CN113345594B - Information prediction method and device - Google Patents

Information prediction method and device Download PDF

Info

Publication number
CN113345594B
CN113345594B CN202011535711.0A CN202011535711A CN113345594B CN 113345594 B CN113345594 B CN 113345594B CN 202011535711 A CN202011535711 A CN 202011535711A CN 113345594 B CN113345594 B CN 113345594B
Authority
CN
China
Prior art keywords
time period
population
city
index
management
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202011535711.0A
Other languages
Chinese (zh)
Other versions
CN113345594A (en
Inventor
李阳
胡博文
陈博
张嘉帅
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.)
China United Network Communications Group Co Ltd
Unicom Big Data Co Ltd
Original Assignee
China United Network Communications Group Co Ltd
Unicom Big Data 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 China United Network Communications Group Co Ltd, Unicom Big Data Co Ltd filed Critical China United Network Communications Group Co Ltd
Priority to CN202011535711.0A priority Critical patent/CN113345594B/en
Publication of CN113345594A publication Critical patent/CN113345594A/en
Application granted granted Critical
Publication of CN113345594B publication Critical patent/CN113345594B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
    • G06F17/12—Simultaneous equations, e.g. systems of linear equations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
    • G06F17/13—Differential equations

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • General Physics & Mathematics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Public Health (AREA)
  • Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Algebra (AREA)
  • Operations Research (AREA)
  • Medical Informatics (AREA)
  • Biomedical Technology (AREA)
  • Pathology (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application provides a method and a device for information prediction, wherein the method comprises the following steps: determining a city management and control index of a target time period, wherein the city management and control index is determined according to a city activity index and a city reworking index; and inputting the city management and control indexes of the target time period and the target time period into a prediction model to obtain a prediction result of the target time period, wherein the prediction model is established based on the city management and control indexes of the historical time period, the number of susceptible people, the number of latent people, the number of infected people and the number of recovery people in the historical time period. The information prediction method and the information prediction device effectively improve the accuracy of the prediction of the evolution trend of the infectious disease population.

Description

Information prediction method and device
Technical Field
The present disclosure relates to the field of information processing, and in particular, to a method and apparatus for information prediction.
Background
In social life, the outbreak and spread of major infectious diseases can have a great influence on the national economic development and the life of people. How to quickly and accurately determine the inflection point of an infectious disease is a matter to be determined after the occurrence of an infectious disease.
Currently, in infectious disease dynamics, a susceptible-latent-infected-recovered (SEIR) model is widely used as a general model. The model reasonably predicts changes of a susceptible group (latent group), a latent group (exposed), an infected group (infected) and a recovered group (recovered) of the infectious disease, and effectively analyzes inflection points of the infectious disease. However, in practical application, the accuracy of the estimated result of the SEIR model is not high, and it is difficult to accurately predict the evolution trend of the infectious disease population under the condition of taking the measures for preventing infectious diseases to interfere.
Disclosure of Invention
The information prediction method and device provided by the application effectively improve the accuracy of prediction of the evolution trend of the infectious disease population.
In a first aspect, a method for information prediction is provided, including: determining a city management and control index of a target time period, wherein the city management and control index is determined according to a city activity index and a city reworking index; and inputting the target time period and the city management and control index of the target time period into a prediction model to obtain a prediction result of the target time period, wherein the prediction model is established based on the city management and control index of the historical time period, the susceptible population number, the latent population number, the infected population number and the recovery population number of the historical time period.
Optionally, the determining the city management index of the target time period includes: and determining the urban management index of the first time period in the historical time period as the urban management index of the target time period, wherein the time difference between the first time period and the target time period is a first threshold value.
Optionally, the city management index of the first period is obtained by the following formula:
M＝{(1-a)+(1-b)}
where a is the city activity index of the first time period, b is the city replication index of the first time period, M (x) = (x-min (x))/(max (x) -min (x)).
Optionally, the predictive model is the following set of equations:
Figure GDA0003198860510000021
wherein S is a susceptible population, E is a latent population, I is an infected population, R is a recovery population, T is an accumulated diagnostic population, n=s (T) +e (T) +i (T) +r (T); beta represents the infection rate, lambda represents the morbidity, and gamma represents the recovery rate. a is a coefficient of isolating people from management and control indexes of susceptible people, b is a coefficient of isolating people from management and control indexes of latent people, C is the urban management and control index, and m is a first threshold.
Optionally, before the inputting the target time period and the city management index of the target time period into the prediction model, the method further comprises: determining a prediction result of a first time period in the historical time period based on the prediction model; and training the prediction model by using the true value of the first time period and the prediction result of the first time period, and updating the parameters beta, lambda, a and b, wherein the true value is at least one of the number of susceptible people, the number of latent people, the number of infected people and the number of recovery people in the first time period.
The method for predicting the information is based on the traditional SEIR model susceptible population, the latent non-isolated population, the confirmed diagnosis population and the cured population, and introduces the urban management and control index to reflect the influence of prevention and control measures on the development of the infectious diseases, so that the household isolated population and the latent isolated population are increased, and the accuracy of predicting the evolution trend of the infectious disease population is effectively improved.
In a second aspect, there is provided an apparatus for information prediction, comprising: the determining module is used for determining a city management and control index of the target time period, wherein the city management and control index is determined according to a city activity index and a city reworking index; the processing module is used for inputting the target time period and the city management and control index of the target time period into the prediction model to obtain a prediction result of the target time period, wherein the prediction model is established based on the city management and control index of the historical time period, the number of susceptible people, the number of latent people, the number of infected people and the number of recovery people in the historical time period.
Optionally, the determining module is specifically configured to: and determining the urban management index of the first time period in the historical time period as the urban management index of the target time period, wherein the time difference between the first time period and the target time period is a first threshold value.
Optionally, the city management index of the first period is obtained by the following formula:
M＝{(1-a)+(1-b)}
where a is the city activity index of the first time period, b is the city replication index of the first time period, M (x) = (x-min (x))/(max (x) -min (x)).
Optionally, the predictive model is the following set of equations:
Figure GDA0003198860510000031
wherein S is a susceptible population, E is a latent population, I is an infected population, R is a recovery population, T is an accumulated diagnostic population, n=s (T) +e (T) +i (T) +r (T); beta represents the infection rate, lambda represents the morbidity, and gamma represents the recovery rate. a is a coefficient of isolating people from management and control indexes of susceptible people, b is a coefficient of isolating people from management and control indexes of latent people, C is the urban management and control index, and m is a first threshold.
Optionally, the determining module is specifically configured to: determining a prediction result of a first time period in the historical time period based on the prediction model; the processing module is further configured to: and training the prediction model by using the true value of the first time period and the prediction result of the first time period, and updating the parameters beta, lambda, a and b, wherein the true value is at least one of the number of susceptible people, the number of latent people, the number of infected people and the number of recovery people in the first time period.
In a third aspect, there is provided another apparatus for information prediction, comprising a processor coupled to a memory, operable to execute instructions in the memory to implement a method as in any one of the possible implementations of the first aspect. Optionally, the apparatus further comprises a memory. Optionally, the apparatus further comprises a communication interface, the processor being coupled to the communication interface.
In one implementation, the information prediction device is a data processing device. When one means of information prediction is a data processing device, the communication interface may be a transceiver, or an input/output interface.
In another implementation, the means for predicting information is a chip configured in a data processing device. When the means for information prediction is a chip arranged in the data processing device, the communication interface may be an input/output interface.
In a fourth aspect, there is provided a processor comprising: input circuit, output circuit and processing circuit. The processing circuitry is configured to receive signals via the input circuitry and to transmit signals via the output circuitry such that the processor performs the method of any one of the possible implementations of the first aspect described above.
In a specific implementation process, the processor may be a chip, the input circuit may be an input pin, the output circuit may be an output pin, and the processing circuit may be a transistor, a gate circuit, a trigger, various logic circuits, and the like. The input signal received by the input circuit may be received and input by, for example and without limitation, a receiver, the output signal may be output by, for example and without limitation, a transmitter and transmitted by a transmitter, and the input circuit and the output circuit may be the same circuit, which functions as the input circuit and the output circuit, respectively, at different times. The embodiments of the present application do not limit the specific implementation manner of the processor and the various circuits.
In a fifth aspect, a processing device is provided that includes a processor and a memory. The processor is configured to read instructions stored in the memory and to receive signals via the receiver and to transmit signals via the transmitter to perform the method of any one of the possible implementations of the first aspect.
Optionally, the processor is one or more and the memory is one or more.
Alternatively, the memory may be integrated with the processor or the memory may be separate from the processor.
In a specific implementation process, the memory may be a non-transient (non-transitory) memory, for example, a Read Only Memory (ROM), which may be integrated on the same chip as the processor, or may be separately disposed on different chips.
It should be appreciated that the related data interaction process, for example, transmitting the indication information, may be a process of outputting the indication information from the processor, and the receiving the capability information may be a process of receiving the input capability information by the processor. Specifically, the data output by the processing may be output to the transmitter, and the input data received by the processor may be from the receiver. Wherein the transmitter and receiver may be collectively referred to as a transceiver.
The processing means in the fifth aspect may be a chip, and the processor may be implemented by hardware or by software, and when implemented by hardware, the processor may be a logic circuit, an integrated circuit, or the like; when implemented in software, the processor may be a general-purpose processor, implemented by reading software code stored in a memory, which may be integrated in the processor, or may reside outside the processor, and exist separately.
In a sixth aspect, there is provided a computer program product comprising: a computer program (which may also be referred to as code, or instructions) which, when executed, causes a computer to perform the method of any one of the possible implementations of the first aspect.
In a seventh aspect, a computer readable storage medium is provided, which stores a computer program (which may also be referred to as code, or instructions) which, when run on a computer, causes the computer to perform the method of any one of the possible implementations of the first aspect.
Drawings
FIG. 1 is a schematic flow chart of a method of information prediction of an embodiment of the present application;
FIGS. 2 to 6 are graphs showing the dynamic relationship between the number of newly added infected persons in different cities and the urban management and control index;
fig. 7 to 11 are graphs showing the trend of urban activity indexes of different cities over time;
fig. 12 to 16 are graphs showing the trend of the urban rework indexes of different cities over time;
FIG. 17 is a schematic representation of a propagation process corresponding to the predictive model provided herein;
FIGS. 18-22 are graphs comparing actual diagnostic population for different cities with model predictions;
FIG. 23 is a schematic block diagram of an apparatus for information prediction of an embodiment of the present application;
fig. 24 is a schematic block diagram of another information prediction apparatus of an embodiment of the present application.
Detailed Description
The technical solutions in the present application will be described below with reference to the accompanying drawings.
The outbreak and the spread of the serious infectious diseases can bring great influence to the national economic development and the life of people, research the transmission rule of the infectious diseases, reasonably and effectively predict the infectious diseases and simulate the transmission process of the infectious diseases, and can effectively provide deduction references for preventing and controlling the infectious diseases.
Currently, infection models are largely classified into statistical models and kinetic models. Statistical models mainly include an exponential model, a logistic regression model, and with recent development of deep learning, a long short-term memory (LSTM) time series model can also be used to build an infectious disease prediction model. The statistical model can reflect the development rule of infectious diseases, but depends on historical data, and the internal mechanism is not clear enough, so that the influence of the change of different prevention and control measures on the infectious diseases is difficult to evaluate in time.
Common dynamics models are a susceptibility-infected (SI) model, a susceptibility-infected (SIs) model, a susceptibility-infected-recovered (SIR) model, an SEIR model, and other algorithm models. Conventional kinetic models can describe the internal long-term laws of infectious disease development, but the parameters in the model are usually fixed parameter values, and the influence of isolation measures such as prevention and control on the actual infectious disease development is not considered.
Differential equations corresponding to the SI model, SIs model, SIR model, and SEIR model are given below.
The differential equation corresponding to the SI model is as follows:
Figure GDA0003198860510000061
the differential equation corresponding to the SIS model is as follows:
Figure GDA0003198860510000062
the differential equation corresponding to the SIR model is as follows:
Figure GDA0003198860510000063
the equation corresponding to the SEIR model is as follows:
Figure GDA0003198860510000064
in differential equations corresponding to the SI model, the SIs model, the SIR model and the SEIR model, S is a susceptible population, E is a latent population, I is an infected population, R is a recovery population, T is a cumulative number of diagnostic persons, and n=s (T) +e (T) +i (T) +r (T); beta represents the infection rate, lambda represents the morbidity, and gamma represents the recovery rate.
In the SI, SIS, SIR, SEIR model mentioned above, the population is generally divided into several categories: (1) Class S, susceptible population (S), refers to the population that is not infected, and is not immune to viruses, and is infected after contact; (2) Class E, latency group (exposed), refers to the group that has been infected without developing a disorder; (3) Class I, infected population, refers to the population with symptoms of infection; (4) Class R, recovery population (recovered), refers to those infected with a loss of infectivity, typically by antibody production or death. The present application assumes that the number of persons in the investigation region is constant.
Among them, SI models consider only susceptible and infected persons, and the infected persons cannot recover, and the described disorders such as HIV and the like cannot recover after the illness. SIS is described as being more suitable for common influenza and the like, and can be repeatedly infected. SIR models consider the situation with antibodies after healing and no longer infected, but the model does not consider the presence of latency. The SEIR model adds latency to the SIR model and is a model that is better suited for the transmission of infectious diseases.
However, the SEIR model only considers the transmission process of the disease, and is suitable for describing the long-term transmission rule of the infectious disease. In practice, however, the transmission of infectious diseases is greatly affected by preventive measures. Thus, in the process of infectious disease development, urban management and crowd isolation play an important role in controlling the transmission of infectious diseases.
In view of the above, the application provides a method and a device for predicting information, which introduces urban management and control indexes to reflect the influence of prevention and control measures on the development of infectious diseases on the basis of a traditional SEIR model susceptible group, a latent non-isolated group, a confirmed diagnosis group and a cured group, increases a household isolated group and a latent isolated group, and effectively improves the accuracy of predicting the evolution trend of the infectious disease group.
Before describing the method and apparatus for information prediction provided in the embodiments of the present application, the following description is made.
First, in the embodiments shown below, terms and english abbreviations, such as SEIR model, city management index, etc., are given as exemplary examples for convenience of description, and should not constitute any limitation to the present application. This application does not exclude the possibility of having or future define other terms that perform the same or similar functions.
Second, the first, second and various numerical numbers in the embodiments shown below are merely for convenience of description and are not intended to limit the scope of the embodiments of the present application. For example, to distinguish between different thresholds, etc.
Third, "at least one" means one or more, and "a plurality" means two or more. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a alone, a and B together, and B alone, wherein a, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b, and c may represent: a, b, or c, or a and b, or a and c, or b and c, or a, b and c, wherein a, b and c can be single or multiple.
The method 100 for information prediction provided in the embodiments of the present application is described in detail below with reference to fig. 1. The method of the embodiment of the present application may be performed by a data processing device, or may be performed by a chip in the data processing device, which is not limited in this embodiment of the present application.
S101, determining a city management and control index of a target time period, wherein the city management and control index is determined according to a city activity index and a city reworking index.
It should be understood that the above-mentioned urban management and control index is continuously changed with time, and represents the effect of isolating the relevant prevention and control measures. The better the prevention and control measures, the higher the urban management and control index, the slower the personnel flow and the lower the effective regeneration number of disease transmission.
The relationship between the city management index and the number of newly added diagnostic persons will be described in detail with reference to fig. 2 to 6. In fig. 2 to 6, a curve "1" represents a city management index; curve "2" represents the number of additional diagnostic persons; curve "3" represents the urban management index after seven days of delay. Fig. 2, 3, 4, 5 and 6 show the dynamic relationship between the number of newly added infected people and the city management and control index on days 2 to 50, city a, city B, city C, city D and city E, respectively. Specifically, as shown in fig. 3, after taking the control measures from day 9, the city control index has a significant tendency to rise, and there is a strong correlation between the city control index and the newly added number of diagnostic persons. As can be seen from fig. 2, 3, 4, 5 and 6, the urban management and control indexes of the five cities have a strong predictive effect on the development trend of the newly-increased diagnosed population after 7 days, and when the urban management and control indexes reach a high level, the newly-increased diagnosed population starts to enter a descending trend. It can be seen that urban management and control has a relatively obvious effect on the transmission of infectious diseases.
It should be understood that the urban activity index is comprehensive measurement and calculation of average activity distance, average activity duration and average activity times of people in the city, which are obtained through analysis of the signaling big data of the operators, so as to reflect macroscopic situation of population activities in the city and reflect implementation effect of urban infectious disease prevention and control measures.
For example, activities of urban population can be obtained from signaling data of cell phone signal connection base stations. Specifically, the city activity index may be the number of people in the city whose range of activity exceeds 600m per the total population of the city.
Fig. 7 to 11 show the trend of the city activity index corresponding to five cities of city a, city B, city C, city D, and city E, respectively, over time. It can be seen from the figure that after day 12, the urban activity index of each city starts to drop rapidly and remains at a low activity index level around and after day 14, fully reflecting the improvement of prevention and control measures and awareness.
It should also be understood that the urban reworking index is that the working population in the city is analyzed by the operator signaling big data, so that the reworking condition of the working population in the city is reflected, and the shutdown and reworking condition in the city can be reflected.
For example, the location of the user may be obtained according to the signaling data of the mobile terminal connected to the base station, the residence time of the user at a certain location may be determined, and the location with the longest residence time from 07:00 to 22:00 in several consecutive days may be selected as the working place of the user. The city reworking index may be the number of people in the city that stay at the workplace for 2 hours/the total number of people in the city.
Fig. 12 to 16 show the trend of the city activity rework index corresponding to five cities of city a, city B, city C, city D, and city E, respectively, over time. From the figure, it can be seen that after day 12, the urban reworking index is always maintained at a low level, reflecting the importance of each enterprise to the prevention and control of infectious diseases.
S102, inputting the city management and control indexes of the target time period and the target time period into a prediction model to obtain a prediction result of the target time period, wherein the prediction model is established based on the city management and control indexes of the historical time period, the number of susceptible people, the number of latent people, the number of infected people and the number of recovery people in the historical time period.
The method for predicting the information is based on the traditional SEIR model susceptible population, the latent non-isolated population, the confirmed diagnosis population and the cured population, and introduces the urban management and control index to reflect the influence of prevention and control measures on the development of the infectious diseases, so that the household isolated population and the latent isolated population are increased, and the accuracy of predicting the evolution trend of the infectious disease population is effectively improved.
As an alternative embodiment, the determining the city management index of the target time period includes: the city management index of the first time period in the historical time period is determined as the city management index of the target time period, and the time difference between the first time period and the target time period is a first threshold.
It is understood that the first threshold described above is the latency of the disease.
As can be seen in connection with the example of fig. 2 above, the latency of the disease may be seven days.
As an alternative embodiment, the city management index for the first period is obtained by the following formula:
M＝{(1-a)+(1-b)}
where a is the city activity index of the first period, b is the city replication index of the first period, M (x) = (x-min (x))/(max (x) -min (x)).
It should be understood that min (x) represents a minimum value and max (x) represents a maximum value.
As an alternative embodiment, the above prediction model is the following set of equations:
Figure GDA0003198860510000101
wherein S is a susceptible population, E is a latent population, I is an infected population, R is a recovery population, T is an accumulated diagnostic population, n=s (T) +e (T) +i (T) +r (T); beta represents the infection rate, lambda represents the morbidity, and gamma represents the recovery rate. a is the coefficient of isolating the population from the management and control index of the susceptible population, b is the coefficient of isolating the population from the management and control index of the latent population, C is the urban management and control index, and m is the first threshold, namely the disease latency.
It should be appreciated that C (t-m) is the city management index that is advanced by m days at the target time. Specifically, C (t-m) is an actual index calculated from operator signaling data. Alternatively, if C (t-m) is unknown, C (t-m-1) may be substituted for C (t-m).
Illustratively, C (t-m) is unknown, if the city regulatory index before day 52 can be obtained (excluding day 52), neither the regulatory index on nor after day 52 is known and cannot be obtained. Then the city management and control index on day 51 is needed to be calculated when predicting the confirmed disease on day 58; when the disease is predicted to be confirmed on the 59 th day, the urban management and control index on the 52 th day is needed, but only the urban management and control index before the 52 th day can be obtained at present, and at this time, the urban management and control index on the 51 th day can be selected as the urban management and control index on the 52 th day to be predicted; on the 60 th day of the prediction, the urban management and control index on the 53 th day is required, and the urban management and control index on the 52 th day can be used as the urban management and control index on the 53 th day, that is, the urban management and control index on the 51 th day is used as the urban management and control index of the target time period for the prediction. It is understood that the city management index on day 51 can be used for prediction on both day 52 and later.
The propagation process corresponding to the prediction model provided by the application is shown in fig. 17. According to the embodiment of the application, the influence of urban management and control is added into the SEIR model, the crowd is finely divided into the isolated crowd G, and the isolated crowd G represents the isolated and home office stationary crowd. Reflecting the proportion of isolated population according to the urban management and control index, wherein the lower the urban management and control index is, the less the proportion of isolated population is, the urban management and control index is increased, and the proportion of isolated population is increased; meanwhile, considering the characteristic that infectious diseases also have infectivity in the incubation period, namely, the characteristic that class E crowd can also infect class S crowd diseases, a USEIR model is formed, wherein the USEIR model is a prediction model adopted in the embodiment of the application, and the USEIR model can be specifically a differential equation set described in the method 100.
It should be appreciated that the parameters in fig. 17 are consistent with the meaning of the parameters in the differential equation set described above.
As an alternative embodiment, before inputting the target time period and the city management index of the target time period into the prediction model, the method 100 further includes: determining a prediction result of a first time period in the historical time period based on the prediction model; and training the prediction model by using the true value of the first time period and the prediction result of the first time period, and updating the parameters beta, lambda, a and b, wherein the true value is at least one of the number of susceptible people, the number of latent people, the number of infected people and the number of recovery people in the first time period.
Illustratively, the accumulated number of corroborates Tt and the existing number of infected persons It of the city C from day 3 to day 32, and the accumulated number of corroborates Tt and the existing number of infected persons It of the city a, city B, city D, city E from day 7 to day 32 are selected as training data, i.e. the actual values of the first time period in the above-mentioned history period.
Calculating the differential equation by Euler method, wherein the initial value of E, I, R is assigned according to various numbers of people actually released, and the initial value E of E 0 Initial value I of the suspected person number I as initial time 0 Initial value R of the number of existing infections R as initial time 0 Is the sum of the number of deaths and the number of healds at the initial time (e.g.) 0 、I 0 And R is 0 Suspected person E actually released for city C on day 3 0 Number of infected persons I 0 Sum of death and cure R 0 ) Initial value S of S 0 ＝N-E 0 -I 0 -R 0 N is each cityPopulation values for the city residents. Iteratively calculating the number of predicted persons of I (T) and T (T) at other times in a first time period, and constructing a loss function by adopting a least square method:
Loss＝Σ t ||I(t)-It|| 2 +||T(t)-Tt|| 2 ，
where Tt and It represent true values in the first period, and T (T) and I (T) represent predicted values in the first period.
And obtaining parameters a, b, beta and gamma which enable the Loss value to be minimum through a grid search method, and updating corresponding parameters in the prediction model. Illustratively, the average latency period is 7 days, and the value of λ takes 1/7.
It should be understood that the parameter λ may be determined by the training, or may be determined according to an average latency period of an infectious disease, which is not limited in this application.
Based on the information prediction method provided by the embodiment of the application, a test example is provided to verify the prediction effect of the prediction model provided by the application. The respective parameters of the SIR model, the SEIR model, and the USEIR model are fitted in combination with the cumulative number of confirmed persons Tt and the existing number of infected persons It of city C on the 3 rd to 32 th days and the cumulative number of confirmed persons Tt and the existing number of infected persons It of city a, city B, city D, city E on the 7 th to 32 th days, and the number of confirmed persons in the above examples are predicted using the parameters.
Fig. 18 to 22 show the prediction results of SIR model, SEIR model, and USEIR model for the diagnosed person of five cities of city a, city B, city C, city D, and city E, respectively, and four curves are included in fig. 18 to 22. Wherein, curve "1" represents the number of people actually diagnosed; curves "2" each represent the number of diagnostic persons predicted by the USEIR model; curves "3" all represent the number of diagnostic persons predicted by the SEIR model; curves "4" each represent the number of diagnostic persons predicted by the SIR model. .
As shown in fig. 18 to 22, the number of diagnosed persons was predicted with the y-axis and the time x-axis. Fig. 18, 19, 20, 21 and 22 are graphs comparing actual numbers of diagnosed persons in cities a, B, C, D and E with the prediction results of the models. From fig. 18 to fig. 22, it can be seen that the predicted trend of the information prediction model (i.e., the USEIR model) provided by the present application is closer to the variation trend of the number of actually diagnosed people, so that the information prediction model provided by the present application is more accurate.
It should be understood that the sequence numbers of the above processes do not mean the order of execution, and the execution order of the processes should be determined by the functions and internal logic of the processes, and should not constitute any limitation on the implementation process of the embodiments of the present application.
The method of information prediction according to the embodiment of the present application is described in detail above with reference to fig. 1 to 22, and the apparatus of information prediction according to the embodiment of the present application will be described in detail below with reference to fig. 23 to 24.
Fig. 23 shows an apparatus 2300 for information prediction provided by an embodiment of the present application, the apparatus 2300 comprising: a determination module 2310 and a processing module 2320.
Wherein, the determining module 2310 is configured to determine a city management and control index of the target time period, where the city management and control index is determined according to the city activity index and the city reworking index;
the processing module 2320 is configured to input the target time period and the city management index of the target time period to a prediction model, so as to obtain a prediction result of the target time period, where the prediction model is established based on the city management index of the historical time period, the number of susceptible people, the number of latent people, the number of infected people and the number of recovery people in the historical time period.
Optionally, the determining module 2310 is specifically configured to: and determining the urban management index of the first time period in the historical time period as the urban management index of the target time period, wherein the time difference between the first time period and the target time period is a first threshold value.
Optionally, the city management index of the first period is obtained by the following formula:
M＝{(1-a)+(1-b)}
where a is the city activity index in the first period, and b is the city replication index in the first period, M (x) = (x-min (x))/(max (x) -min (x)).
Optionally, the above prediction model is the following equation set:
Figure GDA0003198860510000131
wherein S is a susceptible population, E is a latent population, I is an infected population, R is a recovery population, T is an accumulated diagnostic population, n=s (T) +e (T) +i (T) +r (T); beta represents the infection rate, lambda represents the morbidity, and gamma represents the recovery rate. a is the coefficient of the isolation crowd of the susceptible crowd about the management and control index, b is the coefficient of the isolation crowd of the latent crowd about the management and control index, C is the urban management and control index, and m is a first threshold.
Optionally, the apparatus 2300 further includes: the determining module 2310 is specifically configured to: determining a prediction result of a first time period in the historical time period based on the prediction model; the processing module 2320 is further configured to: and training the prediction model by using the true value of the first time period and the prediction result of the first time period, and updating the parameters beta, lambda, a and b, wherein the true value is at least one of the number of susceptible people, the number of latent people, the number of infected people and the number of recovery people in the first time period.
It should be appreciated that the apparatus 2300 herein is embodied in the form of functional modules. The term module herein may refer to an application specific integrated circuit (application specific integrated circuit, ASIC), an electronic circuit, a processor (e.g., a shared, dedicated, or group processor, etc.) and memory that execute one or more software or firmware programs, a combinational logic circuit, and/or other suitable components that support the described functionality. In an alternative example, it will be understood by those skilled in the art that the apparatus 2300 may be specifically a data processing device in the foregoing embodiment, or the functions of the data processing device in the foregoing embodiment may be integrated in the apparatus 2300, and the apparatus 2300 may be used to perform each flow and/or step corresponding to the data processing device in the foregoing method embodiment, which is not described herein for avoiding repetition.
The apparatus 2300 described above has the function of implementing the corresponding steps performed by the data processing device in the method described above; the above functions may be implemented by hardware, or may be implemented by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the functions described above.
In an embodiment of the present application, the device 2300 in fig. 23 may also be a chip or a system of chips, such as: system on chip (SoC). Correspondingly, the determining module 2310 may be a transceiver circuit of the chip, which is not limited herein.
Fig. 24 illustrates another information prediction apparatus 2400 provided by an embodiment of the present application. The apparatus 2400 includes a processor 2410, a transceiver 2420, and a memory 2430. Wherein the processor 2410, the transceiver 2420 and the memory 2430 are in communication with each other through an internal connection path, the memory 2430 is configured to store instructions, and the processor 2410 is configured to execute the instructions stored in the memory 2430 to control the transceiver 2420 to transmit signals and/or receive signals.
It should be understood that the apparatus 2400 may be specifically a data processing device in the foregoing embodiment, or the functions of the data processing device in the foregoing embodiment may be integrated in the apparatus 2400, and the apparatus 2400 may be configured to perform the steps and/or flows corresponding to the data processing device in the foregoing method embodiment. The memory 2430 can optionally include read-only memory and random access memory, and can provide instructions and data to the processor. A portion of the memory may also include non-volatile random access memory. For example, the memory may also store information of the device type. The processor 2410 may be configured to execute instructions stored in the memory and, when executed, perform the steps and/or processes associated with the data processing apparatus in the method embodiments described above.
It should be appreciated that in embodiments of the present application, the processor may be a central processing unit (central processing unit, CPU), the processor may also be other general purpose processors, digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or by instructions in the form of software. The steps of a method disclosed in connection with the embodiments of the present application may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in the processor for execution. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor executes instructions in the memory to perform the steps of the method described above in conjunction with its hardware. To avoid repetition, a detailed description is not provided herein.
The present application provides a readable computer storage medium for storing a computer program for implementing the method shown in the various possible implementations of the above embodiments.
The present application provides a computer program product comprising a computer program (which may also be referred to as code, or instructions) which, when run on a computer, can perform the methods shown in the various possible implementations of the embodiments described above.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (5)

1. A method for predicting the evolution trend of an infectious disease population, comprising:
determining a city management and control index of a target time period, wherein the city management and control index is determined according to a city activity index and a city reworking index, the city activity index is the number of people with the activity range exceeding 600m in the city/the city population, and the city reworking index is the number of people with the people in the city staying at a working place for 2 hours/the city working population;
inputting the target time period and the urban management and control index of the target time period into a prediction model to obtain a prediction result of the target time period, wherein the prediction result is used for indicating the evolution trend of infectious disease groups, and the prediction model is established based on the urban management and control index of a historical time period, the number of susceptible people, the number of latent people, the number of infected people and the number of recovery people in the historical time period;
the determining the city management and control index of the target time period comprises the following steps:
determining a city management index of a first time period in the historical time period as a city management index of the target time period, wherein the time difference between the first time period and the target time period is a first threshold;
the city management and control index of the first time period is obtained by the following formula:
M＝{(1-a)+(1-b)}
wherein a is the city activity index of the first time period, b is the city replication index of the first time period, M (x) = (x-min (x))/(max (x) -min (x)), x= (1-a) + (1-b);
the predictive model is the following set of equations:
Figure FDA0004207019920000011
wherein S is a susceptible population, E is a latent population, I is an infected population, R is a recovery population, T is an accumulated diagnostic population, n=s (T) +e (T) +i (T) +r (T); beta represents the infection rate, lambda represents the morbidity, gamma represents the recovery rate, a is the coefficient of isolated population with respect to the management and control index in the susceptible population, b is the coefficient of isolated population with respect to the management and control index in the latent population, C is the urban management and control index in the target time period, m is the first threshold and m is the disease latency.
2. The method of claim 1, wherein prior to said inputting the target time period and the city management index for the target time period to a predictive model, the method further comprises:
determining a prediction result of a first time period in the historical time period based on the prediction model;
and training the prediction model by using the true value of the first time period and the prediction result of the first time period, and updating the parameters beta, lambda, a and b, wherein the true value is at least one of the number of susceptible people, the number of latent people, the number of infected people and the number of recovery people in the first time period.
3. An apparatus for predicting the evolution trend of an infectious disease population, comprising:
the urban management and control system comprises a determining module, a judging module and a judging module, wherein the determining module is used for determining an urban management and control index of a target time period, the urban management and control index is determined according to an urban activity index and an urban reworking index, the urban activity index is the number of people with the activity range exceeding 600m in the urban population/the urban population, and the urban reworking index is the number of people with people in the urban population staying at a workplace for 2 hours/the urban working population;
the processing module is used for inputting the target time period and the urban management and control index of the target time period into a prediction model to obtain a prediction result of the target time period, wherein the prediction result is used for indicating the evolution trend of the infectious disease population, and the prediction model is established based on the urban management and control index of the historical time period, the susceptible population number, the latent population number, the infected population number and the recovery population number of the historical time period;
the determining module is specifically configured to:
determining a city management index of a first time period in the historical time period as a city management index of the target time period, wherein the time difference between the first time period and the target time period is a first threshold;
the city management and control index of the first time period is obtained by the following formula:
M＝{(1-a)+(1-b)}
wherein a is the city activity index of the first time period, b is the city replication index of the first time period, M (x) = (x-min (x))/(max (x) -min (x)), x= (1-a) + (1-b);
the predictive model is the following set of equations:
Figure FDA0004207019920000031
wherein S is a susceptible population, E is a latent population, I is an infected population, R is a recovery population, T is an accumulated diagnostic population, n=s (T) +e (T) +i (T) +r (T); beta represents the infection rate, lambda represents the morbidity, gamma represents the recovery rate, a is the coefficient of isolated population with respect to the management and control index in the susceptible population, b is the coefficient of isolated population with respect to the management and control index in the latent population, C is the urban management and control index in the target time period, m is the first threshold and m is the disease latency.
4. An apparatus for information prediction, comprising: a processor coupled to a memory for storing a computer program which, when invoked by the processor, causes the apparatus to perform the method of claim 1 or 2.
5. A computer readable storage medium storing a computer program comprising instructions for implementing the method of claim 1 or 2.
CN202011535711.0A 2020-12-22 2020-12-22 Information prediction method and device Active CN113345594B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011535711.0A CN113345594B (en) 2020-12-22 2020-12-22 Information prediction method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011535711.0A CN113345594B (en) 2020-12-22 2020-12-22 Information prediction method and device

Publications (2)

Publication Number Publication Date
CN113345594A CN113345594A (en) 2021-09-03
CN113345594B true CN113345594B (en) 2023-06-20

Family

ID=77467610

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011535711.0A Active CN113345594B (en) 2020-12-22 2020-12-22 Information prediction method and device

Country Status (1)

Country Link
CN (1) CN113345594B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113764109B (en) * 2021-09-15 2023-11-24 医渡云（北京）技术有限公司 Infectious disease transmission scale prediction method, device, medium and electronic equipment

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111489830A (en) * 2020-04-08 2020-08-04 医渡云（北京）技术有限公司 Method and device for predicting epidemic situation data in sections, medium and electronic equipment
CN111743522A (en) * 2020-06-15 2020-10-09 武汉理工大学 Intelligent terminal early warning system of epidemic situation prevention and control
CN111768875A (en) * 2020-06-23 2020-10-13 深圳市城市公共安全技术研究院有限公司 Infectious disease epidemic situation prediction method, system, device and storage medium
CN112071437A (en) * 2020-09-25 2020-12-11 北京百度网讯科技有限公司 Infectious disease trend prediction method and device, electronic equipment and storage medium
CN112086203A (en) * 2020-09-11 2020-12-15 河北工程大学 Epidemic situation prediction method and device and terminal equipment

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080177614A1 (en) * 2007-01-24 2008-07-24 Lianjun An Method and system for estimating dynamics of workforce absenteeism using information on pandemic spread and mitigation actions
US10318875B2 (en) * 2015-12-07 2019-06-11 International Business Machines Corporation Disease prediction and prevention using crowdsourced reports of environmental conditions

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111489830A (en) * 2020-04-08 2020-08-04 医渡云（北京）技术有限公司 Method and device for predicting epidemic situation data in sections, medium and electronic equipment
CN111743522A (en) * 2020-06-15 2020-10-09 武汉理工大学 Intelligent terminal early warning system of epidemic situation prevention and control
CN111768875A (en) * 2020-06-23 2020-10-13 深圳市城市公共安全技术研究院有限公司 Infectious disease epidemic situation prediction method, system, device and storage medium
CN112086203A (en) * 2020-09-11 2020-12-15 河北工程大学 Epidemic situation prediction method and device and terminal equipment
CN112071437A (en) * 2020-09-25 2020-12-11 北京百度网讯科技有限公司 Infectious disease trend prediction method and device, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN113345594A (en) 2021-09-03

Similar Documents

Publication Publication Date Title
Ramírez-Aldana et al. Spatial analysis of COVID-19 spread in Iran: Insights into geographical and structural transmission determinants at a province level
Kong et al. Social, economic, and environmental factors influencing the basic reproduction number of COVID-19 across countries
US11163853B2 (en) Sensor design support apparatus, sensor design support method and non-transitory computer readable medium
US10963807B2 (en) Social collaboration in probabilistic prediction
CN108052528A (en) A kind of storage device sequential classification method for early warning
US20160306689A1 (en) Nexus determination in a computing device
CN113539509B (en) Method, device, terminal equipment and medium for predicting risk of newly-developed infectious disease
EP3648433B1 (en) System and method of training behavior labeling model
US20220036984A1 (en) Identifying and indexing discriminative features for disease progression in observational data
US11790282B1 (en) Communication generation using sparse indicators and sensor data
Ma et al. Predictive monitoring with logic-calibrated uncertainty for cyber-physical systems
CN104751387A (en) System And Method For Probabilistic Evaluation Of Contextualized Reports And Personalized Recommendation
Eilertson et al. Estimation and prediction for a mechanistic model of measles transmission using particle filtering and maximum likelihood estimation
CN111768875A (en) Infectious disease epidemic situation prediction method, system, device and storage medium
Zhang et al. Using internet search data to predict new HIV diagnoses in China: a modelling study
CN113345594B (en) Information prediction method and device
Mehrotra et al. Designing effective movement digital biomarkers for unobtrusive emotional state mobile monitoring
Musoro et al. A joint model for repeated events of different types and multiple longitudinal outcomes with application to a follow‐up study of patients after kidney transplant
CN111739653A (en) Method and device for evaluating the spread of an infectious disease, computer device and storage medium
Yilmaz et al. Kemeny-based testing for COVID-19
Jombart et al. Real-time monitoring of COVID-19 dynamics using automated trend fitting and anomaly detection
Du et al. Optimal diagnostic test allocation strategy during the COVID‐19 pandemic and beyond
CN112486784A (en) Method, apparatus and medium for diagnosing and optimizing data analysis system
CN113269378A (en) Network traffic processing method and device, electronic equipment and readable storage medium
CN111340540B (en) Advertisement recommendation model monitoring method, advertisement recommendation method and advertisement recommendation model monitoring device

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