CN111403051A - Method, device, equipment and medium for predicting epidemic situation morbidity based on period - Google Patents

Method, device, equipment and medium for predicting epidemic situation morbidity based on period Download PDF

Info

Publication number
CN111403051A
CN111403051A CN202010271242.XA CN202010271242A CN111403051A CN 111403051 A CN111403051 A CN 111403051A CN 202010271242 A CN202010271242 A CN 202010271242A CN 111403051 A CN111403051 A CN 111403051A
Authority
CN
China
Prior art keywords
determining
period
patients
patient
day
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
CN202010271242.XA
Other languages
Chinese (zh)
Other versions
CN111403051B (en
Inventor
焦晓康
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.)
Yidu Cloud Beijing Technology Co Ltd
Original Assignee
Yidu Cloud Beijing Technology Co Ltd
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 Yidu Cloud Beijing Technology Co Ltd filed Critical Yidu Cloud Beijing Technology Co Ltd
Priority to CN202210346084.9A priority Critical patent/CN114708987A/en
Priority to CN202010271242.XA priority patent/CN111403051B/en
Publication of CN111403051A publication Critical patent/CN111403051A/en
Application granted granted Critical
Publication of CN111403051B publication Critical patent/CN111403051B/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

Landscapes

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

Abstract

The disclosure relates to a method and a device for predicting epidemic situation morbidity, electronic equipment and a storage medium based on a period, relates to the technical field of computers, and can be applied to a scene of predicting epidemic situation morbidity in an epidemic situation propagation period. The method comprises the following steps: determining patient timing information from the initial patient data, and determining a current effective regeneration number corresponding to the existing statistical period according to the patient timing information; determining a target polynomial according to the current effective regeneration number, fitting a change curve of an effective regeneration number sequence through the target polynomial and the current effective regeneration number, and predicting the future effective regeneration number of the period to be measured according to the change curve; determining the number of newly increased patients in the first day of the period to be detected; and constructing a number prediction function according to the future effective regeneration number and the number of newly added patients on the first day, and predicting the number of newly added patients on the day of the period to be measured according to the number prediction function. The method and the system can predict the number of newly added patients in the future period every day based on actual data.

Description

Method, device, equipment and medium for predicting epidemic situation morbidity based on period
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method for periodically predicting epidemic disease number, an apparatus for periodically predicting epidemic disease number, an electronic device, and a computer-readable storage medium.
Background
The classical epidemic propagation model (SEIR) classifies people within the epidemic into four categories: susceptible (suscentable), Exposed (Exposed), Susceptible (infected) and rehabilitated (Recovered) to build models to analyze various population changes.
In order to estimate the growth trend of new patients in a certain epidemic spread period, researchers measure and calculate the basic regeneration number of the epidemic so as to determine the spreading capacity of the epidemic, namely the change trend of the number of patients. Nowadays, the measurement and calculation of the number of newly added patients mainly comes from the SEIR model, and the number variation trend of each state is calculated based on the SEIR model. In addition, a maximum likelihood algorithm can be adopted, a basic regeneration numerical value is calculated by utilizing a newly added patient sequence every day, and after the basic regeneration numerical value is obtained, the number of new patients which can be infected by the existing patients in an illness period can be calculated after a period.
It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the present disclosure, and thus may include information that does not constitute prior art known to those of ordinary skill in the art.
Disclosure of Invention
The present disclosure aims to provide a method for predicting epidemic disease morbidity based on a period, a device for predicting epidemic disease morbidity based on a period, an electronic device, and a computer readable storage medium, so as to overcome at least to a certain extent the problems that the existing SEIR model cannot be optimized according to the change of the number of actually newly added patients and cannot obtain the change of the newly added patients every day in a calculation period.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows, or in part will be obvious from the description, or may be learned by practice of the invention.
According to a first aspect of the present disclosure, there is provided a method for predicting epidemic disease incidence based on cycle, comprising: determining patient timing information from the initial patient data, and determining a current effective regeneration number corresponding to the existing statistical period according to the patient timing information; determining a target polynomial according to the current effective regeneration number, fitting a change curve of an effective regeneration number sequence through the target polynomial and the current effective regeneration number, and predicting the future effective regeneration number of the period to be measured according to the change curve; determining the number of newly increased patients in the first day of the period to be detected; and constructing a number prediction function according to the future effective regeneration number and the number of newly added patients on the first day, and predicting the number of newly added patients on the day of the period to be measured according to the number prediction function.
Optionally, determining the current effective regeneration number corresponding to the current statistical period according to the patient timing information includes: determining the number of statistical days of a statistical period, and dividing initial patient data according to the number of statistical days and the patient time sequence information to generate a corresponding initial patient sequence; and obtaining a basic regeneration number, and determining the current effective regeneration number corresponding to the existing statistical period through a maximum likelihood algorithm according to the basic regeneration number and the initial patient sequence.
Optionally, the number of people prediction function is constructed based on the future effective regeneration number and the number of newly added patients on the first day, and the method comprises the following steps: determining the total increment of the patients in the period to be detected according to the future effective regeneration number and the number of newly added patients on the first day; determining the statistical days of the statistical period, and determining the base increment of the patient according to the statistical days and the total increment of the patient; determining a plurality of day numbers of a cycle to be tested, and determining an increment proportion corresponding to each day number according to the base increment and each day number; a scaling factor is determined from the initial patient data, and a population prediction function is constructed from the statistical days, the number of future valid regenerations, the delta ratio, and the scaling factor.
Optionally, the people number prediction function is:
Figure BDA0002443222670000021
the first new patient number of the period to be measured is fir, the Rt is the effective future regeneration number corresponding to the period to be measured, a is the statistical days of the statistical period, b is the scaling coefficient, n is the number of the multiple days of the statistical period, and n is 1,2, …, a.
Optionally, the method further includes: determining the actual number of newly increased patients and the actual number of daily increased patients in a plurality of periods before the period to be detected; determining the value range and the step length of the scaling coefficients, and determining a target number of scaling coefficient values according to the value range and the step length; respectively determining the number of newly increased predicted patients and the number of newly increased predicted patients in a plurality of periods before the period to be detected according to the target data volume scaling coefficient values and the number prediction function; determining a loss function of the number prediction function according to the actual number of newly added patients corresponding to the multiple periods, the actual number of daily increased patients corresponding to the multiple periods, the predicted number of newly added patients corresponding to the multiple periods and the predicted number of daily newly added patients corresponding to the multiple periods; introducing the scaling coefficient values into the loss functions one by one for calculation to obtain a target number of loss function values; a target scaling factor value corresponding to the smallest loss function value is determined from the target number of loss function values, and the target scaling factor value is substituted into the population prediction function.
Optionally, determining a loss function of the population prediction function according to the actual number of newly added patients corresponding to the multiple cycles, the actual number of daily-added patients corresponding to the multiple cycles, the predicted number of newly added patients corresponding to the multiple cycles, and the predicted number of daily-added patients corresponding to the multiple cycles, includes: determining the total mean square error of the actual newly added patient number corresponding to the multiple periods and the predicted newly added patient number corresponding to the multiple periods; determining the daily mean square error of the actual daily increase patient number corresponding to the plurality of periods and the predicted daily increase patient number corresponding to the plurality of periods; and determining the total statistical days, and determining a loss function according to the total mean square error, the daily mean square error and the total statistical days.
Optionally, the loss function number loss is:
Figure BDA0002443222670000031
where loss is the loss function, SUMPractice ofFor actual number of newly added patients, SUM, corresponding to multiple cyclesPredictionPredicting a new patient number, DAY, for a plurality of cyclesPractice ofFor a number of cycles corresponding to a real daily increase in patient number, DAYPredictionThe number of patients is increased for the corresponding predicted days of a plurality of cycles, and T is the total number of days of statistics.
According to a second aspect of the present disclosure, there is provided an apparatus for predicting epidemic disease number based on period, comprising: the first regeneration number determining module is used for determining patient time sequence information from the initial patient data and determining the current effective regeneration number corresponding to the existing statistical period according to the patient time sequence information; the second regeneration number determining module is used for determining a target polynomial according to the current effective regeneration number, fitting a change curve of an effective regeneration number sequence through the target polynomial and the current effective regeneration number, and predicting the future effective regeneration number of the period to be measured according to the change curve; the patient number determining module is used for determining the number of newly increased patients in the first day of the period to be measured; and the number prediction module is used for constructing a number prediction function according to the future effective regeneration number and the number of newly added patients in the first day, and predicting the number of newly added patients in the day of the period to be detected according to the number prediction function.
Optionally, the first regeneration number determining module includes a first regeneration number determining unit, configured to determine a number of statistics days of a statistics period, and divide the initial patient data according to the number of statistics days and the patient timing information to generate a corresponding initial patient sequence; and obtaining a basic regeneration number, and determining the current effective regeneration number corresponding to the existing statistical period through a maximum likelihood algorithm according to the basic regeneration number and the initial patient sequence.
Optionally, the number prediction module includes a function construction unit, configured to determine a total patient increment of the period to be measured according to the future effective regeneration number and the number of newly added patients on the first day; determining the statistical days of the statistical period, and determining the base increment of the patient according to the statistical days and the total increment of the patient; determining a plurality of day numbers of a cycle to be tested, and determining an increment proportion corresponding to each day number according to the base increment and each day number; a scaling factor is determined from the initial patient data, and a population prediction function is constructed from the statistical days, the number of future valid regenerations, the delta ratio, and the scaling factor.
Optionally, the device for predicting epidemic disease morbidity based on the period further comprises a scaling factor determining module, configured to determine the actual number of newly added patients and the actual number of daily added patients in a plurality of periods before the period to be detected; determining the value range and the step length of the scaling coefficients, and determining a target number of scaling coefficient values according to the value range and the step length; respectively determining the number of newly increased predicted patients and the number of newly increased predicted patients in a plurality of periods before the period to be detected according to the target data volume scaling coefficient values and the number prediction function; determining a loss function of the number prediction function according to the actual number of newly added patients corresponding to the multiple periods, the actual number of daily increased patients corresponding to the multiple periods, the predicted number of newly added patients corresponding to the multiple periods and the predicted number of daily newly added patients corresponding to the multiple periods; introducing the scaling coefficient values into the loss functions one by one for calculation to obtain a target number of loss function values; a target scaling factor value corresponding to the smallest loss function value is determined from the target number of loss function values, and the target scaling factor value is substituted into the population prediction function.
Optionally, the scaling factor determining module includes a loss function determining unit, configured to determine a total mean square error between an actual number of newly added patients corresponding to the multiple cycles and a predicted number of newly added patients corresponding to the multiple cycles; determining the daily mean square error of the actual daily increase patient number corresponding to the plurality of periods and the predicted daily increase patient number corresponding to the plurality of periods; and determining the total statistical days, and determining a loss function according to the total mean square error, the daily mean square error and the total statistical days.
According to a third aspect of the present disclosure, there is provided an electronic device comprising: a processor; and a memory having computer readable instructions stored thereon, wherein the computer readable instructions, when executed by the processor, implement the method for predicting epidemic outbreak population based on cycle according to any one of the above.
According to a fourth aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method for cycle-based prediction of the number of outbreaks according to any one of the above.
The technical scheme provided by the disclosure can comprise the following beneficial effects:
the method for predicting epidemic morbidity based on the period in the exemplary embodiment of the disclosure determines the patient time sequence information from the initial patient data, and determines the current effective regeneration number corresponding to the existing statistical period according to the patient time sequence information; determining a target polynomial according to the current effective regeneration number, fitting a change curve of an effective regeneration number sequence through the target polynomial and the current effective regeneration number, and predicting the future effective regeneration number of the period to be measured according to the change curve; determining the number of newly increased patients in the first day of the period to be detected; and constructing a number prediction function according to the future effective regeneration number and the number of newly added patients on the first day, and predicting the number of newly added patients on the day of the period to be measured according to the number prediction function. On one hand, the number of newly added patients in the period to be detected is predicted through the number prediction function, the number of newly added patients in each day in the future period can be predicted according to the change of the newly added patients in each day based on actual patient data, and the method is not limited to the number prediction only taking the period as a unit, namely the change of the number of the patients in each day is fitted in a fine-grained manner. On the other hand, a change curve of the effective regeneration number sequence is fitted through the target polynomial and the current effective regeneration number, and the future effective regeneration number can be determined according to the change curve so as to fit different newly added number change trends.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure. It is to be understood that the drawings in the following description are merely exemplary of the disclosure, and that other drawings may be derived from those drawings by one of ordinary skill in the art without the exercise of inventive faculty. In the drawings:
FIG. 1 schematically illustrates a flow chart of a method for cycle-based prediction of epidemic outbreak population according to an exemplary embodiment of the present disclosure;
FIG. 2 schematically illustrates an overall flow chart for predicting an increasing number of patients on a daily basis according to an exemplary embodiment of the present disclosure;
FIG. 3 schematically illustrates a flow chart for determining a current effective regeneration number according to an exemplary embodiment of the present disclosure;
FIG. 4 schematically illustrates a flow chart for constructing a people prediction function according to an exemplary embodiment of the present disclosure;
FIG. 5 schematically illustrates a flow chart for determining a number of newly added patients on a day according to an exemplary embodiment of the present disclosure;
FIG. 6 schematically illustrates a flow chart for determining an optimized people prediction function according to an exemplary embodiment of the present disclosure;
FIG. 7 schematically illustrates a flow chart for constructing a loss function for a people number prediction function according to an exemplary embodiment of the present disclosure;
FIG. 8 schematically illustrates a block diagram of an apparatus for predicting population for an epidemic based on cycles, according to an exemplary embodiment of the present disclosure;
FIG. 9 schematically illustrates a block diagram of an electronic device according to an exemplary embodiment of the present disclosure;
fig. 10 schematically illustrates a schematic diagram of a computer-readable storage medium according to an exemplary embodiment of the present disclosure.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The same reference numerals denote the same or similar parts in the drawings, and thus, a repetitive description thereof will be omitted.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known structures, methods, devices, implementations, materials, or operations are not shown or described in detail to avoid obscuring aspects of the disclosure.
The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in the form of software, or in one or more software-hardened modules, or in different networks and/or processor devices and/or microcontroller devices.
At present, the measurement and calculation of the number of newly-increased people in the epidemic situation spreading period are mainly from a classical SEIR epidemic disease spreading model, a functional relation is constructed based on the number of individuals in an infection state, a latent state, an infection state and an isolation state and by combining the length of the latent state and the infection state, and the number change trend of each state is calculated by using the parameters. However, the prediction of the SEIR model for the newly added patients is based on a set of fixed calculation formulas, and after the initial information is provided, the SEIR model is not optimized along with the change of the number of the actually newly added patients, so that if external factor interference occurs, the model prediction error will become larger and larger. In addition, after obtaining the number of basal regenerations, only the total number of people after a cycle can be deduced, and the newly added patient change per day in a cycle cannot be obtained. For example, when the disease cycle is 10 days, the trend of the population within ten days cannot be known.
Based on this, in the present exemplary embodiment, first, a method for predicting epidemic disease incidence number based on period is provided, the method for predicting epidemic disease incidence number based on period of the present disclosure may be implemented by using a server, and the method of the present disclosure may also be implemented by using a terminal device, where the terminal described in the present disclosure may include a mobile terminal such as a mobile phone, a tablet computer, a laptop computer, a palm computer, a Personal Digital Assistant (PDA), and a fixed terminal such as a desktop computer. Fig. 1 schematically illustrates a schematic diagram of a process flow for a cycle-based method for predicting epidemic incidence according to some embodiments of the present disclosure. Referring to fig. 1, the method for predicting epidemic incidence number based on period may include the following steps:
step S110, determining patient timing information from the initial patient data, and determining a current effective regeneration count corresponding to the current statistical period according to the patient timing information.
And step S120, determining a target polynomial according to the current effective regeneration number, and fitting a change curve of an effective regeneration number sequence through the target polynomial and the current effective regeneration number so as to predict the future effective regeneration number of the period to be measured according to the change curve.
And step S130, determining the number of newly increased patients in the first day of the period to be measured.
And step S140, constructing a number prediction function according to the future effective regeneration number and the number of newly added patients in the first day, and predicting the number of newly added patients in the day of the period to be measured according to the number prediction function.
According to the method for predicting the epidemic disease number based on the period in the embodiment, on one hand, the number of newly increased patients in the period to be detected is predicted through the number prediction function, the number of newly increased patients in each day in the future period can be predicted according to the change of the newly increased patients in each day based on actual patient data, and the method is not limited to the number prediction only taking the period as a unit, namely, the number change in each day is fitted in a fine-grained manner. On the other hand, a change curve of the effective regeneration number sequence is fitted through the target polynomial and the current effective regeneration number, and the future effective regeneration number can be determined according to the change curve so as to fit different newly added number change trends.
Next, the method for predicting the population of epidemic outbreaks based on the period in the present exemplary embodiment will be further described.
In step S110, patient time series information is determined from the initial patient data, and the current effective regeneration count corresponding to the existing statistical period is determined based on the patient time series information.
In some exemplary embodiments of the present disclosure, the initial patient may be all diagnosed patients for a certain disease identified from an existing patient data record. The initial patient data may be data information related to the initial patient, which may include patient personal information of the patient, time of diagnosis of the patient, patient condition information, and the like. The patient timing information may be timing information related to the time of diagnosis for different ones of the initial patients. For example, if confirmed patients within 15 days from the disease are acquired from the existing patient data, the corresponding time-series information 1 may be added to the patient confirmed on day 1, the corresponding time-series information 2 may be added to the patient confirmed on day 2, and so on, and the corresponding time-series information 15 may be added to the patient confirmed on day 15. The existing statistical period may be a statistical period in which the initial patient is located, which is determined according to the patient timing information, for example, if the initial patient is distributed in three statistical periods, the number of the existing statistical periods is three. The effective regeneration Number (Rt) may be the Number of persons who can be infected on average by one patient who starts to develop symptoms at time t during the course of disease transmission and development. In most cases this t represents a time of day, typically in units of days. In the present disclosure, each statistical period corresponds to one effective regeneration number. The current effective regeneration count may be an effective regeneration count calculated from existing actual data.
Referring to fig. 2, fig. 2 schematically illustrates an overall flow chart for predicting the number of newly added patients on a daily basis. In step S210, initial patient data is obtained through a network or a pre-established epidemic situation analysis database, and patient timing information is determined from the initial patient data; in step S220, the corresponding current effective regeneration count is determined based on the patient timing information.
According to some exemplary embodiments of the present disclosure, a statistical number of days of a statistical cycle is determined, initial patient data is divided according to the statistical number of days and patient timing information to generate a corresponding initial patient sequence; and obtaining a basic regeneration number, and determining the current effective regeneration number corresponding to the existing statistical period through a maximum likelihood algorithm according to the basic regeneration number and the initial patient sequence. The statistical period may be a statistical period determined according to the onset of a disease, for example, if the period from infection to symptom of a disease is 10 days, 10 days may be used as a statistical period. The statistical number of days may be a number of days included in a statistical period, for example, the statistical number of days may be 5 days, 10 days, 14 days, etc., and the statistical number of days may be determined according to the onset characteristics of a certain disease, which is not limited in any way by this disclosure. The initial patient sequence may be a patient sequence obtained by dividing the initial patient data according to a statistical period. Basic Reproduction Number (R0) may refer to the Number of persons that can be transmitted by an average patient during the disease cycle in an environment that is entirely susceptible to a population without intervention. The maximum likelihood algorithm, also called maximum likelihood estimation or maximum likelihood estimation, is a method of parameter estimation, which estimates the parameters of a probability model by sampling. The current effective regeneration number may be an effective regeneration number corresponding to each initial patient sequence determined according to the existing initial patient sequence, and the current effective regeneration number may refer to an effective regeneration number corresponding to each existing statistical period, and each statistical period has an effective regeneration number corresponding thereto.
Referring to fig. 3, fig. 3 schematically shows a flow chart for determining The current effective regeneration number, in step S310, a statistical period corresponding to a disease, i.e., The number of days included in a statistical period, is determined according to infection characteristics of The disease, after The initial patient data is obtained, The initial patient data may be divided according to patient timing information, for example, if The statistical number of days of a statistical period is 5 days, The initial patient data is divided according to a period of 5 days, patients with patient timing information of 1,2, 3, 4, 5 are divided into a sequence, and so on, The initial patient data is divided into an independent periodic sequence, and The last patient data less than one period is also divided into an independent periodic sequence, for example, The obtained 18-day patients are divided into 4 periodic sequences, i.e., { x1, x2, x3, x4, x5}, { x6, x7, x8, x 5848, x10, x11, x12, x13, x 638, x9, x 368, x L, x 368, x9, x3, x3, x9, x9, x.
For example, assume that the initial patient sequence conforms to a poisson distribution, assume that the initial patient sequence is: n is a radical of1,N2...Nx，NxThe number of patients corresponding to the xth statistical period may be indicated. Combining the distribution w of patient generation time (latency time + time to onset to time to confirm) yields the maximized log likelihood function as shown in equation 1.
Figure BDA0002443222670000101
Wherein the content of the first and second substances,
Figure BDA0002443222670000102
by maximizing the likelihood function, the effective regeneration number Rt value corresponding to the time series data in the period can be obtained.
In step S120, a target polynomial is determined according to the current effective regeneration number, and a variation curve of the effective regeneration number sequence is fitted through the target polynomial and the current effective regeneration number, so as to predict a future effective regeneration number of the period to be measured according to the variation curve.
In some exemplary embodiments of the present disclosure, the target polynomial may be a polynomial for fitting a variation trend curve of the effective regeneration number. The valid regeneration number sequence may be a valid regeneration number sequence obtained by fitting the current valid regeneration number. The change curve may be a curve reflecting a trend of change in the effective regeneration number. The period to be measured may be a future period in which the number of newly added patients needs to be determined. The future effective regeneration number may be an effective regeneration number corresponding to a future period predicted from the change curve.
Referring to fig. 2, in step S230, a future effective regeneration count for a future cycle may be determined according to the calculated current effective regeneration count. Specifically, after the current effective regeneration number is determined according to the initial patient sequence, a target polynomial for fitting a change curve of the effective regeneration number may be determined according to the current effective regeneration number, for example, in order to fit a more complex jitter curve, a polynomial of order 3 may be selected. The current cycle number is selected as the input value of the target polynomial, for example, the first cycle is 1-5 days, the second cycle is 6-10 days, and the first cycle and the second cycle correspond to the input values 1 and 2, respectively. And taking the actual effective regeneration number Rt of each period as an output value, and fitting by adopting a target polynomial of a 3-order polynomial to obtain a change curve of the effective regeneration number sequence. For example, an expression of the polynomial fitting Rt denoted as fn (n) is shown in formula 2, where n is the period.
Figure BDA0002443222670000103
The fitting process can be carried out by a polyfit function, wherein the polyfit function can be a function used for curve fitting in Matrix laboratory (MATrix L laboratory, MAT L AB) software, wherein the curve fitting can be a data set on known discrete points, namely function values on the known point set, an analytic function (the graph of which is a curve) is constructed to enable the data set to be as close to a given value as possible on the original discrete points, and the future effective regeneration number, namely the effective regeneration number Rt corresponding to the future period can be determined according to the fitted change curve.
In step S130, the number of newly increased patients on the first day of the cycle to be measured is determined.
In some exemplary embodiments of the disclosure, the number of newly-increased patients on the first day may be the number of newly-increased patients on the first day of the period to be measured. The number of newly added patients on the first day of the period to be detected can be determined according to the existing patient data, so that a number prediction function can be constructed according to the number of newly added patients on the first day.
In step S140, a number-of-people prediction function is constructed according to the future effective regeneration number and the number of newly-added patients on the first day, and the number of newly-added patients on the day of the period to be measured is predicted according to the number-of-people prediction function.
In some exemplary embodiments of the disclosure, the number of newly added patients per day may be the number of newly added patients predicted to occur each day in a certain period to be measured according to the number prediction function. According to the obtained number prediction function, the number of newly added patients per day in the period to be measured, namely the number of newly added patients per day, can be predicted, so that a fine-grained prediction result taking the day as a unit is realized. The population prediction function may be a computational model for predicting the number of newly added patients for a disease in a future cycle.
Referring to fig. 2, in step S240, after determining the future effective regeneration number according to the variation curve of the effective regeneration number, a people number prediction function for predicting the number of newly added patients may be constructed according to the effective regeneration number, and the number of newly added patients in a certain future period may be predicted according to the people number prediction function, so as to predict when the propagation and development of the disease reaches a peak according to the variation trend of the number of newly added patients in a day, and then a decision scheme for eliminating the disease is made according to the maximum carrying capacity of hospitals in various regions.
According to some exemplary embodiments of the present disclosure, determining a total patient increment for the cycle under test based on the future effective regeneration count and the number of newly added patients for the first day; determining the statistical days of the statistical period, and determining the base increment of the patient according to the statistical days and the total increment of the patient; determining a plurality of day numbers of a cycle to be tested, and determining an increment proportion corresponding to each day number according to the base increment and each day number; a scaling factor is determined from the initial patient data, and a population prediction function is constructed from the statistical days, the number of future valid regenerations, the delta ratio, and the scaling factor. The total number of newly added patients on the first day of the period to be measured can be the number of newly added patients on the first day in the statistical period. The total patient increment for the period to be measured may be the total number of newly added patients generated during the statistical period, i.e., the total number of newly added patients generated each day during the statistical period. The base increment can be the number of newly added patients determined according to the statistical days and the total increment of the patients. The number of days may be a number corresponding to each day in the period to be measured, for example, if one statistical period is 5 days, the number of days corresponding to each day in the statistical period is "1, 2, 3, 4, 5". The increment proportion can be the proportion of the number of newly added patients in each day in the period to be measured to the total increment of the patients. The scaling factor may be a scaling/stretching factor introduced to control the overall error when predicting the number of new patients in the future period, and may be represented by b. Currently, existing initial patient data is determined.
With the SEIR model of the prior art, according to the definition of the basic regeneration number R0, only the change of the number of newly added patients after a statistical period can be estimated, but the change of the number of people in each day in the statistical period cannot be determined, and for this problem, an initial people number prediction function f (a, b, Rt, fir) based on an exponential function can be constructed, and referring to fig. 4, fig. 4 schematically shows a flowchart for constructing the people number prediction function. The method comprises the following specific steps:
in step S410, determining the number of newly added patients on the first day in the period to be tested, i.e. the number of newly added patients on the first day in the period to be tested, and recording as fir; obtaining a future effective regeneration number, which may be an effective regeneration number Rt corresponding to the period to be measured in the present exemplary embodiment; and determining the total increment of the patient according to the number fir of newly added patients on the first day and the number Rt of effective regeneration in the future, as shown in formula 3.
Total increment of fir × Rt (equation 3)
In step S420, a statistical number of days of the statistical period is obtained and recorded as a; and determining a base increment according to the statistical days and the total increment of the patient, wherein the base increment can be expressed by base, and the base increment is shown as an equation 4.
Figure BDA0002443222670000121
In step S430, according to the base increment, an increment ratio corresponding to the newly increased number of patients in each day in the period to be measured, that is, an increment ratio corresponding to the number n of days can be determinednAs shown in equation 5.
Figure BDA0002443222670000122
In step S440, according to the obtained number of newly added patients on the first day fir, the number of effective regeneration in the future Rt and the increment proportion, the number of newly added patients on the initial day in the period to be measured can be obtained as fir × Rt × rationAnd constructing an initial people number prediction function.
According to some exemplary embodiments of the present disclosure, the people number prediction functions corresponding to different statistical periods are defined to be consistent, in order to control the overall error, a scaling coefficient is introduced, and according to the scaling coefficient and the initial valueThe number of newly added patients on the first day can be predicted as follows:
Figure BDA0002443222670000131
therefore, the expression of the people number prediction function may be as shown in equation 6.
Figure BDA0002443222670000132
According to some exemplary embodiments of the present disclosure, an initial number of newly increased patients per day corresponding to each number of days is predicted from the total number of patient increments and each increment proportion; determining a value range and a step length of the scaling coefficient, and determining an initial scaling coefficient value from the value range according to the step length; and calculating the number of newly added patients on each initial day one by one according to the initial scaling coefficient value so as to determine the number of newly added patients on the day to be detected. The number of newly added patients on the initial day can be the number of newly added patients generated each day in the period to be measured, which is determined according to the established number prediction function. The value range of the scaling factor may be a predefined value interval in which the value of the scaling factor is located. The step size may be a certain number of values that the scaling factor adds at each operation. The scaling factor value may be a specific value corresponding to the scaling factor. The initial scaling factor value can be a scaling factor value determined from the value range of the initial coefficient according to the step length, and is used for calculating the number of newly added patients to be measured on the day of the period to be measured. The number of newly added patients per day can be obtained by scaling the number of newly added patients per day according to the scaling factor.
Referring to fig. 5, fig. 5 schematically illustrates a flow chart for determining a predicted number of new patients on a daily basis. Two methods for determining the scaling factor value are provided in the present disclosure, and the process of determining the scaling factor value from the data characteristics of the existing patient data is disclosed in steps S510-S530 in fig. 5. In step S510, the number of newly added patients on the initial day corresponding to each day number is predicted from the total patient increment and each increment ratio. The number of newly added patients on the initial day can be determined according to the number prediction function. In step S520, after the scaling factor is introduced, a value range of the scaling factor may be determined, and a step length corresponding to the scaling factor is set. In step S530, a scaling factor value may be selected from the value range according to the given step length as an initial scaling factor value, and after the initial scaling factor value is determined, the initial scaling factor value may be respectively calculated with the number of newly added patients on the initial day, so as to obtain the number of newly added patients on the day to be measured. For example, for the scaling coefficient b, the value range of b may be limited to [0.1, 20], and the step length of b is determined to be 0.1, then b values with a target number of 200 may be generated, an initial scaling coefficient value (e.g., 10) may be selected from the 200 b values, and 10 is substituted into the population prediction function, the initial scaling coefficient value and the number of newly increased patients on each initial day are calculated one by one, and the number of newly increased patients on each day in the period to be measured may be obtained, that is, the number of newly increased patients on the new day is predicted.
According to some exemplary embodiments of the present disclosure, in order to optimize a scaling factor according to existing patient data, embodiments of the present invention provide a second method of determining a scaling factor, including: determining the actual number of newly increased patients and the actual number of daily increased patients in a plurality of periods before the period to be detected; determining the value range and the step length of the scaling coefficients, and determining a target number of scaling coefficient values according to the value range and the step length; respectively determining the number of newly increased predicted patients and the number of newly increased predicted patients in a plurality of periods before the period to be detected according to the target data volume scaling coefficient values and the number prediction function; determining a loss function of the number prediction function according to the actual number of newly added patients corresponding to the multiple periods, the actual number of daily increased patients corresponding to the multiple periods, the predicted number of newly added patients corresponding to the multiple periods and the predicted number of daily newly added patients corresponding to the multiple periods; introducing the scaling coefficient values into the loss functions one by one for calculation to obtain a target number of loss function values; a target scaling factor value corresponding to the smallest loss function value is determined from the target number of loss function values, and the target scaling factor value is substituted into the population prediction function.
The plurality of periods before the period to be measured may be periods before the period to be measured, which correspond to the number of actually newly added patients. The number of newly added patients may be the number of newly added patients actually generated in each period before the period to be measuredThe number of people, which can be recorded as SUMPractice of. The actual daily increase of patients can be the number of newly added patients actually generated in each DAY in each period before the period to be detected, and is recorded as DAYPractice of. The predicted number of newly added patients can be the number of newly added patients in each period before the period to be measured predicted according to the number prediction function, the predicted number of newly added patients can be the SUM of the number of newly added patients in each period before the period to be measured predicted, and the predicted number of newly added patients can be recorded as SUMPrediction. The predicted number of the patients increasing daily can be the number of the newly increased patients in each period before the period to be measured predicted according to the number prediction function, and the predicted number of the patients increasing daily can be recorded as DAYPrediction. The target number may be the number of the scaling coefficient values determined according to the value range and the step size. The loss function may be a function reflecting a difference between the newly added number of patients predicted by the number prediction function and the actually added number of patients. The loss function value may be a function value corresponding to a loss function determined by substituting the scaling coefficient value into the loss function. The minimum loss function value may be a loss function value having a smallest value determined from the plurality of loss function values. The target scaling factor value may be a scaling factor value corresponding to the minimum loss function value. The target scaling factor value may be a scaling factor value corresponding to the minimum loss function value obtained by the people number prediction function after the optimization processing is performed on the target polynomial.
Referring to fig. 6, the manner of determining the scaling factor includes: in step S610, the actual number of newly added patients and the actual number of daily patients for a plurality of cycles before the cycle to be measured are determined. In step S620, a value range and a step size of the scaling coefficients are determined, and a target number of scaling coefficient values are determined according to the value range and the step size. In step S630, the number of newly predicted patients and the number of newly predicted patients on the predicted day for a plurality of cycles before the cycle to be measured are respectively determined according to the target data volume scaling factor values and the number prediction function; and summing the number of newly added patients to be detected on the day to obtain the number of newly added patients to be detected. In step S640, a loss function of the population prediction function is determined according to the actual number of newly added patients corresponding to the plurality of periods, the actual number of daily added patients corresponding to the plurality of periods, the predicted number of newly added patients corresponding to the plurality of periods, and the predicted number of newly added patients corresponding to the plurality of periods. In step S650, the scaling coefficient values are brought into the loss function one by one to be calculated, so as to obtain a target number of loss function values; for example, for the scaling coefficient b, the value range of b may be limited to [0.1, 20], and the step size of b is determined to be 0.1, then the target number of 200 b values may be generated, and the 200 b values are respectively brought into the loss function for calculation, so as to obtain 200 loss function values. In step S660, a target scaling factor value corresponding to the smallest loss function value is determined from the target number of loss function values, and the target scaling factor value is substituted into the population size prediction function. And selecting a minimum loss function value from the 200 obtained loss function values, acquiring a target scaling coefficient value corresponding to the minimum loss function value, and bringing the target scaling coefficient value into the people number prediction function so as to optimize the people number prediction function.
According to some exemplary embodiments of the present disclosure, a total mean square error of actual newly added patient numbers corresponding to a plurality of cycles and predicted newly added patient numbers corresponding to a plurality of cycles is determined; determining the daily mean square error of the actual daily increase patient number corresponding to the plurality of periods and the predicted daily increase patient number corresponding to the plurality of periods; and determining the total statistical days, and determining a loss function according to the total mean square error, the daily mean square error and the total statistical days. The total mean square error may be an error determined from the actual number of newly added patients and the predicted number of newly added patients for a plurality of periods before the period to be measured. The daily mean square error may be an error determined from specific values of the actual daily increase patient count and the predicted daily increase patient count for a plurality of periods before the period to be measured. The total number of days counted can be recorded as T.
In steps S250 and S260, the daily mean square error and the total mean square error may be calculated to determine the loss function from the daily mean square error and the total mean square error. Referring to fig. 7, fig. 7 schematically illustrates a flow chart for determining a loss function for a people prediction function. Acquiring the actual number of newly added patients and the actual number of newly added patients on a day in a plurality of periods before the period to be detected; in step S710, calculating a total mean square error between the actual number of newly added patients and the predicted number of newly added patients in a plurality of periods before the period to be measured; in step S720, a daily mean square error between the actual daily gain patient and the predicted daily gain patient for a plurality of periods before the period to be measured is calculated; in step S730, a corresponding loss function may be determined according to the total mean square error, the daily mean square error, and the number of statistical days. The loss function loss is shown in equation 7.
Figure BDA0002443222670000161
∑ (DAY) among themPractice of-DAYPrediction)2Is the sum of the daily mean square errors of a plurality of periods prior to the period to be measured.
In practice, the people number prediction function is found to be optimized only according to the prediction error of the newly added patients on each day in the area with large shaking of the newly added patients, so that the deviation between the predicted accumulated value and the actual value is large after the prediction error of each day is accumulated. This is because the exponential curve is smoother than the jittered data, and if the data fluctuates more, the deviation after smoothing is larger. Therefore, the optimization direction of the human number prediction function in the present disclosure is not limited to reducing the prediction error of each day; in the case of large jitter variations, the optimization objective will also take into account the cumulative value, taking the total patient increment over the period to be measured as part of the constraint. The optimization mode can make the optimization direction of the people number prediction function more macroscopic, and is not limited to the deviation of each day.
In step S270, a target scaling factor value corresponding to the loss function that has the smallest loss function value may be determined; in step S280, the people prediction function may be optimized according to the target scaling factor value, so that the people prediction function may be adjusted according to the actual people change. Specifically, the detailed process of optimizing the people number prediction function may be: after the target number of scaling coefficient values is obtained, different b values can be brought into the loss function, and then the loss function value corresponding to each b value can be obtained. The value b corresponding to the smallest loss function value among the plurality of loss function values obtained is selected as the value b in the population number prediction function f (a, b, Rt, fir), that is, the target scaling coefficient value. And optimizing the people number prediction function according to the target scaling coefficient value. Because the people number prediction function in the method is different from the fixed calculation form of the change of the number of the patients of the SEIR model, the method is a dynamic change scheme for the fitting trend of the change of the number of the newly added patients every day, and is more suitable for the change situation of the actual epidemic situation.
For example, the statistical period corresponding to a certain disease includes 5 days, and after the target scaling coefficient value (i.e., the b value) is determined, the Rt value of the future time period generated by combining fn (n) can be used to calculate the predicted new patient number of each specific day in the future period by using f (a, b, Rt, fir). Wherein, the fir is the actual value and can be directly carried in; if the fir is the value in a certain future period, the fir value of each period in the future can be obtained by calculating backwards cycle by cycle according to the existing fir value of the latest period.
In summary, in the method for predicting the number of epidemic outbreaks based on the period in the exemplary embodiment of the disclosure, the patient timing information is determined from the initial patient data, and the current effective regeneration number corresponding to the current statistical period is determined according to the patient timing information; determining a target polynomial according to the current effective regeneration number, fitting a change curve of an effective regeneration number sequence through the target polynomial and the current effective regeneration number, and predicting the future effective regeneration number of the period to be measured according to the change curve; determining the number of newly increased patients in the first day of the period to be detected; and constructing a number prediction function according to the future effective regeneration number and the number of newly added patients on the first day, and predicting the number of newly added patients on the day of the period to be measured according to the number prediction function. On one hand, the number prediction function constructed in the method can predict the number of newly added patients in each day in a future period aiming at the change of the newly added patients in each day based on actual patient data, is not limited to the number prediction only taking the period as a unit, and realizes fine-grained fitting of the number change in each day in the period. On the other hand, a change curve of the effective regeneration number sequence is fitted through the target polynomial and the current effective regeneration number, and the future effective regeneration number can be determined according to the change curve so as to fit different newly added number change trends. On the other hand, when the newly added number of people in each day is fitted, the total increment of the patients in the period is considered, and the total increment of the patients is restrained, so that the situation that when the data with large fitting jitter is fitted, the number prediction function falls into the fitting of the number of the newly added patients in the day, and the deviation caused by the total increment of the patients is ignored can be avoided. On the other hand, the method and the device can dynamically adjust the prediction result of the number prediction function according to the number of newly added diseases on a day, so that the number prediction function is reconstructed according to the to-be-detected condition of the disease to predict the number of people.
It should be noted that although the steps of the method of the present invention are depicted in the drawings in the order tested, this does not require or imply that the steps must be performed in the order tested or that all of the depicted steps must be performed to achieve the desired results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions, etc.
In addition, in this example embodiment, a device for predicting epidemic situation outbreak number based on cycle is also provided. Referring to fig. 8, the apparatus 800 for predicting epidemic incidence number based on period may include: a first regeneration number determination module 810, a second regeneration number determination module 820, a patient number determination module 830, and a population number prediction module 840.
Specifically, the first regeneration number determining module 810 may be configured to determine patient timing information from the initial patient data, and determine a current effective regeneration number corresponding to an existing statistical period according to the patient timing information; the second regeneration number determining module 820 may be configured to determine a target polynomial according to the current effective regeneration number, and fit a variation curve of the effective regeneration number sequence through the target polynomial and the current effective regeneration number to predict a future effective regeneration number of the period to be measured according to the variation curve; the patient number determination module 830 may be configured to determine the number of newly added patients in the first day of the period to be tested; the number prediction module 840 may be configured to construct a number prediction function according to the future effective regeneration number and the number of newly added patients in the first day, and predict the number of newly added patients in the period to be measured in the day according to the number prediction function.
In an exemplary embodiment of the present disclosure, the first regeneration number determination module includes a first regeneration number determination unit for determining a statistics number of days of a statistics cycle, dividing the initial patient data according to the statistics number of days and the patient timing information to generate a corresponding initial patient sequence; and obtaining a basic regeneration number, and determining the current effective regeneration number corresponding to the existing statistical period through a maximum likelihood algorithm according to the basic regeneration number and the initial patient sequence.
In an exemplary embodiment of the disclosure, the number of people prediction module comprises a function construction unit, which is used for determining the total increment of patients in the period to be measured according to the future effective regeneration number and the number of newly added patients in the first day; determining the statistical days of the statistical period, and determining the base increment of the patient according to the statistical days and the total increment of the patient; determining a plurality of day numbers of a cycle to be tested, and determining an increment proportion corresponding to each day number according to the base increment and each day number; a scaling factor is determined from the initial patient data, and a population prediction function is constructed from the statistical days, the number of future valid regenerations, the delta ratio, and the scaling factor.
In an exemplary embodiment of the disclosure, the loss function determining module includes a scaling factor determining module for determining an actual number of newly increased patients and an actual number of daily increased patients for a plurality of cycles before the cycle to be tested; determining the value range and the step length of the scaling coefficients, and determining a target number of scaling coefficient values according to the value range and the step length; respectively determining the number of newly increased predicted patients and the number of newly increased predicted patients in a plurality of periods before the period to be detected according to the target data volume scaling coefficient values and the number prediction function; determining a loss function of the number prediction function according to the actual number of newly added patients corresponding to the multiple periods, the actual number of daily increased patients corresponding to the multiple periods, the predicted number of newly added patients corresponding to the multiple periods and the predicted number of daily newly added patients corresponding to the multiple periods; introducing the scaling coefficient values into the loss functions one by one for calculation to obtain a target number of loss function values; a target scaling factor value corresponding to the smallest loss function value is determined from the target number of loss function values, and the target scaling factor value is substituted into the population prediction function.
In an exemplary embodiment of the present disclosure, the scaling factor determining module includes a loss function determining unit, configured to determine a total mean square error between an actual number of newly added patients corresponding to a plurality of cycles and a predicted number of newly added patients corresponding to a plurality of cycles; determining the daily mean square error of the actual daily increase patient number corresponding to the plurality of periods and the predicted daily increase patient number corresponding to the plurality of periods; and determining the total statistical days, and determining a loss function according to the total mean square error, the daily mean square error and the total statistical days.
The specific details of each virtual device module for predicting epidemic disease number based on period have been described in detail in the corresponding method for predicting epidemic disease number based on period, and thus are not described herein again.
It should be noted that although in the above detailed description several modules or units of the apparatus for predicting the prevalence based on cycles are mentioned, this division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.
In addition, in an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.
As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a system, method or program product. Thus, various aspects of the invention may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.
An electronic device 900 according to such an embodiment of the invention is described below with reference to fig. 9. The electronic device 900 shown in fig. 9 is only an example and should not bring any limitations to the function and scope of use of the embodiments of the present invention.
As shown in fig. 9, the electronic device 900 is embodied in the form of a general purpose computing device. Components of electronic device 900 may include, but are not limited to: the at least one processing unit 910, the at least one storage unit 920, a bus 930 connecting different system components (including the storage unit 920 and the processing unit 910), and a display unit 940.
Wherein the storage unit stores program code that is executable by the processing unit 910 to cause the processing unit 910 to perform steps according to various exemplary embodiments of the present invention described in the above section "exemplary methods" of the present specification.
The storage unit 920 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)921 and/or a cache memory unit 922, and may further include a read only memory unit (ROM) 923.
Storage unit 920 may include a program/utility 924 having a set (at least one) of program modules 925, such program modules 925 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
Bus 930 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.
Electronic device 900 may also communicate with one or more external devices 970 (e.g., keyboard, pointing device, Bluetooth device, etc.), and may also communicate with one or more devices that enable a user to interact with the electronic device 900, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 900 to communicate with one or more other computing devices.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.
In an exemplary embodiment of the present disclosure, there is also provided a computer-readable storage medium having stored thereon a program product capable of implementing the above-described method of the present specification. In some possible embodiments, aspects of the invention may also be implemented in the form of a program product comprising program code means for causing a terminal device to carry out the steps according to various exemplary embodiments of the invention described in the above-mentioned "exemplary methods" section of the present description, when said program product is run on the terminal device.
Referring to fig. 10, a program product 1000 for implementing the above method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
A computer readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including AN object oriented programming language such as Java, C + +, or the like, as well as conventional procedural programming languages, such as the "C" language or similar programming languages.
Furthermore, the above-described figures are merely schematic illustrations of processes involved in methods according to exemplary embodiments of the invention, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is to be limited only by the terms of the appended claims.

Claims (10)

1. A method for predicting epidemic disease morbidity based on a period is characterized by comprising the following steps:
determining patient timing information from initial patient data, and determining a current effective regeneration number corresponding to an existing statistical period according to the patient timing information;
determining a target polynomial according to the current effective regeneration number, fitting a change curve of an effective regeneration number sequence through the target polynomial and the current effective regeneration number, and predicting the future effective regeneration number of the period to be measured according to the change curve;
determining the number of newly added patients at the first day of the period to be detected;
and constructing a number prediction function according to the future effective regeneration number and the number of newly added patients on the first day, and predicting the number of newly added patients on the day to be detected in the period to be detected according to the number prediction function.
2. The method according to claim 1, wherein the determining the current effective regeneration number corresponding to the current statistical period according to the patient timing information comprises:
determining the number of statistical days of a statistical period, and dividing the initial patient according to the number of statistical days and the patient time sequence information to generate a corresponding initial patient sequence;
and acquiring a basic regeneration number, and determining the current effective regeneration number corresponding to the existing statistical period through a maximum likelihood algorithm according to the basic regeneration number and the initial patient sequence.
3. The method according to claim 1, wherein the constructing a population prediction function according to the effective regeneration number and the number of newly added patients on the first day comprises:
determining the total increment of the patients in the period to be tested according to the future effective regeneration number and the number of newly added patients in the first day;
determining the statistical days of a statistical cycle, and determining the basal increment of the patient according to the statistical days and the total increment of the patient;
determining a plurality of day numbers of the period to be detected, and determining an increment proportion corresponding to each day number according to the base increment and each day number;
determining a scaling factor from the initial patient data, and constructing the population prediction function from the statistical days, the number of future valid regenerations, the delta ratio, and the scaling factor.
4. The method according to claim 3, wherein the population prediction function is:
Figure FDA0002443222660000021
the first-day newly-added patient number of the period to be measured is fir, the Rt is the future effective regeneration number corresponding to the period to be measured, a is the statistical days of the statistical period, b is the scaling coefficient, n is the number of the multiple days of the statistical period, and n is 1,2, …, a.
5. The method according to claim 3 or claim 4, wherein the scaling factor determining method comprises:
determining the actual number of newly increased patients and the actual number of daily increased patients in a plurality of periods before the period to be detected;
determining the value range and the step length of the scaling coefficients, and determining a target number of scaling coefficient values according to the value range and the step length;
respectively determining the number of newly increased predicted patients and the number of newly increased predicted patients in a plurality of periods before the period to be detected according to the target data volume scaling coefficient values and the number prediction function;
determining a loss function of the population prediction function according to the actual number of newly added patients corresponding to the plurality of periods, the actual number of the patients increasing daily corresponding to the plurality of periods, the predicted number of the newly added patients corresponding to the plurality of periods and the predicted number of the newly added patients increasing daily corresponding to the plurality of periods;
bringing the scaling coefficient values into the loss functions one by one for calculation to obtain the target number of loss function values;
determining a target scaling factor value corresponding to a minimum loss function value from the target number of loss function values, and substituting the target scaling factor value into the people number prediction function.
6. The method according to claim 5, wherein the determining the loss function of the population prediction function according to the actual number of newly added patients corresponding to the plurality of periods, the actual number of daily added patients corresponding to the plurality of periods, the predicted number of newly added patients corresponding to the plurality of periods and the predicted number of daily added patients corresponding to the plurality of periods comprises:
determining the total mean square error of the actual newly added patient number corresponding to the plurality of periods and the predicted newly added patient number corresponding to the plurality of periods;
determining a mean-square error between actual daily patient counts for the plurality of cycles and predicted daily patient counts for the plurality of cycles;
and determining the total statistical days, and determining a loss function according to the total mean square error, the daily mean square error and the total statistical days.
7. The method for predicting epidemic morbidity based on cycles according to claim 6, wherein the loss function loss is:
Figure FDA0002443222660000031
wherein loss is the loss function, SUMPractice ofFor the actual number of newly added patients, SUM, corresponding to the plurality of periodsPredictionPredicting a new patient number, DAY, for said plurality of cyclesPractice ofFor actual daily increase of patient number, DAY, corresponding to said plurality of cyclesPredictionAnd increasing the number of patients for the predicted days corresponding to the plurality of periods, wherein T is the total number of days in statistics.
8. A device based on cycle prediction epidemic situation morbidity, its characterized in that includes:
the first regeneration number determining module is used for determining patient time sequence information from initial patient data and determining a current effective regeneration number corresponding to the existing statistical period according to the patient time sequence information;
the second regeneration number determining module is used for determining a target polynomial according to the current effective regeneration number, fitting a change curve of an effective regeneration number sequence through the target polynomial and the current effective regeneration number, and predicting the future effective regeneration number of the period to be measured according to the change curve;
the patient number determining module is used for determining the number of newly added patients on the first day of the period to be detected;
and the number prediction module is used for constructing a number prediction function according to the future effective regeneration number and the number of newly added patients on the first day, and predicting the number of newly added patients on the day to be detected in the period to be detected according to the number prediction function.
9. An electronic device, comprising:
a processor; and
a memory having stored thereon computer readable instructions which, when executed by the processor, implement the method for cycle-based prediction of epidemic incidence according to any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method for cycle-based prediction of the number of outbreaks according to any one of claims 1 to 7.
CN202010271242.XA 2020-04-08 2020-04-08 Method, device, equipment and medium for predicting epidemic situation morbidity based on period Active CN111403051B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202210346084.9A CN114708987A (en) 2020-04-08 2020-04-08 Method, device, equipment and medium for predicting epidemic situation morbidity based on period
CN202010271242.XA CN111403051B (en) 2020-04-08 2020-04-08 Method, device, equipment and medium for predicting epidemic situation morbidity based on period

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010271242.XA CN111403051B (en) 2020-04-08 2020-04-08 Method, device, equipment and medium for predicting epidemic situation morbidity based on period

Related Child Applications (1)

Application Number Title Priority Date Filing Date
CN202210346084.9A Division CN114708987A (en) 2020-04-08 2020-04-08 Method, device, equipment and medium for predicting epidemic situation morbidity based on period

Publications (2)

Publication Number Publication Date
CN111403051A true CN111403051A (en) 2020-07-10
CN111403051B CN111403051B (en) 2022-04-22

Family

ID=71429479

Family Applications (2)

Application Number Title Priority Date Filing Date
CN202010271242.XA Active CN111403051B (en) 2020-04-08 2020-04-08 Method, device, equipment and medium for predicting epidemic situation morbidity based on period
CN202210346084.9A Pending CN114708987A (en) 2020-04-08 2020-04-08 Method, device, equipment and medium for predicting epidemic situation morbidity based on period

Family Applications After (1)

Application Number Title Priority Date Filing Date
CN202210346084.9A Pending CN114708987A (en) 2020-04-08 2020-04-08 Method, device, equipment and medium for predicting epidemic situation morbidity based on period

Country Status (1)

Country Link
CN (2) CN111403051B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112382406A (en) * 2020-11-11 2021-02-19 医渡云（北京）技术有限公司 Method, apparatus, medium, and device for estimating basic regeneration number of infectious disease
CN112992373A (en) * 2021-03-10 2021-06-18 山东大学 Epidemic trend prejudging method and system for infectious diseases

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170308678A1 (en) * 2014-02-19 2017-10-26 Hrl Laboratories, Llc Disease prediction system using open source data
CN108364694A (en) * 2018-03-09 2018-08-03 中华人民共和国陕西出入境检验检疫局 Airport Disease Warning Mechanism based on multi-data source big data and prevention and control system constituting method
US10178120B1 (en) * 2015-07-23 2019-01-08 Hrl Laboratories, Llc Method for determining contagion dynamics on a multilayer network
CN109166630A (en) * 2018-08-03 2019-01-08 杜占玮 A kind of Infectious Diseases Data monitor processing method and system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170308678A1 (en) * 2014-02-19 2017-10-26 Hrl Laboratories, Llc Disease prediction system using open source data
US10178120B1 (en) * 2015-07-23 2019-01-08 Hrl Laboratories, Llc Method for determining contagion dynamics on a multilayer network
CN108364694A (en) * 2018-03-09 2018-08-03 中华人民共和国陕西出入境检验检疫局 Airport Disease Warning Mechanism based on multi-data source big data and prevention and control system constituting method
CN109166630A (en) * 2018-08-03 2019-01-08 杜占玮 A kind of Infectious Diseases Data monitor processing method and system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
周涛等: "新型冠状病毒肺炎基本再生数的初步预测", 《中国循证医学杂志》 *
崔玉美等: "几类传染病模型中基本再生数的计算", 《复杂系统与复杂性科学》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112382406A (en) * 2020-11-11 2021-02-19 医渡云（北京）技术有限公司 Method, apparatus, medium, and device for estimating basic regeneration number of infectious disease
CN112992373A (en) * 2021-03-10 2021-06-18 山东大学 Epidemic trend prejudging method and system for infectious diseases
CN112992373B (en) * 2021-03-10 2022-09-16 山东大学 Epidemic trend prejudging method and system for infectious diseases

Also Published As

Publication number Publication date
CN114708987A (en) 2022-07-05
CN111403051B (en) 2022-04-22

Similar Documents

Publication Publication Date Title
Tran et al. Automatic ARIMA time series modeling for adaptive I/O prefetching
CN108509325B (en) Method and device for dynamically determining system timeout time
Young et al. Fast Bayesian inference for gene regulatory networks using ScanBMA
US6810495B2 (en) Method and system for software rejuvenation via flexible resource exhaustion prediction
CN111739658B (en) Method and device for predicting infectious disease trend based on input case
CN111403051B (en) Method, device, equipment and medium for predicting epidemic situation morbidity based on period
CN109461023B (en) Loss user retrieval method and device, electronic equipment and storage medium
CN112365998A (en) Infectious disease transmission scale simulation method and device and electronic equipment
CN109272348B (en) Method and device for determining number of active users, storage medium and electronic equipment
WO2023046059A1 (en) Cache warmup method and apparatus, and computer device and storage medium
CN114726758B (en) Industrial network abnormity determining method and device, computer equipment and storage medium
CN111489830A (en) Method and device for predicting epidemic situation data in sections, medium and electronic equipment
US20200111576A1 (en) Producing a multidimensional space data structure to perform survival analysis
CN112382406B (en) Method, apparatus, medium, and device for estimating basic regeneration number of infectious disease
CN111683156A (en) Information pushing method and device, electronic equipment and computer readable medium
CN111524610A (en) Method, device, equipment and storage medium for predicting number of confirmed persons of infectious diseases
CN113158435B (en) Complex system simulation running time prediction method and device based on ensemble learning
KR20200061968A (en) Time series data processing device and operating method thereof
CN111430035B (en) Method, device, electronic device and medium for predicting number of infectious diseases
JP5555109B2 (en) Service time prediction apparatus and service time prediction method
CN113345599A (en) Epidemic situation prediction method, epidemic situation prediction device, storage medium and electronic equipment
CN111506382B (en) Progress bar curve determination method and device, storage medium and electronic equipment
JP2020129180A (en) Job power prediction program, job power prediction method, and job power prediction device
CN109669779B (en) Method and device for determining cleaning path of data and cleaning data
KR20220078243A (en) Apparatus and method for predicting based on time series network data

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