Method, system, storage medium and electronic device for identifying hydrological disaster affected areas

Abstract

The present invention relates to the technical field of big data processing, and specifically discloses a method, system, storage medium and electronic device for identifying a hydrological disaster-affected area. The method includes: constructing a sub-document database corresponding to the target hydrological disaster according to a set of professional terms corresponding to the target hydrological disaster; accurately matching each area name in the sub-document database, marking and screening the appearance characteristics of each area name in the sub-document database, and obtaining each screened area name; when the multiple geographic data corresponding to each screened area name meet the preset recognition accuracy, each screened area name is determined as the disaster-affected area corresponding to the target hydrological disaster. The present invention can reduce the time consumption of hydrological disaster area identification and overcome the problem of large workload, improve the efficiency of hydrological disaster area identification, and provide important reference value for future hydrological disaster risk cause analysis and comprehensive management.

Description

Background Art

[0002] The occurrence of specific hydrological disasters is caused by multiple factors such as regional climate, hydrology, and human activities. Locating the occurrence points of hydrological disasters on a global scale is of great significance for large-scale hydrological forecasting, disaster response, and comprehensive management. In traditional methods, the identification of areas affected by hydrological disasters is highly dependent on the experience of practitioners. However, with the continuous improvement of the monitoring network and the explosive growth of research information, it is difficult to fully and comprehensively explain the distribution characteristics of specific hydrological problems in geographic space by relying on the experience summary of a single expert or a team of scholars. This brings challenges to large-scale hydrological analysis, especially the analysis of hydrological disaster problems on a global scale.

[0003] Therefore, it is urgent to provide a technical solution to solve the above problems. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a method, system, storage medium and electronic device for identifying areas affected by hydrological disasters.

[0005] In a first aspect, the present invention provides a method for identifying areas affected by hydrological disasters, and the technical solution of the method is as follows:

[0006] According to the professional term set corresponding to the target hydrological disaster, a sub-document database corresponding to the target hydrological disaster is constructed;

[0007] Precisely matching each region name in the sub-document database, marking and filtering the appearance features of each region name in the sub-document database, and obtaining each filtered region name;

[0008] When the multiple geographic data corresponding to each filtered regional name meet the preset recognition accuracy, each filtered regional name is determined as the disaster-stricken area corresponding to the target hydrological disaster.

[0009] The beneficial effects of the method for identifying the area affected by hydrological disasters of the present invention are as follows:

[0010] The method of the present invention can reduce the time consumption of hydrological disaster area identification and overcome the problem of heavy workload, thereby improving the efficiency of hydrological disaster area identification and providing important reference value for future analysis of the causes of hydrological disaster risks and comprehensive management.

[0011] On the basis of the above scheme, the method for identifying the area affected by hydrological disasters of the present invention can also be improved as follows.

[0012] In an optional manner, the step of constructing a sub-document database corresponding to the target hydrological disaster according to the set of professional terms corresponding to the target hydrological disaster includes:

[0013] Determine the professional terminology set corresponding to the target hydrological disaster; wherein the professional terminology set includes: the original meaning of the terminology and the logical relationship between the terms;

[0014] Determine a general database for retrieval, and input the search terms in the professional term set into the general database according to a logical relationship, obtain a plurality of first document data corresponding to the target hydrological disaster, and perform screening to obtain a plurality of target document data corresponding to the target hydrological disaster;

[0015] According to the key information of each target document data, a sub-document database corresponding to the target hydrological disaster is constructed.

[0016] In an optional manner, each region name is accurately matched in the sub-document database, and the appearance characteristics of each region name in the sub-document database are marked and filtered to obtain each filtered region name, including:

[0017] Precisely matching each region name in the sub-document database, and marking the appearance characteristics of each region name in the sub-document database to obtain an initial matching number of each region name;

[0018] From the initial matching times of each region name, respectively delete the matching items that are not exact matches, to obtain the second matching times of each region name;

[0019] The region names with the second matching times higher than the first threshold and the region names with the second matching times lower than the second threshold are searched again, and the matching items that do not appear as region names in the key information of the document are deleted to obtain each filtered region name.

[0020] In an optional manner, the method further includes:

[0021] Based on the existing regional names, an information database is constructed containing multiple geographic data corresponding to each regional name.

[0022] In an optional manner, when the plurality of geographic data corresponding to each filtered regional name meets a preset recognition accuracy, the step of determining each filtered regional name as a disaster-stricken area corresponding to the target hydrological disaster includes:

[0023] Determining, based on the information database, a plurality of geographic data corresponding to each filtered area name;

[0024] Determine whether the multiple geographic data corresponding to each filtered area name meet the preset recognition accuracy, and obtain a determination result;

[0025] When the judgment result is yes, each filtered area name is determined as the disaster-stricken area corresponding to the target hydrological disaster.

[0026] In an optional manner, the method further includes:

[0027] When the judgment result is no, check the professional terminology set, and return to execute the step of constructing a sub-document database corresponding to the target hydrological disaster based on the professional terminology set corresponding to the target hydrological disaster, until the judgment result is yes, determine each filtered area name as the disaster-stricken area corresponding to the target hydrological disaster.

[0028] In an optional manner, the key information of the document includes: abstract, title and keywords.

[0029] In a second aspect, the present invention provides a system for identifying areas affected by hydrological disasters, and the technical solution of the system is as follows:

[0030] Includes: building module, processing module and recognition module;

[0031] The construction module is used to: construct a sub-document database corresponding to the target hydrological disaster according to a set of professional terms corresponding to the target hydrological disaster;

[0032] The processing module is used to: accurately match each region name in the sub-document database, mark and filter the appearance characteristics of each region name in the sub-document database, and obtain each filtered region name;

[0033] The identification module is used to: when the multiple geographic data corresponding to each filtered area name meet the preset identification accuracy, determine each filtered area name as the disaster-stricken area corresponding to the target hydrological disaster.

[0034] The beneficial effects of the hydrological disaster affected area identification system of the present invention are as follows:

[0035] The system of the present invention can reduce the time consumption of hydrological disaster area identification and overcome the problem of heavy workload, thereby improving the efficiency of hydrological disaster area identification and providing important reference value for future analysis of the causes of hydrological disaster risks and comprehensive management.

[0036] In a third aspect, the present invention provides a storage medium with the following technical solution:

[0037] The storage medium stores instructions, and when a computer reads the instructions, the computer executes the steps of a method for identifying a hydrological disaster affected area according to the present invention.

[0038] In a fourth aspect, a technical solution of an electronic device of the present invention is as follows:

[0039] The method comprises a memory, a processor and a program stored in the memory and running on the processor, wherein when the processor executes the program, the steps of a method for identifying a hydrological disaster-affected area according to the present invention are implemented.

[0040] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings are only used to illustrate the embodiments and are not to be considered as limiting the present invention. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings. In the accompanying drawings:

[0042] Figure 1 A schematic flow chart of a first embodiment of a method for identifying a hydrological disaster affected area provided by the present invention is shown;

[0043] Figure 2 A schematic flow chart of step 110 in a first embodiment of a method for identifying a hydrological disaster affected area provided by the present invention is shown;

[0044] Figure 3 A schematic flow chart of step 120 in a first embodiment of a method for identifying a hydrological disaster affected area provided by the present invention is shown;

[0045] Figure 4 A schematic flow chart of step 130 in a first embodiment of a method for identifying a hydrological disaster affected area provided by the present invention is shown;

[0046] Figure 5 A schematic flow chart of a second embodiment of a method for identifying a hydrological disaster affected area provided by the present invention is shown;

[0047] Figure 6 A structural schematic diagram of an embodiment of a hydrological disaster affected area identification system provided by the present invention is shown. DETAILED DESCRIPTION

[0048] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0049] Figure 1 FIG. 2 is a flow chart showing a first embodiment of a method for identifying a hydrological disaster affected area provided by the present invention. Figure 1 As shown, the following steps are included:

[0050] Step 110: Based on the professional term set corresponding to the target hydrological disaster, a sub-document database corresponding to the target hydrological disaster is constructed.

[0051] ①Hydrological disasters include but are not limited to: flood disasters, tsunami disasters, storm surge disasters, coastal erosion and seawater intrusion, etc.; any one of the target hydrological disasters.

[0052] ② The professional terminology set includes: multiple professional terms related to the target hydrological disaster. The selection of professional terms should correspond to the target hydrological disaster, and the research field of the target hydrological disaster should be limited through the combination of terms.

[0053] ③ Sub-literature database: the literature database corresponding to the target hydrological disaster.

[0054] Step 120: Perform precise matching on each region name in the sub-document database, mark and filter the occurrence features of each region name in the sub-document database, and obtain each filtered region name.

[0055] ① The region name may be, but is not limited to, the name of a city, region, or country. In this embodiment, the city name is used as the region name by default.

[0056] ②Mark the location where the regional name appears in the sub-document database.

[0057] ③ The selected regional names are: regional names whose occurrence times meet the preset requirements as determined by searching in the sub-document database.

[0058] Step 130: When the plurality of geographic data corresponding to each filtered regional name meets the preset recognition accuracy, each filtered regional name is determined as the disaster-stricken area corresponding to the target hydrological disaster.

[0059] ① Multiple geographic data include but are not limited to: longitude and latitude, population, rainfall and other geographic data.

[0060] ② The preset recognition accuracy is judged based on three aspects:

[0061] 1) Determine whether the selected regional names are at the correct order of magnitude based on existing research experience, and judge whether all the selected regional names contain known typical representative regions.

[0062] 2) Whether the number of samples available for statistics is sufficient. When the total number of documents in the sub-document database is less than 1,000, the number of regional names after screening should be greater than 50; when the total number of documents in the sub-document database is greater than or equal to 1,000, the number of regional names after screening should be greater than 2% of the total number of documents in the sub-document database.

[0063] 3) Determine whether multiple geographic data affect one of the elements of the target hydrological disaster. When testing a certain geographic data separately, the known regional names should be divided into two groups, one group is the area where the target hydrological disaster did not occur (not screened out), and the other group is the area where the target hydrological disaster was reported (screened out). The multiple geographic data corresponding to the two groups of regional names are tested for significant differences, including t-test, variance analysis, chi-square test and non-parametric test. When the difference is significant, the process ends. If the difference is not significant, other geographic data should be replaced for comparison until the typical geographic feature data of the hydrological disaster-affected area is obtained through analysis.

[0064] It should be noted that the methods for testing significance of differences include:

[0065] ①t-test:

[0066] (1) The independent sample t-test statistic is:

[0067]

[0068] and is the variance of the two samples; n1 and n2 are the capacity of the two samples.

[0069] (2) Paired Samples Test

[0070] The paired sample t-test can be considered as an extension of the one-sample t-test, but the object of the test is changed from a group of independent samples from a normal distribution to the difference between the observations of two groups of paired samples. 1i With x 2i The difference is d i =x 1i -x 2i independent and come from the normal distribution, then d i Whether the expected value of the population μ is μ0 can be measured using the following statistics:

[0071]

[0072] Where i = 1…n, is the average of the paired sample differences, is the standard deviation of the paired sample difference, and n is the number of paired samples. The statistic t follows a t distribution with n-1 degrees of freedom under the condition that the null hypothesis: μ = μ0 is true.

[0073] ② Analysis of variance

[0074] When the overall variances of multiple groups of observed variables are equal, that is, when the variance homogeneity is satisfied, the F test can be used for one-way ANOVA. When the overall variances of multiple groups of observed variables are not equal, that is, when the variance homogeneity is not satisfied, the variance homogeneity requirement can be achieved by variable transformation, or the corrected one-way ANOVA (Welch test) can be used for comparison.

[0075] 1) F-test

[0076] The total variation of one-way ANOVA can be divided into two parts: between-group variation and within-group variation:

[0077] SS 总 =SS 组间 +SS 组内 , 总 =υ 组间 +υ 组内 ;

[0078] The calculation formula of variance analysis is shown in Table 1. N is the sample size and g is the number of treatment groups.

[0079] Table 1:

[0080]

[0081] 2) Welch test

[0082] The Welch test refers to the use of Welch distribution statistics to test whether the means of each group are equal. The Welch distribution is similar to the F distribution. The Welch test does not require homogeneity of variance, so when the distribution of data does not meet the requirement of homogeneity of variance, it is safer to use the Welch test than the F test. The calculation formula is: in, k is the number of treatment groups. F~F(k-1,df); degrees of freedom:

[0083] Preferably, if Figure 2 As shown, step 110 includes:

[0084] Step 111: Determine the professional terminology set corresponding to the target hydrological disaster.

[0085] ①The set of professional terms includes: the original meaning of the terms and the logical relationship between the terms.

[0086] ② The original meaning of the term should give priority to the expressions commonly used internationally or in academia, with special nouns and noun phrases as the main ones. The term should include all the commonly used expressions of the target hydrological disaster as much as possible.

[0087] ③ Ensure that the query results are comprehensive and accurate through the combination of specific logical relationships between terms. Commonly used logical relationships between terms include: "AND" expresses the logical "and" relationship; "OR" expresses the logical "or" relationship; "NOT" expresses the logical "not" relationship.

[0088] Step 112: Determine a general database for retrieval, and input the search terms in the professional term set into the general database according to a logical relationship, obtain multiple first document data corresponding to the target hydrological disaster and screen them to obtain multiple target document data corresponding to the target hydrological disaster.

[0089] in:

[0090] ① For global-scale research, the Science Citation Index (SCI) database is used as the default general database; for national-scale research, the CNKI database is used as the default general database.

[0091] ②The first literature data is: literature data within the scope of the target hydrological disaster research obtained by searching the search terms in the professional term set.

[0092] ③ The method for screening the first document data is: precise screening by subject category, publication time, document source, etc.

[0093] ④ Target literature data refers to literature data determined by precise screening based on subject categories, publication time, literature sources, etc.

[0094] Step 113: Based on the key information of each target document data, a sub-document database corresponding to the target hydrological disaster is constructed.

[0095] The key information of the literature includes: abstract, title and keywords.

[0096] It should be noted that the process of constructing a sub-document database is to export the abstract, title and keywords of each target document data to form a text document, and establish a sub-document database for the target hydrological disaster. In this process, the readability of the text document should be guaranteed to avoid interference from other information except the title, abstract and keywords.

[0097] Preferably, if Figure 3 As shown, step 120 includes:

[0098] Step 121: perform precise matching on each region name in the sub-document database, and mark the occurrence features of each region name in the sub-document database to obtain the initial matching times of each region name.

[0099] ① The regional names are obtained from public information from various channels, with data officially released by authoritative international or domestic organizations as the main source to ensure the accuracy and authority of the information.

[0100] ② Input each regional name obtained by counting into the target document data for matching retrieval. Mark each matching item (appearing feature) and add 1 to the count of the regional name until all matching items of each regional name are obtained. The count number of each regional name at this time is determined as the initial matching number of each regional name.

[0101] Step 122: Delete the inexact matching items from the initial matching times of each area name to obtain the second matching times of each area name.

[0102] Inexact matching includes, but is not limited to, the following: a region name with English semantics is included in another region name with English semantics. For example, the Dutch city Born is included in the British city Camborn. When matching the region name Born, the count of Camborn needs to be removed, and the number of matches obtained is the second number of matches.

[0103] Step 123: Perform a secondary search on the region names with a second matching number higher than the first threshold and the region names with a second matching number lower than the second threshold, delete the matching items that do not appear as region names in the key information of the document, and obtain each filtered region name.

[0104] ① The first threshold and the second threshold can be set according to actual needs and are not limited here.

[0105] ② The secondary search marks the matching items with specific meanings in the regional names, and checks whether they are represented as regional names in the sub-document database. Those that do not meet the requirements are eliminated.

[0106] Preferably, it also includes:

[0107] Based on the existing regional names, an information database containing multiple geographic data corresponding to each regional name is constructed. Among them:

[0108] ① The integration of geographic data should be based on the data format. Software such as ArcGis, Python, and Excel should be selected for integration processing. The city name should be linked to the country to which it belongs, city population, longitude and latitude, hydrology, and other information for subsequent analysis.

[0109] ②The information database should be exported as a text document with punctuation marks.

[0110] Preferably, if Figure 4As shown, step 130 includes:

[0111] Step 131: Determine multiple geographic data corresponding to each filtered area name according to the information database.

[0112] The information database contains multiple pieces of geographic data corresponding to each region, so it is possible to determine the multiple pieces of geographic data corresponding to each filtered region name from the information database based on the filtered region name.

[0113] Step 132: Determine whether the multiple geographic data corresponding to each filtered area name meet the preset recognition accuracy, and obtain a determination result.

[0114] Step 133A: When the judgment result is yes, each filtered area name is determined as the disaster-stricken area corresponding to the target hydrological disaster.

[0115] Preferably, it also includes:

[0116] Step 133B: When the judgment result is no, check the professional terminology set and return to step 111 until the judgment result is yes, and determine each filtered area name as the disaster-stricken area corresponding to the target hydrological disaster.

[0117] Check whether the data format in the professional term collection is correct.

[0118] In the second embodiment of the method for identifying the affected areas of hydrological disasters of the present invention, two basic assumptions are set: first, professional academic journals will not mention place names outside the study area in titles, keywords, and abstracts; second, hydrological disaster research accurate to the city / region meets the accuracy requirements of global-scale disaster research. Figure 5 As shown, the method includes:

[0119] Step 210: Determine target hydrological hazards;

[0120] Step 220: Screening keywords and professional terms of target hydrological disasters;

[0121] Step 230: Searching for keywords and professional terms using a comprehensive literature database;

[0122] Step 240: exporting the title, summary and keywords of each city name corresponding to the retrieved target hydrological disaster;

[0123] Step 250: Establishing a literature database corresponding to the target hydrological disaster;

[0124] Step 260: Perform precise matching of city names based on the literature database and the comprehensive global city geographic / regional information database to obtain the number of occurrences of each city name in the target literature database;

[0125] Step 270: Manually check the cities with extremely high and extremely low occurrences, and perform spatial location auxiliary verification in combination with the comprehensive global urban geographic / regional information database;

[0126] Step 280: Generate a database of cities / regions affected by target hydrological disasters, and determine whether the number of cities / regions screened is consistent with existing research knowledge;

[0127] Step 290: If not, return to step 260; if yes, determine whether the number of samples available for statistics is sufficient;

[0128] Step 300: If not, return to step 260; if yes, determine whether the geographic information meets the analysis requirements;

[0129] Step 310: If not, adjust the comprehensive global urban geographic / regional information database and return to step 260; if yes, generate a comprehensive geographic database of global target hydrological disaster-affected cities / regions.

[0130] The process of generating a comprehensive global urban geographic / regional information database includes:

[0131] From the global city / region database containing city names, based on the data coupling method and matching with geographical elements such as population, precipitation, and topography, a comprehensive global urban geographic / regional information database is obtained.

[0132] To better illustrate the technical solution of this embodiment, the target hydrological disaster is seawater intrusion as an example for illustration. Specifically:

[0133] Determine the set of professional terms corresponding to seawater intrusion: "seawater intrusion" and "saltwater intrusion"; both expressions are commonly used terms in international journals to describe seawater intrusion problems, so the logical relationship between the two is "OR".

[0134] Construct a sub-document database (seawater intrusion literature information database) corresponding to seawater intrusion: Web of Science literature database. During the search process, any document containing "seawater intrusion" or "saltwater intrusion" in the title, keyword, and abstract will be marked. Narrow the database scope to the Web of Science core database (i.e., SCI index journal database), export and download the abstract, title, and keyword information of all retrieved documents, and construct a seawater intrusion literature information database in text format.

[0135] Build an information database. The information database uses the world city database released by the National Geospatial-Intelligence Agency, the United States Geological Survey, the United States Census Bureau and NASA. The database contains information such as region name, longitude and latitude, population, and country.

[0136] In the Python environment, compare and match the global city database (including each region name) with the seawater intrusion literature data in the seawater intrusion literature information database, use chunk_data to read the seawater intrusion literature data, use the findall function to match all city names in the seawater intrusion literature database, and use the len function to output the count number to the count variable.

[0137] At the same time, define '[a-zA-Z]'+city_name and city_name+'[a-zA-Z]' as two compound city names that should be excluded. Use the findall function to search in the seawater intrusion literature data, and use the len function to output the count number to the error_count1 and error_count2 variables. Define the final count variable as counts, and use the following function to characterize the relationship between each count variable: counts.Append(count-error_count1-error_count2); finally output the corresponding city_name and counts to an excel table, and use the VLOOKUP function in excel to merge the output results with the information database.

[0138] The technical solution of this embodiment can reduce the time consumption of hydrological disaster area identification and overcome the problem of heavy workload, thereby improving the efficiency of hydrological disaster area identification and providing important reference value for future analysis of the causes of hydrological disaster risks and comprehensive management.

[0139] Figure 6 FIG. 2 is a schematic diagram showing a structure of an embodiment of a hydrological disaster affected area identification system provided by the present invention. Figure 6As shown, the system 400 includes: a construction module 410, a processing module 420 and an identification module 430;

[0140] The construction module 410 is used to: construct a sub-document database corresponding to the target hydrological disaster according to a set of professional terms corresponding to the target hydrological disaster;

[0141] The processing module 420 is used to: accurately match each region name in the sub-document database, mark and filter the appearance characteristics of each region name in the sub-document database, and obtain each filtered region name;

[0142] The identification module 430 is used to: when the multiple geographic data corresponding to each filtered area name meet the preset identification accuracy, determine each filtered area name as the disaster-stricken area corresponding to the target hydrological disaster.

[0143] The technical solution of this embodiment can reduce the time consumption of hydrological disaster area identification and overcome the problem of heavy workload, thereby improving the efficiency of hydrological disaster area identification and providing important reference value for future analysis of the causes of hydrological disaster risks and comprehensive management.

[0144] The above-mentioned parameters and steps for each module to implement corresponding functions in the hydrological disaster disaster area identification system 200 of this embodiment can refer to the parameters and steps in the above embodiment of the hydrological disaster disaster area identification method, and will not be repeated here.

[0145] A storage medium provided by an embodiment of the present invention includes: instructions stored in the storage medium, and when a computer reads the instructions, the computer executes steps such as a method for identifying areas affected by hydrological disasters. For details, please refer to the parameters and steps in the embodiment of the method for identifying areas affected by hydrological disasters in the above text, which will not be repeated here.

[0146] Computer storage media such as USB flash drives, mobile hard disks, etc.

[0147] An electronic device provided by an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. The electronic device is characterized in that when the processor executes the computer program, the computer executes the steps of a method for identifying areas affected by hydrological disasters. For details, please refer to the parameters and steps in the embodiment of the method for identifying areas affected by hydrological disasters in the above text, which will not be elaborated here.

[0148] Those skilled in the art will appreciate that the present invention may be implemented as a method, a system, a storage medium, and an electronic device.

[0149] Therefore, the present invention can be specifically implemented in the following forms, that is, it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), or it can be a combination of hardware and software, which is generally referred to as "circuit", "module" or "system" herein. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code. Any combination of one or more computer-readable media can be used. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device. Although the embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and cannot be construed as limiting the present invention, and those skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for identifying areas affected by hydrological disasters, characterized in that: include: According to the professional term set corresponding to the target hydrological disaster, a sub-document database corresponding to the target hydrological disaster is constructed; Precisely matching each region name in the sub-document database, marking and filtering the appearance features of each region name in the sub-document database, and obtaining each filtered region name; When the plurality of geographic data corresponding to each filtered regional name meets the preset recognition accuracy, each filtered regional name is determined as the disaster-stricken area corresponding to the target hydrological disaster; The step of constructing a sub-document database corresponding to the target hydrological disaster according to the set of professional terms corresponding to the target hydrological disaster comprises: Determine the professional terminology set corresponding to the target hydrological disaster; wherein the professional terminology set includes: the original meaning of the terminology and the logical relationship between the terms; Determine a general database for retrieval, and input the search terms in the professional term set into the general database according to a logical relationship, obtain a plurality of first document data corresponding to the target hydrological disaster, and perform screening to obtain a plurality of target document data corresponding to the target hydrological disaster; According to the key information of each target document data, a sub-document database corresponding to the target hydrological disaster is constructed; The steps of respectively accurately matching each region name in the sub-document database, marking and filtering the appearance features of each region name in the sub-document database, and obtaining each filtered region name include: Precisely matching each region name in the sub-document database, and marking the appearance characteristics of each region name in the sub-document database to obtain an initial matching number of each region name; From the initial matching times of each area name, respectively delete the matching items that are not exact matches, to obtain the second matching times of each area name; The region names with the second matching times higher than the first threshold and the region names with the second matching times lower than the second threshold are searched again, and the matching items that do not appear as region names in the key information of the document are deleted to obtain each filtered region name.

2. The method for identifying the area affected by hydrological disasters according to claim 1, characterized in that: Also includes: Based on the existing regional names, an information database is constructed containing multiple geographic data corresponding to each regional name.

3. The method for identifying the area affected by hydrological disasters according to claim 2, characterized in that: When the plurality of geographic data corresponding to each filtered regional name meets the preset recognition accuracy, the step of determining each filtered regional name as the disaster-stricken area corresponding to the target hydrological disaster includes: Determining, based on the information database, a plurality of geographic data corresponding to each filtered area name; Determine whether the multiple geographic data corresponding to each filtered area name meet the preset recognition accuracy, and obtain a determination result; When the judgment result is yes, each filtered area name is determined as the disaster-stricken area corresponding to the target hydrological disaster.

4. The method for identifying the area affected by hydrological disasters according to claim 3, characterized in that: Also includes: When the judgment result is no, check the professional terminology set, and return to execute the step of constructing a sub-document database corresponding to the target hydrological disaster based on the professional terminology set corresponding to the target hydrological disaster, until the judgment result is yes, determine each filtered area name as the disaster-stricken area corresponding to the target hydrological disaster.

5. The method for identifying areas affected by hydrological disasters according to claim 1, characterized in that: The key information of the document includes: abstract, title and keywords.

6. A hydrological disaster affected area identification system, characterized in that: include: Building modules, processing modules and recognition modules; The construction module is used to: construct a sub-document database corresponding to the target hydrological disaster according to a set of professional terms corresponding to the target hydrological disaster; The processing module is used to: accurately match each region name in the sub-document database, mark and filter the appearance characteristics of each region name in the sub-document database, and obtain each filtered region name; The identification module is used to: when the multiple geographic data corresponding to each filtered regional name meet the preset identification accuracy, determine each filtered regional name as the disaster-stricken area corresponding to the target hydrological disaster; The construction module is specifically used to: determine the professional terminology set corresponding to the target hydrological disaster; wherein the professional terminology set includes: the original meaning of the terminology and the logical relationship between the terms; Determine a general database for retrieval, and input the search terms in the professional term set into the general database according to a logical relationship, obtain a plurality of first document data corresponding to the target hydrological disaster, and perform screening to obtain a plurality of target document data corresponding to the target hydrological disaster; According to the key information of each target document data, a sub-document database corresponding to the target hydrological disaster is constructed; The processing module is specifically used for: Precisely matching each region name in the sub-document database, and marking the appearance characteristics of each region name in the sub-document database to obtain an initial matching number of each region name; From the initial matching times of each area name, respectively delete the matching items that are not exact matches, to obtain the second matching times of each area name; The region names with the second matching times higher than the first threshold and the region names with the second matching times lower than the second threshold are searched again, and the matching items that do not appear as region names in the key information of the document are deleted to obtain each filtered region name.

7. A storage medium, characterized in that: The storage medium stores instructions, and when a computer reads the instructions, the computer executes the method for identifying a hydrological disaster-affected area according to any one of claims 1 to 5.

8. An electronic device comprising a memory, a processor, and a program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the steps of the method for identifying the area affected by a hydrological disaster as described in any one of claims 1 to 5 are implemented.

Images