Intelligent meteorological data source selection system and method

Abstract

The invention relates to the technical field of meteorological data sources, and discloses an intelligent meteorological data source selection system and method, and the system comprises a data determination module which determines a plurality of to-be-selected meteorological data sources, obtains initial meteorological data, determines a plurality of meteorological data source selection packets, and a first calculation module which analyzes the meteorological data source selection packets, calculating a data contribution degree corresponding to the meteorological data in the meteorological data source selection packet; a second calculation module performs numerical analysis on the data contribution degree, constructs a plurality of data contribution degree sequences, and calculates the selection value of the meteorological data source in the meteorological data source selection packet based on the data contribution degree sequences; and the data selection module compares the selection values, and takes the meteorological data source corresponding to the maximum selection value as a target meteorological data source. According to the invention, the meteorological data source with the maximum selection value can be intelligently evaluated and screened, the meteorological forecast precision and real-time performance are improved, the labor cost is reduced, and the method is of great significance in enhancing the coping capability of extreme weather events.

Description

Technical Field

[0001] The present invention relates to the technical field of meteorological data sources, and in particular to an intelligent meteorological data source selection system and method. Background Art

[0002] Meteorological data is information collected from various observation platforms and used to analyze and predict weather and climate patterns. This data is essential for meteorological research, weather forecasting, disaster warning and climate monitoring. The main sources of meteorological data include: ground observation stations, radar systems, satellites, sounding balloons, etc. Different data sources have different spatial and temporal resolutions, as well as different accuracy and error ranges. In order to obtain the best weather forecast and climate analysis, it is usually necessary to combine information from multiple data sources.

[0003] Traditional methods for selecting meteorological data sources usually rely on expert experience and manual processing, which is not only time-consuming and labor-intensive, but also susceptible to subjective judgment and may not always select the optimal data source. Moreover, the selection of traditional meteorological data sources is often fixed or based only on simple rules and standards, such as the timestamp of the data, the spatial resolution, or the credibility of the data source. In addition, existing systems usually lack adaptive capabilities and cannot adjust the selection of data sources based on real-time or near-real-time feedback. Summary of the invention

[0004] The present invention provides an intelligent meteorological data source selection system and method, which are used to solve the technical problems in the prior art that the optimal meteorological data source cannot be automatically evaluated and selected, and the accuracy and real-time performance of meteorological forecasts cannot be improved.

[0005] In order to achieve the above object, the first aspect of the present invention provides an intelligent meteorological data source selection system, comprising:

[0006] A data determination module, used to determine a plurality of meteorological data sources to be selected, obtain initial meteorological data of each meteorological data source to be selected, and determine a plurality of meteorological data source selection packages, wherein the meteorological data source selection packages include meteorological data sources and meteorological data;

[0007] A first calculation module, used to parse the meteorological data source selection package and calculate the data contribution corresponding to the meteorological data in the meteorological data source selection package;

[0008] A second calculation module is used to perform numerical analysis on all data contributions, construct multiple data contribution sequences based on the numerical analysis results, and calculate the selection value of the meteorological data source in the meteorological data source selection package based on the data contribution sequences;

[0009] The data selection module is used to compare all selection values ​​and take the meteorological data source corresponding to the maximum selection value as the target meteorological data source.

[0010] Furthermore, the determining module is used to:

[0011] Building an initial meteorological data chain according to the initial meteorological data of the meteorological data source to be selected;

[0012] Performing abnormal fluctuation analysis on the initial meteorological data chain to determine whether there is an abnormal fluctuation node, and if not, determining a meteorological data source selection package according to the initial meteorological data chain;

[0013] If yes, determine the location of the abnormal fluctuation node, and determine the first adjacent initial meteorological data and the second adjacent initial meteorological data of the abnormal fluctuation node;

[0014] Analyze the first adjacent initial meteorological data and the second adjacent initial meteorological data to determine a corresponding first abnormal fluctuation coefficient and a second abnormal fluctuation coefficient;

[0015] When the first abnormal fluctuation coefficient and the second abnormal fluctuation coefficient meet a first preset condition, marking the abnormal fluctuation node as a classifiable node;

[0016] When the first abnormal fluctuation coefficient and the second abnormal fluctuation coefficient meet the second preset condition, the abnormal fluctuation node is eliminated;

[0017] When the first abnormal fluctuation coefficient and the second abnormal fluctuation coefficient meet a third preset condition, marking the abnormal fluctuation node as a suspected node;

[0018] Counting a first number of all suspected nodes, and if the first number is less than a preset number, transferring all suspected nodes to classifiable nodes;

[0019] If the first number is greater than or equal to the preset number, all suspected nodes are eliminated;

[0020] The meteorological data source selection package is determined based on the classifiable nodes and the nodes that have not generated tags.

[0021] Furthermore, the determining module is also used for:

[0022] Based on the collection time of the initial meteorological data, construct time series meteorological data;

[0023] According to the sliding window mechanism, the time series data is divided into multiple data segments, each of which contains a predetermined number of consecutive data points;

[0024] Calculating a volatility index for each data segment, and comparing the volatility index with a preset volatility index;

[0025] If the volatility index is greater than or equal to the preset volatility index, it is determined that there is an abnormal volatility node in the initial meteorological data chain.

[0026] Furthermore, the first calculation module is used for:

[0027] Identify the correlation between the attributes in the meteorological data based on the Pearson correlation coefficient;

[0028] Sort all the correlations by numerical value to obtain a correlation set;

[0029] Selecting a first degree of association and a second degree of association from the degree of association set, and generating a high degree of association set according to the degree of association between the maximum degree of association in the degree of association set and the first degree of association;

[0030] generating a low association set according to the association between the minimum association in the association set and the second association;

[0031] generating a middle association set according to the association degree between the first association degree and the second association degree in the association degree set;

[0032] The data contribution corresponding to the meteorological data is calculated according to the high correlation set, the low correlation set and the medium correlation set.

[0033] Furthermore, the first calculation module is also used for:

[0034] The data contribution corresponding to the meteorological data is calculated according to the following formula:

[0035]

[0036] Among them, H is the data contribution corresponding to the meteorological data, a1 is the weight corresponding to the high correlation set, m is the number of correlations in the high correlation set, ki is the i-th correlation in the high correlation set, J1 is the first correlation, a2 is the weight corresponding to the low correlation set, n is the number of correlations in the low correlation set, J2 is the second correlation, kj is the j-th correlation in the low correlation set, and h is the calculation coefficient of the data contribution.

[0037] Furthermore, the first calculation module is also used for:

[0038] The number of correlations in the correlation set in the statistics;

[0039] Presetting a first preset number and a second preset number;

[0040] The first preset calculation coefficient h1, the second preset calculation coefficient h2, and the third preset calculation coefficient h3 are preset, and 0.8

[0041] When the number is less than the first preset number, the calculation coefficient of the data contribution is set to the first preset calculation coefficient h1;

[0042] When the number is greater than or equal to the first preset number and less than the second preset number, the calculation coefficient of the data contribution is set to the second preset calculation coefficient h2;

[0043] When the number is greater than or equal to the second preset number, the calculation coefficient of the data contribution is set to the third preset calculation coefficient h3.

[0044] Furthermore, the second calculation module is used for:

[0045] Performing numerical analysis on all data contributions, extracting the same data contribution from the data contribution sequence, and obtaining multiple data contribution sequences;

[0046] The first number Q1 of the statistical data contribution sequence;

[0047] Extracting a data contribution from each of all data contribution sequences, and calculating a first data contribution and value R1;

[0048] Obtaining a preset data contribution, eliminating all data contribution sequences that are less than the preset data contribution, and counting a second number Q2 of remaining data contribution sequences;

[0049] Extracting a data contribution from each of the remaining data contribution sequences, and calculating a second data contribution and a value R2;

[0050] The selection value of the meteorological data source in the meteorological data source selection package is calculated according to the first quantity Q1, the second quantity Q2, the first data contribution and value R1, and the second data contribution and value R2.

[0051] Furthermore, the second calculation module is also used for:

[0052] The selection value of the meteorological data source in the meteorological data source selection package is calculated according to the following formula:

[0053]

[0054] Among them, S is the selection value of the meteorological data source in the meteorological data source selection package, and t is the preset data contribution.

[0055] ​In order to achieve the above-mentioned object, the second aspect of the present invention provides an intelligent meteorological data source selection method, which is applied to an intelligent meteorological data source selection system provided in the first aspect of the present invention, comprising:

[0056] Determine a plurality of meteorological data sources to be selected, obtain initial meteorological data of each meteorological data source to be selected, and determine a plurality of meteorological data source selection packages, wherein the meteorological data source selection packages include meteorological data sources and meteorological data;

[0057] Parsing the meteorological data source selection package, and calculating the data contribution corresponding to the meteorological data in the meteorological data source selection package;

[0058] Performing numerical analysis on all data contributions, constructing multiple data contribution sequences based on the numerical analysis results, and calculating the selection value of the meteorological data source in the meteorological data source selection package based on the data contribution sequences;

[0059] All selection values ​​are compared, and the meteorological data source corresponding to the maximum selection value is used as the target meteorological data source.

[0060] Compared with the prior art, the present invention has the following beneficial effects:

[0061] The present invention discloses an intelligent meteorological data source selection system and method, the system comprises: a data determination module determines multiple meteorological data sources to be selected, obtains initial meteorological data, determines multiple meteorological data source selection packages, a first calculation module parses the meteorological data source selection package, and calculates the data contribution corresponding to the meteorological data in the meteorological data source selection package; a second calculation module performs numerical analysis on the data contribution, constructs multiple data contribution sequences, and calculates the selection value of the meteorological data source in the meteorological data source selection package; a data selection module compares the selection values, and uses the meteorological data source corresponding to the maximum selection value as the target meteorological data source. The present invention can intelligently evaluate and screen the meteorological data source with the maximum selection value, improve the accuracy and real-time performance of meteorological forecasts, reduce labor costs, and is of great significance to enhancing the ability to respond to extreme weather events. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0063] Figure 1 A schematic diagram of the structure of an intelligent meteorological data source selection system according to an embodiment of the present invention is shown;

[0064] Figure 2 A schematic flow chart of an intelligent meteorological data source selection method in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0065] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0066] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0067] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0068] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0069] The following is a description of preferred embodiments of the present invention with reference to the accompanying drawings.

[0070] like Figure 1 As shown, an embodiment of the present invention discloses an intelligent meteorological data source selection system, comprising:

[0071] A data determination module, used to determine a plurality of meteorological data sources to be selected, obtain initial meteorological data of each meteorological data source to be selected, and determine a plurality of meteorological data source selection packages, wherein the meteorological data source selection packages include meteorological data sources and meteorological data;

[0072] A first calculation module, used to parse the meteorological data source selection package and calculate the data contribution corresponding to the meteorological data in the meteorological data source selection package;

[0073] A second calculation module is used to perform numerical analysis on all data contributions, construct multiple data contribution sequences based on the numerical analysis results, and calculate the selection value of the meteorological data source in the meteorological data source selection package based on the data contribution sequences;

[0074] The data selection module is used to compare all selection values ​​and take the meteorological data source corresponding to the maximum selection value as the target meteorological data source.

[0075] The beneficial effect of the above technical solution is that the present invention can intelligently evaluate and screen the meteorological data source with the greatest selection value, improve the accuracy and real-time performance of meteorological forecasts, reduce labor costs, and is of great significance to enhancing the ability to respond to extreme weather events.

[0076] In some embodiments of the present application, the determining module is used to:

[0077] The determination module is used to construct an initial meteorological data chain according to the initial meteorological data of the meteorological data source to be selected;

[0078] The determination module is used to perform abnormal fluctuation analysis on the initial meteorological data chain to determine whether there is an abnormal fluctuation node, and if not, determine a meteorological data source selection package according to the initial meteorological data chain;

[0079] If yes, determine the location of the abnormal fluctuation node, and determine the first adjacent initial meteorological data and the second adjacent initial meteorological data of the abnormal fluctuation node;

[0080] The determination module is used to analyze the first adjacent initial meteorological data and the second adjacent initial meteorological data to determine the corresponding first abnormal fluctuation coefficient and second abnormal fluctuation coefficient;

[0081] The determination module is used for marking the abnormal fluctuation node as a classifiable node when the first abnormal fluctuation coefficient and the second abnormal fluctuation coefficient meet a first preset condition;

[0082] The determination module is used for eliminating the abnormal fluctuation node when the first abnormal fluctuation coefficient and the second abnormal fluctuation coefficient meet a second preset condition;

[0083] The determination module is used for marking the abnormal fluctuation node as a suspected node when the first abnormal fluctuation coefficient and the second abnormal fluctuation coefficient meet a third preset condition;

[0084] The determination module is used to count a first number of all suspected nodes, and if the first number is less than a preset number, transfer all suspected nodes to classifiable nodes;

[0085] The determination module is used to eliminate all suspected nodes if the first number is greater than or equal to the preset number;

[0086] The determination module is used to determine the meteorological data source selection package according to the classifiable nodes and the nodes without generating tags.

[0087] In this embodiment, the initial meteorological data includes satellite data, ground observation station data, radar data, sounding balloon data, etc.

[0088] In this embodiment, each node is connected to two initial meteorological data. Therefore, the abnormal fluctuation node has two adjacent initial meteorological data. The first adjacent initial meteorological data is the initial meteorological data on the left, and the second adjacent initial meteorological data is the initial meteorological data on the right.

[0089] In this embodiment, the first abnormal fluctuation coefficient and the second abnormal fluctuation coefficient may be determined based on a pre-selected trained abnormal fluctuation coefficient model.

[0090] In this embodiment, the first preset condition means that the first abnormal fluctuation coefficient and the second abnormal fluctuation coefficient are both less than or equal to the preset abnormal fluctuation coefficient.

[0091] In this embodiment, the second preset condition means that both the first abnormal fluctuation coefficient and the second abnormal fluctuation coefficient are greater than the preset abnormal fluctuation coefficient.

[0092] In this embodiment, the third preset condition means that the first abnormal fluctuation coefficient is greater than the preset abnormal fluctuation coefficient, and the second abnormal fluctuation coefficient is less than or equal to the preset abnormal fluctuation coefficient, or the first abnormal fluctuation coefficient is less than or equal to the preset abnormal fluctuation coefficient, and the second abnormal fluctuation coefficient is greater than the preset abnormal fluctuation coefficient.

[0093] The beneficial effect of the above technical solution is that the present invention determines the meteorological data source selection package according to the classifiable nodes and the nodes without generating marks, which can lay a foundation for the selection of meteorological data sources and provide a reliable selection basis.

[0094] In some embodiments of the present application, the determining module is used to:

[0095] The determination module is used to construct time series meteorological data based on the collection time of the initial meteorological data;

[0096] The determination module is used to divide the time series data into a plurality of data segments according to a sliding window mechanism, each data segment containing a predetermined number of continuous data points;

[0097] The determination module is used to calculate the volatility index of each data segment and compare the volatility index with a preset volatility index;

[0098] The determination module is used to determine whether the initial meteorological data chain has an abnormal fluctuation node if the volatility index is greater than or equal to the preset volatility index.

[0099] In this embodiment, the time series data is constructed based on the collection time of the initial meteorological data, which means that the data is arranged in chronological order, reflecting the characteristics of meteorological parameters changing over time.

[0100] In this embodiment, the entire time series data is divided into multiple data segments using a sliding window mechanism. Each data segment contains a predetermined number of continuous data points. For example, if the sliding window size is set to 5 minutes, each data segment will contain continuous data points within these 5 minutes.

[0101] In this embodiment, for each data segment, its volatility index is calculated. The volatility index is a statistic that measures the degree of change of data within the segment, and can be a standard deviation, variance or other numerical values ​​that measure volatility.

[0102] In this embodiment, the calculated volatility index of each data segment is compared with a preset volatility index threshold value. The preset value is a predefined standard used to determine whether the fluctuation of data is within a normal range.

[0103] In this embodiment, if the volatility index of a data segment is greater than or equal to the preset volatility index, it is considered that the data segment has abnormal fluctuations. The beneficial effect of the above technical solution is: by analyzing the volatility of each data segment in the time series data and comparing it with the preset threshold, possible abnormal data segments can be identified. This method helps to screen out inaccurate data that may be caused by equipment failure, data collection errors or other reasons, thereby ensuring the accuracy and reliability of meteorological data analysis.

[0104] In some embodiments of the present application, the first computing module is used to:

[0105] The first calculation module is used to identify the correlation between various attributes in the meteorological data based on the Pearson correlation coefficient;

[0106] The first calculation module is used to sort all the association degrees by numerical value to obtain an association degree set;

[0107] The first calculation module is used to select a first degree of association and a second degree of association from the degree of association set, and generate a high-association set according to the degree of association between the maximum degree of association in the degree of association set and the first degree of association;

[0108] The first calculation module is used to generate a low correlation set according to the correlation between the minimum correlation in the correlation set and the second correlation;

[0109] The first calculation module is used to generate a middle association set according to the association degree between the first association degree and the second association degree in the association degree set;

[0110] The data contribution corresponding to the meteorological data is calculated according to the high correlation set, the low correlation set and the medium correlation set.

[0111] In this embodiment, the attributes include temperature, humidity, wind speed, etc.

[0112] The beneficial effect of the above technical solution is that the present invention calculates the data contribution corresponding to the meteorological data according to the high correlation set, the low correlation set and the medium correlation set, and can provide reliable data support for calculating the selection value of the meteorological data source in the meteorological data source selection package.

[0113] In some embodiments of the present application, the first computing module is used to:

[0114] The first calculation module is used to calculate the data contribution corresponding to the meteorological data according to the following formula:

[0115]

[0116] Among them, H is the data contribution corresponding to the meteorological data, a1 is the weight corresponding to the high correlation set, m is the number of correlations in the high correlation set, ki is the i-th correlation in the high correlation set, J1 is the first correlation, a2 is the weight corresponding to the low correlation set, n is the number of correlations in the low correlation set, J2 is the second correlation, kj is the j-th correlation in the low correlation set, and h is the calculation coefficient of the data contribution.

[0117] In some embodiments of the present application, the first computing module is used to:

[0118] The first calculation module is used to count the number of associations in the association set;

[0119] The first calculation module is used to pre-set a first preset number and a second preset number;

[0120] The first calculation module is used to preset a first preset calculation coefficient h1, a second preset calculation coefficient h2, and a third preset calculation coefficient h3, and 0.8

[0121] The first calculation module is used for setting the calculation coefficient of the data contribution to the first preset calculation coefficient h1 when the number is less than the first preset number;

[0122] ​The first calculation module is used for setting the calculation coefficient of the data contribution to the second preset calculation coefficient h2 when the number is greater than or equal to the first preset number and less than the second preset number;

[0123] The first calculation module is used to set the calculation coefficient of the data contribution to the third preset calculation coefficient h3 when the number is greater than or equal to the second preset number.

[0124] In this embodiment, the first preset number is smaller than the second preset number.

[0125] The beneficial effect of the above technical solution is: the present invention sets the calculation coefficient of the data contribution according to the relationship between the number of associations in the association set, the first preset number, and the second preset number, thereby ensuring the calculation accuracy of the data contribution, realizing dynamic adjustment, and avoiding large errors.

[0126] In some embodiments of the present application, the second computing module is used to:

[0127] The second calculation module is used to perform numerical analysis on all data contributions, extract the same data contribution from the data contribution sequence, and obtain multiple data contribution sequences;

[0128] The second calculation module is used for counting a first quantity Q1 of a statistical contribution sequence;

[0129] The second calculation module is used to extract a data contribution from all data contribution sequences respectively, and calculate the first data contribution and value R1;

[0130] The second calculation module is used to obtain a preset data contribution, eliminate all data contribution sequences that are less than the preset data contribution, and count a second number Q2 of the remaining data contribution sequences;

[0131] The second calculation module is used to extract a data contribution from the remaining data contribution sequence respectively, and calculate the second data contribution and value R2;

[0132] The selection value of the meteorological data source in the meteorological data source selection package is calculated according to the first quantity Q1, the second quantity Q2, the first data contribution and value R1, and the second data contribution and value R2.

[0133] In this embodiment, if the data contribution is {0.3, 0.3, 0.4, 0.6, 0.7, 0.7, 0.8, 0.8}, then the data contribution sequence is {0.3, 0.3}, {0.7, 0.7}, {0.8, 0.8}, the first number Q1 is 3, and one data contribution is extracted from all the data contribution sequences, that is, 0.3, 0.7, 0.8, and the first data contribution sum value R1 = 0.3 + 0.7 + 0.8. If the preset data contribution is 0.5, the remaining data contribution sequence is {0.7, 0.7}, {0.8, 0.8}, and the second number Q2 of the remaining data contribution is 2, and one data contribution is extracted from the remaining data contribution sequence, that is, 0.7, 0.8, and the second data contribution sum value R2 = 0.7 + 0.8.

[0134] The beneficial effect of the above technical solution is: the present invention calculates the selection value of the meteorological data source in the meteorological data source selection package according to the first quantity Q1, the second quantity Q2, the first data contribution and value R1, and the second data contribution and value R2, so as to realize the intelligent selection of the meteorological data source, improve the accuracy and real-time performance of meteorological forecasts, reduce labor costs, and is of great significance to enhancing the ability to respond to extreme weather events.

[0135] In some embodiments of the present application, the second computing module is used to:

[0136] The second calculation module is used to calculate the selection value of the meteorological data source in the meteorological data source selection package according to the following formula:

[0137]

[0138] Among them, S is the selection value of the meteorological data source in the meteorological data source selection package, and t is the preset data contribution.

[0139] In order to further explain the technical idea of ​​the present invention, the technical solution of the present invention is now described in combination with specific application scenarios.

[0140] Correspondingly, such as Figure 2 As shown, the present application also provides an intelligent meteorological data source selection method, comprising:

[0141] Determine a plurality of meteorological data sources to be selected, obtain initial meteorological data of each meteorological data source to be selected, and determine a plurality of meteorological data source selection packages, wherein the meteorological data source selection packages include meteorological data sources and meteorological data;

[0142] Parsing the meteorological data source selection package, and calculating the data contribution corresponding to the meteorological data in the meteorological data source selection package;

[0143] Performing numerical analysis on all data contributions, constructing multiple data contribution sequences based on the numerical analysis results, and calculating the selection value of the meteorological data source in the meteorological data source selection package based on the data contribution sequences;

[0144] All selection values ​​are compared, and the meteorological data source corresponding to the maximum selection value is used as the target meteorological data source.

[0145] In the description of the above embodiments, specific features, structures, materials or characteristics may be combined in a suitable manner in any one or more embodiments or examples.

[0146] Although the present invention has been described above with reference to the embodiments, various modifications may be made thereto and parts thereof may be replaced with equivalents without departing from the scope of the present invention. In particular, as long as there is no structural conflict, the various features in the embodiments disclosed by the present invention may be used in combination with each other in any manner, and the fact that these combinations are not fully described in this specification is only for the sake of omitting space and saving resources.

[0147] Those skilled in the art can understand that the above are only preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions recorded in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent meteorological data source selection system, characterized in that: include: A data determination module, used to determine a plurality of meteorological data sources to be selected, obtain initial meteorological data of each meteorological data source to be selected, and determine a plurality of meteorological data source selection packages, wherein the meteorological data source selection packages include meteorological data sources and meteorological data; A first calculation module, used to parse the meteorological data source selection package and calculate the data contribution corresponding to the meteorological data in the meteorological data source selection package; A second calculation module is used to perform numerical analysis on all data contributions, construct multiple data contribution sequences based on the numerical analysis results, and calculate the selection value of the meteorological data source in the meteorological data source selection package based on the data contribution sequences; The data selection module is used to compare all selection values ​​and take the meteorological data source corresponding to the maximum selection value as the target meteorological data source.

2. The intelligent meteorological data source selection system according to claim 1 is characterized in that: The determination module is used for: Building an initial meteorological data chain according to the initial meteorological data of the meteorological data source to be selected; Performing abnormal fluctuation analysis on the initial meteorological data chain to determine whether there is an abnormal fluctuation node, and if not, determining a meteorological data source selection package according to the initial meteorological data chain; If yes, determine the location of the abnormal fluctuation node, and determine the first adjacent initial meteorological data and the second adjacent initial meteorological data of the abnormal fluctuation node; Analyze the first adjacent initial meteorological data and the second adjacent initial meteorological data to determine a corresponding first abnormal fluctuation coefficient and a second abnormal fluctuation coefficient; When the first abnormal fluctuation coefficient and the second abnormal fluctuation coefficient meet a first preset condition, marking the abnormal fluctuation node as a classifiable node; When the first abnormal fluctuation coefficient and the second abnormal fluctuation coefficient meet the second preset condition, the abnormal fluctuation node is eliminated; When the first abnormal fluctuation coefficient and the second abnormal fluctuation coefficient meet a third preset condition, marking the abnormal fluctuation node as a suspected node; Counting a first number of all suspected nodes, and if the first number is less than a preset number, transferring all suspected nodes to classifiable nodes; If the first number is greater than or equal to the preset number, all suspected nodes are eliminated; The meteorological data source selection package is determined based on the classifiable nodes and the nodes that have not generated tags.

3. The intelligent meteorological data source selection system according to claim 2 is characterized in that: The determining module is also used for: Based on the collection time of the initial meteorological data, construct time series meteorological data; According to the sliding window mechanism, the time series data is divided into multiple data segments, each of which contains a predetermined number of consecutive data points; Calculating a volatility index for each data segment, and comparing the volatility index with a preset volatility index; If the volatility index is greater than or equal to the preset volatility index, it is determined that there is an abnormal volatility node in the initial meteorological data chain.

4. The intelligent meteorological data source selection system according to claim 1 is characterized in that: The first calculation module is used for: Identify the correlation between the attributes in the meteorological data based on the Pearson correlation coefficient; Sort all the correlations by numerical value to obtain a correlation set; Selecting a first degree of association and a second degree of association from the degree of association set, and generating a high degree of association set according to the degree of association between the maximum degree of association in the degree of association set and the first degree of association; generating a low association set according to the association between the minimum association in the association set and the second association; generating a middle association set according to the association degree between the first association degree and the second association degree in the association degree set; The data contribution corresponding to the meteorological data is calculated according to the high correlation set, the low correlation set and the medium correlation set.

5. The intelligent meteorological data source selection system according to claim 4 is characterized in that: The first calculation module is also used for: The data contribution corresponding to the meteorological data is calculated according to the following formula: Among them, H is the data contribution corresponding to the meteorological data, a1 is the weight corresponding to the high correlation set, m is the number of correlations in the high correlation set, ki is the i-th correlation in the high correlation set, J1 is the first correlation, a2 is the weight corresponding to the low correlation set, n is the number of correlations in the low correlation set, J2 is the second correlation, kj is the j-th correlation in the low correlation set, and h is the calculation coefficient of the data contribution.

6. The intelligent meteorological data source selection system according to claim 5, characterized in that: The first calculation module is also used for: The number of correlations in the correlation set in the statistics; Presetting a first preset number and a second preset number; The first preset calculation coefficient h1, the second preset calculation coefficient h2, and the third preset calculation coefficient h3 are preset, and 0.8 <h1<h2<h3<1.2; When the number is less than the first preset number, the calculation coefficient of the data contribution is set to the first preset calculation coefficient h1; When the number is greater than or equal to the first preset number and less than the second preset number, the calculation coefficient of the data contribution is set to the second preset calculation coefficient h2; When the number is greater than or equal to the second preset number, the calculation coefficient of the data contribution is set to the third preset calculation coefficient h3.

7. The intelligent meteorological data source selection system according to claim 1 is characterized in that: The second calculation module is used for: Performing numerical analysis on all data contributions, extracting the same data contribution from the data contribution sequence, and obtaining multiple data contribution sequences; The first number Q1 of the statistical data contribution sequence; Extracting a data contribution from each of all data contribution sequences, and calculating a first data contribution and value R1; Obtaining a preset data contribution, eliminating all data contribution sequences that are less than the preset data contribution, and counting a second number Q2 of remaining data contribution sequences; Extracting a data contribution from each of the remaining data contribution sequences, and calculating a second data contribution and a value R2; The selection value of the meteorological data source in the meteorological data source selection package is calculated according to the first quantity Q1, the second quantity Q2, the first data contribution and value R1, and the second data contribution and value R2.

8. The intelligent meteorological data source selection system according to claim 7, characterized in that: The second calculation module is also used for: The selection value of the meteorological data source in the meteorological data source selection package is calculated according to the following formula: Among them, S is the selection value of the meteorological data source in the meteorological data source selection package, and t is the preset data contribution.

9. An intelligent meteorological data source selection method, applied to the intelligent meteorological data source selection system according to any one of claims 1 to 8, characterized in that: include: Determine a plurality of meteorological data sources to be selected, obtain initial meteorological data of each meteorological data source to be selected, and determine a plurality of meteorological data source selection packages, wherein the meteorological data source selection packages include meteorological data sources and meteorological data; Parsing the meteorological data source selection package, and calculating the data contribution corresponding to the meteorological data in the meteorological data source selection package; Performing numerical analysis on all data contributions, constructing multiple data contribution sequences based on the numerical analysis results, and calculating the selection value of the meteorological data source in the meteorological data source selection package based on the data contribution sequences; All selection values ​​are compared, and the meteorological data source corresponding to the maximum selection value is used as the target meteorological data source.

Images