Meteorological prediction method and system, intelligent terminal and storage medium

Abstract

The invention relates to a meteorological prediction method and system, an intelligent terminal and a storage medium. The method comprises the following steps: acquiring to-be-predicted meteorological data and prediction task demand information; determining a trained target prediction model from a plurality of preset different types of trained meteorological prediction models according to the prediction task demand information; and according to the to-be-predicted meteorological data, carrying out meteorological prediction through the target prediction model to obtain a meteorological prediction result. Based on the scheme of the invention, the used weather prediction model can be flexibly determined according to actual demands, and the accuracy of weather prediction can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular, to a weather prediction method and system, an intelligent terminal and a storage medium. BACKGROUND

[0002] With the progress of science and technology, the application of weather prediction is becoming more and more extensive, and the requirements of users for weather prediction are also becoming higher and higher.

[0003] Traditional weather prediction relies on a large number of manual operations. Specifically, in the prior art, when performing weather prediction, a user needs to manually select a corresponding weather prediction model, and in the weather prediction process, the pre-manually selected weather prediction model is fixedly used. The problem of the prior art is that the pre-manually selected weather prediction model is fixedly used, which is not flexible and is not conducive to improving the accuracy of weather prediction.

[0004] Therefore, the prior art needs to be improved. SUMMARY

[0005] The present application provides a weather prediction method and system, an intelligent terminal and a storage medium to solve the technical problem that in the prior art, when performing weather prediction, a pre-manually selected weather prediction model is fixedly used, which is not flexible and is not conducive to improving the accuracy of weather prediction.

[0006] In a first aspect, the present application provides a weather prediction method, comprising: obtaining to-be-predicted weather data and prediction task requirement information; determining a trained target prediction model from a plurality of different types of trained weather prediction models pre-set according to the prediction task requirement information; performing weather prediction according to the to-be-predicted weather data through the target prediction model to obtain a weather prediction result.

[0007] Optionally, before the determining a trained target prediction model from a plurality of different types of trained weather prediction models pre-set according to the prediction task requirement information, the method further comprises: obtaining historical weather data; training each type of initial weather prediction model pre-set according to the historical weather data to obtain a plurality of different types of trained weather prediction models, wherein the each type of initial weather prediction model comprises a statistical model, a machine learning model and a deep learning model.

[0008] Optionally, the obtaining historical weather data comprises: In response to a data collection trigger signal, instant data is captured from a plurality of preset meteorological data sources, and the obtained meteorological data is taken as historical meteorological data; The data collection trigger signal is generated according to a preset time interval, and / or the data collection trigger signal is generated when a preset meteorological event occurs.

[0009] Optionally, the historical meteorological data is used to train each type of initial meteorological prediction model to obtain a plurality of trained meteorological prediction models of different types, including: The historical meteorological data is preprocessed according to a preset data preprocessing operation to update the historical meteorological data, wherein the data preprocessing operation includes at least one of data cleaning, missing value processing, data unit conversion, timestamp standardization, data value range adjustment, feature scaling, outlier processing, data feature extraction, data feature combination, multi-source data fusion, and time series construction. The historical meteorological data is preprocessed according to a preset data preprocessing operation to update the historical meteorological data, wherein the data preprocessing operation includes at least one of data cleaning, missing value processing, data unit conversion, timestamp standardization, data value range adjustment, feature scaling, outlier processing, data feature extraction, data feature combination, multi-source data fusion, and time series construction.

[0010] Optionally, after the meteorological prediction result is obtained by the target prediction model according to the to-be-predicted meteorological data, the method further includes: The meteorological prediction result is logically detected according to a preset logical rule. If the logical detection of the meteorological prediction result passes, the meteorological prediction result is verified for rationality according to a preset historical meteorological result, and a verification result is output.

[0011] Optionally, after the meteorological prediction result is obtained by the target prediction model according to the to-be-predicted meteorological data, the method further includes: A meteorological prediction report is generated according to a preset report template and the meteorological prediction result, wherein the meteorological prediction report includes a preset key meteorological index and a visual chart. The meteorological prediction report is published to a target object according to a preset report publishing rule and a report publishing platform.

[0012] Optionally, after the meteorological prediction report is published to the target object according to the preset report publishing rule and the report publishing platform, the method further includes: Feedback data of the target object for the meteorological prediction report is obtained. The target prediction model and / or the report template are updated according to the feedback data.

[0013] In a second aspect, the present application provides a weather prediction system, the system comprising: a data acquisition module configured to acquire weather data to be predicted and prediction task requirement information; a model determination module configured to determine a trained target prediction model from a plurality of different types of trained weather prediction models pre-set according to the prediction task requirement information; a weather prediction module configured to perform weather prediction according to the weather data to be predicted by using the target prediction model to obtain a weather prediction result.

[0014] In a third aspect, the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method as described above when executing the computer program.

[0015] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, wherein the computer program is executable by a processor to implement the method as described above.

[0016] The above technical solution provided by the present application has the following advantages compared with the prior art: in the present application, the weather data to be predicted and the prediction task requirement information are acquired; a trained target prediction model is determined from a plurality of different types of trained weather prediction models pre-set according to the prediction task requirement information; and weather prediction is performed according to the weather data to be predicted by using the target prediction model to obtain a weather prediction result. In this way, in the weather prediction process, the target prediction model required can be automatically determined from a plurality of different types of trained weather prediction models according to the prediction task requirement information, rather than using a pre-set weather prediction model fixedly. Therefore, based on the present application, the weather prediction model used can be determined flexibly according to actual requirements, which is beneficial to improving the accuracy of weather prediction. BRIEF DESCRIPTION OF DRAWINGS The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and serve to explain the principles of the present application together with the specification.

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows, and obviously, other drawings can also be obtained by those skilled in the art without any creative labor based on these drawings.

[0018] One or more embodiments are illustrated by way of example in the drawings and are described herein in connection with these examples. These embodiments are not intended to limit the scope of the embodiments to these examples alone, but rather, these embodiments are intended to cover all possible modifications and equivalents falling within the scope of the embodiments. The drawings are not necessarily to scale, the emphasis instead being placed upon illustrating the principles of the embodiments.

[0019] Figure 1 A flowchart of a weather prediction method provided by an embodiment of the present application; Figure 2 A specific data processing flowchart of a weather prediction automation system based on RPA provided by an embodiment of the present application; Figure 3 A structural diagram of a weather prediction system provided by an embodiment of the present application; Figure 4 A structural diagram of a computer readable storage medium provided by an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0021] In the following description, specific details are set forth in order to provide a thorough understanding of the embodiments of the present application. However, persons of ordinary skill in the art will readily recognize that the embodiments of the present application can be practiced without these specific details. In other instances, well-known structures and functions have not been described in detail in order to avoid obscuring the embodiments of the present application.

[0022] It should be understood that the term "comprising" as used in the specification and in the claims indicates the presence of the recited features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0023] It should also be understood that the terms used in the present specification and the like are merely used to describe particular embodiments and are not intended to limit the present application. As used in the present specification and the like, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

[0024] It should also be further understood that the term "and / or" as used herein, in the specification and in the claims, means any combination of one or more of the associated listed items can be present, and includes all possible combinations.

[0025] As used in the description and the appended claims, the term "if' can be interpreted as meaning "when" or "once" or "in response to determining" or "in response to classifying." Similarly, the phrase "if determined" or "if classified [a described condition or event]" can be interpreted as meaning "once determined" or "in response to determining" or "once classified [a described condition or event]" or "in response to classifying [a described condition or event]," depending on the context.

[0026] The disclosure that follows provides many different embodiments, or examples, for implementing different structures of the application. For the purpose of simplicity and clarity, the elements of the specific examples are described in the following detailed description with reference made to the accompanying drawings. It is to be understood that the same or equivalent elements have been identified with the same or similar reference numerals. It is to be further understood that the description and drawings are not to be used in interpreting the scope of the application.

[0027] Traditional weather prediction relies on a large number of manual operations. For example, data collection, preprocessing and model analysis, which is not only time-consuming but also prone to errors. Specifically, when making weather prediction, the prior art fixedly uses a weather prediction model manually selected in advance, which has low flexibility and is not conducive to improving the accuracy of weather prediction. With the increase of data volume and the improvement of prediction demand, the traditional method has been difficult to meet the demand of modern weather prediction. Therefore, a technology capable of automatically processing complex data and quickly generating prediction results is needed.

[0028] Figure 1 A weather prediction method provided by an embodiment of the present application, the method comprises: S100, obtaining weather data to be predicted and prediction task demand information.

[0029] The weather data to be predicted is current data collected when weather prediction is needed, and the weather data to be predicted can be collected according to actual needs, and can specifically include data collected by at least one of a ground weather station, a satellite, a weather radar and other related weather observation equipment. In an application scenario, the weather data to be predicted can include one or more of temperature, humidity, air pressure, precipitation, precipitation type, precipitation intensity, wind speed, wind direction and visibility, which is not limited here.

[0030] The prediction task requirement information is information for characterizing a weather prediction task. In some application scenarios, the prediction task requirement information can be indication information in the form of natural language input by a user. In other application scenarios, the prediction task requirement information can be identification information (for example, a numerical identifier) for indicating a prediction task requirement, which is not limited herein.

[0031] S200. Determine, according to the prediction task requirement information, a trained target prediction model from among a plurality of different types of trained weather prediction models.

[0032] Specifically, in the embodiments of the present application, a plurality of trained target prediction models of different types are preconfigured and can be used to perform different prediction tasks.

[0033] In some application scenarios, a table for storing the association between prediction task requirement information and different trained weather prediction models can be preconfigured, and the corresponding target prediction model is determined by table lookup. In other application scenarios, a preconfigured large language model can be used to analyze the prediction task requirement information to match and determine the corresponding target prediction model, which is not limited herein.

[0034] Specifically, before determining, according to the prediction task requirement information, a trained target prediction model from among a plurality of different types of trained weather prediction models, the method further includes: obtaining historical weather data; training each type of initial weather prediction model according to the historical weather data to obtain a plurality of different types of trained weather prediction models, wherein the each type of initial weather prediction model includes a statistical model, a machine learning model, and a deep learning model.

[0035] In the embodiments of the present application, the obtaining of the historical weather data includes: in response to a data collection trigger signal, performing real-time data grabbing from a plurality of preconfigured weather data sources, and obtaining weather data as historical weather data; wherein the data collection trigger signal is generated according to a preconfigured time interval, and / or the data collection trigger signal is generated when a preconfigured weather event occurs.

[0036] It should be noted that the weather prediction method provided in the embodiments of the present application can be applied to a weather prediction automation system implemented by using a robot process automation (RPA) technology. The system significantly improves the efficiency and accuracy of weather prediction through automated data collection, processing, model calibration and prediction publishing processes, and can be applied to scenarios that require rapid response and processing of a large amount of weather data, such as weather warning, disaster response, etc. In the embodiments of the present application, the weather prediction method is applied to the weather prediction automation system as an example, but not as a specific.

[0037] Figure 2 is a specific data processing flow diagram of a weather prediction automation system based on RPA provided by the embodiments of the present application, as shown in Figure 2 The weather prediction automation system based on RPA mainly performs the following steps: data source access, data extraction and preprocessing (including data collection and data preprocessing), model selection and model calibration, prediction calculation and verification, report generation and publishing, and system monitoring and maintenance.

[0038] Specifically, the historical weather data can be collected by the data collection module to efficiently and accurately collect necessary weather data from multiple data sources. The data collection module identifies and accesses the data source. Specifically, the data source can be automatically identified, and the RPA system is configured to access multiple preset weather data sources, including ground weather stations, satellites, weather radars and other related weather observation equipment. Application programming interface (API) is used to establish a stable data transmission channel with these data sources to ensure the real-time and integrity of the data.

[0039] Further, the weather prediction automation system based on RPA can also realize automatic data extraction. Specifically, a timing task can be set to automatically extract the latest weather data from each data source at a predetermined time interval (for example, every 10 minutes). When a specific weather event occurs (such as typhoon, heavy rain, etc.), instant data extraction can be triggered to obtain real-time data of related weather changes.

[0040] Further, the historical weather data is used to train each type of initial weather prediction model to obtain a plurality of trained weather prediction models of different types, including: According to the preset data preprocessing operation, the historical meteorological data is preprocessed to update the historical meteorological data, wherein the data preprocessing operation includes at least one of data cleaning, missing value processing, data unit conversion, timestamp standardization, data value range adjustment, feature scaling, outlier processing, data feature extraction, data feature combination, multi-source data fusion and time series construction. According to the updated historical meteorological data, each type of initial meteorological prediction model is trained to obtain a plurality of different types of trained meteorological prediction models.

[0041] Specifically, the original meteorological data obtained from the data collection module can be converted into a format suitable for model analysis by the data preprocessing module of the RPA-based meteorological prediction automation system. Specifically, the data preprocessing module can perform one or more of the following multiple data preprocessing operations.

[0042] Data cleaning: remove invalid data, automatically identify and remove damaged, incomplete or obviously incorrect data records, such as data points with abnormally high or low temperature values.

[0043] Missing value processing: fill in missing data points using interpolation or other statistical methods, such as linear interpolation using previous and subsequent data of the time series or using historical average values at the same time point.

[0044] Data unit conversion: unify units, convert all data to the required unified measurement units for system analysis, such as converting temperature from Fahrenheit to Celsius and wind speed from miles / hour to meters / second.

[0045] Timestamp standardization: unify time format, ensure that all data records are within the same time frame, facilitating time series analysis.

[0046] Data value range adjustment: normalize data, such as through maximum and minimum normalization or Z-score standardization method, to make data values fall within a specific range, improving model processing stability and efficiency.

[0047] Feature scaling: scale data of different magnitudes to ensure balanced weights of each feature in the model.

[0048] Outlier processing: specifically, statistical analysis can be performed to identify and process outliers using statistical methods (such as box plot analysis) to ensure normal distribution of data and avoid the influence of extreme values on model training. Rule-based screening can also be performed to automatically identify and process data points outside the normal range based on professional knowledge of meteorology and historical data thresholds.

[0049] Data Feature Extraction: Extract useful temporal features from timestamps, such as hour, day, month, season, etc., which may have significant impact on weather prediction.

[0050] Data Feature Combination: Combine different data fields to generate new features based on meteorological principles, such as "wet-bulb temperature" which can be calculated from temperature and humidity.

[0051] Multi-source Data Fusion: Integrate weather data from different sources and types into a unified dataset, providing comprehensive input for the model.

[0052] Time Series Construction: Construct continuous time series data to support the needs of time series analysis and prediction models.

[0053] Further, after the above data preprocessing, the data is stored and transported. Specifically, when performing intermediate storage, the preprocessed data is temporarily stored in an efficient data storage system to ensure fast data reading and high concurrent processing capability. When needed, perform secure data transmission, securely and efficiently transmit the processed data to the model calibration module, use encryption and compression techniques to ensure the security and efficiency of data transmission.

[0054] After obtaining the preprocessed historical weather data, model training (calibration) is performed to optimize and adjust the prediction model to ensure its accuracy and adaptability through the model calibration module.

[0055] Specifically, the system is built-in with multiple weather prediction models (which can be integrated in the model library), including statistical models, machine learning models, and deep learning models, etc. In some application scenarios, appropriate models can be automatically selected for training and calibration according to the specific needs of the prediction task. In other application scenarios, all models can be trained and calibrated, and the required model can be called when used, without specific limitation. During model training, the following steps are performed: Parameter Initialization: Set initial parameters for the selected model, which can be based on historical performance data or pre-set standard configuration.

[0056] Historical Data Loading: Receive processed data from the data preprocessing module, including historical weather data and related feature data, as the basis for model training and calibration.

[0057] Batch Model Training: Use batch historical data to preliminarily train the model to obtain baseline performance.

[0058] Online Model Learning: Implement online learning strategies to allow the model to update and adjust in real time based on the latest data, improving the adaptability and prediction accuracy of the model.

[0059] Performance evaluation: Use cross-validation method to evaluate the stability and generalization ability of the model, ensure that the model can maintain good prediction performance on different datasets. Calculate the error between the model prediction result and the actual observation value, analyze the type and pattern of the error, and provide basis for model adjustment.

[0060] Parameter optimization: When automatic parameter tuning, use algorithms such as grid search, random search or Bayesian optimization to automatically optimize parameters and find the optimal model parameter settings. When feedback adjustment, according to the performance evaluation results, automatically adjust model parameters such as learning rate and regularization coefficient to reduce prediction error and improve model accuracy.

[0061] Model update: In the embodiments of the present application, version control is performed for each model calibration and update, and historical models and parameter settings are retained for easy traceability and comparison. The calibrated model is deployed to the production environment for actual weather prediction tasks.

[0062] Monitoring and maintenance: Real-time monitoring and regular maintenance of the model. Monitor the running state and prediction performance of the model to ensure stable operation. Regularly maintain and reevaluate the model, and make necessary updates and optimizations according to the latest data and technological progress.

[0063] S300, according to the weather data to be predicted, weather prediction is performed through the target prediction model to obtain weather prediction results.

[0064] In the embodiments of the present application, the prediction generation and release module of the RPA-based weather prediction automation system automatically generates weather prediction reports and releases the results to the corresponding platform using RPA process automation.

[0065] Specifically, first, automatic prediction and result generation are performed. The system automatically calls the calibrated weather prediction model and inputs the latest weather data to quickly generate prediction results of future weather conditions.

[0066] Further, after the weather prediction is performed according to the weather data to be predicted through the target prediction model to obtain the weather prediction results, the method further comprises: According to the preset logical rule, the weather prediction result is logically detected; If the logical detection of the weather prediction result passes, the weather prediction result is verified for rationality according to the preset historical weather result, and the verification result is output.

[0067] It should be noted that if the logical detection does not pass and / or the rationality verification does not pass, the verification does not pass is output as the verification result.

[0068] Specifically, RPA automatically performs result verification, including logical checks and historical data comparisons, to ensure the accuracy and reasonableness of the prediction results.

[0069] Further, after the weather prediction result is obtained by the target prediction model according to the weather data to be predicted, the method further includes: According to the preset report template and the weather prediction result, a weather prediction report is generated, wherein the weather prediction report includes preset key weather indicators and visual charts. According to the preset report publishing rules and the report publishing platform, the weather prediction report is published to the target object.

[0070] Specifically, according to the preset report template, RPA automatically formats and generates a prediction report containing key weather indicators and graphical visualization. Further intelligent publishing scheduling, RPA automatically publishes the weather prediction report to multiple platforms such as websites, social media and mobile applications according to the predetermined time and publishing rules, ensuring the wide dissemination and timeliness of information.

[0071] In the embodiments of the present application, after the weather prediction report is published to the target object according to the preset report publishing rules and the report publishing platform, the method further includes: Obtain feedback data of the target object for the weather prediction report; Update the target prediction model and / or the report template according to the feedback data.

[0072] Specifically, the RPA-based weather prediction automation system automatically collects user feedback and usage data, analyzes the prediction effect, adjusts the prediction model and report generation process according to the feedback, realizes continuous system optimization and improves user satisfaction, and further realizes feedback and continuous optimization of weather prediction.

[0073] Further, the RPA-based weather prediction automation system can also set up a monitoring and maintenance module to ensure the continuous and stable operation and performance optimization of the system. Specifically, the monitoring and maintenance module realizes the following functions: Real-time monitoring and anomaly detection: RPA system (i.e. RPA-based weather prediction automation system) continuously monitors the key performance indicators and running status of the entire weather prediction system, automatically detects any abnormal or deviating behavior from normal operation. When potential problems are found, RPA immediately triggers an alarm and automatically performs preliminary fault diagnosis to quickly locate the source of the problem.

[0074] Automated Fault Recovery and Data Backup: RPA automatically handles common system failures, executing preset recovery processes such as service restarts or configuration rollbacks to ensure rapid system recovery and minimize downtime. It also regularly and automatically backs up critical data and system configurations, ensuring rapid system recovery from the most recent backup in the event of a serious failure.

[0075] Performance optimization and system updates: RPA regularly and automatically assesses system performance and prediction accuracy, and automatically adjusts system configuration or model parameters based on the assessment results to optimize system operating efficiency and output quality. It automatically detects and applies system updates and security patches to keep system software and functions up-to-date, improving system security and functionality.

[0076] Maintenance logging and user support: RPA automatically logs all maintenance activities, system changes, and troubleshooting in detail, supporting system auditing and subsequent analysis. It provides automated user support, handling user queries and feedback, while collecting and integrating user feedback information to guide future system improvements and user experience optimization.

[0077] Compared with the prior art, the technical solution provided in this application has the following advantages: In this application, meteorological data to be predicted and prediction task requirements information are obtained; based on the prediction task requirements information, a trained target prediction model is determined from multiple pre-set trained meteorological prediction models of different types; based on the meteorological data to be predicted, meteorological prediction is performed through the target prediction model to obtain the meteorological prediction result. Thus, during the meteorological prediction process, the required target prediction model can be automatically determined from multiple trained meteorological prediction models of different types in real time according to the prediction task requirements information, rather than using a fixed pre-set meteorological prediction model. Therefore, based on the solution of this application, the meteorological prediction model used can be flexibly determined according to actual needs, which is beneficial to improving the accuracy of meteorological prediction.

[0078] like Figure 3 As shown, Figure 3 A schematic diagram of a weather forecasting system provided in this application embodiment includes: Data acquisition module 310 is used to acquire meteorological data to be predicted and forecasting task requirements information; The model determination module 320 is used to determine a trained target prediction model from a plurality of pre-set trained meteorological prediction models of different types based on the prediction task requirement information. The weather forecasting module 330 is used to perform weather forecasting based on the weather data to be forecasted and through the target forecasting model to obtain weather forecasting results.

[0079] Thus, in the present application, the weather data to be predicted and prediction task requirement information are acquired; an already trained target prediction model is determined from a plurality of different types of already trained weather prediction models according to the prediction task requirement information; and weather prediction is performed by the target prediction model according to the weather data to be predicted, to obtain a weather prediction result. Thus, in the weather prediction process, the target prediction model required can be determined from a plurality of different types of already trained weather prediction models according to the prediction task requirement information in real time and automatically, instead of using a pre-set weather prediction model fixedly. Therefore, based on the present application, the weather prediction model used can be determined flexibly according to actual requirements, which is beneficial to improving the accuracy of weather prediction.

[0080] As Figure 4 shown, Figure 4 is a structural schematic diagram of a computer readable storage medium provided by an embodiment of the present application. The computer readable storage medium 700 of the embodiment includes a server 710 (only one is shown in the server 710), a client 720, and a computer program 721 stored in the client 720 and executable on the at least one client 720, wherein the client 720 executes the computer program 721 to send a request to the server 710, and the server 710 feeds back a result, to implement the steps in the above method embodiment. Figure 4

[0081] It should be understood that the serial numbers of the steps in the above embodiments do not mean the execution sequence, and the execution sequence of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0082] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is taken as an example for illustration, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit, and the integrated unit can be realized in the form of hardware or software. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the present application. The specific working process of the units and modules in the above system can refer to the corresponding process in the above method embodiments, which will not be described here.

[0083] ​In the above embodiments, the description of each embodiment is focused on, and the part not described in detail or recorded in a certain embodiment can be referred to the relevant description of other embodiments.

[0084] Those skilled in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present application can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software manner depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0085] In the embodiments provided in the present application, it should be understood that the disclosed apparatus / terminal device and method can be implemented in other ways. For example, the apparatus / terminal device embodiments described above are merely schematic, for example, the division of the modules or units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be through some interface, indirect coupling or communication connection between the devices or units, which can be electrical, mechanical or other forms.

[0086] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software functional unit.

[0087] The integrated module / unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. The computer program can implement the steps of the above-mentioned various method embodiments when executed by a processor. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms. The computer readable medium can include any entity or device, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc. that can carry the computer program code. It should be noted that the contents included in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0088] The above-mentioned embodiment methods can also be completed by a computer program product, which, when running on a terminal device, causes the terminal device to execute the steps in the above-mentioned various method embodiments.

[0089] The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, rather than limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A weather prediction method characterized by, The method comprises: obtaining meteorological data to be predicted and prediction task requirement information; determining a trained target prediction model from a plurality of preset different types of trained meteorological prediction models according to the prediction task requirement information; performing meteorological prediction by the target prediction model according to the meteorological data to be predicted to obtain a meteorological prediction result.

2. The weather prediction method according to claim 1, characterized in that, Before the step of determining a trained target prediction model from a plurality of preset different types of trained meteorological prediction models according to the prediction task requirement information, the method further comprises: obtaining historical meteorological data; training a plurality of different types of trained meteorological prediction models according to the historical meteorological data, wherein the initial meteorological prediction models of each type include statistical models, machine learning models and deep learning models.

3. The weather prediction method of claim 2, wherein, The step of obtaining historical meteorological data comprises: in response to a data collection trigger signal, performing real-time data grabbing from a plurality of preset meteorological data sources, and obtaining meteorological data as historical meteorological data; wherein the data collection trigger signal is generated according to a preset time interval, and / or the data collection trigger signal is generated when a preset meteorological event occurs.

4. The weather prediction method of claim 2, wherein, The step of training a plurality of different types of trained meteorological prediction models according to the historical meteorological data comprises: performing data preprocessing on the historical meteorological data to update the historical meteorological data according to a preset data preprocessing operation, wherein the data preprocessing operation includes at least one of data cleaning, missing value processing, data unit conversion, timestamp standardization, data value range adjustment, feature scaling, outlier processing, data feature extraction, data feature combination, multi-source data fusion and time series construction; training a plurality of different types of trained meteorological prediction models according to the updated historical meteorological data.

5. The weather prediction method of claim 1, wherein, After the step of performing meteorological prediction by the target prediction model according to the meteorological data to be predicted to obtain a meteorological prediction result, the method further comprises: performing logical detection on the meteorological prediction result according to a preset logical rule; if the logical detection of the meteorological prediction result passes, performing rationality verification on the meteorological prediction result according to a preset historical meteorological result, and outputting a verification result.

6. The weather prediction method according to any one of claims 1 to 5, characterized in that, After the step of performing meteorological prediction by the target prediction model according to the meteorological data to be predicted to obtain a meteorological prediction result, the method further comprises: generating a meteorological prediction report according to a preset report template and the meteorological prediction result, wherein the meteorological prediction report includes a preset key meteorological index and a visual chart; publishing the meteorological prediction report to a target object according to a preset report publishing rule and a report publishing platform.

7. The weather prediction method of claim 6, wherein, After the step of publishing the meteorological prediction report to the target object according to the preset report publishing rule and the report publishing platform, the method further comprises: obtaining feedback data of the target object for the meteorological prediction report; updating the target prediction model and / or the report template according to the feedback data.

8. A weather prediction system characterized by, The system comprises: a data acquisition module configured to acquire to-be-predicted meteorological data and prediction task requirement information; a model determination module configured to determine a trained target prediction model from a plurality of different types of trained meteorological prediction models according to the prediction task requirement information; a meteorological prediction module configured to perform meteorological prediction according to the to-be-predicted meteorological data by using the target prediction model to obtain a meteorological prediction result.

9. A terminal, characterized by comprising: The terminal comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program, when executed by the processor, implements the steps of the meteorological prediction method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer program is stored on the computer readable storage medium and, when executed by the processor, implements the steps of the meteorological prediction method according to any one of claims 1 to 7.

Images