Weather forecasting method and device, terminal equipment and readable storage medium

Abstract

The invention provides a weather forecasting method and device, terminal equipment and a readable storage medium, and is suitable for the technical field of data processing, and the method comprises the steps: obtaining historical weather modal information and current weather modal information; generating target historical weather modal information according to the historical weather modal information; according to the current weather modal information and target historical weather modal information, obtaining modal occurrence times and modal forecast times of initial forecast weather modal information; according to the modal occurrence frequency and the modal forecast frequency, calculating modal forecast weights of the multiple pieces of initial forecast weather modal information; and generating target forecast weather modal information according to the current weather modal information and the modal forecast weight, and performing weather forecast according to the target forecast weather modal information. According to the method and the device, the conversion mode weight of the current weather mode is dynamically calculated, so that the problem that the forecasting result is inaccurate due to the fact that the weight of the weather mode is not changed in the prior art is solved.

Description

Technical Field

[0001] The present application belongs to the field of data processing technology, and in particular, relates to a weather forecast method, apparatus, terminal device, and readable storage medium. Background Art

[0002] In weather forecasting, different forecasting skills vary significantly due to different initialization schemes, physical parameterization schemes, data sources, etc. Commonly used methods for evaluating forecasting skills include: the spatial correlation coefficient between the anomalies of the forecast variables (such as temperature and precipitation) of all grid points in the region and the anomalies of the corresponding observed variables, the root mean square error between the anomalies of the forecast variables and the anomalies of the observed variables at all grid points in the region, the regional average of the absolute error between the anomalies of the forecast variables and the anomalies of the observed variables, and scoring indicators such as the omission rate, the false alarm rate, and the false alarm rate.

[0003] In the prior art, the model ensemble forecasting method is usually used for weather forecasting. In order to eliminate the systematic deviation of the model ensemble forecast and make full use of the effective forecast information of different models to improve the forecasting skills, the single model ensemble and multi-model ensemble technology have been rapidly developed in recent years. The single model ensemble is a method of assigning weights to multiple samples in the ensemble forecast of the model. Compared with the single model correction method, the multi-model ensemble technology is essentially a model correction method that assigns weights to different models, which theoretically has a better forecasting effect.

[0004] However, the existing model ensemble forecasting methods all have a common shortcoming: the weight calculation of samples / models only depends on the observation and forecast data during the training period, that is, the weight has been determined before the current forecast begins, and the subsequent forecast effect of the current forecast itself is not considered. Therefore, the weight of the samples / models in the current forecast is given in advance, and the high-skill sample / model forecast information in the current forecast is not given higher attention, thereby reducing the accuracy of weather forecasts. Summary of the invention

[0005] In view of this, the embodiments of the present application provide a weather forecast method, apparatus, terminal device and readable storage medium. By considering historical weather modal forecasts and observations, the weight of the conversion mode of the current weather modal is dynamically calculated, and the weather forecast of the current weather modal is output according to the dynamically calculated weight. This can solve the problem of low accuracy of weather forecast results caused by not considering the weight of the weather modal in the prior art.

[0006] A first aspect of an embodiment of the present application provides a weather forecast method, comprising: Get multiple historical weather modal information and current weather modal information; Classifying and processing the plurality of historical weather modal information to generate target historical weather modal information; According to the current weather modal information and the target historical weather modal information, a matching calculation is performed to obtain a plurality of initial forecast weather modal information matching the current weather modal information; wherein the initial forecast weather modal information includes the modal occurrence times and the modal forecast times of the initial forecast weather modal; Calculating modal forecast weights of multiple initial forecast weather modal information according to the number of times the modal occurs and the number of times the modal is forecasted; According to the multiple current weather modal information and the modal forecast weights, target forecast weather modal information is generated to perform weather forecast according to the target forecast weather modal information.

[0007] A second aspect of an embodiment of the present application provides a weather forecast device, comprising: An information acquisition module is used to obtain multiple historical weather modal information and current weather modal information; A target historical weather modal information module is used to classify and process the plurality of historical weather modal information to generate target historical weather modal information; An initial forecast weather modal information calculation module is used to perform matching calculations based on the current weather modal information and the target historical weather modal information to obtain a plurality of initial forecast weather modal information that matches the current weather modal information; wherein the initial forecast weather modal information includes the modal occurrence times of the initial forecast weather modal and the modal forecast times; A modal forecast weight calculation module, used to calculate the modal forecast weights of multiple initial forecast weather modal information according to the number of times the modal occurs and the number of times the modal is forecasted; The target forecast weather modal information generation module is used to generate target forecast weather modal information according to the multiple current weather modal information and the modal forecast weights, so as to perform weather forecast according to the target forecast weather modal information.

[0008] A third aspect of an embodiment of the present application provides a terminal device, which includes a memory and a processor, wherein the memory stores a computer program that can be executed on the processor, and when the processor executes the computer program, it implements the steps of the weather forecast method as described in any one of the first aspects above.

[0009] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, comprising: a computer program stored therein, wherein when the computer program is executed by a processor, the steps of the weather forecast method as described in any one of the first aspects above are implemented.

[0010] The beneficial effect of the embodiments of the present application compared with the prior art is as follows: the present application classifies and processes historical weather modal information, matches the classified weather modal information with the current weather modal information to confirm the specific meteorological mode corresponding to the current weather modal information and the possible conversion mode, and dynamically calculates the weight of the conversion mode of the current weather mode by considering the forecast and observation conditions of the conversion mode in the historical weather modal information, thereby outputting the weather forecast of the current weather mode according to the dynamically calculated weight, which can solve the problem of low accuracy of weather forecast results caused by fixed weights of weather modalities in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art 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 creative labor.

[0012] Figure 1 It is a schematic diagram of the implementation flow of the weather forecast method provided in the embodiment of the present application; Figure 2 It is a schematic diagram of the implementation flow of the weather forecast method provided in the embodiment of the present application; Figure 3 It is a schematic diagram of the implementation flow of the weather forecast method provided in the embodiment of the present application; Figure 4 It is a schematic diagram of the implementation flow of the weather forecast method provided in the embodiment of the present application; Figure 5 It is a schematic diagram of the implementation flow of the weather forecast method provided in the embodiment of the present application; Figure 6 It is a schematic diagram of the implementation flow of the weather forecast method provided in the embodiment of the present application; Figure 7 It is a schematic diagram of the implementation flow of the weather forecast method provided in the embodiment of the present application; Figure 8 is a structural schematic diagram of a weather forecast device provided in an embodiment of the present application; Fig. 9 It is a schematic diagram of a terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0013] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0014] In order to illustrate the technical solution described in this application, a specific embodiment is provided below for illustration.

[0015] Figure 1 The following is a flowchart of the implementation of the weather forecast method provided in Example 1 of the present application, which is described in detail as follows: Step S101, obtaining multiple historical weather modal information and current weather modal information.

[0016] In this embodiment, the weather mode refers to the changing rules and patterns of the climate characteristics or states of certain areas in the atmosphere within a certain period of time, such as hurricanes, cold currents, rain turning to clear weather, etc. that occur within a certain period of time. Multiple historical weather modal information can be meteorological data recorded in the past 20 years or the past 50 years, and can be presented in the form of a three-dimensional map of meteorological elements, including the number of times each weather mode has been observed in history and the number of times it has been effectively forecasted. Historical weather modal information can be obtained from existing data, and data appearing in paper materials can be manually screened, confirmed and entered into a computer. Current weather modal information refers to the currently observed weather modal information, which can be obtained by weather observation staff manually entering the data obtained by measuring the weather conditions into a computer, or it can be obtained by automatically sending back meteorological data through weather observation equipment installed in various places.

[0017] Step S102, classifying and processing the plurality of historical weather modal information to generate target historical weather modal information.

[0018] In this embodiment, the historical weather modal information and the current weather modal information can be presented in the form of a three-dimensional distribution map of meteorological elements. It is understandable that the sample size of the historical weather modal information is very large. When the current weather modal information needs to be determined in a specific meteorological mode, matching one or more three-dimensional distribution maps of meteorological elements corresponding to the current weather modal information with the historical weather modal information with a huge sample size will reduce the efficiency of determining the current weather modal information. Therefore, it is necessary to classify the historical weather modal information. For example, hurricanes and cold currents belong to two different meteorological modes. The historical weather modal information is classified and processed. For example, the meteorological space map of hurricanes in the historical weather modal information can be divided into one category and synthesized into a hurricane summary map, and the meteorological space map of cold currents in the historical weather modal information can be divided into another category and synthesized into another cold current summary map. If the meteorological space map of the current weather modal information successfully matches the hurricane summary map, and fails to match the cold current summary map, it means that the specific weather mode corresponding to the current weather modal information is a hurricane. The classification process of historical weather modal information can be performed by using empirical orthogonal decomposition or cluster analysis methods. It can be understood that the categories obtained by classification can be used to represent joint modes, such as the joint mode of temperature and circulation in East Asia in winter and the joint mode of precipitation and circulation. The joint mode contains both the spatial morphological characteristics of temperature or precipitation and the spatial morphological characteristics of the corresponding large-scale circulation. The information obtained after the classification process of historical weather modal information is the target historical weather modal information, which is used to match with the current weather modal information in the future, determine the specific meteorological mode corresponding to the current weather modal information, and determine the number of times the specific meteorological mode has been observed in history and the number of times it has been forecasted in historical weather forecasts.

[0019] In this embodiment, optionally, the constructed joint mode of temperature / precipitation-atmospheric circulation morphology is not the mode commonly used in the prior art to be constructed based on the atmospheric circulation morphology alone. If only the atmospheric circulation is used to construct the mode, the atmospheric circulation mode may not correspond to the temperature / precipitation anomaly. A confusion often encountered in actual prediction: the circulation is reported correctly, but the temperature / precipitation is not reported correctly. Therefore, in order to reduce the loss of forecast information in the secondary projection process from "atmospheric mode" to "temperature / precipitation", this application adopts a method of directly selecting a joint mode. In addition, the predictability of a single temperature / precipitation mode is low, and the predictability and stability of the forecasting technique are increased by the joint mode. Taking the East Asian region as an example, in the construction of the coupled mode, the spatial range of the atmospheric circulation morphology is roughly selected from the Atlantic-Eurasian-Pacific range in the northern hemisphere, and according to the different characteristics of the temperature / precipitation anomaly in East Asia, the spatial range of the joint mode may be multiple spatial scale ranges to cover more atmospheric teleconnection patterns, which is more suitable for describing the evolution characteristics of temperature and precipitation processes at different scales in East Asia. Taking winter as an example, there may be several joint modes of temperature / precipitation and atmospheric circulation to ensure that the entire winter weather pattern transition process can be covered. Among them, the joint modes corresponding to extreme cold wave events or extreme precipitation events are considered first to ensure that the joint modes can effectively reflect the time transition process and intensity of extreme events.

[0020] Step S103, performing a matching calculation based on the current weather modal information and the target historical weather modal information to obtain multiple initial forecast weather modal information that matches the current weather modal information; wherein the initial forecast weather modal information includes the number of modal occurrences of the initial forecast weather modal and the number of times the modal is forecast.

[0021] In this embodiment, the spatial similarity of the current weather modal information and the target historical weather modal information may be calculated. When the calculated spatial similarity is less than a preset spatial similarity threshold, it indicates that the match is successful, indicating that the specific meteorological modality corresponding to the current weather modal information has been observed in history or presented as a weather forecast. The conversion modality of the matched target historical weather modal information is used as the initial forecast weather modal information to determine the number of times the conversion modality of the specific meteorological modality has been observed in history and the number of times it has been presented as a weather forecast, so as to be used in the subsequent calculation of the forecast weight. The transition mode refers to the meteorological mode that may be formed after the meteorological transition of the current weather mode within a certain period of time. For example, if the current weather mode is cloudy, then the transition mode of cloudy means that it may be sunny or rainy. Both sunny and rainy are regarded as the transition mode of cloudy. It is necessary to count the number of times cloudy turns to sunny in historical meteorological records and the number of times this situation has been predicted as a weather forecast, as well as the number of times cloudy turns to rainy and the number of times this situation has been predicted as a weather forecast. Among them, the number of mode occurrences refers to the number of historical observations of the mode, that is, the number of times the transition mode has been observed in history; the number of times the mode has been predicted refers to the number of times the mode has been effectively predicted, that is, the number of times the transition mode has been effectively predicted as a weather forecast in history. It can be understood that there is no absolute correlation between the number of mode occurrences and the number of times the mode has been predicted.

[0022] Step S104, calculating the modal forecast weights of multiple initial forecast weather modal information according to the number of times the modal occurs and the number of times the modal is forecast.

[0023] In this embodiment, the modal forecast weight of the initial forecast weather modal information may be calculated by the number of times the modal is forecasted, and the modal forecast weight calculated by the number of times the modal is forecasted is used as the first-level weight, and a higher degree of importance is given to the conversion modal corresponding to the first-level weight; when the number of times the modal is forecasted is zero, the modal forecast weight of the initial forecast weather modal information is calculated by the number of times the modal occurs, but the modal forecast weight is additionally multiplied by a coefficient less than 1, and the calculation result of the coefficient and the modal forecast weight is used as the second-level weight, and the degree of importance given to the conversion modal corresponding to the second-level weight will be lower than the conversion modal corresponding to the first-level weight.

[0024] Step S105, generating target forecast weather modal information according to the multiple current weather modal information and the modal forecast weights, so as to perform weather forecast according to the target forecast weather modal information.

[0025] In this embodiment, for example, the current weather modal information is cloudy, the corresponding representation value is X, the modal forecast weight of the conversion mode sunny is 0.7, and the modal forecast weight of the conversion mode rain is 0.3, then the generated target forecast weather modal information can be numerically expressed as Y=0.7X+0.3X, wherein the forecast weather modality of the conversion mode sunny can be expressed as Y1=0.7X, and the forecast weather modality of the conversion mode rain can be expressed as Y2=0.3X. It can be understood that in actual weather forecasting, Y1 and Y2 can both be visualized as lines in a three-dimensional map of meteorological elements, and the meteorological space map with the visualized lines is used as a weather forecast result for visual presentation, thereby realizing weather forecasting according to the target forecast weather modal information.

[0026] The weather forecast method provided in the embodiment of the present application classifies and processes historical weather modal information, matches the classified weather modal information with the current weather modal information to confirm the specific meteorological mode corresponding to the current weather modal information and the possible conversion mode, and dynamically calculates the weight of the conversion mode of the current weather mode by considering the forecast and observation conditions of the conversion mode in the historical weather modal information, thereby outputting the weather forecast of the current weather mode according to the dynamically calculated weight, which can solve the problem of low accuracy of weather forecast results caused by not considering the weight of the weather modal in the prior art.

[0027] Figure 2 The following is a flowchart of the implementation of the weather forecast method provided in the second embodiment of the present application. The difference between the second embodiment and the first embodiment is that the step S102 specifically includes: Step S201, randomly generate multiple initial class center points.

[0028] In this embodiment, the initial class center point refers to the classification center point used as a reference in the classification process, that is, all historical weather modal data are classified based on the classification center point. The number of initial class center points can be set manually or randomly generated, but the relative spatial and temporal positions of the initial class center points are randomly generated and used for the initial classification of historical weather modal information.

[0029] Step S202, calculating the relative distance between the plurality of historical weather modal information and the initial class center point.

[0030] In this embodiment, the relative distance may be Euclidean distance, Manhattan distance, Chebyshev distance, or Minkowski distance‌‌.

[0031] Step S203, generating a plurality of historical weather modal information subclasses according to the relative distance and the historical weather modal information; the historical weather modal information subclasses include a plurality of weather modal individuals.

[0032] In this embodiment, a relative distance threshold may be set, and the historical weather modal information whose relative distance to the initial class center point is less than or equal to the relative distance threshold is used as the historical weather modal information subclass where the initial class center point is located. It can be understood that each initial class center point belongs to a historical weather modal information subclass. When the relative distances of a historical weather modal information to multiple initial class center points are all less than or equal to the relative distance threshold, the historical weather modal information may belong to the historical weather modal information subclass where the initial class center point with the closest relative distance is located, or may belong to multiple historical weather modal information subclasses as a joint meteorological modality.

[0033] Step S204, performing spatial displacement calculation according to the multiple weather modal individuals in the historical weather modal information subclass and the preset weather modal individual spatial displacement function to generate target historical weather modal information.

[0034] In the present embodiment, it can be understood that when performing classification calculation, the historical weather modal information is mapped into a nonlinear space, and then the classification calculation is performed through the initial class center point randomly generated in the nonlinear space. The preset weather modal individual spatial displacement function can be a Griewank function, a Rastrigin function, a Schaffer function, an Ackley function, or a Rosenbrock function, which is used for the relative displacement of data points in the nonlinear space for classification calculation. The multiple weather modal individuals in the historical weather modal information subclass are used as data points that undergo relative displacement in the nonlinear space, and the numerical values ​​of the data points in the nonlinear space are used as the independent variables of the weather modal individual spatial displacement function. The obtained function value is further analyzed and calculated to obtain the target historical weather modal information for matching with the current weather modal information.

[0035] In this embodiment, optionally, historical weather modal information can be used as the independent variable of the spatial displacement function of the weather modal individual, and the function value of the spatial displacement function of the weather modal individual is calculated as the spatial displacement of the weather modal individual in the historical weather modal information subclass, and the class center point is re-determined according to the spatial displacement, and it is determined whether the re-determined class center point is consistent with the initial class center point. If not, the relative distances between multiple weather modal individuals and multiple class center points in the historical weather modal information subclass are recalculated, and then the historical weather modal information subclass is re-determined, and then the spatial displacement of each weather modal individual in the current historical weather modal information subclass is calculated according to the preset weather modal individual spatial displacement function, and then the class center point is re-determined according to the spatial displacement, until the re-determined class center point is consistent with the class center point obtained in the last iterative calculation, then multiple meteorological modal summary graphs are generated for each current historical weather modal information subclass, and the generated multiple meteorological modal summary graphs are used as the target historical weather modal information.

[0036] The weather forecast method provided in the embodiment of the present application classifies and processes historical weather modal information with a large sample size through randomly generated initial class center points, and determines the historical weather modal information subclasses to which multiple weather modal individuals belong by calculating the logical distance between the initial class center points and each weather modal individual in the non-linear space, thereby realizing the classification of historical weather modal information into different types of meteorological modalities according to the randomly generated multiple class center points.

[0037] Figure 3 The implementation flow chart of the weather forecast method provided in the third embodiment of the present application is shown. The difference between the third embodiment and the second embodiment is that the step S204 specifically includes: Step S301, calculating the spatial displacement function value of each weather modal individual in the historical weather modal information subclass according to multiple weather modal individuals in the historical weather modal information subclass and a preset weather modal individual spatial displacement function.

[0038] In this embodiment, the representative values ​​of multiple weather modal individuals in the historical weather modal information subclass in the nonlinear space can be used as the independent variables of the weather modal individual spatial displacement function, and the function value of the weather modal individual spatial displacement function can be calculated as the offset of the weather modal individual in the nonlinear space, that is, the spatial displacement function value of each weather modal individual in the historical weather modal information subclass.

[0039] Step S302: taking the weather mode individual corresponding to the extreme value of the spatial displacement function value as the cluster center point after spatial displacement.

[0040] In this embodiment, the weather mode individual corresponding to the maximum value of the spatial displacement function value can be used as the class center point after spatial displacement to reclassify the weather mode individual, so that the classification result approaches the global optimal solution, improves the reliability of the classification calculation, and thus improves the subsequent matching accuracy and effectiveness of the current weather mode.

[0041] Step S303, determining whether the cluster center point after the spatial displacement is the same as the initial cluster center point, if so, proceeding to step S304; if not, proceeding to step S305.

[0042] In this embodiment, when the class center point after spatial displacement is the same as the initial class center point, it means that the current calculation of the class center point has converged, and even if the class center point is calculated again, the class center point in the classification result will not change, which means that the historical weather modal information subclass obtained by analyzing and calculating the class center point is the global optimal solution, and the target historical weather modal information can be directly generated according to the currently obtained historical weather modal information subclass. When the class center point after spatial displacement is different from the initial class center point, it means that the current calculation of the class center point has not converged, and further calculations are required for the displacement of the weather modal individual in the nonlinear space and the class center point until the class center point after spatial displacement is the same as the class center point obtained after the last calculation of the spatial displacement.

[0043] Step S304: Generate target historical weather modal information according to the plurality of historical weather modal information subcategories.

[0044] In this embodiment, each weather modal information subclass that has occurred in history can be used to generate multiple meteorological modal summary information, and the generated multiple meteorological modal summary information can be used as the target historical weather modal information for subsequent matching of the current weather modal information to confirm the specific meteorological modal type of the current weather modal. It can be understood that the summary information can be the value of the variable at the spatial grid point, and can include a three-dimensional array of temperature (longitude, latitude, altitude).

[0045] Step S305, taking the spatially displaced cluster center point as the initial cluster center point, and returning to step S202.

[0046] In this embodiment, when the class center point after spatial displacement is different from the initial class center point, it means that the current calculation of the class center point has not converged, and further calculation is required for the displacement of the weather mode individual in the nonlinear space and the class center point until the class center point after spatial displacement is the same as the class center point obtained after the last calculation of the spatial displacement.

[0047] The weather forecast method provided in the embodiment of the present application calculates the spatial displacement of multiple weather modal individuals in the historical weather modal information subclass in the nonlinear space, and readjusts the value of the class center point according to the extreme value of the spatial displacement, so as to ensure that the historical weather modal information subclass calculated by the adjusted class center point is closer to the global optimal solution. When the class center point after the spatial displacement is consistent with the class center point before the spatial displacement, it indicates that the current calculation of the class center point has converged, and there is no need to redetermine the historical weather modal information subclass. The currently calculated historical weather modal information subclass generates multiple meteorological modal summary graphs, and the multiple meteorological modal summary graphs are determined as the target historical weather modal information, thereby enhancing the robustness of the classification calculation of the historical weather modal information, so as to improve the subsequent matching accuracy and effectiveness of the current weather modal, thereby effectively improving the accuracy of the weather forecast.

[0048] Figure 4 The following is a flowchart of the implementation of the weather forecast method provided in the fourth embodiment of the present application. The difference between the fourth embodiment and the first embodiment is that the step S103 specifically includes: Step S401, calculating the spatial similarity between the current weather modal information and the target historical weather modal information.

[0049] In this embodiment, the spatial similarity may be cosine similarity.

[0050] Step S402, determining whether the spatial similarity is greater than a preset similarity threshold, if so, obtaining a plurality of historical modal information matching the current weather modal information; if not, the current weather modal information does not match the historical modal information.

[0051] In this embodiment, the preset similarity threshold can be set manually. It can be understood that when the spatial similarity is greater than the preset similarity threshold, it means that the current weather modal information matches the target historical weather modal information successfully, and it is necessary to determine the corresponding conversion mode for the successfully matched target historical weather modal information, and determine the actual occurrence mode and forecast mode. The meteorological mode of the conversion mode corresponding to the target historical weather modal information that has been observed and recorded in history is used as the actual occurrence mode of the historical modal information, and the conversion mode that has been forecasted in history is used as the forecast mode for the subsequent calculation of the weight of the weather mode in the current weather forecast. When the spatial similarity is less than or equal to the preset similarity threshold, it means that the current weather modal information cannot be matched successfully with the target historical weather modal information, and it is necessary to continue to match the current weather modal information with other meteorological summary maps in the target historical weather modal information until the match is successful.

[0052] Step S403, according to the target historical weather modal information, determining the actual occurrence modalities and forecast modalities of multiple historical modal information, and obtaining multiple initial forecast weather modal information.

[0053] In this embodiment, if the current weather modal information matches the target historical weather modal information successfully, it is necessary to determine the corresponding conversion modality for the successfully matched target historical weather modal information, and determine the actual occurrence modality and the forecast modality. The meteorological modality of the conversion modality corresponding to the target historical weather modal information that has been observed and recorded in history is used as the actual occurrence modality of the historical modal information, and the conversion modality that has been forecasted in history is used as the forecast modality. Multiple possible conversion modes, namely the initial forecast weather modal information, are used for the subsequent calculation of the weight of the weather modality in the current weather forecast.

[0054] The weather forecast method provided in the embodiment of the present application calculates the spatial similarity between the current weather modal information and the target historical weather modal information, matches the current weather modal information with the target historical weather modal information, so as to determine the actual weather modal after conversion corresponding to the historical modal and the forecasted conversion modal, thereby determining the conversion modal that is most similar to the historical law according to the current weather modal as the initial forecast weather modal information, which is used for calculating the subsequent forecast weights and presenting the weather forecast content.

[0055] Figure 5 The implementation flow chart of the weather forecast method provided in the fifth embodiment of the present application is shown, which differs from the first embodiment in that: the multiple initial weather forecast modal information includes first initial weather forecast modal information and second initial weather forecast modal information; the first initial weather forecast modal information includes the number of occurrences of the first modal and the number of forecasts of the first modal; the second initial weather forecast modal information includes the number of occurrences of the second modal and the number of forecasts of the second modal; The step S104 specifically includes: Step S501, determine whether the number of times the first mode is predicted and the number of times the second mode is predicted are both not zero, if so, proceed to step S502; if not, proceed to step S505.

[0056] In the present embodiment, the initial forecast weather modal information includes the first initial forecast weather modal information and the second initial forecast weather modal information, which means that after the current weather modality is converted within a certain time period, the weather modality formed may be the first initial forecast weather modal information or the second initial forecast weather modal information. The certain time period may be 3 days, 10 days or 15 days, etc. It can be understood that the first initial forecast weather modal information or the second initial forecast weather modal information is only used to exemplarily represent the weather modality that may be formed after the current weather modality is converted. There are far more than one or two weather modalities that may be formed after the current weather modality is converted. In the present application, only two of them are named as the first initial forecast weather modal information and the second initial forecast weather modal information, which is convenient for the subsequent explanation of the calculation of the forecast weight and the description of the weather forecast method of the present application. When the number of forecasts of the first initial forecast weather modal information and the second initial forecast weather modal information is not zero, it means that the first initial forecast weather modal information and the second initial forecast weather modal information have been forecasted as meteorological modes in weather forecasts in history, and the first initial forecast weather modal information and the second initial forecast weather modal information are used as important references for the weather forecast of the current weather mode. When the number of forecasts of the first mode is not zero and the number of forecasts of the second mode is zero, the number of forecasts of the first mode and the number of occurrences of the second mode can be summed to obtain a forecast weight variable, and then the number of forecasts of the first mode is divided by the forecast weight variable, and the result of the division is multiplied by the first coefficient set manually to obtain the first mode forecast weight; then the number of occurrences of the second mode is divided by the forecast weight variable, and the result of the division is multiplied by the second coefficient set manually to obtain the second mode forecast weight; wherein the first coefficient is greater than the second coefficient, which is used to characterize that the importance of the number of forecasts of the mode is higher than the number of occurrences of the mode in the calculation process of the weather forecast.

[0057] In this embodiment, it can be understood that the first and the second are only used for exemplary expressions, and in actual situations, multiple initial forecast weather modal information may include not only the first initial forecast weather modal information and the second initial forecast weather modal information, but also the third initial forecast weather modal information, the fourth initial forecast weather modal information and so on.

[0058] Step S502: sum the number of times the first mode is predicted and the number of times the second mode is predicted to obtain a prediction weight variable.

[0059] In this embodiment, the number of times the first modality is predicted and the number of times the second modality is predicted can be added to obtain a prediction weight variable as an intermediate variable for calculating the modal prediction weight, which is used to further calculate the modal prediction weight in the subsequent process.

[0060] Step S503, calculating the first modality prediction weight according to the number of times the first modality is predicted and the prediction weight variable.

[0061] In this embodiment, the number of times the first modality is predicted can be used as the numerator and the forecast weight variable as the denominator. The number of times the first modality is predicted can be divided by the forecast weight variable. The calculation result is the first modality forecast weight, which can characterize the importance of the first initial forecast weather modal information in the weather forecast results and is used for the subsequent generation of weather forecast results.

[0062] Step S504, calculating the second modality prediction weight according to the number of times the second modality is predicted and the prediction weight variable.

[0063] In this embodiment, the number of times the second modality is predicted can be used as the numerator and the forecast weight variable as the denominator. The number of times the second modality is predicted can be divided by the forecast weight variable. The calculation result is the second modality forecast weight, which can characterize the importance of the second initial forecast weather modal information in the weather forecast results and be used for subsequent generation of weather forecast results.

[0064] Step S505, determine whether the number of times the first modal is predicted and the number of times the second modal is predicted are both zero, if so, proceed to step S506; if not, calculate the first modal prediction weight and the second modal prediction weight based on the number of times the first modal is predicted, the number of times the second modal is predicted, the number of times the first modal occurs, and the number of times the second modal occurs.

[0065] In this embodiment, when the number of forecasts of the first initial forecast weather modal information and the second initial forecast weather modal information are both zero, it means that the first initial forecast weather modal information and the second initial forecast weather modal information have not been forecast as meteorological modes in the weather forecast in history, then the first initial forecast weather modal information and the second initial forecast weather modal information are used as auxiliary references for the weather forecast for the current weather mode.

[0066] Step S506: sum the number of occurrences of the first mode and the number of occurrences of the second mode to obtain a prediction weight variable.

[0067] In this embodiment, the number of occurrences of the first modal and the number of occurrences of the second modal are added to obtain a prediction weight variable, which is used as an intermediate variable for calculating the modal prediction weight and is used to further calculate the modal prediction weight in the subsequent process.

[0068] Step S507, calculating the first modal prediction weight according to the first modal occurrence number and the prediction weight variable.

[0069] In this embodiment, the number of occurrences of the first modal can be used as the numerator and the forecast weight variable as the denominator. The number of occurrences of the first modal can be divided by the forecast weight variable. The calculation result is the first modal forecast weight, which can characterize the importance of the first initial forecast weather modal information in the weather forecast results and be used for subsequent generation of weather forecast results.

[0070] Step S508, calculating the second modality prediction weight according to the second modality occurrence number and the prediction weight variable.

[0071] In this embodiment, the number of occurrences of the second modality can be used as the numerator and the forecast weight variable as the denominator. The number of occurrences of the second modality can be divided by the forecast weight variable. The calculation result is the second modality forecast weight, which can characterize the importance of the second initial forecast weather modal information in the weather forecast results and be used for subsequent generation of weather forecast results.

[0072] The step S105 specifically includes: Step S509, generating target forecast weather modal information according to the multiple current weather modal information, the first modal forecast weight and the second modal forecast weight, so as to perform weather forecast according to the target forecast weather modal information.

[0073] In this embodiment, it can be understood that the sum of the first modal forecast weight and the second modal forecast weight is 1, that is, the sum of the modal forecast weights of all conversion modes of the current weather modality is 1. The result of multiplying the current weather modal information by the first modal forecast weight can be used as one of the forecast results of the current weather modality, and the result of multiplying the current weather modal information by the second modal forecast weight can be used as another forecast result of the current weather modality. All forecast results are statistically summarized to obtain the target forecast weather modal information, and then all forecast results in the target forecast weather modal information are visualized, and the visualized results are visually presented as weather forecast results.

[0074] The weather forecast method provided in the embodiment of the present application calculates the weight of the conversion mode of the current weather mode by the number of times the mode occurs and the number of times the mode is predicted, so as to quantify the importance of each possible conversion mode in the weather forecast process, and focuses on the weather modes that have been forecasted many times in the historical records. If the weather modes that have been observed but not forecasted in the historical records are used as auxiliary references, when different weather modes are used as initial conditions, different weather mode weights will be dynamically calculated, so as to calculate the weather forecast results according to the weight values ​​that change dynamically in each forecasting work, so as to improve the accuracy of the weather forecast results.

[0075] Figure 6The flowchart of the implementation of the weather forecast method provided in the sixth embodiment of the present application is shown. The difference between the sixth embodiment and the fifth embodiment is that the step S509 specifically includes: Step S601, obtaining first modal forecast information according to the current weather modal information and the first modal forecast weight.

[0076] In this embodiment, the meteorological value of the current weather mode may be multiplied by the first modal forecast weight to obtain the first modal forecast information for subsequent generation of weather forecast results.

[0077] Step S602, obtaining second modal forecast information according to the current weather modal information and the second modal forecast weight.

[0078] In this embodiment, the meteorological value of the current weather mode may be multiplied by the second modality forecast weight to obtain the second modality forecast information for subsequent generation of weather forecast results.

[0079] Step S603, superimposing the first modal forecast information and the second modal forecast information to generate target forecast weather modal information, so as to perform weather forecast according to the target forecast weather modal information.

[0080] In this embodiment, the modal forecast information can be superimposed in the meteorological space to generate the target forecast weather modal information, and after the target forecast weather modal information is visualized, it can be used for the presentation of the weather forecast. It can be understood that in the actual weather forecast, the first modal forecast information and the second modal forecast information can be visualized as lines in the meteorological space map, and the lines representing the first modal forecast information and the lines representing the second modal forecast information are superimposed and displayed, so that the meteorological space map with visualized lines is visually presented as the weather forecast result, thereby realizing the weather forecast according to the target forecast weather modal information.

[0081] The weather forecast method provided in the embodiment of the present application calculates modal forecast information through current weather modal information and modal forecast weights, which is used to linearly represent visual lines in the meteorological space. By superimposing the modal forecast information in the meteorological space, target forecast weather modal information is generated. After the target forecast weather modal information is visualized, it can be used for weather forecast presentation, thereby improving the accuracy and intuitiveness of the weather forecast.

[0082] Figure 7 The flowchart of the weather forecast method provided in the seventh embodiment of the present application is shown. The difference between the seventh embodiment and the first embodiment is that after the step S105, the method further includes: Step S701, obtaining actual weather modal information after the weather forecast.

[0083] In this embodiment, the actual weather modal information after the weather forecast can be obtained by observing the weather, and can be obtained by the staff who conducts the meteorological observation inputting the observation results into a computer.

[0084] Step S702, determining whether the actual weather modal information is the same as the current weather modal information, if so, returning to step S105; if not, proceeding to step S703.

[0085] In this embodiment, when the actual weather modal information is the same as the current weather modal information, it means that the current weather modal has not been converted. There is no need to further determine the conversion mode of the current weather modal and recalculate the forecast weight of the conversion mode. The weather forecast is still performed based on the calculation result of the current weather modal.

[0086] Step S703, taking the actual weather modal information as current weather modal information, and returning to step S103.

[0087] In this embodiment, when the actual weather modal information is different from the current weather modal information, it means that the current weather modal has been converted, and it is necessary to update the conversion modality and forecast weight relative to the actual weather modal according to the actual weather modal information after the modal conversion, for subsequent weather forecast for the actual weather modal.

[0088] The weather forecasting method provided in the embodiment of the present application determines the actual weather mode after the forecast, and determines whether the current weather mode has been converted by judging whether the actual weather mode information is the same as the current weather mode information. When the weather mode has been converted, the forecast weight is dynamically updated based on the converted weather mode as the initial condition to perform the next round of weather forecast, so as to ensure the accuracy and reliability of the forecast after the weather mode is converted.

[0089] Corresponding to the method of the above embodiment, Figure 8 A structural block diagram of a weather forecast device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown. Figure 8 The exemplary weather forecast device may be an execution subject of the weather forecast method provided in the aforementioned first embodiment.

[0090] Reference Figure 8 , the weather forecast device comprises: The information acquisition module 810 is used to acquire a plurality of historical weather modal information and current weather modal information; The target historical weather modal information module 820 is used to classify and process the plurality of historical weather modal information to generate target historical weather modal information; The initial forecast weather modal information calculation module 830 is used to perform matching calculation according to the current weather modal information and the target historical weather modal information to obtain a plurality of initial forecast weather modal information matching the current weather modal information; wherein the initial forecast weather modal information includes the modal occurrence times and the modal forecast times of the initial forecast weather modal; A modal forecast weight calculation module 840 is used to calculate the modal forecast weights of multiple initial forecast weather modal information according to the number of times the modal occurs and the number of times the modal is forecasted; The target forecast weather modal information generation module 850 is used to generate target forecast weather modal information according to the multiple current weather modal information and the modal forecast weights, so as to perform weather forecast according to the target forecast weather modal information.

[0091] The process of each module in the weather forecast device provided in the embodiment of the present application realizing its own function can be specifically referred to in the aforementioned Figure 1 The description of the first embodiment is not repeated here.

[0092] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0093] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0094] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0095] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0096] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish descriptions, and cannot be understood as indicating or suggesting relative importance. It should also be understood that although the terms "first", "second", etc. are used to describe various elements in some embodiments of the present application in the text, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, the first table can be named as the second table, and similarly, the second table can be named as the first table without departing from the scope of the various described embodiments. The first table and the second table are both tables, but they are not the same table.

[0097] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0098] The weather forecast method provided in the embodiments of the present application can be applied to terminal devices such as mobile phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (AR) / virtual reality (VR) devices, laptop computers, ultra-mobile personal computers (UMPC), netbooks, personal digital assistants (PDA), etc. The embodiments of the present application do not impose any restrictions on the specific types of terminal devices.

[0099] For example, the terminal device can be a station (STAION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a vehicle networking terminal, a computer, a laptop computer, a handheld communication device, a handheld computing device, a satellite wireless device, a wireless modem card, a TV set top box (STB), a customer premises equipment (CPE) and / or other devices for communicating on a wireless system and a next-generation communication system, such as a mobile terminal in a 5G network or a mobile terminal in a future evolved Public Land Mobile Network (PLMN) network, etc.

[0100] As an example but not limitation, when the terminal device is a wearable device, the wearable device can also be a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not just hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are fully functional, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0101] Fig. 9 FIG. 1 is a schematic diagram of the structure of a terminal device provided by an embodiment of the present application. Fig. 9 As shown, the terminal device 9 of this embodiment includes: at least one processor 90 ( Fig. 9 Only one is shown in the figure), a memory 91, wherein the memory 91 stores a computer program 92 that can be run on the processor 90. When the processor 90 executes the computer program 92, the steps in the above-mentioned weather forecast method embodiments are implemented, such as Figure 1 Alternatively, when the processor 90 executes the computer program 92, the functions of each module / unit in the above-mentioned device embodiments are realized, for example, Figure 8Functions of modules 810 to 850 are shown.

[0102] The terminal device 9 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal device may include, but is not limited to, a processor 90 and a memory 91. Those skilled in the art will appreciate that Fig. 9 It is only an example of the terminal device 9 and does not constitute a limitation on the terminal device 9. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device may also include an input sending device, a network access device, a bus, etc.

[0103] The processor 90 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0104] In some embodiments, the memory 91 may be an internal storage unit of the terminal device 9, such as a hard disk or memory of the terminal device 9. The memory 91 may also be an external storage device of the terminal device 9, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device 9. Further, the memory 91 may also include both an internal storage unit of the terminal device 9 and an external storage device. The memory 91 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 91 may also be used to temporarily store data that has been sent or is to be sent.

[0105] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0106] An embodiment of the present application also provides a terminal device, which includes at least one memory, at least one processor, and a computer program stored in the at least one memory and executable on the at least one processor, wherein when the processor executes the computer program, the terminal device implements the steps in any of the above-mentioned method embodiments.

[0107] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0108] An embodiment of the present application provides a computer program product. When the computer program product runs on a terminal device, the terminal device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0109] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0110] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0111] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0112] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0113] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A weather forecast method, characterized in that: include: Get multiple historical weather modal information and current weather modal information; Classifying and processing the plurality of historical weather modal information to generate target historical weather modal information; According to the current weather modal information and the target historical weather modal information, a matching calculation is performed to obtain a plurality of initial forecast weather modal information matching the current weather modal information; wherein the initial forecast weather modal information includes the modal occurrence times and the modal forecast times of the initial forecast weather modal; Calculating modal forecast weights of multiple initial forecast weather modal information according to the number of times the modal occurs and the number of times the modal is forecasted; According to the multiple current weather modal information and the modal forecast weights, target forecast weather modal information is generated to perform weather forecast according to the target forecast weather modal information.

2. The weather forecast method according to claim 1, characterized in that: The step of classifying the plurality of historical weather modal information to generate target historical weather modal information specifically includes: Randomly generate multiple initial class center points; Calculating the relative distances between the plurality of historical weather modal information and the initial class center points; Generate a plurality of historical weather modal information subclasses according to the relative distance and the historical weather modal information; the historical weather modal information subclasses include a plurality of weather modal individuals; According to the multiple weather modal individuals in the historical weather modal information subclass and the preset weather modal individual spatial displacement function, spatial displacement calculation is performed to generate target historical weather modal information.

3. The weather forecast method according to claim 2, characterized in that: The step of performing spatial displacement calculation according to the plurality of weather modal individuals in the historical weather modal information subclass and the preset weather modal individual spatial displacement function to generate the target historical weather modal information specifically includes: Calculating the spatial displacement function value of each weather modal individual in the historical weather modal information subclass according to the plurality of weather modal individuals in the historical weather modal information subclass and the preset weather modal individual spatial displacement function; The weather mode individual corresponding to the extreme value of the spatial displacement function value is taken as the cluster center point after spatial displacement; Determine whether the cluster center point after the spatial displacement is the same as the initial cluster center point; If yes, generating target historical weather modal information according to the plurality of said historical weather modal information subcategories; If not, the spatially displaced cluster center point is used as the initial cluster center point, and the process returns to the step of calculating the relative distance between the plurality of historical weather modal information and the initial cluster center point.

4. The weather forecast method according to claim 1, characterized in that: The step of performing matching calculation according to the current weather modal information and the target historical weather modal information to obtain a plurality of initial forecast weather modal information matching the current weather modal information specifically includes: Calculating the spatial similarity between the current weather modal information and the target historical weather modal information; When the spatial similarity is greater than a preset similarity threshold, a plurality of historical modal information matching the current weather modal information is obtained; According to the target historical weather modal information, actual occurrence modalities and forecast modalities of multiple historical modal information are determined to obtain multiple initial forecast weather modal information.

5. The weather forecast method according to claim 1, characterized in that: The multiple initial weather forecast modal information include first initial weather forecast modal information and second initial weather forecast modal information; The first initial forecast weather modal information includes the number of occurrences of the first modal and the number of forecasts of the first modal; The second initial weather forecast modal information includes the number of occurrences of the second modal and the number of forecasts of the second modal; The step of calculating the modal forecast weights of a plurality of initial forecast weather modal information according to the number of times the modal occurs and the number of times the modal is forecasted specifically comprises: When the number of times the first mode is predicted and the number of times the second mode is predicted are both not zero, summing the number of times the first mode is predicted and the number of times the second mode is predicted to obtain a prediction weight variable; Calculating a first modal prediction weight according to the number of times the first modal is predicted and a prediction weight variable; Calculating a second modality prediction weight according to the number of times the second modality is predicted and a prediction weight variable; When the number of times the first mode is predicted and the number of times the second mode is predicted are both zero, summing the number of times the first mode occurs and the number of times the second mode occurs to obtain a prediction weight variable; Calculating a first modal prediction weight according to the first modal occurrence number and a prediction weight variable; Calculating a second modality prediction weight according to the second modality occurrence number and a prediction weight variable; The step of generating target forecast weather modal information according to the multiple current weather modal information and the modal forecast weights, and performing weather forecast according to the target forecast weather modal information, specifically includes: According to the multiple current weather modal information, the first modal forecast weight and the second modal forecast weight, target forecast weather modal information is generated to perform weather forecast according to the target forecast weather modal information.

6. The weather forecast method according to claim 5, characterized in that: The step of generating target forecast weather modal information according to the multiple current weather modal information, the first modal forecast weight and the second modal forecast weight, and performing weather forecast according to the target forecast weather modal information, specifically includes: Obtaining first modal forecast information according to the current weather modal information and the first modal forecast weight; Obtaining second modal forecast information according to the current weather modal information and the second modal forecast weight; The first modal forecast information and the second modal forecast information are superimposed to generate target forecast weather modal information, so as to perform weather forecast according to the target forecast weather modal information.

7. The weather forecast method according to claim 1, characterized in that: After the step of generating target forecast weather modal information according to the plurality of current weather modal information and the modal forecast weights, and performing weather forecast according to the target forecast weather modal information, the method further includes: Get the actual weather mode information after the weather forecast; When the actual weather modal information is different from the current weather modal information, the actual weather modal information is used as the current weather modal information, and the process returns to the step of performing matching calculation based on the current weather modal information and the target historical weather modal information to obtain multiple initial forecast weather modal information that matches the current weather modal information.

8. A weather forecast device, characterized in that: include: An information acquisition module is used to obtain multiple historical weather modal information and current weather modal information; A target historical weather modal information module is used to classify and process the plurality of historical weather modal information to generate target historical weather modal information; An initial forecast weather modal information calculation module is used to perform matching calculations based on the current weather modal information and the target historical weather modal information to obtain a plurality of initial forecast weather modal information that matches the current weather modal information; wherein the initial forecast weather modal information includes the modal occurrence times of the initial forecast weather modal and the modal forecast times; A modal forecast weight calculation module, used to calculate the modal forecast weights of multiple initial forecast weather modal information according to the number of times the modal occurs and the number of times the modal is forecasted; The target forecast weather modal information generation module is used to generate target forecast weather modal information according to the multiple current weather modal information and the modal forecast weights, so as to perform weather forecast according to the target forecast weather modal information.

9. A terminal device, characterized in that: The terminal device includes a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images