CN112071437B - Infectious disease trend prediction method and device, electronic equipment and storage medium - Google Patents
Infectious disease trend prediction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112071437B CN112071437B CN202011027596.6A CN202011027596A CN112071437B CN 112071437 B CN112071437 B CN 112071437B CN 202011027596 A CN202011027596 A CN 202011027596A CN 112071437 B CN112071437 B CN 112071437B
- Authority
- CN
- China
- Prior art keywords
- prediction model
- trend prediction
- sample
- natural
- current
- 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.)
- Active
Links
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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)
- Business, Economics & Management (AREA)
- Public Health (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Medical Informatics (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a method, a device, electronic equipment and a storage medium for predicting infectious disease trend, and relates to the field of epidemic situation trend prediction. The implementation scheme is as follows: acquiring the number of isolation personnel in each history period in N history periods before the current period; inputting the number of the isolation personnel in each history period into a trained trend prediction model; acquiring a trend prediction model based on the number of isolation persons in each historical period and the number of isolation persons in each future period in M future periods after the current period output by the pre-acquired prior knowledge; epidemic trends of infectious diseases in M future periods are predicted based on the number of segregators for each future period. The embodiment of the application not only can improve the accuracy of disease prediction, but also can give out the basic index of disease transmission, has strong interpretation, and simultaneously solves the problem that generalization capability is difficult to ensure.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to epidemic situation trend prediction technology, and specifically relates to an infectious disease trend prediction method, an infectious disease trend prediction device, electronic equipment and a storage medium.
Background
The effective prevention and treatment of infectious diseases are common challenges facing all human beings, and the transmission trend and speed of the infectious diseases are accurately predicted through big data, particularly the time-space correlation characteristics of the data, so that the method is greatly beneficial to the control of the infectious diseases in the human society and the public health safety of the society is ensured. It is desirable to employ big data technology to aid in the prediction and control of the spread of infectious diseases to build a predictive model of infectious diseases to enhance the cognition and control of human beings on infectious diseases.
It is generally desirable to have a predictive ability of future trends at the beginning of an infectious disease to assist government authorities in taking precautionary measures as early as possible, so that generally there are very few available sample sizes.
Disclosure of Invention
The present disclosure provides a method, apparatus, electronic device, and storage medium for infectious disease trend prediction.
In a first aspect, an embodiment of the present application provides a method for predicting an infectious disease trend, the method including:
acquiring the number of isolation personnel in each history period in N history periods before the current period; wherein the number of isolation personnel includes: the number of dead people and the number of recovery people;
inputting the number of the isolation personnel in each history period into a trained trend prediction model; acquiring the trend prediction model based on the number of isolation personnel in each historical period and the number of isolation personnel in each future period in M future periods after the current period output by the pre-acquired prior knowledge;
Predicting epidemic trends of infectious diseases in the M future periods based on the number of isolation personnel in each future period; wherein, N and M are natural numbers greater than or equal to 1.
In a second aspect, an embodiment of the present application provides an infectious disease trend prediction apparatus, including: the system comprises an acquisition module, an input and output module and a prediction module; wherein, the liquid crystal display device comprises a liquid crystal display device,
the acquisition module is used for acquiring the number of isolation personnel in each history period in N history periods before the current period; wherein the number of isolation personnel includes: the number of dead people and the number of recovery people;
the input/output module is used for inputting the number of the isolation personnel in each history period into the trained trend prediction model; acquiring the trend prediction model based on the number of isolation personnel in each historical period and the number of isolation personnel in each future period in M future periods after the current period output by the pre-acquired prior knowledge;
the prediction module is used for predicting epidemic trend of infectious diseases in the M future periods based on the number of isolation personnel in each future period; wherein, N and M are natural numbers greater than or equal to 1.
In a third aspect, an embodiment of the present application provides an electronic device, including:
one or more processors;
a memory for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method for training a lightweight detection model according to any embodiment of the present application.
In a fourth aspect, an embodiment of the present application provides a storage medium having a computer program stored thereon, where the program when executed by a processor implements the training method of the lightweight detection model according to any embodiment of the present application.
The accuracy of disease prediction can be improved according to the techniques of the present application.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The drawings are included to provide a better understanding of the present application and are not to be construed as limiting the application. Wherein:
FIG. 1 is a schematic diagram of a first flow chart of a method for predicting an infectious disease trend according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a trend prediction model according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a second flow chart of a method for predicting an infectious disease trend according to an embodiment of the present application;
FIG. 4 is a schematic diagram of a first configuration of an infection trend prediction apparatus according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a second configuration of an infection trend prediction apparatus according to an embodiment of the present application;
fig. 6 is a block diagram of an electronic device for implementing the infectious disease trend prediction method of an embodiment of the present application.
Detailed Description
Exemplary embodiments of the present application will now be described with reference to the accompanying drawings, in which various details of the embodiments of the present application are included to facilitate understanding, and are to be considered merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Example 1
Fig. 1 is a schematic flow chart of a method for predicting an infectious disease trend according to an embodiment of the present application, where the method may be performed by an infectious disease trend prediction apparatus or an electronic device, and the apparatus or the electronic device may be implemented in software and/or hardware, and the apparatus or the electronic device may be integrated into any intelligent device having a network communication function. As shown in fig. 1, the infectious disease trend prediction method may include the steps of:
S101, acquiring the number of isolation personnel in each history period in N history periods before a current period; wherein the number of isolation personnel includes: the number of dead people and the number of recovery people.
In a specific embodiment of the present application, the electronic device may obtain the number of isolation people in each of N history periods before the current period; wherein the number of isolation personnel includes: the number of dead people and the number of recovery people. The recovery person in the embodiment of the application refers to a person who changes from a sick state to a healthy state in each history period. Specifically, the number of recovery personnel can be derived from the number of hospital stays and discharge counts of each hospital and the type of illness of each individual. The historical period and the future period in embodiments of the present application may be in days, respectively. In this step, the electronic device may acquire the number of isolation persons per day in N days before the current day; for example, when N takes a value of 3, the electronic device obtains the number of the isolation persons on the previous day, the number of the isolation persons on the previous two days, and the number of the isolation persons on the previous three days in the target geographic range based on the date of the current day.
S102, inputting the number of the isolation personnel in each history period into a trained trend prediction model; the trend prediction model is obtained based on the number of persons isolated for each historical period and the number of persons isolated for each future period M future periods after the current period of the pre-obtained a priori knowledge output.
Fig. 2 is a schematic structural diagram of a trend prediction model according to an embodiment of the present application. As shown in fig. 2, the trend prediction model in the present application may be a SEIQ model; wherein S represents a susceptible population; e represents the exposure latency population, and I represents the diagnosis-confirmed population; q represents isolated population; in addition, the susceptible population, the exposed latent population, the diagnosed population and the isolated population have conversion and restriction relations with each other. The SEIQ model is an infectious disease dynamic prediction model combining an improved infectious disease model and a machine learning parameter fitting technology, and divides a crowd into a Susceptible person (Susceptible state), an exposer (exposed state), a infected person (infected state) and an isolated person (isolated state), wherein the Susceptible person (susceptable), namely a crowd which is not infected but lacks immunity, is easy to be infected after being contacted with the infected person; exposer (Exposed), i.e. latent patient, adapted for infectious diseases with long latency; a pathogen (Infectious), i.e., a person who is infected with an Infectious disease, can be transmitted to a susceptible state to change it into an exposer or a pathogen; the isolators are people in isolation state during epidemic situation, namely the isolators can be people who are isolated by the pathologist after a period of time.
In the step, the electronic equipment can input the number of the isolation personnel in each history period into a trained trend prediction model; acquiring a trend prediction model based on the number of isolation persons in each historical period and the number of isolation persons in each future period in M future periods after the current period output by the pre-acquired prior knowledge; the prior knowledge may include, among others: infection probability b, average number of contacts R0, latency exposure coefficient sigma, death or recovery coefficient R; wherein, the value range of the infection probability b is 0.01-0.07; the value range of the average contact number R0 is [2-7]; the value range of the exposure coefficient sigma of the incubation period is [1/14-1/10]; the death or recovery factor r is in the range of [1/10-1]. The a priori knowledge may be determined based on user input. For example, the user may enter city size, initial, new daily population, date of administration, etc. in the input interface; the electronic device may determine the probability of infection, average number of contacts, latency exposure factor, and mortality or recovery factor based on the user's input. Preferably, in the embodiment of the present application, the value of the infection probability b may be 0.05249; the average number of contacts R0 may have a value of 7; the latency exposure coefficient sigma may take on a value of 1/7.
Further, the electronic device may acquire the number of the isolation person per one history period in the N history periods before the current period, and the number of the isolation person per one future period in the M future periods after the current period output by the trend prediction model based on the number of the isolation person per one history period and the pre-acquired prior knowledge, after inputting the number of the isolation person per one history period in the N history periods before the current period into the trend prediction model. For example, when the value of M is 3, the electronic device obtains the number of the future one-day segregators, the number of the future two-day segregators, and the number of the future three-day segregators within the target geographic range based on the date of the day.
S103, predicting epidemic trend of infectious diseases in M future periods based on the number of isolation personnel in each future period; wherein, N and M are natural numbers greater than or equal to 1.
In a specific embodiment of the application, the electronic device may predict epidemic trends of infectious diseases in M future periods based on the number of isolation personnel for each future period; wherein, N and M are natural numbers greater than or equal to 1. Specifically, the electronic device may mark the number of isolation personnel for each future period in the history cumulative map and the daily newly-added map, respectively; and then predicting epidemic trend of the infectious disease in M future periods based on the historical cumulative map and the daily newly-added map. Specifically, the electronic device can predict epidemic trends in the natural disease stage and the urban management and control stage, respectively.
The infectious disease trend prediction method provided by the embodiment of the application firstly obtains the number of isolation personnel in each historical period in N historical periods before the current period; wherein the number of isolation personnel includes: the number of dead people and the number of recovery people; then inputting the number of the isolation personnel in each history period into a trained trend prediction model; then, acquiring a trend prediction model based on the number of isolation personnel in each historical period and the number of isolation personnel in each future period in M future periods after the current period output by the pre-acquired prior knowledge; and predicting epidemic trend of the infectious disease in M future periods based on the number of isolation personnel in each future period. That is, the application optimizes the existing SEIR model, unifies the number of dead people and the number of recovery people into the number of isolation people, thus reducing the parameters related to the dead people, having small parameter jumping and fast convergence speed. Because the application adopts the technical means of uniformly inducing the number of dead people and the number of recovery people into the number of isolation people, the technical problems that the SQIR model in the prior art is very sensitive to parameters, has great difficulty in parameter adjustment, poor interpretation and difficult guarantee of generalization capability are solved; in addition, the technical scheme of the embodiment of the application is simple and convenient to realize, convenient to popularize and wider in application range.
Example two
Fig. 3 is a second flow chart of an infectious disease trend prediction method according to an embodiment of the present application. As shown in fig. 3, the infectious disease trend prediction method may include the steps of:
s301, extracting a data sample from the data samples in the natural morbidity stage as a current natural sample.
In a specific embodiment of the present application, the electronic device may extract a data sample from the data samples in the natural attack stage as the current natural sample; wherein, the data sample of the natural morbidity stage comprises: the number of people in the target geographic range in a predetermined onset state in the natural onset phase; the predetermined morbidity state may include: a susceptible state, an exposed state, a pathogenic state, and an isolated state.
S302, if the trend prediction model does not meet the convergence condition corresponding to the preset natural morbidity stage, inputting a current natural sample into the trend prediction model, and training the trend prediction model by using the current natural sample to obtain at least one natural parameter of the trend prediction model; and taking the next natural sample of the current natural sample as the current natural sample, and repeatedly executing the operation until the trend prediction model meets the convergence condition corresponding to the natural morbidity stage.
In a specific embodiment of the present application, if the trend prediction model does not meet a convergence condition corresponding to a preset natural morbidity stage, the electronic device may input a current natural sample into the trend prediction model, and train the trend prediction model by using the current natural sample to obtain at least one natural parameter of the trend prediction model; and taking the next natural sample of the current natural sample as the current natural sample, and repeatedly executing the operation until the trend prediction model meets the convergence condition corresponding to the natural morbidity stage. Specifically, the electronic device may calculate, according to the prediction result of the trend prediction model for the current natural sample and the real result of the trend prediction model for the current natural sample, a loss function value corresponding to the current natural sample by using a root mean square logarithmic error method; the trend prediction model is then trained based on the loss function value.
The purpose of pre-training the trend prediction model in the natural onset stage is to train and obtain a set of natural parameters [ R0, b, sigma, R ] of infectious diseases by utilizing the natural development stage of the infectious diseases, namely the stage that the initial government does not manage and control the infectious diseases. At this stage, the application uses two modes of greedy method and gradient descent: loss = rmsle newly added daily + rmsle accumulated daily; subsequent learning of the control parameters is also the same training mode.
S303, extracting a data sample from the data samples in the urban management and control stage as a current management and control sample.
In a specific embodiment of the present application, the electronic device may extract a data sample from the data samples in the urban management and control stage as the current management and control sample; the data sample of the urban management and control stage comprises: the number of people in the target geographic range in a preset disease state in the urban management and control stage; the predetermined morbidity state may include: a susceptible state, an exposed state, a pathogenic state, and an isolated state.
S304, if the trend prediction model does not meet the convergence condition corresponding to the preset urban management and control stage, inputting a current management and control sample into the trend prediction model, and training the trend prediction model by using the current management and control sample to obtain at least one management and control parameter of the trend prediction model; and taking the next control sample of the current control sample as the current control sample, and repeatedly executing the operation until the trend prediction model meets the convergence condition corresponding to the urban control stage.
In a specific embodiment of the present application, if the trend prediction model does not meet the convergence condition corresponding to the preset urban management and control stage, the electronic device may input the current management and control sample to the trend prediction model, and train the trend prediction model using the current management and control sample to obtain at least one management and control parameter of the trend prediction model; and taking the next control sample of the current control sample as the current control sample, and repeatedly executing the operation until the trend prediction model meets the convergence condition corresponding to the urban control stage. Specifically, the electronic device may calculate, according to the prediction result of the trend prediction model for the current control sample and the actual result of the trend prediction model for the current control sample, a loss function value corresponding to the current control sample by using a root mean square logarithmic error method; the trend prediction model is then trained based on the loss function value.
Preferably, in the embodiment of the present application, when the population in the target geographic range migrates outside the target geographic range or the population outside the target geographic range migrates inside the target geographic range, the electronic device may extract a new data sample from the new data samples in the natural attack stage as the current new natural sample; if the trend prediction model does not meet the new convergence condition corresponding to the preset natural morbidity stage, the electronic equipment can input a current new natural sample into the trend prediction model, and train the trend prediction model by using the current new natural sample to obtain at least one new natural parameter of the trend prediction model; and taking the next new natural sample of the current new natural sample as the current new natural sample, and repeatedly executing the operation until the trend prediction model meets the new convergence condition corresponding to the natural morbidity stage.
Preferably, in the embodiment of the present application, when the population in the target geographic area migrates outside the target geographic area or the population outside the target geographic area migrates inside the target geographic area, the electronic device may further extract a new data sample from the new data samples in the urban management and control stage as the current new management and control sample; if the trend prediction model does not meet the new convergence condition corresponding to the preset urban management and control stage, the electronic equipment can input a current new management and control sample into the trend prediction model, and train the trend prediction model by using the current new management and control sample to obtain at least one new management and control parameter of the trend prediction model; and taking the next new control sample of the current new control sample as the current new control sample, and repeatedly executing the operation until the trend prediction model meets the new convergence condition corresponding to the urban control stage.
In the specific embodiment of the application, along with the exposure of infectious diseases, the government can carry out corresponding strong management and control measures to avoid the spread of epidemic situations; the model parameter R0 is a decreasing trend with time, and this trend is a decreasing trend of increasing speed. Therefore, the application uses two exponential functions of parameter control drop, and b_c1, b_c2 and b_c3 are obtained through training; the use of these three parameters may indicate a rapid decrease in the rate of increase.
S305, acquiring the number of isolation personnel in each history period in N history periods before the current period; wherein the number of isolation personnel includes: the number of dead people and the number of recovery people.
S306, inputting the number of the isolation personnel in each history period into a trained trend prediction model; the trend prediction model is obtained based on the number of persons isolated for each historical period and the number of persons isolated for each future period M future periods after the current period of the pre-obtained a priori knowledge output.
S307, predicting epidemic trend of infectious diseases in M future periods based on the number of isolation personnel in each future period; wherein, N and M are natural numbers greater than or equal to 1.
The infectious disease trend prediction method provided by the embodiment of the application firstly obtains the number of isolation personnel in each historical period in N historical periods before the current period; wherein the number of isolation personnel includes: the number of dead people and the number of recovery people; then inputting the number of the isolation personnel in each history period into a trained trend prediction model; then, acquiring a trend prediction model based on the number of isolation personnel in each historical period and the number of isolation personnel in each future period in M future periods after the current period output by the pre-acquired prior knowledge; and predicting epidemic trend of the infectious disease in M future periods based on the number of isolation personnel in each future period. That is, the application optimizes the existing SEIR model, unifies the number of dead people and the number of recovery people into the number of isolation people, thus reducing the parameters related to the dead people, having small parameter jumping and fast convergence speed. Because the application adopts the technical means of uniformly inducing the number of dead people and the number of recovery people into the number of isolation people, the technical problems that the SQIR model in the prior art is very sensitive to parameters, has great difficulty in parameter adjustment, poor interpretation and difficult guarantee of generalization capability are solved; in addition, the technical scheme of the embodiment of the application is simple and convenient to realize, convenient to popularize and wider in application range.
Example III
Fig. 4 is a first structural schematic diagram of an infectious disease trend prediction apparatus according to an embodiment of the present application. As shown in fig. 4, the apparatus 400 includes: an acquisition module 401, an input-output module 402 and a prediction module 403; wherein, the liquid crystal display device comprises a liquid crystal display device,
the acquiring module 401 is configured to acquire the number of isolation personnel in each history period in N history periods before the current period; wherein the number of isolation personnel includes: the number of dead people and the number of recovery people;
the input/output module 402 is configured to input the number of isolation personnel in each history period into a trained trend prediction model; acquiring the trend prediction model based on the number of isolation personnel in each historical period and the number of isolation personnel in each future period in M future periods after the current period output by the pre-acquired prior knowledge;
the prediction module 403 is configured to predict epidemic trend of the infectious disease in the M future periods based on the number of isolation personnel in each future period; wherein, N and M are natural numbers greater than or equal to 1.
Further, the prior knowledge includes: probability of infection, average number of contacts, latency exposure coefficient, mortality or recovery coefficient; wherein, the value range of the infection probability is 0.01-0.07; the value range of the average number of contacts is [2-7]; the value range of the exposure coefficient of the incubation period is [1/14-1/10]; the death or recovery coefficient has a value in the range of [1/10-1].
Fig. 5 is a second schematic structural diagram of an infectious disease trend prediction apparatus according to an embodiment of the present application. As shown in fig. 5, the apparatus 500 further includes: the training module 404 is configured to extract a data sample from the data samples in the natural attack stage as a current natural sample; if the trend prediction model does not meet the preset convergence condition corresponding to the natural morbidity stage, inputting the current natural sample into the trend prediction model, and training the trend prediction model by using the current natural sample to obtain at least one natural parameter of the trend prediction model; and taking the next natural sample of the current natural sample as the current natural sample, and repeatedly executing the operation until the trend prediction model meets the convergence condition corresponding to the natural morbidity stage.
Further, the training module 404 is further configured to extract a data sample from the data samples in the urban management and control stage as a current management and control sample; if the trend prediction model does not meet the preset convergence condition corresponding to the urban management and control stage, inputting the current management and control sample into the trend prediction model, and training the trend prediction model by using the current management and control sample to obtain at least one management and control parameter of the trend prediction model; and taking the next control sample of the current control sample as the current control sample, and repeatedly executing the operation until the trend prediction model meets the convergence condition corresponding to the urban control stage.
Further, the data samples of the natural morbidity stage include: the number of people in a target geographic range in a predetermined onset state in the natural onset phase; wherein the predetermined morbidity state comprises: a susceptible state, an exposed state, a pathogenic state, and an isolated state.
Further, the data samples of the urban management and control stage include: the number of people in the target geographic range in the preset disease state in the urban management and control stage; wherein the predetermined morbidity state comprises: a susceptible state, an exposed state, a pathogenic state, and an isolated state.
Further, the training module 404 is further configured to extract a new data sample from the new data samples in the natural attack stage as a current new natural sample when the population in the target geographic range migrates outside the target geographic range or the population outside the target geographic range migrates inside the target geographic range; if the trend prediction model does not meet a preset new convergence condition corresponding to the natural morbidity stage, inputting the current new natural sample into the trend prediction model, and training the trend prediction model by using the current new natural sample to obtain at least one new natural parameter of the trend prediction model; and taking the next new natural sample of the current new natural sample as the current new natural sample, and repeatedly executing the operation until the trend prediction model meets the new convergence condition corresponding to the natural morbidity stage.
Further, the training module 404 is further configured to extract a new data sample from the new data samples in the urban management stage as a current new management sample; if the trend prediction model does not meet the preset new convergence condition corresponding to the urban management and control stage, inputting the current new management and control sample into the trend prediction model, and training the trend prediction model by using the current new management and control sample to obtain at least one new management and control parameter of the trend prediction model; and taking the next new control sample of the current new control sample as the current new control sample, and repeatedly executing the operation until the trend prediction model meets the new convergence condition corresponding to the urban control stage.
The infectious disease trend prediction device can execute the method provided by any embodiment of the application, and has the corresponding functional modules and beneficial effects of the execution method. Technical details not described in detail in this embodiment may be referred to the infectious disease trend prediction method provided in any embodiment of the present application.
Example IV
According to an embodiment of the present application, the present application also provides an electronic device and a readable storage medium.
As shown in fig. 6, is a block diagram of an electronic device of a method of infectious disease trend prediction according to an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the applications described and/or claimed herein.
As shown in fig. 6, the electronic device includes: one or more processors 601, memory 602, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions executing within the electronic device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In other embodiments, multiple processors and/or multiple buses may be used, if desired, along with multiple memories and multiple memories. Also, multiple electronic devices may be connected, each providing a portion of the necessary operations (e.g., as a server array, a set of blade servers, or a multiprocessor system). One processor 601 is illustrated in fig. 6.
The memory 602 is a non-transitory computer readable storage medium provided by the present application. The memory stores instructions executable by the at least one processor to cause the at least one processor to perform the infectious disease trend prediction method provided by the present application. The non-transitory computer-readable storage medium of the present application stores computer instructions for causing a computer to execute the infectious disease trend prediction method provided by the present application.
The memory 602 is used as a non-transitory computer readable storage medium for storing non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules (e.g., the acquisition module 401, the input/output module 402, and the prediction module 403 shown in fig. 4) corresponding to the infectious disease trend prediction method in the embodiment of the present application. The processor 601 executes various functional applications of the server and data processing by running non-transitory software programs, instructions, and modules stored in the memory 602, i.e., implements the infectious disease trend prediction method in the above-described method embodiments.
The memory 602 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application program required for a function; the storage data area may store data created from the use of the electronic device predicted from the trend of infectious diseases, and the like. In addition, the memory 602 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory 602 may optionally include memory remotely located with respect to processor 601, which may be connected to the electronic device of the infectious disease trend prediction method via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device of the infectious disease trend prediction method may further include: an input device 603 and an output device 604. The processor 601, memory 602, input device 603 and output device 604 may be connected by a bus or otherwise, for example in fig. 6.
The input device 603 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the electronic device of the infectious disease trend prediction method, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, a pointer stick, one or more mouse buttons, a track ball, a joystick, and the like. The output means 604 may include a display device, auxiliary lighting means (e.g., LEDs), tactile feedback means (e.g., vibration motors), and the like. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device may be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASIC (application specific integrated circuit), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
These computing programs (also referred to as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented in a high-level procedural and/or object-oriented programming language, and/or in assembly/machine language. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), the internet, and blockchain networks.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
According to the technical scheme of the embodiment of the application, the number of isolation personnel in each history period in N history periods before the current period is firstly obtained; wherein the number of isolation personnel includes: the number of dead people and the number of recovery people; then inputting the number of the isolation personnel in each history period into a trained trend prediction model; then, acquiring a trend prediction model based on the number of isolation personnel in each historical period and the number of isolation personnel in each future period in M future periods after the current period output by the pre-acquired prior knowledge; and predicting epidemic trend of the infectious disease in M future periods based on the number of isolation personnel in each future period. That is, the application optimizes the existing SEIR model, unifies the number of dead people and the number of recovery people into the number of isolation people, thus reducing the parameters related to the dead people, having small parameter jumping and fast convergence speed. Because the application adopts the technical means of uniformly inducing the number of dead people and the number of recovery people into the number of isolation people, the technical problems that the SQIR model in the prior art is very sensitive to parameters, has great difficulty in parameter adjustment, poor interpretation and difficult guarantee of generalization capability are solved; in addition, the technical scheme of the embodiment of the application is simple and convenient to realize, convenient to popularize and wider in application range.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present application may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution disclosed in the present application can be achieved, and are not limited herein.
The above embodiments do not limit the scope of the present application. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the scope of the present application.
Claims (12)
1. A method of predicting an infectious disease trend, the method comprising:
extracting a data sample from the data samples in the natural morbidity stage to serve as a current natural sample; if the trend prediction model does not meet the preset convergence condition corresponding to the natural morbidity stage, inputting the current natural sample into the trend prediction model, and training the trend prediction model by using the current natural sample to obtain at least one natural parameter of the trend prediction model; taking the next natural sample of the current natural sample as the current natural sample, and repeatedly executing the operation until the trend prediction model meets the convergence condition corresponding to the natural morbidity stage;
Extracting a data sample from the data samples in the urban management and control stage to serve as a current management and control sample; if the trend prediction model does not meet the preset convergence condition corresponding to the urban management and control stage, inputting the current management and control sample into the trend prediction model, and training the trend prediction model by using the current management and control sample to obtain at least one management and control parameter of the trend prediction model; taking the next control sample of the current control sample as the current control sample, and repeatedly executing the above operation until the trend prediction model meets the convergence condition corresponding to the urban control stage;
acquiring the number of isolation personnel in each history period in N history periods before the current period; wherein the number of isolation personnel includes: the number of dead people and the number of recovery people;
inputting the number of the isolation personnel in each history period into a trained trend prediction model; acquiring the trend prediction model based on the number of isolation personnel in each historical period and the number of isolation personnel in each future period in M future periods after the current period output by the pre-acquired prior knowledge; the a priori knowledge includes: probability of infection, average number of contacts, latency exposure coefficient, mortality or recovery coefficient; wherein, the value range of the infection probability is 0.01-0.07; the value range of the average number of contacts is [2-7]; the value range of the exposure coefficient of the incubation period is [1/14-1/10]; the value range of the death or recovery coefficient is [1/10-1];
Predicting epidemic trends of infectious diseases in the M future periods based on the number of isolation personnel in each future period; wherein, N and M are natural numbers greater than or equal to 1.
2. The method of claim 1, the data sample of the natural morbidity phase comprising: the number of people in a target geographic range in a predetermined onset state in the natural onset phase; wherein the predetermined morbidity state comprises: a susceptible state, an exposed state, a pathogenic state, and an isolated state.
3. The method of claim 1, the data samples of the urban management phase comprising: the number of people in the target geographic range in the preset disease state in the urban management and control stage; wherein the predetermined morbidity state comprises: a susceptible state, an exposed state, a pathogenic state, and an isolated state.
4. The method of claim 1, the method further comprising:
when population in the target geographic range is migrated outside the target geographic range or population outside the target geographic range is migrated inside the target geographic range, extracting a new data sample from the new data sample in the natural morbidity stage to serve as a current new natural sample;
If the trend prediction model does not meet a preset new convergence condition corresponding to the natural morbidity stage, inputting the current new natural sample into the trend prediction model, and training the trend prediction model by using the current new natural sample to obtain at least one new natural parameter of the trend prediction model; and taking the next new natural sample of the current new natural sample as the current new natural sample, and repeatedly executing the operation until the trend prediction model meets the new convergence condition corresponding to the natural morbidity stage.
5. The method of claim 4, the method further comprising:
extracting a new data sample from the new data sample of the urban management and control stage to serve as a current new management and control sample;
if the trend prediction model does not meet the preset new convergence condition corresponding to the urban management and control stage, inputting the current new management and control sample into the trend prediction model, and training the trend prediction model by using the current new management and control sample to obtain at least one new management and control parameter of the trend prediction model; and taking the next new control sample of the current new control sample as the current new control sample, and repeatedly executing the operation until the trend prediction model meets the new convergence condition corresponding to the urban control stage.
6. An infectious disease trend prediction apparatus, the apparatus comprising: the system comprises a training module, an acquisition module, an input and output module and a prediction module; wherein, the liquid crystal display device comprises a liquid crystal display device,
the training module is used for extracting a data sample from the data samples in the natural morbidity stage to serve as a current natural sample; if the trend prediction model does not meet the preset convergence condition corresponding to the natural morbidity stage, inputting the current natural sample into the trend prediction model, and training the trend prediction model by using the current natural sample to obtain at least one natural parameter of the trend prediction model; taking the next natural sample of the current natural sample as the current natural sample, and repeatedly executing the operation until the trend prediction model meets the convergence condition corresponding to the natural morbidity stage; extracting a data sample from the data samples in the urban management and control stage to serve as a current management and control sample; if the trend prediction model does not meet the preset convergence condition corresponding to the urban management and control stage, inputting the current management and control sample into the trend prediction model, and training the trend prediction model by using the current management and control sample to obtain at least one management and control parameter of the trend prediction model; taking the next control sample of the current control sample as the current control sample, and repeatedly executing the above operation until the trend prediction model meets the convergence condition corresponding to the urban control stage;
The acquisition module is used for acquiring the number of isolation personnel in each history period in N history periods before the current period; wherein the number of isolation personnel includes: the number of dead people and the number of recovery people;
the input/output module is used for inputting the number of the isolation personnel in each history period into the trained trend prediction model; acquiring the trend prediction model based on the number of isolation personnel in each historical period and the number of isolation personnel in each future period in M future periods after the current period output by the pre-acquired prior knowledge; wherein the prior knowledge comprises: probability of infection, average number of contacts, latency exposure coefficient, mortality or recovery coefficient; wherein, the value range of the infection probability is 0.01-0.07; the value range of the average number of contacts is [2-7]; the value range of the exposure coefficient of the incubation period is [1/14-1/10]; the value range of the death or recovery coefficient is [1/10-1];
the prediction module is used for predicting epidemic trend of infectious diseases in the M future periods based on the number of isolation personnel in each future period; wherein, N and M are natural numbers greater than or equal to 1.
7. The apparatus of claim 6, the data sample of the natural morbidity phase comprising: the number of people in a target geographic range in a predetermined onset state in the natural onset phase; wherein the predetermined morbidity state comprises: a susceptible state, an exposed state, a pathogenic state, and an isolated state.
8. The apparatus of claim 6, the data samples of the city management stage comprising: the number of people in the target geographic range in the preset disease state in the urban management and control stage; wherein the predetermined morbidity state comprises: a susceptible state, an exposed state, a pathogenic state, and an isolated state.
9. The apparatus of claim 6, the training module further to extract a new data sample from the new data samples of the natural onset phase as a current new natural sample when a population within a target geographic range migrates outside the target geographic range or a population outside the target geographic range migrates inside the target geographic range; if the trend prediction model does not meet a preset new convergence condition corresponding to the natural morbidity stage, inputting the current new natural sample into the trend prediction model, and training the trend prediction model by using the current new natural sample to obtain at least one new natural parameter of the trend prediction model; and taking the next new natural sample of the current new natural sample as the current new natural sample, and repeatedly executing the operation until the trend prediction model meets the new convergence condition corresponding to the natural morbidity stage.
10. The apparatus of claim 9, the training module further configured to extract a new data sample from new data samples of the city administration phase as a current new administration sample; if the trend prediction model does not meet the preset new convergence condition corresponding to the urban management and control stage, inputting the current new management and control sample into the trend prediction model, and training the trend prediction model by using the current new management and control sample to obtain at least one new management and control parameter of the trend prediction model; and taking the next new control sample of the current new control sample as the current new control sample, and repeatedly executing the operation until the trend prediction model meets the new convergence condition corresponding to the urban control stage.
11. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.
12. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011027596.6A CN112071437B (en) | 2020-09-25 | 2020-09-25 | Infectious disease trend prediction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011027596.6A CN112071437B (en) | 2020-09-25 | 2020-09-25 | Infectious disease trend prediction method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112071437A CN112071437A (en) | 2020-12-11 |
| CN112071437B true CN112071437B (en) | 2023-08-29 |
Family
ID=73682755
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011027596.6A Active CN112071437B (en) | 2020-09-25 | 2020-09-25 | Infectious disease trend prediction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112071437B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112529329A (en) * | 2020-12-21 | 2021-03-19 | 广东珠江智联信息科技股份有限公司 | Infectious disease prediction method based on BP algorithm and SEIR model |
| CN113345594B (en) * | 2020-12-22 | 2023-06-20 | 中国联合网络通信集团有限公司 | Information prediction method and device |
| CN112687396A (en) * | 2020-12-31 | 2021-04-20 | 医渡云（北京）技术有限公司 | Disease information processing method, device, equipment and medium based on epidemic prevention measures |
| CN113658713B (en) * | 2021-01-07 | 2023-01-06 | 腾讯科技（深圳）有限公司 | Infection tendency prediction method, device, equipment and storage medium |
| CN113837588B (en) * | 2021-09-17 | 2023-12-29 | 北京百度网讯科技有限公司 | Training method and device for evaluation model, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101960504B1 (en) * | 2017-12-18 | 2019-07-15 | 세종대학교산학협력단 | Apparatus and method for epidemic spread prediction modeling |
| CN110993119A (en) * | 2020-03-04 | 2020-04-10 | 同盾控股有限公司 | Epidemic situation prediction method and device based on population migration, electronic equipment and medium |
| CN111063451A (en) * | 2020-03-17 | 2020-04-24 | 广州地理研究所 | Infectious disease epidemic situation early risk situation analysis method based on input-diffusion function |
| CN111430041A (en) * | 2020-03-26 | 2020-07-17 | 北京懿医云科技有限公司 | Infectious disease epidemic situation prediction method and device, storage medium and electronic equipment |
| CN111430042A (en) * | 2020-03-31 | 2020-07-17 | 南方科技大学 | Method, apparatus, computer device and storage medium for predicting the spread of an infectious disease |
| CN111524611A (en) * | 2020-04-24 | 2020-08-11 | 腾讯科技（深圳）有限公司 | Method, device and equipment for constructing infectious disease trend prediction model |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3108393A4 (en) * | 2014-02-19 | 2017-11-01 | HRL Laboratories, LLC | Disease prediction system using open source data |
-
2020
- 2020-09-25 CN CN202011027596.6A patent/CN112071437B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101960504B1 (en) * | 2017-12-18 | 2019-07-15 | 세종대학교산학협력단 | Apparatus and method for epidemic spread prediction modeling |
| CN110993119A (en) * | 2020-03-04 | 2020-04-10 | 同盾控股有限公司 | Epidemic situation prediction method and device based on population migration, electronic equipment and medium |
| CN111063451A (en) * | 2020-03-17 | 2020-04-24 | 广州地理研究所 | Infectious disease epidemic situation early risk situation analysis method based on input-diffusion function |
| CN111430041A (en) * | 2020-03-26 | 2020-07-17 | 北京懿医云科技有限公司 | Infectious disease epidemic situation prediction method and device, storage medium and electronic equipment |
| CN111430042A (en) * | 2020-03-31 | 2020-07-17 | 南方科技大学 | Method, apparatus, computer device and storage medium for predicting the spread of an infectious disease |
| CN111524611A (en) * | 2020-04-24 | 2020-08-11 | 腾讯科技（深圳）有限公司 | Method, device and equipment for constructing infectious disease trend prediction model |
Non-Patent Citations (1)
| Title |
|---|
| 日、韩新型冠状病毒肺炎疫情分析与趋势预测;匡征凌;匡远凤;郭凯文;方瑾;;中国人兽共患病学报(第05期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112071437A (en) | 2020-12-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112071437B (en) | Infectious disease trend prediction method and device, electronic equipment and storage medium | |
| JP7228662B2 (en) | Event extraction method, device, electronic device and storage medium | |
| CN111681726B (en) | Processing method, device, equipment and medium of electronic medical record data | |
| CN112347769B (en) | Entity recognition model generation method and device, electronic equipment and storage medium | |
| US20210397947A1 (en) | Method and apparatus for generating model for representing heterogeneous graph node | |
| US11928432B2 (en) | Multi-modal pre-training model acquisition method, electronic device and storage medium | |
| CN111524611A (en) | Method, device and equipment for constructing infectious disease trend prediction model | |
| EP3937060A1 (en) | Method and apparatus for training semantic representation model, device and computer storage medium | |
| CN106407666A (en) | Method, apparatus and system for generating electronic medical record information | |
| JP7262571B2 (en) | Knowledge graph vector representation generation method, apparatus and electronic equipment | |
| WO2021232724A1 (en) | Method for extracting geographic location point spatial relationship, method for training extraction model, and devices | |
| KR102635800B1 (en) | Pre-training method, device, electronic equipment and medium of neural network model | |
| CN112528037A (en) | Edge relation prediction method, device, equipment and storage medium based on knowledge graph | |
| WO2023005287A1 (en) | Model pre-training method and apparatus, electronic device, and storage medium | |
| JP7300475B2 (en) | Entity Relationship Mining Method, Apparatus, Electronic Device, Computer Readable Storage Medium and Computer Program | |
| WO2023168909A1 (en) | Pre-training method and model fine-tuning method for geographical pre-training model | |
| US20210407693A1 (en) | Method, apparatus for predicting epidemic situation, device, storage medium and program product | |
| WO2023231350A1 (en) | Task processing method implemented by using integer programming solver, device, and medium | |
| JP2022173453A (en) | Deep learning model training method, natural language processing method and apparatus, electronic device, storage medium, and computer program | |
| US11514334B2 (en) | Maintaining a knowledge database based on user interactions with a user interface | |
| CN116306396A (en) | Chip verification method and device, equipment and medium | |
| KR102523034B1 (en) | Method and apparatus for detecting adverseness in medicine, electronic device, storage medium and program | |
| CN112949433B (en) | Method, device and equipment for generating video classification model and storage medium | |
| CN114723045B (en) | Model training method, device, system, apparatus, medium, and program product | |
| CN116434933B (en) | Intelligent nursing remote data processing method and system based on intelligent medical treatment |
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 |