Influenza risk forecasting method, device and equipment based on high-impact weather classification
By using an influenza risk forecasting method based on high-impact weather classification, information on future, current, and previous high-impact weather processes is obtained, and a complex intensity index is constructed. This solves the problem of low accuracy in influenza forecasts and enables precise forecasting of influenza meteorological risks.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- LANGFANG METEOROLOGICAL BUREAU
- Filing Date
- 2026-01-26
- Publication Date
- 2026-06-05
AI Technical Summary
Existing influenza forecasting and prediction models struggle to capture the lag and cumulative effects of influenza onset and transmission, have limited forward-looking predictive capabilities regarding the risks posed by high-impact weather, and suffer from low forecast accuracy.
Based on the classification of high-impact weather, by acquiring information on future, current and previous high-impact weather processes, a high-impact weather complexity intensity index is constructed. Combined with an influenza risk forecasting model, the intrinsic link between weather changes and the occurrence and spread of influenza is accurately established.
It has achieved accurate forecasting of influenza meteorological risks, overcome the limitations of meteorological data, and provided scientific and accurate influenza risk forecasts, thus providing a basis for public health prevention and control.
Smart Images
Figure CN122158177A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of influenza risk forecasting technology, and in particular to an influenza risk forecasting method, device, and equipment based on high-impact weather classification. Background Technology
[0002] Influenza, a highly prevalent acute respiratory infectious disease worldwide, is significantly influenced by meteorological conditions in its transmission and spread, making it a meteorologically sensitive disease and a key concern for public health prevention and control. Drastic temperature fluctuations, dry air, and extreme temperature drops can affect the survival and transmission efficiency of the influenza virus in the air, and may also lead to a decline in human immunity, indirectly exacerbating the risk of infection and transmission. With global warming and the increasing frequency of extreme weather events, the driving role of high-impact weather processes in influenza transmission is becoming increasingly prominent. Establishing a precise and forward-looking influenza meteorological risk forecasting system is of great significance for the early deployment of prevention and control resources and the reduction of public health losses.
[0003] In existing technologies, influenza forecasting and prediction are typically based on statistical correlation models between historical influenza incidence data and real-time meteorological factors (such as temperature, humidity, and wind speed), as well as methods such as machine learning to construct mapping relationships between incidence risk and meteorological indicators. However, the forecasting and prediction models in this approach struggle to capture the lag and cumulative effects of influenza onset and transmission, have limited forward-looking predictive capabilities regarding the risks of extreme and high-impact weather events affecting influenza, and thus have low forecasting and prediction accuracy. Summary of the Invention
[0004] This invention provides a method, apparatus, and equipment for influenza risk forecasting based on high-impact weather classification, in order to solve the problems of insufficient forward-looking prediction capability and low forecast accuracy in the prior art based on meteorological element indicators.
[0005] In a first aspect, embodiments of the present invention provide an influenza risk forecasting method based on high-impact weather classification, including: Acquire weather forecast data for future periods and determine information on future high-impact weather processes based on the weather forecast data for future periods; whereby the information on future high-impact weather processes includes: the process type of future high-impact weather processes; Obtain information on the current high-impact weather event and the previous high-impact weather event; The complexity intensity index of high-impact weather is determined based on information from the previous high-impact weather event, the current high-impact weather event, and the future high-impact weather event. The influenza risk forecast level is determined based on the complexity intensity index of high-impact weather and the process type of future high-impact weather events.
[0006] Secondly, embodiments of the present invention provide an influenza risk forecasting device based on high-impact weather classification, comprising: The first parameter acquisition module is used to acquire weather forecast data for future periods and determine information on future high-impact weather processes based on the weather forecast data for future periods; wherein, the information on future high-impact weather processes includes: the process type of future high-impact weather processes; The second parameter acquisition module is used to acquire information on the current high-impact weather process and the previous high-impact weather process. The index determination module is used to determine the complexity intensity index of high-impact weather based on information from the previous high-impact weather event, the current high-impact weather event, and the future high-impact weather event. The forecast level output module is used to determine the influenza risk forecast level based on the complexity intensity index of high-impact weather and the process type of future high-impact weather events.
[0007] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the influenza risk forecasting method based on high-impact weather classification as described in the first aspect or any possible implementation of the first aspect.
[0008] This invention provides a method, apparatus, and device for influenza risk forecasting based on high-impact weather classification. The method includes: acquiring weather forecast data for future periods and determining future high-impact weather events based on this data; acquiring information on the current and previous high-impact weather events; determining a high-impact weather complexity intensity index based on the previous, current, and future high-impact weather events; and determining the influenza risk forecast level based on the high-impact weather complexity intensity index and the event type of the future high-impact weather events. This invention constructs a forecasting model based on the risk characteristics of different complex forms of high-impact weather and their impact on influenza, overcoming the limitations of relying solely on meteorological data. It accurately correlates severe weather changes and their evolution trends with the intrinsic relationship between influenza occurrence and spread, resulting in more scientific and accurate forecasts. Attached Figure Description
[0009] Figure 1 This is a flowchart illustrating the implementation of an influenza risk forecasting method based on high-impact weather classification provided in an embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of the influenza risk forecasting device based on high-impact weather classification provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation
[0010] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
[0011] See Figure 1 The document illustrates a flowchart of an influenza risk forecasting method based on high-impact weather classification provided by an embodiment of the present invention, detailed below: High-impact weather events such as cold waves, strong winds and temperature drops, and haze can promote influenza outbreaks by affecting human immunity (e.g., sudden temperature changes reduce respiratory mucosal resistance), the virus survival environment (e.g., low temperature and low humidity are conducive to the spread of influenza viruses), and population gathering behavior (e.g., rain and snow lead to increased indoor gathering rates). This application utilizes interdisciplinary analysis of meteorology, climatology, epidemiology, mathematical statistics, meteorological big data cloud platforms, and intelligent meteorological grid forecasting methods, data, and technologies to identify high-impact weather types conducive to influenza outbreaks, classifying them into six categories: cold waves, precipitation, fog-haze, precipitation with fog-haze, strong winds, and light fog-haze-continuous low temperatures. A cold wave refers to a large-scale invasion of cold air from high latitudes into mid- and low latitudes, causing a sharp drop in temperature.
[0012] Precipitation refers to a weather event with daily precipitation ≥ 0.1 mm; in addition, precipitation may also be accompanied by light fog, haze-like conditions, continuous low temperatures, and strong winds.
[0013] Fog-haze refers to a weather process with fog or haze; in addition, it may also be accompanied by light fog, haze-like conditions, continuous low temperatures, and strong winds.
[0014] Precipitation with fog / haze refers to a weather event with daily precipitation ≥0.1mm accompanied by fog / haze. It may also be accompanied by light fog, haze-like conditions, prolonged low temperatures, and strong winds.
[0015] Strong winds refer to weather events with maximum wind speeds of level 6 or above (≥10.8 m / s); in addition, they may be accompanied by blowing sand, dust, light fog, haze-like conditions, and continuous low temperatures.
[0016] Light fog-haze-continuous low temperature refers to a weather process of light fog, haze-like conditions, and / or continuous low temperature lasting for more than 3 days.
[0017] A correlation statistical analysis was conducted between local high-impact weather events such as cold waves, precipitation, strong winds, fog, and haze and influenza cases. The types, lengths, probabilities, and monthly distributions of various high-impact weather processes that cause influenza were summarized. An interdisciplinary mathematical statistical cross-analysis was performed on the distribution of influenza cases in conjunction with high-impact weather processes. The meteorological risk impacts of various high-impact weather types, months of occurrence, duration of processes, and complex configurations were assigned values, and relevant mathematical models were established to achieve influenza meteorological risk level forecasting.
[0018] The above-mentioned influenza risk forecasting methods based on high-impact weather classification include: S101: Obtain weather forecast data for future periods and determine information on future high-impact weather processes based on the weather forecast data for future periods; wherein, the information on future high-impact weather processes includes: the process type of future high-impact weather processes; Specifically, weather forecast data for future periods can be obtained using intelligent meteorological grid forecast products.
[0019] S102: Obtain information on the current high-impact weather event and the previous high-impact weather event; Specifically, information on the current high-impact weather events and the previous high-impact weather events can be obtained from the meteorological big data cloud platform, Tianqing.
[0020] Based on meteorological element data for future time periods (such as 7 days or up to 14 days) output by meteorological numerical forecast models, identify high-impact weather processes that will occur in the future and determine their process information.
[0021] At the same time, information on currently occurring high-impact weather processes and information on previously concluded high-impact weather processes are retrieved from the meteorological monitoring database to form a "previous-current-future" high-impact weather time series chain.
[0022] S103: Determine the complexity intensity index of high-impact weather based on information from the previous high-impact weather event, the current high-impact weather event, and the future high-impact weather event. The continuous, alternating, and superimposed evolution patterns of multi-hazard high-impact weather processes can affect the survival and transmission environment of influenza viruses and the state of human immunity in multiple dimensions. For example, the continuous process of "continuous fog-haze + low temperature": In foggy-haze weather, air circulation is poor, and influenza viruses can attach to particulate matter and remain suspended for a long time (in ordinary sunny weather, viruses are easily inactivated by ultraviolet rays); low temperature (especially 0-10℃) is the "suitable survival temperature" for influenza viruses. Sustained low temperature + stable meteorological conditions will prolong the survival time of the virus in the environment and increase the probability of human-to-human transmission.
[0023] Similarly, the duration of information on the previous high-impact weather event and the current high-impact weather event can be 7 days, with a maximum of 14 days.
[0024] Therefore, this application introduces the time series evolution characteristics of high-impact, influenza-sensitive weather processes, constructs a complete weather evolution time chain based on the three-stage weather process of "precursor-current-future", accurately captures the key environmental factors affecting the occurrence and spread of influenza, and constructs a multi-dimensional complex intensity evaluation index system, realizing the comprehensive and dynamic quantification of the environmental conditions for the occurrence and spread of influenza.
[0025] In one possible implementation, S103 may include: S1031: Determine the first complexity intensity index based on information from the previous high-impact weather event; The first complexity intensity index is a quantitative assessment of the intensity of the "transmission basis triggers" of the previous high-impact weather process, which reflects the initial environmental foundation laid by the weather process for the occurrence and spread of influenza.
[0026] In one possible implementation, the information on the preceding high-impact weather event includes: the event type, duration, and cumulative number of days of high-impact weather; S1031 may include: 1. Based on the process type and duration of the previous high-impact weather event, the first impact index is obtained by referring to the table; 2. Based on the cumulative number of days of high-impact weather during the previous high-impact weather event, the second impact index is obtained by referring to the table; 3. Summing the first influence index and the second influence index yields the first complexity intensity index.
[0027] For example, the first impact index can be obtained by looking up Table 1 based on the process type and duration of the previous high-impact weather process.
[0028] Table 1. Process Type and Process Duration Index
[0029] For example, if the preceding high-impact weather event is a cold wave, the base value of the first impact index is 2; if it is accompanied by strong winds, the value is increased by 1; if it is accompanied by fog or haze, the value is increased by another 1; if the event lasts for 7 days, the value is increased by another 3; thus, the final value of the first impact index is 2+1+1+3=7.
[0030] For example, if the previous high-impact weather event is characterized by light fog-haze-continuous low temperatures, the base value of the first impact index is 0.5, without considering strong winds or fog-haze, only the duration of the event is taken into account; if the duration of the event is 3 days, the final value of the first impact index is 0.5 + 0.5 = 1.
[0031] For example, the second impact index is obtained by looking up the table in Table 2 based on the cumulative number of days of high-impact weather in the previous high-impact weather process (the length of the high-impact weather process and the number of days of high-impact weather usually do not match).
[0032] Table 2 Impact Table of Cumulative Days of High-Impact Weather
[0033] For example, if the preceding high-impact weather process is a cold wave (a cold wave is a complex severe weather process characterized by a sharp drop in temperature, which may be accompanied by fog, haze, precipitation, strong winds, and other high-impact weather events), and if the cumulative number of days with the aforementioned high-impact weather events such as cold waves, fog, haze, and precipitation during the weather process is 8 days, and it is accompanied by strong winds and continuous temperature drops, then the second impact index is 10; if it is not accompanied by strong winds and continuous temperature drops, then the second impact index is 5.
[0034] S1032: Determine the second complexity intensity index based on current information on high-impact weather events; The second complexity intensity index is an important quantitative indicator of the "real-time propagation dynamics" of the current high-impact weather process. The current environment has a promoting and reinforcing effect on the spread and outbreak of influenza in the future.
[0035] In one possible implementation, the current high-impact weather process information includes: the process type, duration, and cumulative number of days of high-impact weather; S1032 may include: 1. Based on the process type and duration of the current high-impact weather event, the third impact index is obtained by referring to the table; Similarly, based on the current high-impact weather process type and duration, the third impact index is obtained by referring to Table 1.
[0036] 2. Based on the cumulative number of days of high-impact weather during the current high-impact weather process, the fourth impact index is obtained by referring to the table; Similarly, based on the cumulative number of days of high-impact weather during the current high-impact weather process, the fourth impact index is obtained by referring to Table 2.
[0037] 3. Summing the third and fourth influence indices yields the second complexity intensity index.
[0038] S1033: Determine the third complexity intensity index based on information on future high-impact weather events; The third complexity intensity index is a quantification of the "spreading trend orientation" of future high-impact weather processes, reflecting the different impacts of future weather evolution on the occurrence and spread of influenza, such as increase or decrease.
[0039] In one possible implementation, the information on future high-impact weather events may further include: the duration of the future high-impact weather event, the cumulative number of days with high-impact weather, and the month in which it occurs; S1033 may include: 1. Based on the process type and duration of future high-impact weather events, the fifth impact index is obtained by referring to the table; 2. Based on the cumulative number of days of high-impact weather during future high-impact weather events, the sixth impact index is obtained by referring to the table; Similarly, by referring to Tables 1 and 2, we can obtain the fifth and sixth influence indices.
[0040] It should be noted that if there are no high-impact weather events in the future, the fifth and sixth impact indices will both be set to 0.
[0041] 3. Based on the month in which the future high-impact weather event will occur, the seventh impact index is obtained by referring to the table; For example, the seventh impact index can be obtained by referring to Table 3 based on the month in which the future high-impact weather event will occur.
[0042] Table 3 Monthly Impact Table
[0043] For example, if the month in which a high-impact weather event is expected to occur is September, then the seventh impact index will be 0.3.
[0044] 4. Summing the fifth, sixth, and seventh influence indices yields the third complexity intensity index.
[0045] S1034: Determine the first associated complexity intensity index based on the information of the previous high-impact weather event and the current high-impact weather event; The first complexity intensity index reflects the continuation, enhancement, or weakening effect of preceding weather on current weather; In one possible implementation, the information on the previous high-impact weather event includes: the start and end times of the previous high-impact weather event; the information on the current high-impact weather event includes: the start and end times of the current high-impact weather event; S1034 may include: 1. Based on the start and end times of the previous high-impact weather event and the start and end times of the current high-impact weather event, determine the interval between the previous high-impact weather event and the current high-impact weather event, and use it as the first interval; 2. Based on the first interval, look up the table to obtain the first association complexity strength index.
[0046] For example, the first association complexity intensity index is obtained by looking up Table 4 based on the first interval.
[0047] Table 4. Impact of Interval Duration
[0048] For example, if the first interval is 3 days, then the first association complexity strength index is 1.5.
[0049] S1035: Determine the second associated complexity intensity index based on current and future information on high-impact weather events; The second correlation complexity intensity index reflects the continuation, enhancement, or weakening effect of current weather on future weather; The same steps as S1034 are used to look up the table, and the details will not be repeated here.
[0050] S1036: The high-impact weather complexity intensity index is obtained by summing the first complexity intensity index, the second complexity intensity index, the third complexity intensity index, the first associated complexity intensity index, and the second associated complexity intensity index.
[0051] The summation-based fusion logic directly reflects the core logic that "single-stage intensity is the foundation, and inter-stage correlation is the supplement." It not only preserves the independent intensity characteristics of each stage of weather process, but also strengthens the continuity of weather evolution and the superposition, compounding, enhancement, and weakening effects through correlation indices, ensuring that the comprehensive index can fully cover the complete evolution chain of "previous-current-future".
[0052] S104: Determine the influenza risk forecast level based on the complexity intensity index of high-impact weather and the process type of future high-impact weather events.
[0053] This application studies, analyzes, and establishes an influenza incidence risk level forecasting model based on high-impact weather classification, achieving accurate mapping between high-impact weather and its complex and evolving characteristics and influenza meteorological risk forecast levels.
[0054] In one possible implementation, S104 may include: S1041: Input the complexity intensity index of high-impact weather and the process type of future high-impact weather events into the forecast model to obtain the influenza risk forecast level.
[0055] In one possible implementation, the forecast model can be a preset table.
[0056] For example, the influenza risk forecast level can be determined by referring to Table 5 based on the complexity intensity index of high-impact weather and the process type of future high-impact weather events, thereby achieving accurate forecasting of influenza risk.
[0057] Table 5 Influenza Risk Forecast Level Table
[0058] This application presents an influenza incidence risk level forecasting model based on high-impact weather classification and comprehensively considering the composite configuration of high-impact weather. It breaks through the limitations of forecasting based on meteorological data such as temperature and humidity, accurately links the weather change trend with the occurrence and spread of influenza, and can achieve accurate forecasting of influenza meteorological risk levels. This provides a basis for governments and relevant departments to guide the public to take scientific and timely measures to prevent influenza.
[0059] In one possible implementation, the above method may further include: The influenza risk forecast level is sent to the display terminal and displayed.
[0060] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
[0061] The following are device embodiments of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.
[0062] Figure 2 The diagram shows a schematic representation of an influenza risk forecasting device based on high-impact weather classification according to an embodiment of the present invention. For ease of explanation, only the parts relevant to the embodiment of the present invention are shown, and are described in detail below: like Figure 2 As shown, the influenza risk forecasting device based on high-impact weather classification includes: The first parameter acquisition module 21 is used to acquire weather forecast data for future periods and determine information on future high-impact weather processes based on the weather forecast data for future periods; wherein, the information on future high-impact weather processes includes: the process type of future high-impact weather processes; The second parameter acquisition module 22 is used to acquire information on the current high-impact weather process and the previous high-impact weather process. The index determination module 23 is used to determine the complexity intensity index of high-impact weather based on the information of the previous high-impact weather process, the current high-impact weather process, and the future high-impact weather process. The forecast level output module 24 is used to determine the influenza risk forecast level based on the complexity intensity index of high-impact weather and the process type of future high-impact weather events.
[0063] In one possible implementation, the index determination module 23 may include: The first calculation unit is used to determine the first complexity intensity index based on the information of the previous high-impact weather event; The second calculation unit is used to determine the second complexity intensity index based on the current information on high-impact weather processes; The third calculation unit is used to determine the third complexity intensity index based on information on future high-impact weather events; The fourth calculation unit is used to determine the first associated complexity intensity index based on the information of the previous high-impact weather event and the current high-impact weather event. The fifth calculation unit is used to determine the second associated complexity intensity index based on current and future high-impact weather information. The index output unit is used to sum the first complexity intensity index, the second complexity intensity index, the third complexity intensity index, the first associated complexity intensity index, and the second associated complexity intensity index to obtain the high-impact weather complexity intensity index.
[0064] In one possible implementation, the information on the preceding high-impact weather event includes: the event type, duration, and cumulative number of days of high-impact weather; the first calculation unit can be specifically used for: 1. Based on the process type and duration of the previous high-impact weather event, the first impact index is obtained by referring to the table; 2. Based on the cumulative number of days of high-impact weather during the previous high-impact weather event, the second impact index is obtained by referring to the table; 3. Summing the first influence index and the second influence index yields the first complexity intensity index.
[0065] In one possible implementation, the current high-impact weather process information includes: the process type, duration, and cumulative number of days of high-impact weather; the second calculation unit can be specifically used for: 1. Based on the process type and duration of the current high-impact weather event, the third impact index is obtained by referring to the table; 2. Based on the cumulative number of days of high-impact weather during the current high-impact weather process, the fourth impact index is obtained by referring to the table; 3. Summing the third and fourth influence indices yields the second complexity intensity index.
[0066] In one possible implementation, the information on future high-impact weather events further includes: the duration of the future high-impact weather event, the cumulative number of days with high impact, and the month in which it occurs; the third calculation unit can be specifically used for: 1. Based on the process type and duration of future high-impact weather events, the fifth impact index is obtained by referring to the table; 2. Based on the cumulative number of days of high-impact weather during future high-impact weather events, the sixth impact index is obtained by referring to the table; 3. Based on the month in which the future high-impact weather event will occur, the seventh impact index is obtained by referring to the table; 4. Summing the fifth, sixth, and seventh influence indices yields the third complexity intensity index.
[0067] In one possible implementation, the information on the previous high-impact weather event includes: the start and end times of the previous high-impact weather event; the information on the current high-impact weather event includes: the start and end times of the current high-impact weather event; the fourth calculation unit can be specifically used for: 1. Based on the start and end times of the previous high-impact weather event and the start and end times of the current high-impact weather event, determine the interval between the previous high-impact weather event and the current high-impact weather event, and use it as the first interval; 2. Based on the first interval, look up the table to obtain the first association complexity strength index.
[0068] In one possible implementation, the forecast level output module 24 may include: The forecasting unit is used to input the complexity intensity index of high-impact weather and the process type of future high-impact weather events into the forecasting model to obtain the influenza risk forecast level.
[0069] In one possible implementation, the process type may include: cold wave, precipitation, fog-haze, precipitation with fog-haze, strong wind, light fog-haze-continuous low temperature.
[0070] Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. For example... Figure 3 As shown, the electronic device 3 in this embodiment includes a processor 30 and a memory 31. The memory 31 stores a computer program 32. When the processor 30 executes the computer program 32, it implements the steps in the various method embodiments described above. Alternatively, when the processor 30 executes the computer program 32, it implements the functions of each module / unit in the various device embodiments described above. The exemplary computer program 32 can be written in the .NET programming language, uses the MVC framework, interacts with data in the form of a Web API, and uses JSON as the data exchange carrier.
[0071] For example, computer program 32 may be divided into one or more modules / units, which are stored in memory 31 and executed by processor 30 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 32 in electronic device 3.
[0072] Electronic device 3 may include, but is not limited to, processor 30 and memory 31. Those skilled in the art will understand that... Figure 3 This is merely an example of electronic device 3 and does not constitute a limitation on electronic device 3. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device 3 may also include input / output devices, network access devices, buses, etc.
[0073] The processor 30 can be a central processing unit (CPU), or 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. The general-purpose processor can be a microprocessor or any conventional processor.
[0074] The memory 31 can be an internal storage unit of the electronic device 3, such as a hard disk or memory of the electronic device 3. The memory 31 can also be an external storage device of the electronic device 3, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device 3. Furthermore, the memory 31 can include both internal and external storage units of the electronic device 3. The memory 31 is used to store the computer program 32 and other programs and data required by the electronic device 3. The memory 31 can also be used to temporarily store data that has been output or will be output.
[0075] For the sake of simplicity and clarity, only the above-described functional modules / units are used as examples. In practical applications, the functions described above can be assigned to different functional modules / units as needed. These modules / units can be implemented in hardware, software, or a combination of both.
[0076] This invention also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the methods described in the above-described method embodiments.
[0077] This invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the methods described in the above-described method embodiments.
[0078] Computer programs include computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. Computer-readable media can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.
[0079] In the above embodiments, the descriptions of each embodiment have their own emphasis. Parts not detailed or described in a particular embodiment can be referred to in the relevant descriptions of other embodiments. Unless otherwise specified or in conflict with logic, the terminology and / or descriptions between different embodiments are consistent and can be referenced interchangeably. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.
[0080] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.
Claims
1. A method for influenza risk forecasting based on high-impact weather classification, characterized in that, include: Acquire weather forecast data for future periods, and determine information on future high-impact weather processes based on the weather forecast data for future periods; wherein, the information on future high-impact weather processes includes: the process type of the future high-impact weather process; Obtain information on the current high-impact weather event and the previous high-impact weather event; Based on the information of the previous high-impact weather event, the information of the current high-impact weather event, and the information of the future high-impact weather event, the high-impact weather complexity intensity index is determined; The influenza risk forecast level is determined based on the complexity intensity index of the high-impact weather and the process type of the future high-impact weather event.
2. The influenza risk forecasting method based on high-impact weather classification according to claim 1, characterized in that, The step of determining the complexity intensity index of high-impact weather based on the information of the previous high-impact weather event, the information of the current high-impact weather event, and the information of the future high-impact weather event includes: Based on the information from the previous high-impact weather event, the first complexity intensity index is determined; Based on the current information on high-impact weather events, a second complexity intensity index is determined; Based on the information on future high-impact weather events, a third complexity intensity index is determined; Based on the information of the previous high-impact weather event and the information of the current high-impact weather event, a first associated complexity intensity index is determined; Based on the current high-impact weather process information and the future high-impact weather process information, a second associated complexity intensity index is determined; The high-impact weather complexity index is obtained by summing the first complexity intensity index, the second complexity intensity index, the third complexity intensity index, the first associated complexity intensity index, and the second associated complexity intensity index.
3. The influenza risk forecasting method based on high-impact weather classification according to claim 2, characterized in that, The information on the preceding high-impact weather event includes: the event type, duration, and cumulative number of days of high-impact weather. Determining the first complexity intensity index based on the preceding high-impact weather event information includes: Based on the process type and duration of the previous high-impact weather event, the first impact index is obtained by referring to the table. Based on the cumulative number of days of high-impact weather during the previous high-impact weather process, the second impact index is obtained by looking up the table. The first complexity intensity index is obtained by summing the first influence index and the second influence index.
4. The influenza risk forecasting method based on high-impact weather classification according to claim 2, characterized in that, The current high-impact weather process information includes: the process type, duration, and cumulative number of high-impact weather days of the current high-impact weather process; determining the second complexity intensity index based on the current high-impact weather process information includes: Based on the process type and duration of the current high-impact weather event, the third impact index is obtained by referring to the table. Based on the cumulative number of days of high-impact weather during the current high-impact weather process, the fourth impact index is obtained by referring to the table. The second complexity intensity index is obtained by summing the third influence index and the fourth influence index.
5. The influenza risk forecasting method based on high-impact weather classification according to claim 2, characterized in that, The information on future high-impact weather processes also includes: the duration of the future high-impact weather process, the cumulative number of days with high impact, and the month in which it occurs; the determination of the third complexity intensity index based on the information on future high-impact weather processes includes: Based on the process type and duration of the future high-impact weather events, the fifth impact index is obtained by referring to the table. Based on the cumulative number of days of high-impact weather during the future high-impact weather process, the sixth impact index is obtained by looking up the table. Based on the month in which the future high-impact weather event is located, the seventh impact index is obtained by referring to the table; The third complexity intensity index is obtained by summing the fifth, sixth, and seventh influence indices.
6. The influenza risk forecasting method based on high-impact weather classification according to claim 2, characterized in that, The information on the previous high-impact weather event includes: the start and end times of the previous high-impact weather event; the information on the current high-impact weather event includes: the start and end times of the current high-impact weather event; determining the first associated complexity intensity index based on the information on the previous high-impact weather event and the information on the current high-impact weather event includes: Based on the start and end times of the previous high-impact weather event and the start and end times of the current high-impact weather event, the interval between the previous high-impact weather event and the current high-impact weather event is determined as the first interval; The first association complexity strength index is obtained by looking up a table based on the first interval.
7. The influenza risk forecasting method based on high-impact weather classification according to any one of claims 1 to 6, characterized in that, The determination of the influenza risk forecast level based on the high-impact weather complexity intensity index and the process type of the future high-impact weather event includes: By inputting the complexity intensity index of the high-impact weather and the process type of the future high-impact weather process into the forecast model, the influenza risk forecast level is obtained.
8. The influenza risk forecasting method based on high-impact weather classification according to any one of claims 1 to 6, characterized in that, The process types include: cold wave, precipitation, fog-haze, precipitation with fog-haze, strong wind, light fog-haze-continuous low temperature.
9. An influenza risk forecasting device based on high-impact weather classification, characterized in that, include: The first parameter acquisition module is used to acquire weather forecast data for future periods and determine information on future high-impact weather processes based on the weather forecast data for future periods; wherein, the information on future high-impact weather processes includes: the process type of the future high-impact weather process; The second parameter acquisition module is used to acquire information on the current high-impact weather process and the previous high-impact weather process. The index determination module is used to determine the complexity intensity index of high-impact weather based on the information of the previous high-impact weather process, the information of the current high-impact weather process, and the information of the future high-impact weather process. The forecast level output module is used to determine the influenza risk forecast level based on the complexity intensity index of the high-impact weather and the process type of the future high-impact weather process.
10. An electronic device, characterized in that, It includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the influenza risk forecasting method based on high-impact weather classification as described in any one of claims 1 to 8.