A weather forecasting method, device and storage medium based on multi-mode field comprehensive calculation
Through multi-mode field comprehensive calculation, linear splitting of mode weight values and weather types is established, which solves the problem of the difference between weather forecast results and actual conditions, and achieves more accurate weather forecasts.
Patent Information
- Application Number
- CN202111620445.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-12-28
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2041-12-28
AI Technical Summary
The existing weather forecast is calculated based on different mode fields, which leads to the weather forecast results that may be far from the actual situation and lack accuracy.
Using a method based on multi-mode field synthesis calculation, the comprehensive value of the mode field is calculated to correct the weather forecast results and improve the accuracy of the forecast by establishing the linear splitting and classification of the mode weight value and weather type.
Through linear arrangement and weight correction, more reasonable weather phenomena can be derived, effectively correct the deviation of weather forecast results, and improve the accuracy of weather forecasts.
Smart Images

Figure GDA0005034751150000071 
Figure GDA0005034751150000081 
Figure GDA0005034751150000091
Abstract
Description
Technical Field
[0001] The present invention relates to the field of weather forecasting technology, and in particular to a weather forecasting method, device and storage medium based on multi-mode field comprehensive calculation. Background Art
[0002] As people's living standards improve, they often hold various activities in their lives due to weddings and funerals. However, before preparing for such activities, most people with common sense will check the weather forecast of the local meteorological bureau to make preparations in advance. It can be seen that the public's requirements for the accuracy of weather forecasts are also increasing.
[0003] However, most of the existing weather forecasts are calculated based on different model fields. Therefore, the weather results calculated under different model fields may not be exactly the same. The results of any model field may deviate from the actual situation. Therefore, people in daily life sometimes feel that the weather forecast is far from the actual situation. Summary of the invention
[0004] To this end, the main purpose of the present invention is to provide a weather forecasting method, device and storage medium based on comprehensive calculation of multi-mode fields, so as to perform comprehensive calculation based on multi-mode fields, thereby correcting the problem that weather forecast results occasionally deviate seriously from actual conditions.
[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present invention, a weather forecasting method based on comprehensive calculation of multiple model fields is provided, and the steps include: S1 establishes a first reference table: to assign model weight values to multiple model fields based on weather forecasts in the same area; S2 establishes a second reference table: to linearly split the weather types into multiple weather categories including rain, snow, suspended particulate matter, fog and assign classification codes; S3 establishes a third reference table: to classify each weather type from each weather category in the second reference table, and to perform linear coefficient splitting on each weather type, and the steps include: sorting from large to small according to rainfall and snowfall, and compiling them into linear parameters, and using numerical values to represent the amount of rain and snowfall; sorting from small to large according to suspended particulate matter in the atmosphere, and compiling them into linear parameters, and using numerical values to represent the amount of suspended particulate matter; according to The suspended water particles in the atmosphere are sorted from few to many and compiled into linear parameters, with numerical values representing the amount of suspended water vapor to determine the linear coefficients of each weather type; S4 classifies the weather forecast results of each model field for the same area, and judges whether it belongs to the major weather category in the second benchmark table and its corresponding third benchmark table to obtain the linear coefficient of the corresponding weather type; S5 adjusts the linear coefficient of the weather type corresponding to each model field in step S4 by the model weight value of each model field to obtain the weather type weight correction value; and calculates the model field comprehensive value c=a / b and rounds it, wherein the sum of the weather type weight correction values of each model field is a, and the sum of the model weight values of each model field is b; S6 reversely checks the third benchmark table based on the model field comprehensive value c to obtain the weather type corresponding to the linear coefficient value with the same c value as the weather forecast result.
[0006] In a possible preferred embodiment, the model field includes: computer model fields of meteorological bureaus of different regions or countries.
[0007] In a possible preferred implementation manner, the major weather categories in the second reference table include: rain, corresponding to classification code 1, snow, corresponding to classification code 2, suspended particulate matter, corresponding to classification code 3, and fog, corresponding to classification code 4.
[0008] In a possible preferred implementation manner, the weather types corresponding to the major weather category of rain and the corresponding linear coefficients include: sunny, linear coefficient 1, cloudy, linear coefficient 2, overcast, linear coefficient 3, showers, linear coefficient 4, light rain, linear coefficient 5, light to moderate rain, linear coefficient 6, moderate rain, linear coefficient 7, moderate to heavy rain, linear coefficient 8, heavy rain, linear coefficient 9, heavy to torrential rain, linear coefficient 10, torrential rain, linear coefficient 11, torrential rain to heavy rain, linear coefficient 12, heavy rain, linear coefficient 13, heavy rain to extremely heavy rain, linear coefficient 14, extremely heavy rain, linear coefficient 15.
[0009] In a possible preferred implementation manner, the weather types corresponding to the major weather category of snow and the corresponding linear coefficients include: sunny, linear coefficient 1, cloudy, linear coefficient 2, overcast, linear coefficient 3, sleet, linear coefficient 4, snow showers, linear coefficient 5, light snow, linear coefficient 6, light to moderate snow, linear coefficient 7, moderate snow, linear coefficient 8, moderate to heavy snow, linear coefficient 9, heavy snow, linear coefficient 10, heavy to blizzard, linear coefficient 11, blizzard, linear coefficient 12.
[0010] In a possible preferred implementation manner, the weather types corresponding to the major weather category of suspended particulate matter and the corresponding linear coefficients include: sunny, linear coefficient 1, cloudy, linear coefficient 2, overcast, linear coefficient 3, floating dust, linear coefficient 4, blowing sand, linear coefficient 5, sandstorm, linear coefficient 6, strong sandstorm, linear coefficient 7.
[0011] In a possible preferred implementation manner, the weather type corresponding to the weather category of fog and the corresponding linear coefficients include: sunny, linear coefficient 1, cloudy, linear coefficient 2, overcast, linear coefficient 3, foggy, linear coefficient 4.
[0012] In a possible preferred embodiment, the mode field integrated value c is rounded to an integer.
[0013] In order to achieve the above-mentioned purpose, according to the second aspect of the present invention, a weather forecast device is also provided, which includes: a data transceiver unit: receiving the weather forecast instruction of the instruction party, so as to instruct the data collection unit: to collect the weather forecast results of multiple model fields for the same area; a data storage unit: which stores a first reference table including the model weight value of each model field, and a second reference table containing major weather categories and their classification codes, and in the second reference table, each major weather category is classified into various weather types including: rain, snow, suspended particles, fog, and each weather type is linearly coefficient-split, and the steps include: sorting from large to small according to the amount of rainfall and snow, and compiling them into linear parameters, using numerical values to represent the amount of rain and snow; sorting from small to large according to the amount of suspended particles in the atmosphere, and compiling them into linear parameters, using numerical values to represent the amount of suspended particles; sorting from small to large according to the amount of suspended water particles in the atmosphere, and compiling them into Linear parameters, using numerical values to represent the amount of suspended water vapor, to determine the third reference table of linear coefficients for each weather type; data processing unit: classify the weather forecast results of each model field for the same area, and determine whether it belongs to the major weather category in the second reference table and its corresponding third reference table, to obtain the linear coefficient of the corresponding weather type; adjust the linear coefficient of the weather type corresponding to each model field by the weight of each model field to obtain the weather type weight correction value; and calculate the model field comprehensive value c = a / b and round it, where the sum of the weather type weight correction values of each model field is a, and the sum of the model weight values of each model field is b; then check the third reference table based on the model field comprehensive value c to obtain the weather type corresponding to the linear coefficient value that is the same as the c value as the weather forecast result, and send it to the data transceiver unit; the data transceiver unit receives the weather forecast result sent by the data processing unit and feeds it back to the instruction party.
[0014] In order to achieve the above-mentioned purpose, according to the third aspect of the present invention, there is also provided a computer-readable storage medium, on which a computer program is stored, characterized in that when the computer program is executed by a computer processor, the steps of the weather forecasting method based on comprehensive calculation of multi-mode fields as described in any of the above items are implemented.
[0015] Through the weather forecasting method, device and storage medium based on comprehensive calculation of multiple model fields provided by the present invention, the same weather phenomena can be linearly arranged so that the results fluctuate between the same weather types; then combined with the accuracy of each model field, the reasonable value (linear value) of the size of a certain weather phenomenon is calculated, thereby deriving a more reasonable weather phenomenon, thereby performing comprehensive calculations based on multiple model fields, thereby correcting the problem that the weather forecast results occasionally deviate seriously from the actual situation, thereby improving the accuracy of the weather forecast. DETAILED DESCRIPTION
[0016] In order to enable those skilled in the art to better understand the technical solution of the present invention, the specific technical solution of the present invention will be clearly and completely described in conjunction with the embodiments below to help those skilled in the art further understand the present invention. Obviously, the embodiments described in this case are only embodiments of a part of the present invention, not all of the embodiments. It should be pointed out that for those of ordinary skill in the art, the embodiments in this application and the features in the embodiments can be combined with each other without departing from the concept of the present invention and without conflicting with each other. Based on the embodiments in the present invention, all other embodiments obtained without creative work by those of ordinary skill in the art should belong to the disclosure and protection scope of the present invention.
[0017] In addition, the terms "first", "second", "S1", "S2", etc. in the specification and claims of the present invention are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those described herein. At the same time, the terms "including" and "having" in the present invention and any variations thereof are intended to cover non-exclusive inclusions.
[0018] Since the weather results calculated by different model fields (computer model fields for weather forecasts) may not be exactly the same, the results of any model field may deviate from the actual situation. Therefore, once the data of an individual model field is abnormal, the weather forecast results given by the meteorological bureau using the model field will seriously deviate from the actual situation.
[0019] Therefore, in order to solve this problem, the invention of this case is conceived to perform linear splitting for different weather types, and combine the weights of each model field, and use a series of algorithms for secondary calibration, which can effectively correct the deviation of weather forecast.
[0020] Specifically, according to the inventor's observation, when a weather forecast is misreported, it is often due to the deviation of certain weather factors between the same weather types, resulting in inaccurate forecasts. For example, at the same moment, the deviation in the prediction of cloud cover size can lead to different weather phenomena: sunny, cloudy, and overcast.
[0021] Therefore, the inventor can determine the weight of each mode field after calculating the empirical model based on the characteristics of each mode field. Then the same weather phenomenon is linearly arranged so that the results fluctuate between the same weather types; combined with the weight of each mode field, the reasonable value (linear value) of a certain weather phenomenon can be calculated, thereby deriving a more reasonable weather phenomenon.
[0022] Based on the above inventive concept, the present invention provides a weather forecasting method based on comprehensive calculation of multi-mode fields, the steps comprising:
[0023] S1 establishes a first reference table: to assign model weight values to multiple model fields based on weather forecasts for the same region;
[0024] S2 establishes a second benchmark table: linearly splits the weather types into multiple weather categories and assigns classification codes;
[0025] S3 establishes a third reference table: classifies each weather type according to each weather category in the second reference table, and performs linear coefficient splitting on each weather type to determine the linear coefficient of each weather type;
[0026] S4 classifies the weather forecast results of each model field for the same area, and determines whether it belongs to the corresponding weather category in the second benchmark table and its corresponding third benchmark table, so as to obtain the linear coefficient of the corresponding weather type; S5 adjusts the linear coefficient of the weather type corresponding to each model field in step S4 by the model weight value of each model field to obtain the weather type weight correction value; and calculates the model field comprehensive value c=a / b and rounds it, wherein the sum of the weather type weight correction values of each model field is a, and the sum of the model weight values of each model field is b; S6 reversely checks the third benchmark table based on the model field comprehensive value c, so as to obtain the weather type corresponding to the linear coefficient value with the same value as c as the weather forecast result.
[0027] Specifically, as shown in Table 1, it is the first reference table. The model field under this embodiment includes: computer model fields of meteorological bureaus in different regions or countries. Five model fields are used as examples for subsequent calculations. It should be noted that the names of the five model fields are only for example purposes. Since they involve the commercial confidentiality of the applicant's data source, they are modified in the embodiment, but they do not affect the weather forecast results.
[0028]
[0029]
[0030] Table 1
[0031] The “Example” in Table 1 represents the weather type output by the meteorological bureau at a certain time and place;
[0032] "Mode weight" is the mode weight value obtained after the inventor summarizes the characteristics of each mode field and the accuracy experience value based on historical data and calculates it through the empirical model. The larger the value, the higher the accuracy.
[0033] As shown in Table 2, which is the second reference table, in this embodiment, the weather categories are preferably divided into four main types, and for these four types, linear coefficients are split for each type in Tables 3.1 to 3.4.
[0034] Classification Code Weather Linear Type Contains weather type examples 1 rain Heavy, moderate and light rain 2 Snow Heavy, medium and light snow 3 Suspended particulate matter Dust / sand 4 fog Fog / Heavy Fog
[0035] Table 2
[0036] As shown in Tables 3.1-3.4, which are the third reference tables, this embodiment shows linear splitting for the four major weather categories one by one, and the splitting rules are as follows:
[0037] -rain
[0038] It is mainly sorted from large to small according to rainfall, and compiled into linear parameters, with numerical values indicating the size of the rain.
[0039]
[0040] Table 3.1
[0041] -Snow
[0042] The snowfall is mainly sorted from large to small and compiled into linear parameters, with numerical values used to represent the amount of snowfall.
[0043]
[0044] Table 3.2
[0045] -Suspended particles
[0046] It is mainly based on the sorting of suspended particles in the atmosphere from small to large, and compiled into linear parameters, with numerical values representing the amount of suspended particles.
[0047]
[0048]
[0049] Table 3.3
[0050] -fog
[0051] It is mainly based on the sorting of suspended water particles in the atmosphere from few to many, and compiled into linear parameters, using numerical values to represent the amount of suspended water vapor.
[0052]
[0053] Table 3.4
[0054] After the above three reference tables are established, specific calculations can be performed. The calculation process of step S4 in this embodiment includes calculating the following formula 1:
[0055]
[0056] Where: x = t(q 1~5 ), indicating that the five model field results are classified by weather type, corresponding to Table 1. 1~5 Identify the output results of the 5 mode fields.
[0057] Where: f 1n =f1(q n ,x), represents the linear coefficient value of the result of a certain model field,
[0058] Corresponding to Table 3.1 to Table 3.4. Among them, q n Represents the output result of a certain pattern field.
[0059] Where: f 2n =f2(Q n ), represents the weight value of a certain mode field, corresponding to the “mode weight” in Table 1. n Represents a pattern field.
[0060] in: Represents the sum of the weather type weight correction values of the five model fields.
[0061] in: Represents the sum of the mode weight values of the five mode fields.
[0062] Where: c = a / b, representing the comprehensive value of the pattern field.
[0063] Where: y = P (c, x), which means looking up the weather type in Table 3.1-3.4 according to the linear coefficient represented by the comprehensive value of the model field to obtain the weather type corresponding to the linear coefficient value that is the same as the c value as the weather forecast result.
[0064] Calculation Example
[0065] -Real scenario example 1:
[0066] At 10:41 on August 5, 2021, in Yanta District, Xi'an City, Shaanxi Province, the original data obtained from the data source are as follows:
[0067]
[0068] According to formula 1, the results of each model field are classified. In this example, all weather phenomena can be classified as "rain". Therefore, this group of data is rain data, that is, x = 1.
[0069] Calculate the coefficient f of each mode field line result 1n =f1(q n ,x):
[0070]
[0071]
[0072] Calculate the weight f of each mode field 2n =f2(Q n ):
[0073]
[0074] Calculate the sum of the weather type weight correction values for each model field
[0075] That is: a=5*3+2*2+5*1+7*3+9*1=54
[0076] Calculate the sum of the weights of each mode field
[0077] That is: b = 3 + 2 + 1 + 3 + 1 = 10
[0078] Calculate the comprehensive value of the linear coefficient of each mode field c = a / b
[0079] That is: c = 54 / 10 = 5.4, after rounding C = 5
[0080] From the linear coefficient of rain type, we can reversely check the corresponding weather and get the result y=P(c,x).
[0081] Since the comprehensive coefficient is 5 and the weather type is rain, by looking up Table 3.1, the weather type corresponding to 5 is "light rain". Therefore: y = P (5, rain) = light rain.
[0082] According to actual observations, at 10:41 on August 5, 2021, it was drizzling in Yanta District, Xi'an City, Shaanxi Province, which is consistent with the calculation results.
[0083] -Real scenario example 2:
[0084] At 12:21 on August 8, 2021, in Yanta District, Xi'an City, Shaanxi Province, the original data obtained from the data source are as follows:
[0085]
[0086] According to formula 1, it is calculated that this group of data is rain data, that is, x = 1.
[0087] Calculate the coefficient f of each mode field line result 1n =f1(q n ,x):
[0088]
[0089] Calculate the weight f of each mode field 2n =f2(Q n ):
[0090]
[0091] Calculate the sum of the weather type weight correction values for each model field
[0092] That is, a=5*3+7*2+7*1+5*3+5*1=56
[0093] Calculate the sum of the weights of each mode field
[0094] That is, b = 3 + 2 + 1 + 3 + 1 = 10
[0095] Calculate the comprehensive value of the linear coefficient of each mode field c = a / b
[0096] That is, a=56 / 10=5.6, after rounding, C=6
[0097] From the linear coefficient of rain type, we can reversely check the corresponding weather and get the result y=P(c,x).
[0098] Since the comprehensive coefficient is 6 and the weather type is rain, by looking up Table 3.1, the weather type corresponding to 6 is "light to moderate rain". Therefore: y = P (6, rain) = light to moderate rain.
[0099] According to actual observations, at 12:21 on August 8, 2021, it was raining light to moderate rain (i.e. light to moderate rain) in Yanta District, Xi'an City, Shaanxi Province, which is consistent with the calculation results.
[0100] -Real scenario example 3: At 09:32 on October 14, 2021, in Yanta District, Xi'an City, Shaanxi Province, the original data obtained from the data source is as follows:
[0101]
[0102] According to formula 1, it is calculated that this group of data is rain data, that is, x = 1.
[0103] Calculate the coefficient f of each mode field line result 1n =f1(q n ,x):
[0104]
[0105] Calculate the weight f of each mode field 2n =f2(Q n ):
[0106]
[0107] Calculate the sum of the weather type weight correction values for each model field
[0108] That is, a=1*3+3*2+3*1+5*3+5*1=32
[0109] Calculate the sum of the weights of each mode field
[0110] That is, b = 3 + 2 + 1 + 3 + 1 = 10
[0111] Calculate the comprehensive value of the linear coefficient of each mode field c = a / b
[0112] That is, a = 32 / 10 = 3.2, rounded to C = 3
[0113] From the linear coefficient of rain type, we can reversely check the corresponding weather and get the result y=P(c,x).
[0114] Since the comprehensive coefficient is 3 and the weather type is rain, we can check Table 3.1 and the weather type corresponding to 3 is "cloudy". Therefore: y = P (3, rain) = cloudy.
[0115] According to actual observations, around 09:30 on October 14, 2021, it had just rained in Yanta District, Xi'an City, Shaanxi Province, and the sky did not clear up. It was more reasonable to be cloudy, which was consistent with the calculation results.
[0116] Case Summary
[0117]
[0118] Corresponding to Embodiment 1, the second aspect of the present invention further provides a weather forecasting device to execute the above-mentioned weather forecasting method based on comprehensive calculation of multi-mode fields, wherein the weather forecasting device can be various computer devices such as smart devices, PCs, servers, etc. that can run computer software and execute calculation instructions, and at least includes:
[0119] Data transceiver unit: Receives weather forecast instructions from the command party to
[0120] Data collection unit: collects weather forecast results of multiple model fields for the same area;
[0121] A data storage unit: the data storage unit stores a first reference table including the mode weight values of each mode field, a second reference table including the weather categories and their classification codes, and a third reference table for classifying each weather category into each weather type in the second reference table and performing linear coefficient splitting on each weather type to determine the linear coefficient of each weather type;
[0122] The data processing unit: classifies the weather forecast results of each mode field for the same area, and respectively determines the weather category to which it belongs in the second reference table and the corresponding third reference table, so as to obtain the linear coefficient of the corresponding weather type; adjusts the linear coefficient of the weather type corresponding to each mode field by the weight of each mode field to obtain the weather type weight correction value; and calculates the mode field comprehensive value c=a / b and rounds it, wherein the sum of the weather type weight correction values of each mode field is a, and the sum of the mode weight values of each mode field is b; then, according to the mode field comprehensive value c, the third reference table is reversely checked to obtain the weather type corresponding to the linear coefficient value identical to the c value as the weather forecast result, so as to send it to the data transceiver unit;
[0123] The data transceiver unit receives the weather forecast result sent by the data processing unit and feeds it back to the instruction party.
[0124] The command party in this embodiment generally refers to various intelligent devices that can communicate with the weather forecasting device to form intelligent interaction, such as mobile terminals, PCs, servers, etc., and can also be various IoT intelligent terminals, or cars with unmanned driving functions, etc.
[0125] The third aspect of the present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a computer processor, the steps of the weather forecasting method based on comprehensive calculation of multi-mode fields as described in any of the above items are implemented.
[0126] In summary, through the weather forecasting method, device and storage medium based on comprehensive calculation of multi-mode fields provided by the present invention, the same weather phenomena can be linearly arranged so that the results fluctuate between the same weather types; then combined with the accuracy of each model field, the reasonable value (linear value) of a certain weather phenomenon is calculated, thereby deriving a more reasonable weather phenomenon, thereby performing comprehensive calculations based on multi-mode fields, thereby correcting the problem that the weather forecast results occasionally deviate seriously from the actual situation, thereby improving the accuracy of the weather forecast.
[0127] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is only limited by the claims and their full scope and equivalents. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.
[0128] Those skilled in the art can understand that, in addition to implementing the system, device and its various modules provided by the present invention in a purely computer-readable program code, it is entirely possible to implement the same program in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers and embedded microcontrollers by logically programming the method steps. Therefore, the system, device and its various modules provided by the present invention can be considered as a hardware component, and the modules included therein for implementing various programs can also be regarded as structures within the hardware component; the modules for implementing various functions can also be regarded as both software programs for implementing the method and structures within the hardware component.
[0129] In addition, all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including a number of instructions to enable a single-chip microcomputer, a chip or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), disk or optical disk and other media that can store program codes.
[0130] In addition, various implementation modes of the embodiments of the present invention may be arbitrarily combined, and as long as they do not violate the concept of the embodiments of the present invention, they should also be regarded as the contents disclosed by the embodiments of the present invention.
Claims
1. A weather forecasting method based on multi-mode field comprehensive calculation, comprising the following steps: S1 establishes a first reference table: to assign model weight values to multiple model fields based on weather forecasts for the same region; S2 establishes a second reference table: linearly splits the weather types into multiple weather categories including rain, snow, suspended particles, and fog, and assigns classification codes; S3 establishes a third reference table: classifies each weather type from each weather category in the second reference table, and performs linear coefficient splitting on each weather type, the steps comprising: Sort the rainfall and snowfall from large to small and compile them into linear parameters, using numerical values to represent the amount of rain and snowfall; Sort the suspended particles in the atmosphere from small to large and compile them into linear parameters, using numerical values to represent the amount of suspended particles; Sort the suspended water particles in the atmosphere from few to many and compile them into linear parameters, using numerical values to represent the amount of suspended water vapor; To determine the linear coefficients for each weather type; S4 classifies the weather forecast results of each model field for the same area, and respectively determines whether it belongs to the corresponding weather category in the second reference table and the corresponding third reference table, so as to obtain the linear coefficient of the corresponding weather type; S5 adjusts the linear coefficient of the weather type corresponding to each mode field in step S4 by the mode weight value of each mode field to obtain the weather type weight correction value; and calculates the mode field comprehensive value c=a / b and rounds it, wherein the sum of the weather type weight correction values of each mode field is a, and the sum of the mode weight values of each mode field is b; S6: Look up the third reference table according to the model field comprehensive value c to obtain the weather type corresponding to the linear coefficient value that is the same as the c value as the weather forecast result.
2. The weather forecasting method based on comprehensive calculation of multiple model fields according to claim 1, wherein the model field comprises: Computer model fields from meteorological bureaus in different regions or countries.
3. The weather forecasting method based on multi-mode field comprehensive calculation according to claim 1, wherein the weather type corresponding to the major weather category of rain and the corresponding linear coefficient include: Sunny, linear coefficient 1, cloudy, linear coefficient 2, overcast, linear coefficient 3, showers, linear coefficient 4, light rain, linear coefficient 5, light to moderate rain, linear coefficient 6, moderate rain, linear coefficient 7, moderate to heavy rain, linear coefficient 8, heavy rain, linear coefficient 9, heavy to torrential rain, linear coefficient 10, torrential rain, linear coefficient 11, torrential rain to heavy rain, linear coefficient 12, heavy rain, linear coefficient 13, heavy rain to extremely heavy rain, linear coefficient 14, extremely heavy rain, linear coefficient 15.
4. The weather forecasting method based on multi-mode field comprehensive calculation according to claim 1, wherein the weather type corresponding to the weather category of snow and the corresponding linear coefficient include: Sunny, linear coefficient 1, cloudy, linear coefficient 2, overcast, linear coefficient 3, sleet, linear coefficient 4, snow showers, linear coefficient 5, light snow, linear coefficient 6, light to moderate snow, linear coefficient 7, moderate snow, linear coefficient 8, moderate to heavy snow, linear coefficient 9, heavy snow, linear coefficient 10, heavy to blizzard, linear coefficient 11, blizzard, linear coefficient 12.
5. The weather forecasting method based on multi-mode field comprehensive calculation according to claim 1, wherein the weather type corresponding to the weather category of suspended particulate matter and the corresponding linear coefficient include: Sunny, linear coefficient 1; cloudy, linear coefficient 2; overcast, linear coefficient 3; floating dust, linear coefficient 4; blowing sand, linear coefficient 5; sandstorm, linear coefficient 6; strong sandstorm, linear coefficient 7.
6. The weather forecasting method based on multi-mode field comprehensive calculation according to claim 1, wherein the weather type corresponding to the major weather category of fog and the corresponding linear coefficient include: Sunny, linear coefficient 1; cloudy, linear coefficient 2; overcast, linear coefficient 3; foggy, linear coefficient 4.
7. The weather forecasting method based on multi-model field comprehensive calculation according to claim 1, wherein the model field comprehensive value c is rounded to an integer.
8. A weather forecasting device, comprising: Data transceiver unit: Receives weather forecast instructions from the command party to Data collection unit: collects weather forecast results of multiple model fields for the same area; Data storage unit: It stores a first reference table including the weight values of each mode field mode, and a second reference table containing weather categories and their classification codes, and in the second reference table, each weather category is classified into various weather types including rain, snow, suspended particles, and fog, and each weather type is split into linear coefficients, including: Sort the rainfall and snowfall from large to small and compile them into linear parameters, using numerical values to represent the amount of rain and snowfall; Sort the suspended particles in the atmosphere from small to large and compile them into linear parameters, using numerical values to represent the amount of suspended particles; Sort the suspended water particles in the atmosphere from few to many and compile them into linear parameters, using numerical values to represent the amount of suspended water vapor; A third reference table for determining linear coefficients for each weather type; The data processing unit: classifies the weather forecast results of each model field for the same area, and respectively determines the weather category to which it belongs in the second reference table and the corresponding third reference table, so as to obtain the linear coefficient of the corresponding weather type; adjusts the linear coefficient of the weather type corresponding to each model field by the weight of each model field to obtain the weather type weight correction value; and calculates the model field comprehensive value c=a / b and rounds it, wherein the sum of the weather type weight correction values of each model field is a, and the sum of the model weight values of each model field is b; then, according to the model field comprehensive value c, the third reference table is reversely checked to obtain the weather type corresponding to the linear coefficient value that is the same as the c value as the weather forecast result, so as to send it to the data transceiver unit; The data transceiver unit receives the weather forecast result sent by the data processing unit and feeds it back to the instruction party.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a computer processor, the steps of the weather forecasting method based on multi-mode field comprehensive calculation as claimed in any one of claims 1 to 7 are implemented.
