Meteorological data forecasting method, device, equipment, storage medium and program product

Abstract

The present application discloses a meteorological data prediction method, device, equipment, storage medium and program product, which relates to the field of data analysis. The method includes: obtaining meteorological measurement data for a target geographical location in a first time period, and predicted meteorological data for the target geographical location in the first time period from at least two meteorological sources; determining the prediction weights of the meteorological sources corresponding to the second time period based on the meteorological measurement data and the predicted meteorological data of the meteorological source; obtaining the predicted meteorological data of the meteorological source for the second time period; based on the predicted weights of the meteorological source, determining the weighted calculation results of the predicted meteorological data of the at least two meteorological sources for the second time period, and obtaining the meteorological data prediction results for the second time period. Through the above methods, the advantages of multiple meteorological sources can be fully utilized, the deviation of each meteorological source can be reduced, and the prediction characteristics in the meteorological data prediction process can be adjusted in real time according to time changes to obtain meteorological data prediction results with higher accuracy.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of data analysis, and in particular to a meteorological data prediction method, device, equipment, storage medium and program product. Background Art

[0002] In recent years, with the continuous upgrading of meteorological business data forecasting systems and the rapid development of communication levels, people have put forward higher requirements for weather forecasting. For example, economic construction and agricultural development require accurate long-term weather forecasts, and industries such as aviation activities and energy generation require medium-term or short-term weather forecasts for wind speed and visibility. The role of meteorological data forecasting in social and economic development and people's daily lives is becoming increasingly prominent.

[0003] In related technologies, in order to accurately forecast meteorological data, a machine learning model is usually built based on a single meteorological source to obtain a meteorological data prediction model, and the meteorological data prediction results corresponding to the time period to be predicted are obtained based on the meteorological prediction model.

[0004] However, the above-mentioned meteorological forecasting methods are generally based on a single machine learning model, which cannot effectively and simultaneously take advantage of the advantages of multiple meteorological sources, and thus cannot achieve the purpose of accurately predicting meteorological data. Summary of the invention

[0005] The embodiments of the present application provide a meteorological data prediction method, device, equipment, storage medium and program product, which can obtain meteorological data prediction results with higher accuracy. The technical solution is as follows.

[0006] In one aspect, a method for forecasting meteorological data is provided, the method comprising:

[0007] Acquire meteorological measurement data for a target geographical location in a first time period, and predicted meteorological data for the target geographical location in the first time period from at least two meteorological sources, wherein a kth meteorological source is used to predict and obtain a kth group of predicted meteorological data, where k is a positive integer;

[0008] Determine, based on the meteorological measurement data and the predicted meteorological data of the at least two meteorological sources, prediction weights of the at least two meteorological sources corresponding to a second time period, respectively, the first time period being before the second time period;

[0009] Obtaining forecasted meteorological data for the second time period from at least two meteorological sources;

[0010] Based on the prediction weights of the at least two meteorological sources, a weighted calculation result of the predicted meteorological data of the at least two meteorological sources for the second time period is determined to obtain a prediction result of the meteorological data for the second time period at the target geographical location.

[0011] In another aspect, a meteorological data prediction device is provided, the device comprising:

[0012] A first acquisition module is used to acquire meteorological measurement data for a target geographical location in a first time period, and predicted meteorological data for the target geographical location in the first time period from at least two meteorological sources, wherein a k-th meteorological source is used to predict and obtain a k-th group of predicted meteorological data, where k is a positive integer;

[0013] A first determination module is used to determine the prediction weights of the at least two meteorological sources corresponding to a second time period respectively based on the meteorological measurement data and the predicted meteorological data of the at least two meteorological sources, wherein the first time period is before the second time period;

[0014] A second acquisition module, used to acquire the forecasted meteorological data for the second time period from at least two meteorological sources;

[0015] The second determination module is used to determine the weighted operation result of the at least two meteorological sources on the predicted meteorological data of the second time period based on the prediction weights of the at least two meteorological sources, and obtain the meteorological data prediction result of the second time period at the target geographical location.

[0016] On the other hand, a computer device is provided, which includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement a meteorological data prediction method as described in any of the above-mentioned embodiments of the present application.

[0017] On the other hand, a computer-readable storage medium is provided, in which at least one instruction, at least one program, a code set or an instruction set is stored. The at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement a meteorological data prediction method as described in any of the above-mentioned embodiments of the present application.

[0018] On the other hand, a computer program product or a computer program is provided, the computer program product or the computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the meteorological data prediction method described in any of the above embodiments.

[0019] The beneficial effects brought by the technical solution provided by the embodiment of the present application include at least:

[0020] After obtaining the meteorological measurement data for the target geographical location in the first time period and the predicted meteorological data for the first time period from multiple meteorological sources, the prediction weights for the second time period corresponding to the multiple meteorological sources are determined according to the meteorological measurement data and the predicted meteorological data of each of the multiple meteorological sources. Then, according to the predicted meteorological data for the second time period from the multiple meteorological sources and the prediction weights of the multiple meteorological sources, the meteorological data prediction result for the target geographical location in the second time period is obtained. Through the above method, the advantages of multiple meteorological sources can be fully utilized, the deviation of each meteorological source can be reduced, and the prediction characteristics in the meteorological data prediction process can be adjusted in real time according to time changes to obtain a more accurate meteorological data prediction result. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 It is a schematic diagram of an implementation environment provided by an exemplary embodiment of the present application;

[0023] Figure 2 is a flow chart of a meteorological data prediction method provided by an exemplary embodiment of the present application;

[0024] Figure 3 is a flow chart of a meteorological data prediction method provided by another exemplary embodiment of the present application;

[0025] Figure 4 is a flow chart of a meteorological data prediction method provided by another exemplary embodiment of the present application;

[0026] Figure 5 is a flow chart of a meteorological data prediction method provided by another exemplary embodiment of the present application;

[0027] Figure 6 is a structural block diagram of a meteorological data prediction device provided by an exemplary embodiment of the present application;

[0028] Figure 7 It is a structural block diagram of a server provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0029] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0030] In the related art, in order to accurately forecast meteorological data, a machine learning model is usually built based on a single meteorological source to construct a meteorological data prediction model, and the meteorological data prediction results corresponding to the time period to be predicted are obtained based on the meteorological prediction model. However, the above meteorological prediction methods are generally based on a single machine learning model, which cannot efficiently take advantage of multiple meteorological sources at the same time, and thus cannot achieve the purpose of accurately predicting meteorological data.

[0031] In an embodiment of the present application, a meteorological data prediction method is provided, which makes the meteorological data prediction result more accurate. The meteorological data prediction method obtained by training in the present application includes at least one of the following scenarios when applied.

[0032] 1. Applied to wind speed prediction.

[0033] Wind energy is a renewable, high-energy clean energy, and it can be better utilized by monitoring meteorological data. Wind power is usually obtained in the form of wind power generation. With the development of the wind power industry, the grid-connected capacity has increased rapidly, and the connection between wind power grids and public power grids has become increasingly close. When a large-scale wind power generation system is connected to the power grid, the intermittent and uncertain characteristics of wind power generation will pose a major challenge to the safe operation of the public power grid. Indicatively, through the meteorological data prediction method provided by this application, with "day" as the time period division standard, for the target geographical location, based on the wind speed measurement data obtained in the previous few days at the target geographical location and the predicted wind speed data of the target geographical location from multiple meteorological sources, the prediction weights corresponding to each of the multiple meteorological sources are determined, and then the results of the wind speed data prediction from multiple meteorological sources are combined to predict the wind speed for the target geographical location in the next day or a few days, so as to obtain a more accurate wind speed data prediction result.

[0034] 2. Applied in the agricultural field.

[0035] Agricultural development depends on climate change, and temperature, air pressure, precipitation, etc. will have an impact on agriculture. In an illustrative manner, through the meteorological data prediction method provided by this application, with "year" as the time period division standard, it is possible to obtain only a single type of meteorological data, or to obtain multiple meteorological data at the same time for analysis. According to the obtained meteorological measurement data of the previous few years and the predicted meteorological data of multiple meteorological sources, the prediction weights corresponding to each of the multiple meteorological sources are determined, and then the results of meteorological data prediction from multiple meteorological sources are combined to predict the meteorological data of the next year or the next few years, so as to obtain a more accurate meteorological data prediction result.

[0036] It is worth noting that the above application scenarios are only illustrative examples. The meteorological data prediction method provided in this embodiment can also be applied to other scenarios, and the embodiments of the present application are not limited to this.

[0037] Next, the implementation environment involved in the embodiments of the present application is described. For illustration, please refer to Figure 1 The implementation environment involves a meteorological source 110 , a terminal 120 and a server 130 .

[0038] In some embodiments, the meteorological source 110 has a meteorological forecasting function for obtaining forecast meteorological data; or, the meteorological source 110 has a meteorological measurement function for obtaining meteorological measurement data. Optionally, the meteorological source 110 is used to send forecast meteorological data (including multiple sets of forecast meteorological data for target geographical locations in multiple time periods) to the terminal 120, and then the terminal 120 sends the forecast meteorological data sent by the meteorological source 110 and the data measurement data obtained by the local terminal to the server 130. Optionally, the server 130 obtains the meteorological data forecast result through the meteorological measurement data and the forecast meteorological data, and feeds the meteorological data forecast result back to the terminal 120. Among them, the meteorological source 110 is a machine or program for forecasting or measuring meteorological data. Schematically, the meteorological source 110 is a weather forecast application installed on the terminal 120; or, the meteorological source 110 is a meteorological forecast website, etc.

[0039] In an optional embodiment, the server 130 determines the prediction weights corresponding to the target geographical location in the second time period from different meteorological sources based on the meteorological measurement data sent by the terminal 120 and the predicted meteorological data for the target geographical location in the first time period in multiple sets of predicted meteorological data; then, based on the predicted meteorological data for the target geographical location in the second time period and the prediction weights in multiple sets of predicted meteorological data, the weighted calculation results of the predicted meteorological data for the second time period from different meteorological sources are determined to obtain the meteorological data prediction results for the target geographical location in the second time period, thereby realizing the meteorological prediction process. Among them, the predicted meteorological data for the first time period and the predicted meteorological data for the second time period are the predicted meteorological data sent by the meteorological source 110 to the terminal 120. Optionally, after obtaining the meteorological data prediction results, the server 130 sends the meteorological data prediction results to the terminal 120, and the terminal 120 displays the meteorological data prediction results.

[0040] It is worth noting that the above-mentioned terminals can be implemented as mobile terminals such as mobile phones, tablet computers, portable laptops, etc., or as desktop computers, etc.; the above-mentioned servers can be independent physical servers, or they can be server clusters or distributed systems composed of multiple physical servers, or they can be cloud servers that provide basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), as well as big data and artificial intelligence platforms.

[0041] Among them, cloud technology refers to a hosting technology that unifies hardware, application programs, networks and other resources within a wide area network or local area network to achieve data computing, storage, processing and sharing. Cloud technology is a general term for network technology, information technology, integration technology, management platform technology, application technology, etc. based on the cloud computing business model. It can form a resource pool that can be used on demand and is flexible and convenient. Cloud computing technology will become an important support. The background services of technical network systems require a large amount of computing and storage resources, such as video websites, picture websites and more portal websites. With the high development and application of the Internet industry, in the future, each item may have its own identification mark, and all need to be transmitted to the background system for logical processing. Data of different levels will be processed separately. All kinds of industry data require strong system backing support, which can only be achieved through cloud computing.

[0042] In some embodiments, the above-mentioned server can also be implemented as a node in a blockchain system. Blockchain is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, the platform product service layer, and the application service layer.

[0043] Combined with the above-mentioned noun introduction and application scenarios, the meteorological data prediction method provided by this application is explained, and the method is applied to a server as an example. Figure 2 As shown, the method includes the following steps 210 to 240.

[0044] Step 210: Obtain meteorological measurement data for a target geographical location in a first time period, and forecast meteorological data for the target geographical location in the first time period from at least two meteorological sources.

[0045] Among them, the kth meteorological source is used to predict and obtain the kth group of predicted meteorological data, and k is a positive integer.

[0046] Meteorological measurement data refers to meteorological data that can reflect weather conditions and is obtained by measuring instruments in historical time periods; forecasted meteorological data refers to meteorological data that is obtained by inferring the possible trends of meteorological development in future time periods based on the meteorological evolution laws in past time periods. Alternatively, meteorological measurement data refers to data obtained by processing, collating and analyzing observed meteorological resources, usually using professional meteorological equipment such as meteorological instruments. In principle, meteorological measurement data includes various meteorological data such as air pressure data, temperature data, wind direction and speed data, precipitation data, evaporation data, and sunshine hours.

[0047] The target geographical location is the geographical location corresponding to the obtained meteorological measurement data. Optionally, the meteorological measurement data is meteorological data obtained from a website. If the meteorological measurement data to be obtained is meteorological measurement data of location A, location A is the target geographical location; or, when the meteorological measurement data is meteorological data obtained by a meteorological data measuring instrument, the geographical location where the meteorological data measuring instrument is located is regarded as the target geographical location.

[0048] The first time period is a period of time. Optionally, according to the difference in the time period division method, the first time period can be expressed as 12 hours, one day, one month, one year, etc. Indicatively, the meteorological measurement data for the target geographical location in the first time period can be obtained by downloading from a website, for example, through the Chinese Standard Weather Data website (CSWD), the European Space Agency's Weather Change Initiative website, the FAO Geographic website, the National Aeronautics and Space Administration website (NASA), etc. Select the first time period and the meteorological data to be obtained in the first time period in the above websites, and obtain the meteorological measurement data of the first time period through the data retrieval function. For example: select "Hourly Observation Data of China's Ground Meteorological Stations" under the "Data Service" option on the China Standard Meteorological Data Website, and select the first time period according to the date prompt, such as: the first time period is set to "00:00 on November 8, 2021 to 23:00 on November 8, 2021"; then determine the "station selection" according to the geographical location of the meteorological measurement data to be obtained, that is, determine the target geographical location of the meteorological measurement data, such as: the station selection is "Beijing"; then check at least one meteorological element to be obtained in the "Element Selection" tab (that is, at least one meteorological measurement data to be obtained), such as: the element selection is set to "maximum wind speed" and "minimum temperature". After the query information is selected, data retrieval is performed to obtain the maximum wind speed data and minimum temperature data of Beijing from 00:00 on November 8, 2021 to 23:00 on November 8, 2021, and complete the process of obtaining the meteorological measurement data for the target geographical location in the first time period. The above is only an illustrative example, and the embodiments of the present application are not limited to this.

[0049] Meteorological sources are sources of forecasted meteorological data. Schematically, different weather forecast applications can be regarded as different meteorological sources; or, different weather forecast websites can be regarded as different meteorological sources, etc. Meteorological sources use meteorological, dynamic, statistical and other principles and methods based on past meteorological measurement data to make qualitative and quantitative forecasts of the weather in the future. Schematically, common meteorological forecasting models include: The Weather Research and Forecasting Model (WRF), known as the next generation of mesoscale weather forecasting model, which can not only be used for case simulation of real weather, but also as a theoretical basis for the discussion of basic physical processes; European Centre for Medium-Range Weather Forecasts (EC), used to provide deterministic forecasts for the European Centre for Medium-Range Weather Forecasts; International Business Machines Corporation (IBM), used to provide deterministic forecasts for IBM's meteorological forecasting agency "The Weather Company".

[0050] Schematically, different meteorological sources will predict different meteorological forecast results according to different algorithms or different forecasting methods. Optionally, the meteorological source has a meteorological forecasting function, such as forecasting meteorological data for future time periods; a meteorological measurement function, such as measuring meteorological data for the current time period; and a saving function, such as automatically saving meteorological forecast data for previous time periods so as to analyze the saved meteorological forecast data later.

[0051] Optionally, at least two meteorological sources are first determined as sources of predicted meteorological data, and then the predicted meteorological data of the at least two meteorological sources in the first time period are obtained, so as to obtain the predicted meteorological data corresponding to the at least two meteorological sources in the first time period. The kth meteorological source is used to predict and obtain the kth group of predicted meteorological data, and k is a positive integer. Schematically, a time period may correspond to multiple predicted meteorological data. When obtaining the predicted meteorological data corresponding to the first time period, the predicted meteorological data may exist in the form of a group, wherein a group of predicted meteorological data includes at least one predicted meteorological data.

[0052] Step 220: Determine prediction weights of the at least two meteorological sources corresponding to the second time period based on the meteorological measurement data and the predicted meteorological data of the at least two meteorological sources.

[0053] The first time period is before the second time period.

[0054] Optionally, when the first time period is a time period before the current moment, the second time period is a time period after the current moment. For example, if "day" is used as the time period division standard, "today" is the current moment, the first time period is "yesterday", and the second time period is "tomorrow", when making a weather forecast, it is regarded as: predicting tomorrow's forecast weather data based on yesterday's weather measurement data and forecast weather data.

[0055] Schematically, different meteorological sources correspond to different meteorological forecast data, and there are meteorological forecast differences between different meteorological sources. The meteorological forecast differences are used to indicate the differences between meteorological measurement data and forecast meteorological data, and the meteorological forecast differences can be distinguished by deviations. When the deviation between meteorological measurement data and forecast meteorological data is small, it means that the meteorological forecast effect of the meteorological source is good; when the deviation between meteorological measurement data and forecast meteorological data is large, it means that the meteorological forecast effect of the meteorological source is poor.

[0056] Different meteorological forecast deviations corresponding to different meteorological sources can be distinguished by the weights corresponding to the meteorological sources. Optionally, there are differences in the forecasted meteorological data of meteorological sources in different time periods. When determining the weights corresponding to the meteorological sources, the weight ratios corresponding to different time periods will change in real time. That is, considering that the statistical characteristics of the deviation of the forecasted meteorological data relative to the meteorological measurement data will change with time, the weights corresponding to different meteorological sources will be continuously updated during the forecast process in different time periods.

[0057] After obtaining the meteorological measurement data and the predicted meteorological data of at least two meteorological sources, the meteorological measurement data are compared with the predicted meteorological data corresponding to the at least two meteorological sources respectively, so as to determine the prediction weights of the at least two meteorological sources respectively corresponding to the second time period.

[0058] Step 230: Obtain forecasted meteorological data for a second time period from at least two meteorological sources.

[0059] Optionally, different meteorological sources correspond to different prediction algorithms, and different meteorological forecast results will be obtained. Schematically, the i meteorological source is taken as an example for explanation. The i meteorological source obtains the data measurement results of the first time period, and the i meteorological source predicts the meteorological data of the second time period based on the meteorological measurement data of the first time period, and obtains the meteorological forecast result corresponding to the i meteorological source. That is: the i meteorological source obtains the predicted meteorological data of the second time period at the target geographical location based on the data measurement results of the first time period and the predicted meteorological data of the first time period.

[0060] Based on the above method, different meteorological sources predict different predicted meteorological data. The predicted meteorological data predicted by different meteorological sources for the second time period are acquired to obtain the predicted meteorological data for the second time period from at least two meteorological sources.

[0061] Step 240, based on the prediction weights of at least two meteorological sources, determine the weighted calculation results of the at least two meteorological sources on the predicted meteorological data for the second time period, and obtain the meteorological data prediction result for the second time period at the target geographical location.

[0062] In an illustrative manner, the predicted meteorological results of at least two meteorological sources for the second time period and the prediction weights of at least two meteorological sources corresponding to the second time period are weighted, that is, the prediction weight representing the deviation between the meteorological measurement data and the meteorological prediction data and the predicted meteorological data of at least two meteorological sources for the second time period are weighted to obtain a weighted calculation result. Then, based on the weighted calculation result, the meteorological data prediction result for the second time period at the target geographical location is obtained.

[0063] The second time period is a time period for which meteorological data is to be predicted. Optionally, the second time period is a time period after the current moment, that is, the second time period has not yet occurred; or, the second time period is a time period that has already occurred, such as: the second time period has already occurred, but the purpose is to predict the meteorological forecast data of the second time period based on the meteorological data (including meteorological measurement data and meteorological forecast data) between the second time period.

[0064] In an optional embodiment, the time period division standard is "day". When the second time period is "tomorrow" (i.e., the meteorological data for tomorrow is to be predicted), considering that the meteorological data for "today" is not yet complete, the first time period is determined as "yesterday", that is, the meteorological measurement data for "yesterday" and the meteorological forecast data for "yesterday" from multiple meteorological sources are used to determine the meteorological data forecast result for "tomorrow". The above is only an illustrative example, and the embodiments of the present application are not limited to this.

[0065] In summary, after obtaining the meteorological measurement data for the target geographical location in the first time period and the predicted meteorological data for the first time period from multiple meteorological sources, the prediction weights for the second time period corresponding to the multiple meteorological sources are determined according to the meteorological measurement data and the predicted meteorological data of each of the multiple meteorological sources. Then, according to the predicted meteorological data for the second time period from the multiple meteorological sources and the prediction weights of the multiple meteorological sources, the meteorological data prediction result for the target geographical location in the second time period is obtained. Through the above method, the advantages of multiple meteorological sources can be fully utilized, the deviation of each meteorological source can be reduced, and the prediction characteristics in the meteorological data prediction process can be adjusted in real time according to time changes to obtain a more accurate meteorological data prediction result.

[0066] In an optional embodiment, the prediction weight for the second time period is determined based on the meteorological measurement data and the predicted meteorological data from at least two meteorological sources. Figure 3 As shown above Figure 2 Step 220 in the illustrated embodiment may also be implemented as steps 310 to 320 as follows.

[0067] Step 310: Determine data error parameters of at least two meteorological sources for a second time period based on the meteorological measurement data and the predicted meteorological data of at least two meteorological sources.

[0068] The data error parameter is a prediction parameter, which is a parameter generated in the process of predicting the meteorological data prediction result of the second time period, and is used to indicate the possible error between the meteorological data prediction result of the second time period and the meteorological measurement data of the second time period. Optionally, the meteorological measurement data of the second time period is the true value corresponding to the meteorological data of the second time period.

[0069] In an optional embodiment, the difference between the meteorological measurement data and the predicted meteorological data of at least two meteorological sources is determined as the meteorological error of the at least two meteorological sources in a first time period; the historical data error parameters used in the meteorological data prediction process of the first time period are determined; and based on the meteorological error and the historical data error parameters of the first time period, the data error parameters of the second time period are determined.

[0070] The meteorological error of the first time period is used to indicate the difference between the meteorological measurement data (true value) and the predicted meteorological data (predicted value) corresponding to at least two meteorological sources in the first time period. For example: in the first time period, the meteorological measurement data is m, and the predicted meteorological data corresponding to the Lth meteorological source and the Nth meteorological source are l and n, respectively. Then the meteorological error of the Lth meteorological source in the first time period is ml; the meteorological error of the Nth meteorological source in the first time period is mn, that is, the meteorological errors of at least two meteorological sources in the first time period are determined.

[0071] Indicatively, the historical data error parameter is determined based on the previous time period of the first time period. For example, take any meteorological source as an example, and use "day" as the time period division standard. Today is the first time period - "August 8", and yesterday is the previous time period of the first time - "August 7". The meteorological measurement data of "August 7" and the meteorological forecast data of "August 6" for "August 7" are known. The historical data error parameter can be determined based on the meteorological measurement data of "August 7" and the meteorological forecast data of "August 7".

[0072] In an optional embodiment, based on the error adjustment factor, the meteorological error and historical data error parameters of the first time period are adjusted to obtain an adjustment result; based on the adjustment result, the data error parameter of the second time period is determined.

[0073] The error adjustment factor is a preset value used to distinguish between different errors in different time periods. Optionally, the error adjustment factor uses a forgetting factor, which determines the probability that the latest error information is absorbed. To keep the algorithm stable, the value of the forgetting factor is generally between 0.9 and 1.

[0074] Alternatively, taking meteorological source i as an example, without considering the influence of time period on data error parameter, the expression of data error parameter is as follows:

[0075]

[0076] Among them, μ i is the data error parameter of meteorological source i; y is the meteorological measurement data; is the weather forecast data of weather source i; It is used to indicate the meteorological forecast data based on the meteorological measurement data and the i meteorological source, solve the expectation of the i meteorological source, and then obtain the data error parameter of the i meteorological source.

[0077] In schematic form, when considering the impact of different time periods on the data error parameters, that is, the data error parameters are parameters updated in real time, different time periods will update different data error parameters. Taking meteorological source i as an example, the data error parameters of the second time period can be obtained based on the following expression.

[0078]

[0079] Where i is the meteorological source; t represents the second time period; t-1 represents the first time period; μ is the data error parameter; λ is the error adjustment factor; y is the meteorological measurement data; is the weather forecast data; μ t,i Used to indicate the data error parameter of meteorological source i in the second time period; μ t-1,i Used to indicate the historical data error parameter corresponding to the first time period; t-1 Meteorological measurement data for indicating a first time period; Used to indicate the weather forecast data of weather source i in the first time period.

[0080] Optionally, there is an iterative relationship between the data error parameter and the historical data error parameter, that is, the historical data error parameter corresponding to the first time period is obtained based on the above data error parameter expression through the historical data error parameter of the time period before the first time period, that is, the historical data error parameter corresponding to the first time period is the data error parameter corresponding to the historical data error parameter of the time period before the first time period. Schematically, after obtaining the historical data error parameter corresponding to the first time period, the data error parameter corresponding to the second time period can be determined based on the above data error parameter expression. Optionally, the above process is iterated using a high-performance recursive least squares method to implement iterative updates of the data error parameter during the data prediction process.

[0081] Step 320: Determine prediction weights of at least two meteorological sources corresponding to the second time period based on the meteorological measurement data, the predicted meteorological data of at least two meteorological sources, and the data error parameter.

[0082] Among them, the prediction weight is used to indicate the deviation between the meteorological measurement data and the meteorological forecast data of different meteorological sources within a certain time period. The larger the prediction weight corresponding to a meteorological source, the smaller the prediction deviation of the meteorological source within the time period, and the better the meteorological forecast data corresponding to the meteorological source; the smaller the prediction weight corresponding to a meteorological source, the larger the prediction deviation of the meteorological source within the time period, and the worse the meteorological forecast data corresponding to the meteorological source.

[0083] In an optional embodiment, based on the meteorological errors of at least two meteorological sources in the first time period, the covariance relationship of at least two meteorological sources in the first time period is determined; based on the data error parameters, the covariance relationship and the error adjustment factor, the prediction weights of at least two meteorological sources corresponding to the second time period are determined.

[0084] Schematically, taking meteorological source i and meteorological source j as an example, the covariance relationship expression between meteorological source i and meteorological source j is as follows.

[0085]

[0086] Among them, V ij It is used to indicate the covariance relationship between meteorological sources i and j; y is the meteorological measurement data; is the meteorological forecast data corresponding to meteorological source i; is the meteorological forecast data corresponding to the j meteorological source.

[0087] Optionally, after obtaining the meteorological measurement data in the first time period and the meteorological forecast data corresponding to the i meteorological source and the j meteorological source respectively, the meteorological errors corresponding to the i meteorological source and the j meteorological source respectively in the first time period can be determined. Then, based on the covariance relationship expression between the i meteorological source and the j meteorological source, the covariance relationship between the i meteorological source and the j meteorological source in the first time period is obtained.

[0088] Optionally, when the covariance relationship between the i meteorological source and the j meteorological source is determined based on the time period division standard, the above covariance relationship expression can be transformed into a covariance expression as shown below.

[0089]

[0090] Where i is the i meteorological source; j is the j meteorological source; t represents the second time period; t-1 represents the first time period; V t,ij It is used to indicate the covariance relationship between meteorological source i and meteorological source j corresponding to the second time period; λ is the error adjustment factor; V t-1,ij It is used to indicate the covariance relationship between the meteorological source i and the meteorological source j corresponding to the first time period; t-1 Used to indicate meteorological measurement data corresponding to the first time period; Used to indicate the weather forecast data of weather source i in the first time period; μ t,i Used to indicate the data error parameter of meteorological source i in the second time period; Used to indicate the weather forecast data of j weather source in the first time period; μ t,j Used to indicate the data error parameter of the j meteorological source in the second time period.

[0091] Taking the covariance expression considering the time period as an example, after determining the covariance relationship between the meteorological source i and the meteorological source j in the first time period, the error adjustment factor, the covariance relationship between the meteorological source i and the meteorological source j in the first time period, the meteorological measurement data corresponding to the first time period, the meteorological forecast data of the meteorological source i and the meteorological source j in the first time period, and the data error parameters of the meteorological source i and the meteorological source j in the second time period are substituted into the above covariance expression to obtain the covariance relationship between the meteorological source i and the meteorological source j corresponding to the second time period.

[0092] Afterwards, based on the covariance relationship between the meteorological source i and the meteorological source j corresponding to the second time period, the weight relationship corresponding to the meteorological source i and the meteorological source j in the second time period is determined. Schematically, the expression of the prediction weight is as follows:

[0093]

[0094] Among them, β is the prediction weight corresponding to the meteorological source; f is the functional relationship; V is the covariance relationship between different meteorological sources, and the function represents the relationship between the prediction weight and V. Schematically, when the covariance relationship between different meteorological sources is updated in real time over time, the prediction weight will also be updated accordingly, for example: the function is a linear function; or the function is an exponential function.

[0095] In schematic form, the i meteorological source and the j meteorological source are taken as an example, and the function is a linear function. First, the covariance relationship between the i meteorological source and the j meteorological source is determined to be i=4j according to the above method, and then, based on the sum of the weight ratios being 1, the prediction weight ratios of the i meteorological source and the j meteorological source are calculated, and the prediction weight ratios of the i meteorological source and the j meteorological source are obtained to be 0.8 and 0.2, respectively.

[0096] Optionally, in the process of predicting meteorological data based on multiple meteorological sources, taking one meteorological source as a benchmark, according to the above method, the covariance relationship between the meteorological source and other meteorological sources is calculated, the covariance relationship between the meteorological source and other meteorological sources is substituted into the above function, and the prediction weights corresponding to each of the multiple meteorological sources are determined, thereby realizing the process of obtaining the prediction weights.

[0097] In summary, according to the meteorological measurement data and the predicted meteorological data of each of the multiple meteorological sources, the prediction weights of the second time period corresponding to the multiple meteorological sources are determined, and according to the predicted meteorological data of the second time period by the multiple meteorological sources and the prediction weights of the multiple meteorological sources, the meteorological data prediction result of the second time period at the target geographical location is obtained. Through the above method, the deviation of each meteorological source can be reduced, and a more accurate meteorological data prediction result can be obtained.

[0098] In an embodiment of the present application, the process of obtaining the prediction weight is described. Based on the meteorological measurement data and the predicted meteorological data of multiple meteorological sources for the first time period, the meteorological prediction errors corresponding to different meteorological sources can be determined, and the prediction weights of the second time period corresponding to each of the multiple meteorological sources can be determined based on the meteorological measurement data, the predicted meteorological data of multiple meteorological sources, and the data error parameters. Through the above method, the meteorological prediction data of different meteorological sources in the same time period can be analyzed to obtain the degree of difference in the meteorological data predictions of different meteorological sources, and then determine the prediction weights of different meteorological sources, that is, determine the weight ratio of different meteorological sources in meteorological prediction. The above method can also adjust the data error parameters and covariance relationship in the meteorological data prediction process in real time according to time changes, thereby improving the accuracy of the meteorological data prediction results.

[0099] In an optional embodiment, the weather data forecast result at the target geographical location in the second time period is obtained based on the forecast weights of at least two weather sources. Figure 3As shown above Figure 2 Step 240 in the illustrated embodiment may also be implemented as steps 440 to 450 as follows.

[0100] Step 410: Obtain meteorological measurement data for a target geographical location in a first time period, and forecast meteorological data for the target geographical location in the first time period from at least two meteorological sources.

[0101] Among them, the kth meteorological source is used to predict and obtain the kth group of predicted meteorological data, and k is a positive integer.

[0102] The description of obtaining the meteorological measurement data for the target geographical location in the first time period and the predicted meteorological data for the target geographical location in the first time period from at least two meteorological sources in step 410 has been described in detail in the above step 210 and will not be repeated here.

[0103] Step 420: Determine prediction weights of the at least two meteorological sources corresponding to the second time period based on the meteorological measurement data and the predicted meteorological data of the at least two meteorological sources.

[0104] The first time period is before the second time period.

[0105] The description of determining the prediction weight in step 420 has been described in detail in the above step 220 and will not be repeated here.

[0106] Step 430: Obtain forecasted meteorological data for a second time period from at least two meteorological sources.

[0107] The description of obtaining the forecasted meteorological data for the second time period in step 430 has been described in detail in the above step 230 and will not be repeated here.

[0108] Step 440 , based on the prediction weights of at least two meteorological sources and at least two meteorological sources, weighted calculation is performed on the predicted meteorological data for the second time period to obtain a candidate prediction result for the second time period at the target geographic location.

[0109] Schematically, after obtaining the prediction weights of at least two meteorological sources, the deviation between the meteorological measurement data and the meteorological prediction data of different meteorological sources in a certain time period can be determined. Optionally, the meteorological prediction results corresponding to different meteorological sources in the second time period and the prediction weights of the meteorological sources in the second time period are weighted, and schematically, the weighted calculation includes at least one of the following calculation methods.

[0110] 1. Weighted average operation.

[0111] Indicatively, a weighted average operation is performed on the predicted meteorological data of the second time period. For example, taking the second time period as an example, there are two meteorological sources participating in the prediction of meteorological results, namely meteorological source i and meteorological source j. First, the predicted meteorological data corresponding to meteorological source i and the predicted meteorological data corresponding to meteorological source j are determined, and the prediction weight corresponding to meteorological source i and the prediction weight corresponding to meteorological source j are determined. After that, the predicted meteorological data corresponding to meteorological source i is multiplied by the prediction weight corresponding to meteorological source i, and then the product of the predicted meteorological data corresponding to meteorological source j and the prediction weight corresponding to meteorological source j is added to obtain the total weight value, and the total weight value is averaged, that is, the total weight value is divided by 2 (two meteorological sources) to realize the weighted average operation process.

[0112] 2. Weighted sum operation.

[0113] Indicatively, a weighted average operation is performed on the predicted meteorological data of the second time period. For example, taking the second time period as an example, there are two meteorological sources participating in the prediction of meteorological results, namely meteorological source i and meteorological source j. First, the predicted meteorological data corresponding to meteorological source i and the predicted meteorological data corresponding to meteorological source j are determined, and the prediction weight corresponding to meteorological source i and the prediction weight corresponding to meteorological source j are determined. After that, the predicted meteorological data corresponding to meteorological source i is multiplied by the prediction weight corresponding to meteorological source i, and then the product of the predicted meteorological data corresponding to meteorological source j and the prediction weight corresponding to meteorological source j is added to realize the weighted sum operation process.

[0114] The above are merely illustrative examples, and the embodiments of the present application are not limited thereto.

[0115] After performing the above-mentioned weighted operation on the predicted meteorological data of the second time period, a candidate prediction result of the second time period at the target geographical location is obtained, and the candidate prediction result is used to obtain the meteorological data prediction result.

[0116] Step 450, standardize the candidate prediction results to obtain the meteorological data prediction results for the second time period after removing noise.

[0117] Optionally, the candidate prediction results contain noise, for example, in the process of weighted calculation of the predicted meteorological data, the noise generated in the process of predicting the meteorological data is also weighted. In order to eliminate the interference of noise, the candidate meteorological data is standardized.

[0118] In schematic form, taking meteorological source i as an example, the meteorological forecast data results of meteorological source i in any time period are as follows:

[0119]

[0120] Among them, y is the meteorological measurement value; is the meteorological forecast value of meteorological source i; μ i is the data error parameter of meteorological source i; e i is the white noise of the meteorological source.

[0121] After adding the numerical predictions of meteorological source i in multiple time periods, the overall meteorological forecast data results are as follows:

[0122]

[0123] Where y is the meteorological measurement value; β i is the weight parameter; is the meteorological forecast value of meteorological source i; μ i is the data error parameter of meteorological source i; e i is the white noise of the meteorological source.

[0124] Indicatively, the normalization operation is an operation to remove white noise. For example, the normalization operation is to make E(e i )=0. After the above-mentioned overall weather forecast data results are standardized, the weather forecast results with noise removed are obtained, that is, the weather forecast data expression is as follows:

[0125]

[0126] in, is the weather forecast data after removing white noise; β i is the weight parameter; is the meteorological forecast value of meteorological source i; μ i is the data error parameter of meteorological source i.

[0127] Optionally, when performing weather forecasts for multiple weather sources, the above weather forecast data expression is subjected to matrix transformation, and the obtained weather forecast data is as follows:

[0128]

[0129] in, is the meteorological forecast data after removing white noise; β is the weight parameter corresponding to the meteorological source; is the meteorological forecast value of the meteorological source; μ is the data error parameter corresponding to the meteorological source.

[0130] In an optional embodiment, based on the above-mentioned meteorological data prediction method, a meteorological data prediction model is obtained by using the recursive least square method, and after the meteorological measurement data and meteorological prediction data of a certain period of time are input into the above-mentioned meteorological data prediction model, the meteorological data prediction result can be obtained. For example: nearly a week of meteorological measurement data and meteorological prediction data corresponding to three meteorological sources are input into the meteorological data prediction model, and the meteorological data for the next day are predicted to obtain the meteorological data prediction result.

[0131] In summary, according to the meteorological measurement data and the predicted meteorological data of each of the multiple meteorological sources, the prediction weights of the second time period corresponding to the multiple meteorological sources are determined, and according to the predicted meteorological data of the second time period by the multiple meteorological sources and the prediction weights of the multiple meteorological sources, the meteorological data prediction result of the second time period at the target geographical location is obtained. Through the above method, the deviation of each meteorological source can be reduced, and a more accurate meteorological data prediction result can be obtained.

[0132] In an embodiment of the present application, the process of obtaining the meteorological data prediction result is described. Based on the prediction weights of multiple meteorological sources, a weighted operation is performed on the predicted meteorological data of the time period to be predicted to obtain a candidate prediction result of the time period to be predicted, and then the candidate prediction result is subjected to a standardization operation to remove noise to obtain the meteorological data prediction result of the time period to be predicted. Through the above method, the prediction result obtained after the weighted operation can be denoised, so that the meteorological data prediction result eliminates the interference of noise, thereby improving the accuracy of the meteorological data prediction result.

[0133] In an optional embodiment, the meteorological data prediction method is applied to wind speed prediction, such as Figure 5 As shown, the method includes the following steps 510 to 540.

[0134] Step 510: Obtain wind speed measurement data for a target geographical location in a first time period, and predicted wind speed data for the target geographical location in the first time period from at least two meteorological sources.

[0135] Wind speed refers to the speed of air movement relative to a fixed location on the earth, and the common unit is m / s. Wind speed measurement data refers to wind speed data measured by wind speed detection equipment and other means that can reflect wind speed conditions.

[0136] Optionally, wind speed data is a type of meteorological data, so wind speed data can be obtained through a method for obtaining meteorological data. For example: obtain through websites such as the China Standard Wind Speed ​​Data Website and the FAO Geographic Website; or obtain through meteorological newspapers, books, etc. The above are only illustrative examples, and the embodiments of the present application are not limited to this. The predicted wind speed data is based on the evolution law of past wind speeds, and infers the possible trend of wind speed development in a certain period in the future.

[0137] The target geographical location is the geographical location corresponding to the obtained wind speed measurement data. Optionally, the wind speed measurement data is wind speed data obtained from a website. If the wind speed measurement data to be obtained is wind speed measurement data of location B, location B is the target geographical location; or, when the wind speed measurement data is wind speed data obtained by a wind speed measuring instrument (e.g., anemometer, fan, etc.), the geographical location where the wind speed measuring instrument is located is regarded as the target geographical location.

[0138] Schematically, the first time period is a time period before the current moment, and the wind speed measurement data is the real wind speed data obtained. Optionally, at least two meteorological sources are first determined as sources of predicted wind speed data, and then the predicted wind speed data of at least two meteorological sources in the first time period are obtained, so as to obtain the predicted wind speed data corresponding to at least two meteorological sources in the first time period. Among them, the kth meteorological source is used to predict the kth group of predicted wind speed data, and k is a positive integer.

[0139] Step 520: Determine prediction weights of the at least two meteorological sources corresponding to the second time period based on the wind speed measurement data and the predicted wind speed data of the at least two meteorological sources.

[0140] The process of performing wind speed prediction in the first time period before the second time period is a process of predicting the predicted wind speed data of the second time period based on the wind speed measurement data and predicted wind speed data of the first time period.

[0141] Schematically, different meteorological sources correspond to different wind speed forecast data, and there are wind speed forecast differences between different meteorological sources. The wind speed forecast difference is used to indicate the difference between the wind speed measurement data and the forecast wind speed data, and the wind speed forecast difference can be distinguished by the deviation. When the deviation between the wind speed measurement data and the forecast wind speed data is small, it means that the wind speed forecast effect of the meteorological source is better; when the deviation between the wind speed measurement data and the forecast wind speed data is large, it means that the wind speed forecast effect of the meteorological source is poor.

[0142] Optionally, different meteorological sources correspond to different wind speed prediction deviations, and the wind speed prediction errors can be distinguished by the weights corresponding to the meteorological sources. When determining the weights corresponding to the meteorological sources, the weight ratios corresponding to different time periods will change in real time, so the weights corresponding to different meteorological sources will be continuously updated during the prediction process.

[0143] After obtaining wind speed measurement data and predicted wind speed data of at least two meteorological sources, the wind speed measurement data is compared with the predicted wind speed data corresponding to the at least two meteorological sources respectively, so as to determine the prediction weights of the at least two meteorological sources respectively corresponding to the second time period.

[0144] Step 530, obtaining predicted wind speed data for a second time period from at least two meteorological sources.

[0145] Optionally, different meteorological sources correspond to different prediction algorithms, and different wind speed prediction results may be obtained. When predicting the wind speed in the second time period in combination with the wind speed prediction results of the meteorological sources, the predicted wind speed data for the second time period from different meteorological sources are first obtained.

[0146] Step 540, based on the prediction weights of at least two meteorological sources, determine the weighted calculation results of the predicted wind speed data of the at least two meteorological sources for the second time period, and obtain the wind speed data prediction result at the target geographical location for the second time period.

[0147] In an illustrative manner, the predicted wind speed results of at least two meteorological sources for the second time period and the prediction weights of at least two meteorological sources corresponding to the second time period are weighted, that is, according to the prediction weights, the predicted wind speed data of at least two meteorological sources for the second time period are weighted to obtain a weighted calculation result. Then, based on the weighted calculation result, the wind speed data prediction result corresponding to the target geographical location in the second time period is obtained.

[0148] In summary, after obtaining the wind speed measurement data for the target geographical location in the first time period and the predicted wind speed data for the first time period from multiple meteorological sources, the prediction weights for the second time period corresponding to the multiple meteorological sources are determined based on the wind speed measurement data and the predicted wind speed data of each of the multiple meteorological sources. Then, based on the predicted wind speed data for the second time period from multiple meteorological sources and the prediction weights of the multiple meteorological sources, the wind speed data prediction result for the target geographical location in the second time period is obtained. Through the above method, the advantages of multiple meteorological sources can be combined to reduce the deviation of each meteorological source. The prediction characteristics in the wind speed data prediction process can also be adjusted in real time according to time changes to obtain a more accurate wind speed data prediction result.

[0149] Figure 6 is a structural block diagram of a meteorological data prediction device provided by an exemplary embodiment of the present application, such as Figure 6 As shown, the device includes the following parts:

[0150] A first acquisition module 610 is used to acquire meteorological measurement data for a target geographical location in a first time period, and predicted meteorological data for the target geographical location in the first time period from at least two meteorological sources, wherein a k-th meteorological source is used to predict and obtain a k-th group of predicted meteorological data, where k is a positive integer;

[0151] A first determination module 620, configured to determine prediction weights of the at least two meteorological sources corresponding to a second time period respectively based on the meteorological measurement data and the predicted meteorological data of the at least two meteorological sources, the first time period being before the second time period;

[0152] A second acquisition module 630 is used to acquire the forecasted meteorological data for the second time period from at least two meteorological sources;

[0153] The second determination module 640 is used to determine the weighted operation result of the at least two meteorological sources on the predicted meteorological data of the second time period based on the prediction weights of the at least two meteorological sources, and obtain the meteorological data prediction result of the second time period at the target geographical location.

[0154] In an optional embodiment, the first determination module 620 is used to determine the data error parameters of at least two meteorological sources for the second time period based on the meteorological measurement data and the predicted meteorological data of the at least two meteorological sources; based on the meteorological measurement data, the predicted meteorological data of the at least two meteorological sources and the data error parameters, determine the prediction weights of the at least two meteorological sources corresponding to the second time period respectively.

[0155] In an optional embodiment, the first determination module 620 is also used to determine the difference between the meteorological measurement data and the predicted meteorological data of the at least two meteorological sources as the meteorological error of the at least two meteorological sources in the first time period; determine the historical data error parameters used in the meteorological data prediction process of the first time period; and determine the data error parameters of the second time period based on the meteorological error of the first time period and the historical data error parameters.

[0156] In an optional embodiment, the first determination module 620 is also used to adjust the meteorological error of the first time period and the historical data error parameter based on an error adjustment factor to obtain an adjustment result, wherein the error adjustment factor is a pre-set value; based on the adjustment result, determine the data error parameter of the second time period.

[0157] In an optional embodiment, the first determination module 620 is also used to determine the covariance relationship of the at least two meteorological sources in the second time period based on the meteorological errors of the at least two meteorological sources in the first time period; based on the data error parameters, the covariance relationship and the error adjustment factor, determine the prediction weights of the at least two meteorological sources corresponding to the second time period respectively.

[0158] In an optional embodiment, the second determination module 640 is also used to perform a weighted operation on the predicted meteorological data of the second time period based on the prediction weights of the at least two meteorological sources and the at least two meteorological sources to obtain a candidate prediction result for the second time period at the target geographic location; and perform a standardization operation on the candidate prediction results to obtain a prediction result of the meteorological data for the second time period after removing noise.

[0159] It should be noted that the meteorological data prediction device provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the meteorological data prediction device provided in the above embodiment and the meteorological data prediction method embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0160] Figure 7 The schematic diagram of the structure of a server provided by an exemplary embodiment of the present application is shown. The server 700 includes a central processing unit (CPU) 701, a system memory 704 including a random access memory (RAM) 702 and a read-only memory (ROM) 703, and a system bus 705 connecting the system memory 704 and the central processing unit 701. The server 700 also includes a mass storage device 706 for storing an operating system 713, an application program 714, and other program modules 715.

[0161] The mass storage device 706 is connected to the central processing unit 701 through a mass storage controller (not shown) connected to the system bus 705. The mass storage device 706 and its associated computer readable media provide non-volatile storage for the server 700. That is, the mass storage device 706 may include a computer readable medium (not shown) such as a hard disk or a compact disc read only memory (CD-ROM) drive.

[0162] Without loss of generality, computer-readable media may include computer storage media and communication media. Computer storage media include volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information such as computer-readable instructions, data structures, program modules or other data. Computer storage media include RAM, ROM, Erasable Programmable Read Only Memory (EPROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other solid-state storage technology, CD-ROM, Digital Versatile Disc (DVD) or other optical storage, cassettes, tapes, disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that computer storage media are not limited to the above. The above-mentioned system memory 704 and mass storage device 706 can be collectively referred to as memory.

[0163] According to various embodiments of the present application, the server 700 can also be connected to a remote computer on the network through a network such as the Internet. That is, the server 700 can be connected to the network 712 through the network interface unit 711 connected to the system bus 705, or the network interface unit 711 can be used to connect to other types of networks or remote computer systems (not shown).

[0164] The above-mentioned memory also includes one or more programs, and the one or more programs are stored in the memory and configured to be executed by the CPU.

[0165] An embodiment of the present application also provides a computer device, which includes a processor and a memory, in which at least one instruction, at least one program, a code set or an instruction set is stored, and the at least one instruction, at least one program, a code set or an instruction set is loaded and executed by the processor to implement the meteorological data prediction method provided by the above-mentioned method embodiments.

[0166] An embodiment of the present application also provides a computer-readable storage medium, on which is stored at least one instruction, at least one program, code set or instruction set, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by a processor to implement the meteorological data prediction method provided by the above-mentioned method embodiments.

[0167] The embodiments of the present application also provide a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the meteorological data prediction method described in any of the above embodiments.

[0168] Optionally, the computer readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a solid state drive (SSD), or an optical disk. Among them, the random access memory may include a resistance random access memory (ReRAM) and a dynamic random access memory (DRAM). The serial numbers of the above embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments.

[0169] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0170] The above description is only an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A meteorological data prediction method, characterized in that: The method comprises: Acquire meteorological measurement data for a target geographical location in a first time period, and predicted meteorological data for the target geographical location in the first time period from at least two meteorological sources, wherein a kth meteorological source is used to predict and obtain a kth group of predicted meteorological data, where k is a positive integer; Determine a difference between the meteorological measurement data and the predicted meteorological data corresponding to the at least two meteorological sources respectively as a meteorological error of the at least two meteorological sources in the first time period; Determining historical data error parameters respectively used by the at least two meteorological sources in the meteorological data forecasting process of the first time period; Based on the error adjustment factor, the meteorological error and the historical data error parameter are adjusted to obtain an adjustment result, wherein the error adjustment factor is a preset value and the error adjustment factor is used to determine an adjustment weight for adjusting the meteorological error and the historical data error parameter; Determining data error parameters of the at least two meteorological sources for a second time period based on adjustment results respectively corresponding to the at least two meteorological sources, the first time period being before the second time period; Determine the prediction weights of the second time period respectively corresponding to the at least two meteorological sources based on the meteorological measurement data, the predicted meteorological data respectively corresponding to the at least two meteorological sources, and the data error parameters of the at least two meteorological sources for the second time period; Obtaining forecasted meteorological data for the second time period from at least two meteorological sources; Based on the prediction weights of the at least two meteorological sources, a weighted calculation result of the at least two meteorological sources on the predicted meteorological data for the second time period is determined to obtain a prediction result of the meteorological data for the second time period at the target geographical location.

2. The method according to claim 1, characterized in that The determining, based on the meteorological measurement data, the predicted meteorological data respectively corresponding to the at least two meteorological sources, and the data error parameters of the at least two meteorological sources for the second time period, the prediction weights of the second time period respectively corresponding to the at least two meteorological sources include: Determining a covariance relationship between the at least two meteorological sources in the second time period based on meteorological errors of the at least two meteorological sources in the first time period; Based on the data error parameter, the covariance relationship and the error adjustment factor, prediction weights of the second time periods respectively corresponding to the at least two meteorological sources are determined.

3. The method according to claim 1 or 2, characterized in that: The step of determining a weighted calculation result of the at least two meteorological sources on the predicted meteorological data for the second time period based on the prediction weights of the at least two meteorological sources, and obtaining a meteorological data prediction result for the second time period at the target geographical location, includes: Based on the prediction weights respectively corresponding to the at least two meteorological sources and the at least two meteorological sources, weighted calculation is performed on the predicted meteorological data of the at least two meteorological sources in the second time period to obtain a candidate prediction result for the second time period at the target geographical location; The candidate prediction results are standardized to obtain the meteorological data prediction results for the second time period at the target geographic location after noise is removed.

4. A meteorological data prediction device, characterized in that: The device comprises: A first acquisition module is used to acquire meteorological measurement data for a target geographical location in a first time period, and predicted meteorological data for the target geographical location in the first time period from at least two meteorological sources, wherein a k-th meteorological source is used to predict and obtain a k-th group of predicted meteorological data, where k is a positive integer; A first determination module is used to determine the difference between the meteorological measurement data and the predicted meteorological data corresponding to the at least two meteorological sources as the meteorological error of the at least two meteorological sources in the first time period; determine the historical data error parameters used by the at least two meteorological sources in the meteorological data prediction process of the first time period; adjust the meteorological error and the historical data error parameter based on the error adjustment factor to obtain an adjustment result, the error adjustment factor is a preset value, and the error adjustment factor is used to determine the adjustment weight of the meteorological error and the historical data error parameter; based on the adjustment results corresponding to the at least two meteorological sources, determine the data error parameters of the at least two meteorological sources for a second time period, the first time period is before the second time period; based on the meteorological measurement data, the predicted meteorological data corresponding to the at least two meteorological sources, and the data error parameters of the at least two meteorological sources for the second time period, determine the prediction weight of the second time period corresponding to the at least two meteorological sources; A second acquisition module is used to obtain the forecast meteorological data for the second time period from at least two meteorological sources; The second determination module is used to determine the weighted calculation result of the at least two meteorological sources on the predicted meteorological data of the second time period based on the prediction weights of the at least two meteorological sources, and obtain the meteorological data prediction result of the second time period at the target geographical location.

5. A computer device, characterized in that: The computer device includes a processor and a memory, wherein the memory stores at least one program, and the at least one program is loaded and executed by the processor to implement the meteorological data prediction method as described in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that: The storage medium stores at least one program, and the at least one program is loaded and executed by the processor to implement the meteorological data prediction method according to any one of claims 1 to 3.

7. A computer program product, characterized in that It comprises a computer program, which, when executed by a processor, implements the meteorological data forecasting method as claimed in any one of claims 1 to 3.

Images