiming at each region, setting the early warning level of each region as a preset higher level if the target infectious disease condition is serious, and adjusting the early warning threshold of each region to a preset lower threshold; if the target infectious disease condition is not serious, setting the early warning level of each region as a preset lower level, and adjusting the early warning threshold value of each region to a preset higher threshold value;
a resource judgment step: aiming at each region, acquiring the change of the medical resource condition of the target infectious disease of each region, and if the tension degree of the medical resource condition is increased, reducing the early warning level of each region and increasing the early warning threshold of each region; if the tension degree of the medical resource condition is reduced, improving the early warning level of each area, and reducing the early warning threshold value of each area;
a user priority judging step: acquiring information of each user aiming at each user, setting the early warning level of each user to be a preset higher level if the user bears important work tasks or belongs to a group with key cares, and adjusting the early warning threshold value of each user to be a preset lower threshold value; if the user does not undertake important work tasks and does not belong to the group of key careers, the early warning level of the area to which each user belongs is taken as the early warning level of each user, and the early warning threshold value of each user is adjusted to be the early warning threshold value of the area to which each user belongs; the people who pay special attention to the care include medical care personnel, pregnant women, the old and children;
judging the state of the patient: aiming at each user, acquiring the suspected infection target infectious disease degree of each user, if the suspected infection target infectious disease degree of each user is higher than a preset suspected degree threshold value, setting the early warning level of each user to be a preset higher level, and adjusting the early warning threshold value of each user to be a preset lower threshold value; if the suspected infection target infectious disease degree of the user is lower than a preset suspected degree threshold value, keeping the existing early warning level and early warning threshold value of each user;
cost coping steps: recommending coping schemes with different costs according to the early warning level;
the cost coping step specifically comprises the following steps: if the early warning level is high, recommending a coping scheme with high cost; if the early warning level is low, recommending a coping scheme with low cost;
and (3) coping aging step: recommending coping schemes with different timeliness according to the early warning level;
the aging treatment step specifically comprises: if the early warning level is higher, recommending a coping scheme with higher timeliness; and if the early warning level is low, recommending a coping scheme with low timeliness.
2. The artificial intelligence method of claim 1, wherein the method further comprises:
the intelligent early warning coping step of the user: obtaining each user in a training sample, obtaining a target infectious disease state of an area to which each user belongs in the training sample, a change of a target infectious disease medical resource state of the area to which each user belongs in the training sample, information of each user in the training sample, and a suspected target infectious disease infection degree of each user in the training sample as input, obtaining an early warning suggestion and a coping suggestion corresponding to each user in the training sample as expected output, training a deep learning neural network model to obtain a user intelligent early warning coping deep learning neural network model, and taking the target infectious disease state of the area to which the user belongs, the change of the target infectious disease medical resource state of the area to which the user belongs, the information of the user, and the suspected target infectious disease infection degree of the user as input of the user intelligent early warning coping deep learning neural network model, the calculated output is an early warning suggestion and a corresponding suggestion corresponding to the user;
regional intelligent early warning coping steps: the method comprises the steps of obtaining each region in a training sample, obtaining a target infectious disease state of each region in the training sample and a change of a target infectious disease medical resource state of each region as input, obtaining an early warning suggestion and a response suggestion corresponding to each region in the training sample as expected output, training a deep learning neural network model to obtain a regional intelligent early warning response deep learning neural network model, using the target infectious disease state of each region and the change of the target infectious disease medical resource state of each region as input of the regional intelligent early warning response deep learning neural network model, and obtaining the calculated output which is the early warning suggestion and the response suggestion corresponding to each region.
3. The artificial intelligence method of claim 2,
the steps of acquiring a target infectious disease condition of a region specifically include: judging the stage of the target infectious disease of the region, wherein the stage of the target infectious disease comprises a peak period or a low peak period or a grade or a quantized value; judging whether the target infectious disease condition of the region is serious according to the stage of the target infectious disease of the region; if the stage of the target infectious disease of the region is in a peak period or high or the quantitative value exceeds a first preset value, the target infectious disease condition of the region is serious, otherwise, the target infectious disease condition of the region is not serious;
the step of judging the stage of the target infectious disease of the region specifically comprises the following steps: acquiring the number of newly-increased confirmed cases per day of an area, if the number of newly-increased confirmed cases per day of the area exceeds K1, the current stage of the area belongs to level 1, if the number of newly-increased confirmed cases per day of the area is K1-K2, the current stage of the area belongs to level 2, if the number of newly-increased confirmed cases per day of the area is K2-K3, the severity of the illness state of the area at the current stage belongs to level 3, and so on; wherein K1, K2 and K3 are natural numbers, and K1 is more than K2 and less than K3; or standardizing the number of newly-added confirmed cases in the area every day to be used as a quantitative value of the severity of the disease condition; standardizing the number of newly-added confirmed cases per day in the area comprises dividing the number of newly-added confirmed cases per day in the area by the number of the area population;
the steps for acquiring the change of the target infectious disease medical resource condition of the region specifically comprise: judging the current medical resource tension degree of the target infectious disease in the region, wherein the current medical resource tension degree of the target infectious disease comprises a grade or a quantized value; judging the change of the medical resource condition of the target infectious disease in each region according to the current medical resource tension degree of the target infectious disease in the region; if the level of the current medical resource tension degree of the target infectious disease in the region is increased or the increment of the quantitative value exceeds a second preset value, the current medical resource tension degree of the target infectious disease in the region is increased; if the level of the current medical resource tension degree of the target infectious disease in the region is not changed or the change of the quantitative value does not exceed a second preset value, the current medical resource tension degree of the target infectious disease in the region is not changed; if the level of the current medical resource tension degree of the target infectious disease in the region is reduced or the reduction value of the quantitative value exceeds a third preset value, the current medical resource tension degree of the target infectious disease in the region is reduced;
the step of judging the current medical resource tension degree of the target infectious disease in the region specifically comprises the following steps: acquiring the current medical resource occupancy rate of the target infectious disease of the region, wherein if the current medical resource occupancy rate of the target infectious disease of the region exceeds A1%, the current medical resource tension degree of the target infectious disease of the region belongs to grade 1, if the current medical resource occupancy rate of the target infectious disease of the region is A1% -A2%, the current medical resource tension degree of the target infectious disease of the region belongs to grade 2, and if the current medical resource occupancy rate of the target infectious disease of the region is A2% -A3%, the current medical resource tension degree of the target infectious disease of the region belongs to grade 3, and so on; wherein A1, A2, A3 are all non-negative numbers between 0 and 100 and A1< A2< A3; or taking the current medical resource occupancy rate of the target infectious disease of the area as a quantitative value of the current medical resource tension degree of the target infectious disease of the area.
4. The artificial intelligence method of claim 1,
the step of acquiring the information of the user specifically comprises: acquiring a head portrait of a user through a camera, automatically identifying an identity card number of the user, asking the user to confirm, and acquiring user information according to the identity card number if the user confirms the identified identity card number; if the user does not confirm or deny the identified identity card number, identifying the user information according to the head portrait of the user; the identification number and the user information of each user are stored in a user knowledge base in advance; the user information comprises age or/and occupation;
the step of acquiring the head portrait of the user through the camera and automatically identifying the identity card number of the user specifically comprises the following steps: acquiring a sample set of a user head portrait and an identity card number, acquiring the user head portrait through a camera, automatically identifying the identity card number of the user as input and expected output respectively, training a deep learning neural network model to obtain an identity recognition deep learning neural network model, inputting the head portrait of the user into the identity recognition deep learning neural network model, and calculating to obtain output as the identity card number of the user;
the step of identifying the user information according to the avatar of the user specifically includes: acquiring a user head portrait and a sample set of identity information, acquiring the user head portrait through a camera, automatically identifying the identity information of the user as input and expected output respectively, training a deep learning neural network model to obtain an identity information identification deep learning neural network model, inputting the head portrait of the user into the identity information identification deep learning neural network model, and calculating to obtain output as the identity information of the user.
5. An artificial intelligence system, the system comprising:
a target infectious disease acquisition module: acquiring infectious diseases to be dealt with as target infectious diseases;
the early warning coping module: acquiring the level of early warning, and determining the level of response according to the level of early warning;
epidemic situation judging module: acquiring a target infectious disease condition of each region aiming at each region, setting the early warning level of each region as a preset higher level if the target infectious disease condition is serious, and adjusting the early warning threshold of each region to a preset lower threshold; if the target infectious disease condition is not serious, setting the early warning level of each region as a preset lower level, and adjusting the early warning threshold value of each region to a preset higher threshold value;
a resource judgment module: aiming at each region, acquiring the change of the medical resource condition of the target infectious disease of each region, and if the tension degree of the medical resource condition is increased, reducing the early warning level of each region and increasing the early warning threshold of each region; if the tension degree of the medical resource condition is reduced, improving the early warning level of each area, and reducing the early warning threshold value of each area;
a user priority judging module: acquiring information of each user aiming at each user, setting the early warning level of each user to be a preset higher level if the user bears important work tasks or belongs to a group with key cares, and adjusting the early warning threshold value of each user to be a preset lower threshold value; if the user does not undertake important work tasks and does not belong to the group of key careers, the early warning level of the area to which each user belongs is taken as the early warning level of each user, and the early warning threshold value of each user is adjusted to be the early warning threshold value of the area to which each user belongs; the people who pay special attention to the care include medical care personnel, pregnant women, the old and children;
the user state of an illness judging module: aiming at each user, acquiring the suspected infection target infectious disease degree of each user, if the suspected infection target infectious disease degree of each user is higher than a preset suspected degree threshold value, setting the early warning level of each user to be a preset higher level, and adjusting the early warning threshold value of each user to be a preset lower threshold value; if the suspected infection target infectious disease degree of the user is lower than a preset suspected degree threshold value, keeping the existing early warning level and early warning threshold value of each user;
a cost handling module: recommending coping schemes with different costs according to the early warning level;
the cost coping module specifically comprises: if the early warning level is high, recommending a coping scheme with high cost; if the early warning level is low, recommending a coping scheme with low cost;
the coping aging module: recommending coping schemes with different timeliness according to the early warning level;
the coping aging module specifically comprises: if the early warning level is higher, recommending a coping scheme with higher timeliness; and if the early warning level is low, recommending a coping scheme with low timeliness.
6. The artificial intelligence system of claim 5, wherein the system further comprises:
user's intelligence early warning deals with the module: obtaining each user in a training sample, obtaining a target infectious disease state of an area to which each user belongs in the training sample, a change of a target infectious disease medical resource state of the area to which each user belongs in the training sample, information of each user in the training sample, and a suspected target infectious disease infection degree of each user in the training sample as input, obtaining an early warning suggestion and a coping suggestion corresponding to each user in the training sample as expected output, training a deep learning neural network model to obtain a user intelligent early warning coping deep learning neural network model, and taking the target infectious disease state of the area to which the user belongs, the change of the target infectious disease medical resource state of the area to which the user belongs, the information of the user, and the suspected target infectious disease infection degree of the user as input of the user intelligent early warning coping deep learning neural network model, the calculated output is an early warning suggestion and a corresponding suggestion corresponding to the user;
regional intelligent early warning reply module: the method comprises the steps of obtaining each region in a training sample, obtaining a target infectious disease state of each region in the training sample and a change of a target infectious disease medical resource state of each region as input, obtaining an early warning suggestion and a response suggestion corresponding to each region in the training sample as expected output, training a deep learning neural network model to obtain a regional intelligent early warning response deep learning neural network model, using the target infectious disease state of each region and the change of the target infectious disease medical resource state of each region as input of the regional intelligent early warning response deep learning neural network model, and obtaining the calculated output which is the early warning suggestion and the response suggestion corresponding to each region.
7. The artificial intelligence system of claim 6,
the module for acquiring the target infectious disease condition of the region specifically comprises the following modules: judging the stage of the target infectious disease of the region, wherein the stage of the target infectious disease comprises a peak period or a low peak period or a grade or a quantized value; judging whether the target infectious disease condition of the region is serious according to the stage of the target infectious disease of the region; if the stage of the target infectious disease of the region is in a peak period or high or the quantitative value exceeds a first preset value, the target infectious disease condition of the region is serious, otherwise, the target infectious disease condition of the region is not serious;
the module for judging the stage of the target infectious disease in the region specifically comprises: acquiring the number of newly-increased confirmed cases per day of an area, if the number of newly-increased confirmed cases per day of the area exceeds K1, the current stage of the area belongs to level 1, if the number of newly-increased confirmed cases per day of the area is K1-K2, the current stage of the area belongs to level 2, if the number of newly-increased confirmed cases per day of the area is K2-K3, the severity of the illness state of the area at the current stage belongs to level 3, and so on; wherein K1, K2 and K3 are natural numbers, and K1 is more than K2 and less than K3; or standardizing the number of newly-added confirmed cases in the area every day to be used as a quantitative value of the severity of the disease condition; standardizing the number of newly-added confirmed cases per day in the area comprises dividing the number of newly-added confirmed cases per day in the area by the number of the area population;
the module for acquiring the change of the target infectious disease medical resource condition of the region specifically comprises the following modules: judging the current medical resource tension degree of the target infectious disease in the region, wherein the current medical resource tension degree of the target infectious disease comprises a grade or a quantized value; judging the change of the medical resource condition of the target infectious disease in each region according to the current medical resource tension degree of the target infectious disease in the region; if the level of the current medical resource tension degree of the target infectious disease in the region is increased or the increment of the quantitative value exceeds a second preset value, the current medical resource tension degree of the target infectious disease in the region is increased; if the level of the current medical resource tension degree of the target infectious disease in the region is not changed or the change of the quantitative value does not exceed a second preset value, the current medical resource tension degree of the target infectious disease in the region is not changed; if the level of the current medical resource tension degree of the target infectious disease in the region is reduced or the reduction value of the quantitative value exceeds a third preset value, the current medical resource tension degree of the target infectious disease in the region is reduced;
the module for judging the current medical resource shortage degree of the target infectious disease in the region specifically comprises the following steps: acquiring the current medical resource occupancy rate of the target infectious disease of the region, wherein if the current medical resource occupancy rate of the target infectious disease of the region exceeds A1%, the current medical resource tension degree of the target infectious disease of the region belongs to grade 1, if the current medical resource occupancy rate of the target infectious disease of the region is A1% -A2%, the current medical resource tension degree of the target infectious disease of the region belongs to grade 2, and if the current medical resource occupancy rate of the target infectious disease of the region is A2% -A3%, the current medical resource tension degree of the target infectious disease of the region belongs to grade 3, and so on; wherein A1, A2, A3 are all non-negative numbers between 0 and 100 and A1< A2< A3; or taking the current medical resource occupancy rate of the target infectious disease of the area as a quantitative value of the current medical resource tension degree of the target infectious disease of the area;
the module for acquiring the information of the user specifically comprises: acquiring a head portrait of a user through a camera, automatically identifying an identity card number of the user, asking the user to confirm, and acquiring user information according to the identity card number if the user confirms the identified identity card number; if the user does not confirm or deny the identified identity card number, identifying the user information according to the head portrait of the user; the identification number and the user information of each user are stored in a user knowledge base in advance; the user information comprises age or/and occupation;
the module for acquiring the head portrait of the user and automatically identifying the identity card number of the user through the camera specifically comprises: acquiring a sample set of a user head portrait and an identity card number, acquiring the user head portrait through a camera, automatically identifying the identity card number of the user as input and expected output respectively, training a deep learning neural network model to obtain an identity recognition deep learning neural network model, inputting the head portrait of the user into the identity recognition deep learning neural network model, and calculating to obtain output as the identity card number of the user;
the module for identifying the user information according to the avatar of the user specifically includes: acquiring a user head portrait and a sample set of identity information, acquiring the user head portrait through a camera, automatically identifying the identity information of the user as input and expected output respectively, training a deep learning neural network model to obtain an identity information identification deep learning neural network model, inputting the head portrait of the user into the identity information identification deep learning neural network model, and calculating to obtain output as the identity information of the user.
8. An artificial intelligence device, wherein the device is configured to implement the steps of the method of any of claims 1-4.
9. A robot comprising a memory, a processor and an artificial intelligence robot program stored on the memory and executable on the processor, wherein the steps of the method of any one of claims 1 to 4 are carried out when the program is executed by the processor.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 4.
CN202011629860.3A 2020-12-30 2020-12-30 Infectious disease coping method and robot based on big data artificial intelligence Active CN112863685B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011629860.3A CN112863685B (en) 2020-12-30 2020-12-30 Infectious disease coping method and robot based on big data artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011629860.3A CN112863685B (en) 2020-12-30 2020-12-30 Infectious disease coping method and robot based on big data artificial intelligence

Publications (2)

Publication Number Publication Date
CN112863685A true CN112863685A (en) 2021-05-28
CN112863685B CN112863685B (en) 2023-07-21

Family

ID=75999749

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011629860.3A Active CN112863685B (en) 2020-12-30 2020-12-30 Infectious disease coping method and robot based on big data artificial intelligence

Country Status (1)

Country Link
CN (1) CN112863685B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113270182A (en) * 2021-07-20 2021-08-17 武汉泰乐奇信息科技有限公司 Common medical access contract generation method and system based on long-term and short-term memory network
CN113327684A (en) * 2021-06-07 2021-08-31 航天科工智能运筹与信息安全研究院(武汉)有限公司 Epidemic situation simulation method and device based on war game deduction and computer readable medium
CN113327685A (en) * 2021-06-07 2021-08-31 航天科工智能运筹与信息安全研究院(武汉)有限公司 Urban epidemic situation development deduction method, device and computer readable medium
CN113609656A (en) * 2021-07-19 2021-11-05 航天科工智能运筹与信息安全研究院(武汉)有限公司 Intelligent city decision system and method based on digital twin
CN114131631A (en) * 2021-12-16 2022-03-04 山东新一代信息产业技术研究院有限公司 Patrol robot alarm threshold setting method, device and medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2020000650A (en) * 2018-06-29 2020-01-09 日本電信電話株式会社 Infection prevention support device, method, and program
CN111556095A (en) * 2020-03-31 2020-08-18 世强先进(深圳)科技股份有限公司 Infectious disease epidemic situation early warning method and system based on positioning technology
CN112037925A (en) * 2020-07-29 2020-12-04 郑州大学第一附属医院 LSTM algorithm-based early warning method for newly-released major infectious diseases
CN112117011A (en) * 2020-09-25 2020-12-22 平安国际智慧城市科技股份有限公司 Infectious disease early risk early warning method and device based on artificial intelligence
CN112117010A (en) * 2020-07-13 2020-12-22 北京大瑞集思技术有限公司 Intelligent infectious disease early warning system and management platform
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

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2020000650A (en) * 2018-06-29 2020-01-09 日本電信電話株式会社 Infection prevention support device, method, and program
CN111556095A (en) * 2020-03-31 2020-08-18 世强先进(深圳)科技股份有限公司 Infectious disease epidemic situation early warning method and system based on positioning technology
CN112117010A (en) * 2020-07-13 2020-12-22 北京大瑞集思技术有限公司 Intelligent infectious disease early warning system and management platform
CN112037925A (en) * 2020-07-29 2020-12-04 郑州大学第一附属医院 LSTM algorithm-based early warning method for newly-released major infectious diseases
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
CN112117011A (en) * 2020-09-25 2020-12-22 平安国际智慧城市科技股份有限公司 Infectious disease early risk early warning method and device based on artificial intelligence

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
曾凤屏等: "分级预警运行模式应用于重大传染病疫情的效果分析", 《现代临床护理》 *
曾凤屏等: "分级预警运行模式应用于重大传染病疫情的效果分析", 《现代临床护理》, no. 04, 30 August 2006 (2006-08-30), pages 67 - 69 *

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113327684A (en) * 2021-06-07 2021-08-31 航天科工智能运筹与信息安全研究院(武汉)有限公司 Epidemic situation simulation method and device based on war game deduction and computer readable medium
CN113327685A (en) * 2021-06-07 2021-08-31 航天科工智能运筹与信息安全研究院(武汉)有限公司 Urban epidemic situation development deduction method, device and computer readable medium
CN113327684B (en) * 2021-06-07 2023-10-20 航天科工智能运筹与信息安全研究院(武汉)有限公司 Epidemic situation simulation method and device based on chess deduction and computer readable medium
CN113327685B (en) * 2021-06-07 2023-10-20 航天科工智能运筹与信息安全研究院(武汉)有限公司 Urban epidemic development deduction method and device and computer readable medium
CN113609656A (en) * 2021-07-19 2021-11-05 航天科工智能运筹与信息安全研究院(武汉)有限公司 Intelligent city decision system and method based on digital twin
CN113270182A (en) * 2021-07-20 2021-08-17 武汉泰乐奇信息科技有限公司 Common medical access contract generation method and system based on long-term and short-term memory network
CN113270182B (en) * 2021-07-20 2021-09-28 武汉泰乐奇信息科技有限公司 Common medical access contract generation method and system based on long-term and short-term memory network
CN114131631A (en) * 2021-12-16 2022-03-04 山东新一代信息产业技术研究院有限公司 Patrol robot alarm threshold setting method, device and medium
CN114131631B (en) * 2021-12-16 2024-02-02 山东新一代信息产业技术研究院有限公司 Method, device and medium for setting alarm threshold of inspection robot

Also Published As

Publication number Publication date
CN112863685B (en) 2023-07-21

Similar Documents

Publication Publication Date Title
CN112863685A (en) Infectious disease coping method based on big data artificial intelligence and robot
Shamsuddin et al. An overview on crime prediction methods
US20220319706A1 (en) A drgs automatic grouping method based on a convolutional neural network
CN111611297B (en) Propagation model establishment method considering parameter time variability and prediction method thereof
CN112259210B (en) Medical big data access control method and device and computer readable storage medium
CN113889252B (en) Remote internet big data intelligent medical system based on vital sign big data clustering core algorithm and block chain
CN111477336A (en) Fusion method, system and storage medium for infectious disease diagnosis data
Sivasankar et al. Knowledge discovery in medical datasets using a fuzzy logic rule based classifier
CN110210694A (en) Space management, device, storage medium and computer equipment
CN117292844A (en) Epidemic situation prediction method and system based on epidemic situation trend and management and control policy association model
CN117976200A (en) Cerebral apoplexy risk prediction method and system
CN116188953A (en) Medical image data processing method, system and electronic equipment for realizing data security
CN113420059A (en) Method and device for actively treating citizen hot line problem
Radovanović et al. Making hospital readmission classifier fair–What is the cost?
CN110232957A (en) A kind of diagnosis and therapy system and its construction method based on artificial intelligence, equipment and storage medium
Kobashikawa et al. Fuzzy algorithm for group decision making with participants having finite discriminating abilities
Saleh et al. Integration of different fuzzy rule-induction methods to improve the classification of patients with diabetic retinopathy
CN117556192B (en) User growth type operation system and method based on artificial intelligence
CN117808636B (en) Personnel management system and method based on safety training
CN113744870B (en) System and method for main diagnosis and prediction of medical records front page
CN116343449B (en) Safety monitoring and early warning method, device and system for construction site
CN118095927A (en) Intelligent constructed wetland monitoring method and system based on machine learning
Cole Improving Medical Diagnosis with Artificial Intelligence: Naive Bayesian Classification Algorithms
CN118522453A (en) Intelligent community resident health management system
CN117542503A (en) Schizophrenia multi-view classification method based on dynamic evidence fusion neural network

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