Geographic Information Acquisition Method and System Based on GIS

Abstract

The present invention relates to the field of data processing technology, and in particular to a geographic information acquisition method and system based on GIS. The method comprises the steps of: taking the length of a data segment obtained within a single acquisition time as the length of an initial filtering window of a data point; recording a cluster of data points in a cluster of data segments corresponding to the initial filtering window and its left and right adjacent data segments, and including both the data segment and any other adjacent data segment as a diversity clustering cluster, and obtaining the trend characteristics of the initial filtering window by the proportion of the diversity clustering cluster in the number of all clusters; obtaining the random characteristics of the initial filtering window by the average value of the data points in the data segment and the data segment; calculating the length of the filtering window of the data point; and using the length of the filtering window of each data point in the SG filtering algorithm for filtering processing to achieve the acquisition of geographic information, which can effectively improve the accuracy of geographic information acquisition.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a geographic information acquisition method and system based on GIS. Background Art

[0002] Geographic Information System (GIS) is a technical platform that integrates a variety of geographic data and information. The geographic data obtained through GIS can be used to conduct spatiotemporal analysis of meteorological data, reveal the trends and laws of climate change, predict future climate conditions, and timely detect and warn of disastrous weather such as floods, typhoons, and heavy rains, providing decision-making support for the formulation of effective response strategies.

[0003] There are many applications and studies on the use of GIS for meteorological early warning in the prior art. For example, the patent application document with publication number CN117826275A discloses a meteorological monitoring and early warning system based on GIS. The input end of the meteorological information acquisition module of the system is connected to the meteorological monitoring sensor group, and the output end of the meteorological information acquisition module is connected to the main control module through the meteorological data transmission unit. The main control module is connected to the meteorological data aggregation unit and the early warning unit. The main control module is connected to the meteorological information monitoring module through the data transmission module. The meteorological information monitoring module is provided with a meteorological information database, a meteorological data display unit and a meteorological remote display unit, which can realize real-time collection and monitoring of meteorological information.

[0004] The above-mentioned prior art does not take into account the impact of noise data caused by various external factors when implementing GIS-based meteorological monitoring and early warning. It directly obtains the meteorological information database through the meteorological information monitoring module to obtain the monitoring results, which may lead to low accuracy of the monitoring results due to noise data.

[0005] Based on this, how to effectively improve the accuracy of geographic information data acquisition is an urgent problem to be solved by technical personnel in this field. Summary of the invention

[0006] In order to solve the technical problem of how to effectively improve the accuracy of obtaining geographic information data, the present invention provides a geographic information acquisition method and system based on GIS.

[0007] In the first aspect, the present invention provides a method for obtaining geographic information based on GIS, which adopts the following technical solution:

[0008] The method for obtaining geographic information based on GIS includes the following steps:

[0009] Acquire multiple data points in a meteorological data time series, and use the length of a data segment obtained within a single acquisition time as the length of an initial filtering window for the data point; obtain the clustering result of the data segment corresponding to the initial filtering window and its left and right adjacent data segments, record the clustering clusters in which the data points in the clustering clusters simultaneously contain the data points in the data segment and any other adjacent data segments as diversity clustering clusters, and obtain the trend characteristics of the initial filtering window by the proportion of diversity clustering clusters in the number of all clustering clusters; obtain the first fluctuation feature by the absolute value of the difference between the data point in the data segment and the mean of the data segment, obtain the second fluctuation feature by the ratio of the first fluctuation feature to the extreme difference of the data segment, and use the ratio of the number of data points in the data segment whose second fluctuation feature is greater than the mean of the second fluctuation feature of the data segment to the total number of data points in the data segment as the random feature of the initial filtering window; calculate the length of the filtering window for the data point: ;

[0010] In the formula, represents the length of the filtering window for the data points, represents the length of the initial filtering window, represents the random characteristics of the initial filtering window, represents the trend characteristics of the initial filtering window, Indicates the round-up symbol. represents a linear normalization function; in the SG filtering algorithm, the length of the filtering window of each data point is used to perform filtering processing to achieve the acquisition of geographic information.

[0011] When acquiring geographic information data, the present invention takes into account that noise data will affect the accuracy of data acquisition. Therefore, by analyzing the data consistency and data fluctuation of the data segment corresponding to the initial filtering window of the data point, the initial filtering window of the data point is accurately adjusted to accurately implement filtering and denoising of the data point, thereby effectively improving the accuracy of geographic information acquisition.

[0012] According to the GIS-based geographic information acquisition method provided by the present invention, the acquisition of multiple data points in a meteorological data time series sequence includes: collecting meteorological data by presetting a single collection time, taking the meteorological data collected each time as a data point, and performing preprocessing to obtain the meteorological data time series sequence.

[0013] The present invention takes into account the possibility of missing data in the collected original data, which may affect the subsequent data processing. Therefore, the meteorological data is pre-processed to effectively improve the overall data quality and facilitate subsequent data processing.

[0014] According to the GIS-based geographic information acquisition method provided by the present invention, the clustering result of the data segment corresponding to the initial filtering window and its left and right adjacent data segments includes: obtaining the left and right adjacent data segments of the data segment, processing the data points in the data segment and its left and right adjacent data segments by a clustering algorithm, and obtaining multiple cluster clusters.

[0015] According to the GIS-based geographic information acquisition method provided by the present invention, the trend characteristics of the initial filtering window are obtained by the proportion of the diversity clustering clusters in the number of all clustering clusters, including: using the proportion of the number of diversity clustering clusters in the number of all clustering clusters as the exponential input of an exponential function with base e to obtain an exponential function value, and subtracting the exponential function value from 1 to obtain the trend characteristics of the initial filtering window.

[0016] The present invention obtains the proportion of diverse clusters to reflect the degree of data overlap between different data segments. When the proportion is high, it means that there are more common features or patterns between the data segments, so the proportion of data categories in each cluster can be analyzed based on this to accurately obtain the trend of the data segment.

[0017] According to the GIS-based geographic information acquisition method provided by the present invention, the length of the filter window of each data point is used for filtering processing in the SG filtering algorithm, including: obtaining the filter window of the data point based on the length of the filter window; using the least squares method to fit all data points in the filter window to obtain a polynomial; and using the fitting value of the polynomial for each data point in the filter window as the filter value of the data point.

[0018] The present invention takes into account that the SG filtering algorithm can retain some data features while filtering and denoising the data. Therefore, the meteorological data time series is filtered and denoised by the SG filtering algorithm, thereby improving the overall accuracy and effectiveness of the data.

[0019] According to the GIS-based geographic information acquisition method provided by the present invention, the acquisition of geographic information includes: storing the time series of meteorological data obtained after the filtering process into the meteorological information database of the GIS.

[0020] According to the GIS-based geographic information acquisition method provided by the present invention, the acquisition of geographic information further includes: performing abnormal monitoring and early warning on the meteorological data time series sequence obtained after the filtering process.

[0021] The present invention takes into account that the meteorological data after filtering and denoising contains important meteorological information, and therefore monitors and warns the meteorological information, so that necessary preventive measures can be taken in advance to reduce safety hazards and losses.

[0022] In a second aspect, the present invention provides a geographic information acquisition system based on GIS, which adopts the following technical solution:

[0023] The GIS-based geographic information acquisition system comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned GIS-based geographic information acquisition method is implemented.

[0024] By adopting the above technical solution, the above GIS-based geographic information acquisition method is generated into a computer program and stored in a memory to be loaded and executed by a processor, so that a terminal device is made according to the memory and the processor for easy use.

[0025] The present invention has the following technical effects:

[0026] Based on the above technical solution, when realizing the acquisition of geographic information data, the present invention can accurately adjust the initial filtering window of the data point by analyzing the data consistency and data fluctuation of the data segment corresponding to the initial filtering window of the data point, and accurately realize the filtering and denoising of the data point, thereby effectively improving the accuracy of geographic information acquisition. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0028] Figure 1 A flowchart of a method for acquiring geographic information based on GIS is provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0030] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0031] It should be noted that in the process of meteorological data collection, there may be many external influencing factors that cause noise data in the collected meteorological data, such as the obstruction of the meteorological station by buildings and trees, etc. Therefore, the collected meteorological data needs to be filtered.

[0032] SG filtering (Savitzky-Golay filtering) is a commonly used digital signal processing technology. This algorithm can maintain the characteristics and shape of the signal, such as peaks and inflection points, while smoothing the data. It is suitable for filtering meteorological data. However, meteorological data varies in various forms. For example, temperature and precipitation may show a clear upward or downward trend over a long period of time, and there may also be natural random fluctuations, such as sudden local meteorological phenomena such as thunderstorms and storms. SG filtering uses a self-set filtering window, which cannot take into account the trend and randomness of meteorological data, resulting in low filtering accuracy.

[0033] Based on this, the embodiment of the present invention discloses a method for obtaining geographic information based on GIS, which analyzes the trend and randomness of meteorological data in the initial filtering window of data points, adjusts the initial filtering window to achieve accurate filtering, and thus accurately obtains meteorological geographic information data. Figure 1 As shown, Figure 1 A flowchart of a method for obtaining geographic information based on GIS is provided in an embodiment of the present invention. The method includes the following steps S1 to S4.

[0034] S1: Acquire multiple data points in the meteorological data time series, and use the length of the data segment obtained within a single acquisition time as the length of the initial filtering window of the data point.

[0035] For example, in an embodiment of the present invention, multiple data points in a time series sequence of meteorological data are obtained, including: collecting meteorological data by presetting a single collection time, taking each collected meteorological data as a data point, and performing preprocessing to obtain a time series sequence of meteorological data.

[0036] The meteorological data may be temperature, humidity, air pressure, wind speed, etc., which may be set according to actual needs, and the embodiments of the present invention do not impose too many restrictions on this. The preprocessing may be data format conversion, data cleaning, etc., which may be set according to actual needs, and the embodiments of the present invention do not impose too many restrictions on this.

[0037] Among them, the single collection time can be preset to 1 hour, the collection frequency can be set to once per second, and the single collection time and collection frequency can be set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0038] It is understandable that in order to facilitate subsequent data processing, the single data collection duration and collection frequency within a period of time can remain unchanged.

[0039] Take an example to illustrate the setting of the initial filter window: if the number of data points collected in a single collection time is 3600, the length of the initial filter window of all data points is 3600.

[0040] After the length of the initial filtering window of the data point is obtained based on the above method, the initial filtering window of each data point can be obtained based on the length of the initial filtering window.

[0041] For example, in the embodiment of the present invention, when obtaining the filtering window of the data point, the following two possible implementation methods are included:

[0042] In a possible implementation, when obtaining a filtering window of a data point, a number of data points may be equally obtained on both sides of the data point with the current data point as the center, and the current data point and the data points on both sides thereof together constitute the filtering window of the data point.

[0043] In this way, the embodiment of the present invention can more comprehensively consider the data situation around the current data point by acquiring equal amounts of data points on both sides of the data point to form a filtering window, without losing the relative relationship between the data points, which helps to maintain the integrity and accuracy of the data.

[0044] In another possible implementation, when obtaining a filtering window of a data point, the current data point may be used as the end point, and several data points may be obtained in the historical data. The current data point and the data points in the historical data together constitute the filtering window of the data point.

[0045] In this way, the embodiment of the present invention can fully utilize existing data resources by acquiring a number of data points from historical data to form a filtering window, without waiting for subsequent data, thereby effectively improving the efficiency and accuracy of data filtering.

[0046] It can be understood that the initial filtering window of a data point obtained based on any of the above-mentioned methods for obtaining the initial filtering window includes the data point itself.

[0047] To facilitate understanding, the embodiment of the present invention continues to be described by taking the first possible implementation manner as an example.

[0048] S2: Get the clustering results of the data segment corresponding to the initial filtering window and its left and right adjacent data segments, record the clusters whose data points contain both the data segment and the data points in any other adjacent data segments as diversity clusters, and obtain the trend characteristics of the initial filtering window by the proportion of diversity clusters in the number of all clusters.

[0049] It should be noted that meteorological data may show regular changes or data fluctuations over a period of time. In order to obtain the data trend in the filtering window of the data point, the data clustering results between the data segment corresponding to the filtering window and its left and right adjacent data segments can be obtained. By clustering the data segment of the initial filtering window with its adjacent data segments, the correlation and changing trend of the data in different time periods can be revealed.

[0050] By way of example, in an embodiment of the present invention, the clustering results of the data segment corresponding to the initial filtering window and its left and right adjacent data segments are obtained, including: obtaining the left and right adjacent data segments of the data segment, processing the data points in the data segment and its left and right adjacent data segments through a clustering algorithm, and obtaining multiple cluster clusters.

[0051] The clustering algorithm may be k-means clustering, density-based clustering method, etc., which may be set according to actual needs, and the embodiment of the present invention does not impose too many restrictions here. The specific steps of obtaining the clustering result by the corresponding clustering algorithm can be implemented by the existing technology, and the embodiment of the present invention will not be repeated here.

[0052] Based on the above steps, the data segment and its left and right adjacent data segments are clustered to obtain multiple clusters, and the proportion of diverse clusters actually reflects the degree of data overlap between different data segments. When the proportion is high, it means that there are many common features or patterns between the data segments. Analyzing the proportion of data categories in each cluster can accurately obtain the trend of the data segment.

[0053] By way of example, in an embodiment of the present invention, the trend characteristics of the initial filtering window are obtained by the proportion of the diversity clustering clusters in the number of all clustering clusters, including: taking the proportion of the number of diversity clustering clusters in the number of all clustering clusters as the exponential input of an exponential function with base e to obtain an exponential function value, and subtracting the exponential function value from 1 to obtain the trend characteristics of the initial filtering window.

[0054] Specifically, the trend characteristics of the data segment corresponding to the initial filtering window can be determined by referring to the following relationship:

[0055] ;

[0056] In the formula, represents the trend characteristics of the initial filtering window, represents the exponential function with base e, Indicates the number of diverse clusters in a data segment and its left and right adjacent data segments. The total number of clusters of a data segment and its left and right adjacent data segments.

[0057] It can be understood that the trend characteristics of the initial filtering window obtained based on the above method are also the trend characteristics of the data segment corresponding to the initial filtering window of the data point.

[0058] S3: The first fluctuation feature is obtained by the absolute value of the difference between the data point in the data segment and the mean of the data segment, the second fluctuation feature is obtained by the ratio of the first fluctuation feature to the range of the data segment, and the ratio of the number of data points in the data segment whose second fluctuation feature is greater than the mean of the second fluctuation feature of the data segment to the total number of data points in the data segment is used as the random feature of the initial filtering window.

[0059] It should be noted that when obtaining the random characteristics of the initial filtering window, the degree of data fluctuation in the data segment corresponding to the initial filtering window can be obtained. The higher the degree of fluctuation, the higher the randomness of the data in the current data segment, and the higher the possibility of sudden local meteorological phenomena in the current data segment.

[0060] For example, in an embodiment of the present invention, when determining the second fluctuation characteristic of a data point, the first fluctuation characteristic of the data point can be obtained by the absolute value of the difference between the data point in the data segment and the mean of the data segment, and then the second fluctuation characteristic of the data point can be obtained by the ratio of the first fluctuation characteristic to the range of the data segment.

[0061] For example, when determining the second fluctuation feature of each data point in the data segment, the following relationship may be specifically referred to:

[0062] ;

[0063] In the formula, represents the second fluctuation characteristic of the i-th data point, represents the data value of the i-th data point, Represents the mean value of each data point in the data segment. Indicates the maximum data value in the data segment. Indicates the minimum data value in the data segment. represents the first fluctuation feature of the i-th data point, Indicates that the data segment is extremely poor. Represents the absolute value symbol.

[0064] In the above formula, the deviation degree between the data point and the mean of the data segment can be obtained by obtaining the first fluctuation feature. The larger the first fluctuation feature, the greater the deviation degree of the data point from the whole, and the greater the fluctuation degree. The range of the data segment is used as the oscillation range of the data point. Within this range, the deviation of the data point from the mean and the oscillation range of the entire data segment are compared to obtain the relative degree of fluctuation of the data point relative to the entire data segment.

[0065] It can be understood that the data points in the data segment whose second fluctuation feature is greater than the mean of the second fluctuation feature of the data segment are data points with large fluctuations. The higher the proportion of such data points in all data points, the greater the degree of data fluctuation in the data segment, and the higher the random characteristics of the corresponding initial filtering window.

[0066] After respectively acquiring the trend characteristics and random characteristics of the data segment corresponding to the initial filtering window based on the above steps, the length of the initial filtering window can be adjusted based on the trend characteristics and random characteristics of the initial filtering window.

[0067] S4: Calculate the length of the filter window of the data point, and use the length of the filter window of each data point to perform filtering processing in the SG filtering algorithm to achieve the acquisition of geographic information.

[0068] It should be noted that, based on the above steps, the trend and randomness of the data segment corresponding to the initial filtering window can be obtained respectively. The trend indicates the consistency between the data segment and the surrounding data segments, and the randomness describes the degree of data fluctuation in the data segment. The trend of the data segment corresponding to the initial filtering window is greater than the randomness, which means that the more obvious the trend of the data segment is, the larger the initial filtering window needs to be adjusted to quickly smooth the data and improve efficiency; the trend of the data segment is less than the randomness, which means that the more obvious the randomness of the data segment is, the smaller the initial filtering window needs to be adjusted to avoid smoothing such random changes; the trend of the data segment is equal to the randomness, which means that the trend and randomness in the initial filtering window of the data segment are in a relatively balanced state, and there is no need to adjust the size of the filtering window.

[0069] For example, in the embodiment of the present invention, the length of the filtering window of the data point is determined, and specifically, the following relationship can be referred to:

[0070] ;

[0071] In the formula, represents the length of the filtering window for the data points, represents the length of the initial filtering window, represents the random characteristics of the initial filtering window, represents the trend characteristics of the initial filtering window, Indicates the round-up symbol. represents the linear normalization function.

[0072] In the above formula, Indicates the degree of adjustment of the initial filter window. The greater the random characteristics and trend characteristics of the initial filter window, the greater the degree of adjustment of the initial filter window.

[0073] By adjusting the size of the initial filter window of the data point based on the above method, the length of the filter window actually required for each data point can be accurately obtained. In the SG filtering algorithm, the length of the filter window of the data point can be used to achieve filtering and denoising of the data point.

[0074] By way of example, in an embodiment of the present invention, the length of the filter window of each data point is used for filtering processing in the SG filtering algorithm, including: obtaining the filter window of the data point based on the length of the filter window; using the least squares method to fit all data points in the filter window to obtain a polynomial; and using the fitting value of the polynomial for each data point in the filter window as the filter value of the data point.

[0075] The steps for implementing the filter window for obtaining data points are similar to the steps for implementing the initial filter window for obtaining data points, and are not described in detail in the embodiment of the present invention.

[0076] The specific steps of obtaining the filter value of each data point through the SG filtering algorithm can be implemented through the existing technology, and the embodiments of the present invention will not be described in detail here.

[0077] Based on the above method, filtering and denoising of all data points in the meteorological data time series can be achieved.

[0078] For example, in an embodiment of the present invention, the acquisition of geographic information is achieved, including: storing the time series of meteorological data obtained after filtering processing in a meteorological information database of a GIS.

[0079] In this way, the embodiment of the present invention stores the filtered and denoised meteorological data in a meteorological information database to achieve the acquisition of geographic information.

[0080] Filtering and denoising the meteorological data time series based on the above steps can effectively improve the overall quality of the data, so that abnormal monitoring and early warning of meteorological data can be accurately achieved based on this.

[0081] For example, in an embodiment of the present invention, the acquisition of geographic information is achieved, and then the method further includes: performing abnormal monitoring and early warning on the time series of meteorological data obtained after filtering.

[0082] Among them, the specific steps of performing abnormal monitoring and early warning on the meteorological data time series obtained after filtering can be achieved through existing technologies, and the embodiments of the present invention will not be described in detail here.

[0083] It can be seen that in an embodiment of the present invention, when acquiring geographic information data, multiple data points in a meteorological data time series sequence can be acquired, and the length of the data segment obtained within a single acquisition time is used as the length of the initial filtering window of the data point; the clustering results of the data segment corresponding to the initial filtering window and its left and right adjacent data segments are acquired, and the clustering clusters in which the data points in the clustering clusters simultaneously contain the data points in the data segment and any other adjacent data segments are recorded as diversity clustering clusters, and the trend characteristics of the initial filtering window are obtained by the proportion of diversity clustering clusters in the number of all clustering clusters; the first fluctuation feature is obtained by the absolute value of the difference between the data point in the data segment and the mean of the data segment, the second fluctuation feature is obtained by the ratio of the first fluctuation feature to the extreme difference of the data segment, and the ratio of the number of data points in the data segment whose second fluctuation feature is greater than the mean of the second fluctuation feature of the data segment to the total number of data points in the data segment is used as the random feature of the initial filtering window; the length of the filtering window of the data point is calculated; and the length of the filtering window of each data point is used in the SG filtering algorithm for filtering processing to achieve geographic information acquisition.

[0084] In this way, the embodiment of the present invention can accurately adjust the initial filtering window of the data point by analyzing the data consistency and data fluctuation of the data segment corresponding to the initial filtering window of the data point, accurately implement filtering and denoising of the data point, thereby effectively improving the accuracy of geographic information acquisition.

[0085] The embodiment of the present invention further discloses a geographic information acquisition system based on GIS, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the geographic information acquisition method based on GIS according to the present invention is implemented.

[0086] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0087] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM, a dynamic random access memory DRAM, a static random access memory SRAM, an enhanced dynamic random access memory EDRAM, a high bandwidth memory HBM, a hybrid memory cube HMC, etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0088] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0089] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for acquiring geographic information based on GIS, characterized in that: include: Acquire multiple data points in the meteorological data time series, and use the length of the data segment obtained within a single acquisition time as the length of the initial filtering window of the data point; Obtain the clustering results of the data segment corresponding to the initial filtering window and its left and right adjacent data segments, record the clusters whose data points in the clusters include both the data segment and data points in any other adjacent data segments as diversity clusters, and obtain the trend characteristics of the initial filtering window by the proportion of diversity clusters in the number of all clusters; A first fluctuation feature is obtained by the absolute value of the difference between a data point in the data segment and a mean value of the data segment, a second fluctuation feature is obtained by the ratio of the first fluctuation feature to the range of the data segment, and a ratio of the number of data points in the data segment whose second fluctuation feature is greater than the mean value of the second fluctuation feature of the data segment to the total number of data points in the data segment is used as a random feature of the initial filtering window; Calculate the length of the filtering window for the data point: ; In the formula, represents the length of the filtering window for the data points, represents the length of the initial filtering window, represents the random characteristics of the initial filtering window, represents the trend characteristics of the initial filtering window, Indicates the round-up symbol. represents the linear normalization function; In the SG filtering algorithm, the length of the filtering window of each data point is used to perform filtering processing to achieve the acquisition of geographic information.

2. The GIS-based geographic information acquisition method according to claim 1, characterized in that: The step of obtaining a plurality of data points in a time series of meteorological data includes: The meteorological data is collected by presetting a single collection time, and the meteorological data collected each time is taken as a data point, and preprocessing is performed to obtain the meteorological data time series sequence.

3. The GIS-based geographic information acquisition method according to claim 1, characterized in that: The obtaining of clustering results of the data segment corresponding to the initial filtering window and the left and right adjacent data segments thereof includes: The left and right adjacent data segments of the data segment are obtained, and the data points in the data segment and the left and right adjacent data segments are processed by a clustering algorithm to obtain a plurality of clusters.

4. The GIS-based geographic information acquisition method according to claim 1, characterized in that: The trend characteristics of the initial filtering window are obtained by calculating the proportion of the diversity clusters in the number of all clusters, including: The proportion of the number of the diversity clusters in the number of all clusters is used as the exponential input of an exponential function with e as the base to obtain an exponential function value, and the trend characteristics of the initial filtering window are obtained by subtracting the exponential function value from 1.

5. The GIS-based geographic information acquisition method according to claim 1, characterized in that: The filtering process using the length of the filtering window of each data point in the SG filtering algorithm includes: Acquire a filter window for the data point based on the length of the filter window; All data points in the filtering window are fitted using the least square method to obtain a polynomial; and the fitting value of the polynomial to each data point in the filtering window is used as the filtering value of the data point.

6. The GIS-based geographic information acquisition method according to claim 1, characterized in that: The method of obtaining geographic information comprises: The meteorological data time series obtained after the filtering process is stored in the meteorological information database of the GIS.

7. The GIS-based geographic information acquisition method according to claim 6, characterized in that: The method of obtaining geographic information further comprises: The meteorological data time series obtained after the filtering process is subjected to abnormal monitoring and early warning.

8. The GIS-based geographic information acquisition system is characterized by: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the GIS-based geographic information acquisition method according to any one of claims 1 to 7 is implemented.

Images