Method for associating geographic unit with spatial view in document

Abstract

The invention belongs to the technical field of geographic information, and aims to solve the problem of positioning visualization of geographic units in document reading through automatic identification of the geographic units in documents and association with spatial views. In text reading, the spatial position and the mutual relation of geographic elements are an important aspect of understanding contents, and the existing technical method does not have a method for automatically extracting and quickly positioning the geographic name elements. A user needs to jump out of a reading interface when acquiring the position of a geographic element, retrieval and positioning are carried out through other applications, the reading process is interrupted, and the reading thought is influenced. According to the method, word segmentation processing is carried out on a text, matching is carried out based on a database, association between geographic units and spatial elements is established, a real-time spatial view is generated, and a geographic spatial position is displayed. According to the method, rapid positioning and visualization of the position of the geographic unit in the reading process can be achieved, the understanding of the spatial position and the mutual relation in the reading process is enhanced, the reading efficiency is improved, and the reading experience is optimized.

Description

Technical Field

[0001] The invention belongs to the field of geographic information technology and provides a method for associating geographic units and spatial views in a document. Background Art

[0002] In the field of geographic information technology, combining GIS systems with text information is a popular trend nowadays. [1-2] In reading, the spatial location and interrelationship of geographical elements are crucial for a deep understanding of the text content. [3] However, when processing text information, traditional GIS systems cannot directly obtain the coordinates and range of geographic locations through text descriptions, which makes it difficult to associate geographic units with spatial views in documents. [4] , which limits the presentation and analysis of information. At the same time, although map applications provide map display functions, they often lack a direct way to associate text information with geographic locations. [5] As a result, in the traditional reading process, users usually need to leave the reading interface and use other applications, such as online maps such as Google Maps or Baidu Maps, to retrieve and locate geographic elements. [6-7] These operations will interfere with the coherence of reading and affect the fluency of thinking, so it is of great significance to combine text information with GIS system.

[0003] At present, the research on natural language-based place name recognition technology and geographic information system has been quite fruitful. Among them, natural language-based place name recognition technology continues to integrate language models, deep learning, and entity relationship extraction technologies, which improves the accuracy and application scope of place name recognition. [8-9] The research on geographic information systems mainly focuses on spatial data models, geographic information data mining, geographic visualization, spatial analysis technology, etc., which promotes the close integration of geographic information science and computer science.

[10] The integration of natural language processing and geographic information systems can effectively solve the association problem between text and spatial information. [11-12] , to make up for the inability to directly view spatial locations during reading. For example, researchers such as Yu Jianfeng and others use natural language morphology to identify place names, associate place names in texts with spatial data, and locate and display them.

[13] . This method uses an algorithm to extract and merge layers to identify geographic units. For non-standard place name texts or identical place names, this may lead to recognition failure or positioning deviation. On the other hand, Jin Xianfeng and others developed a method for extracting and spatially locating place name information in Internet texts. They used the trained Bi-LSTM-CRF model to extract place name information, obtained the spatial position through an interface, and then located the spatial position of the place name through a correlation algorithm.

[14] However, due to the complexity of domestic place names, this method of separating place names from spatial locations has certain uncertainties, especially for the identification of similar place names, which is prone to ambiguity and leads to positioning errors. In addition, this method can only locate current place names, and historical place names are not fully covered.

[0004] In order to eliminate ambiguity and improve the accuracy of place name recognition and positioning, this method uses the place name attributes in the GIS database to expand the full-text text, thereby enhancing the accuracy of place name recognition. Since there is a mapping relationship between the place name attributes and the spatial elements in the GIS database, in this method, the place name information in the text can be directly associated with the spatial elements, further enhancing the accuracy of positioning. With the support of the GIS database, this method can also realize the recognition and positioning of historical place names. And with the help of online map tools, the text and spatial views can be displayed synchronously, allowing users to interact with place names and switch spatial views in real time, thereby improving the user experience.

[0005] The above methods effectively meet the needs of rapid location and visualization of geographic units during reading. The real-time generated spatial view presents the spatial location of geographic units, making the reading process smooth. Users can intuitively understand the location of geographic elements during reading and strengthen their understanding of spatial locations and relationships, thereby improving reading efficiency and optimizing reading experience.

[0006] References

[0007] [1] Zhang Siyuan, Guo Kena. Study on the distribution of place names in literature based on GIS[J]. Modern Computer (Professional Edition), 2017, (35): 48-51.

[0008] [2] Li Yusen, Zhang Xueying, Yuan Zhengwu. Research on geographic named entity recognition for GIS[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2008, 20(06): 719-724.

[0009] [3] Chi Yukai, Mo Lei, Guan Yanhua. Non-cued updating of the spatial dimension of the situation model during text reading[J]. Acta Psychologica Sinica, 2004, (03): 290-297.

[0010] [4]Monteiro BR , Davis CA , Fonseca F .A survey on the geographicscope of textual documents[J].Computers & Geosciences, 2016, 96(nov.):23-34.DOI:10.1016 / j.cageo.2016.07.017.

[0011] [5] Zhou Tong, Long Yi. A review of the recent development of mobile maps and Internet maps in my country[J]. Geography and Geographic Information Science, 2012, 28(05): 1-5.

[0012] [6] Google Maps [EB / OL]. [2024 / 10 / 31]. Access address: https: / / maps.google.cn / .

[0013] [7] Baidu Map [EB / OL]. [2024 / 10 / 31]. Access address: https: / / map.baidu.com / .

[0014] [8] Wang Wentao, Xi Xuefeng, Cui Zhiming, et al. Research and prospects of place name entity recognition[J]. Computer Engineering and Applications, 2023, 59(21): 66-82.

[0015] [9] Wei Yong, Li Hongfei, Hu Danlu, et al. A Chinese place name recognition method based on composite features[J]. Journal of Wuhan University (Information Science Edition), 2018, 43(01): 17-23. DOI: 10.13203 / j.whugis20150538.

[0016]

[10] Wang Jiayao. Thoughts on the future development of geographic information system[J]. Journal of Wuhan University (Information Science Edition), 2022, 47(10): 1535-1545. DOI: 10.13203 / j.whugis20210679.

[0017]

[11] Ling Chaoyang, Li Rui, Wu Huayi, et al. Semantic-driven geographic entity association network construction and knowledge service[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(03): 478-489.

[0018]

[12] Hou Mengfei, Tan Yongbin, Zhu Xuancheng, et al. Research progress on location information extraction and spatialization in online texts[J]. Jiangxi Science, 2021, 39(02): 354-359. DOI: 10.13990 / j.issn1001-3679.2021.02.029.

[0019]

[13] Yu Jianfeng, Wu Zhengsheng. Research on spatial information retrieval based on automatic recognition of place names in text[J]. Journal of Surveying and Mapping Science and Technology, 2011, 28(03): 227-230.

[0020]

[14] Jin Xianfeng, Luo Yue, He Xiaobo, et al. A method for extracting place name information and spatial positioning in Internet texts [P]. Chongqing: CN202111434039.0, 2022-02-25. Summary of the invention

[0021] The object of the present invention is to provide a method for associating geographic units with spatial views in a document, so as to solve the above problems raised in the above background technology.

[0022] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: Based on the support of GIS vector database, the system performs word segmentation and matching on the text input by the user, establishes the association between geographical units and spatial elements, generates a real-time spatial view, displays the geographical spatial position, and is used for the positioning and visualization of geographical units in document reading;

[0023] The present invention further comprises the following steps:

[0024] S1 input text, the user inputs text, which is used for the identification of geographic units and the association with the spatial view;

[0025] S2 word segmentation processing: the system uses natural language processing tools to perform word segmentation on the input text;

[0026] S3 text matching, by traversing and matching, matches the segmented text with the place name attribute (a);

[0027] S4 association, based on the matching results, establishes the association between geographic unit information and spatial elements. Users can choose to further edit and process the association relationship;

[0028] S5 outputs text. Based on the result of the associated code text replacement, the system outputs text and uses map services to achieve spatial view visualization.

[0029] Furthermore, the GIS vector database (A) provides support for this method;

[0030] The GIS vector database (A) includes place name attributes (a) and spatial elements (b);

[0031] The place name attribute (a) is used to expand the segmented text;

[0032] The place name attribute (a) is used to match text containing geographic units;

[0033] The spatial element (b) includes latitude and longitude or a spatial element expressed using GIS data;

[0034] There is a mapping relationship between place name attributes (a) and spatial elements (b).

[0035] Furthermore, in S2, natural language processing tools are used to perform word segmentation on the input text;

[0036] Through the text segmentation tool, the text is reasonably divided into meaningful words or phrases according to the grammatical and semantic rules of the language to obtain the effective minimum morphemes of the input text.

[0037] Furthermore, in S3, the segmented text is matched with the place names through manual matching or related algorithms, the successfully matched place names and their mapped elements are recorded, and the spatial location information is extracted;

[0038] The system matches the segmented text with the place name attribute (a) information:

[0039] If the text is successfully matched, the place name attribute (a) and its mapped spatial attribute (b) are obtained and the association step is entered;

[0040] If the text matching fails, the text is incorrectly input, ambiguous, or there is no corresponding place name attribute in the database. In this case, the text will not be processed as a place name.

[0041] Furthermore, in S4, the association between the place name information and the spatial elements is established according to the matching results;

[0042] The system calls the application program interface of the geocoding service and uses the successfully matched geographic unit as an input parameter to initiate a geocoding request;

[0043] Convert the acquired spatial features (b) into digital code form and return it to the geocoding service;

[0044] The system stores the association code between the geographic unit and the spatial element (b).

[0045] Furthermore, the user in S4 may choose to further edit and process the association relationship;

[0046] The user can choose whether to execute this part according to actual needs;

[0047] When there are time or space differences between the same geographical unit text in the text, the user checks and analyzes the same geographical unit information, and further edits the associated code of the same geographical unit to ensure that the attribute information is consistent with the actual situation;

[0048] The system stores the association code edited by the user.

[0049] Further, in S5, according to the result of the associated code text replacement, the system outputs the text;

[0050] The system replaces the associated code text with the associated text (1) to generate new output text.

[0051] Furthermore, S5 uses map services to achieve spatial view visualization;

[0052] User interaction outputs geographic units in text;

[0053] The system reads the geographic unit association code;

[0054] Use the map service to call the spatial elements (b), obtain the spatial location and range (2) information of each geographic unit through the spatial element data returned by the map service, and use the data visualization tool to generate a spatial view in real time;

[0055] The geographic unit is associated with the spatial view;

[0056] The spatial view can be interactively operated to zoom, drag, and view detailed information.

[0057] The beneficial effects of the present invention are:

[0058] Enhanced understanding of spatial information: The system associates the geographic units in the document with the spatial view to achieve a fusion display of text information and geographic location, solve the problem of rapid positioning and visualization of the geographic unit position during the reading process, enhance the understanding of spatial position and their relationships during the reading process, improve reading efficiency, and optimize the reading experience.

[0059] Convenient and fast operation method: This method provides a convenient and fast method. The user only needs to enter a text description, and the system can automatically complete the geographic location association through word segmentation, text matching and other steps to achieve a visual display of the spatial location, saving user time and energy and improving the efficiency of visual processing of geographic information.

[0060] Expanding application areas: The application of this method is not limited to the field of geographic information technology, but can also be applied in various fields, such as tourism planning, market analysis, geological exploration, etc. By associating text information with geographic location, the present invention provides users with rich and diverse application possibilities and expands the application scope of geographic information technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The drawings are used to enhance the understanding of the present invention and constitute a part of the specification. The drawings are used to explain the present invention in conjunction with the embodiments but do not impose any limitation on the present invention.

[0062] Figure 1 is a flow chart of an embodiment of the present invention.

[0063] In the attached drawings: A, GIS vector database, a, place name attribute, b, spatial element, S1, input text, S2, word segmentation processing, S3, text matching, S4, association, S5, output text, 1, association code text replacement, 2, spatial position and range. DETAILED DESCRIPTION

[0064] The technical solution will be described in detail below through the accompanying drawings of the embodiments of the present invention. The embodiments only represent part of the implementation of the present invention, not all implementation schemes. According to the embodiments of the present invention, those skilled in the art should recognize that all other embodiments are within the scope of protection of the present invention without making creative work.

[0065] Example:

[0066] See also Figure 1 ,The present invention provides a method for associating geographic units and spatial views in a document. Based on the support of GIS vector database, the system performs word segmentation and matching on the text input by the user, establishes the association between the geographic unit and the spatial element, generates a real-time spatial view, and displays the geographic spatial position, which is used for the location visualization display of the geographic unit in document reading;

[0067] The present invention is further described below with reference to the accompanying drawings:

[0068] The present invention is based on the support of GIS vector database (A);

[0069] The GIS vector database (A) includes place name attributes (a) and spatial elements (b);

[0070] The place name attribute (a) is used to expand the segmented text;

[0071] The place name attribute (a) is used to match text containing geographic units;

[0072] The spatial element (b) includes latitude and longitude or a spatial element expressed using GIS data;

[0073] There is a mapping relationship between place name attributes (a) and spatial elements (b);

[0074] In the example:

[0075] The GIS vector database (A) includes data on countries, cities, rivers, watersheds, and mountains;

[0076] The place name attribute (a) includes place name information of countries, cities, rivers, river basins, and mountains;

[0077] The spatial element (b) also includes information on administrative divisions, topography, climate, environment, cultural characteristics, transportation networks, and economic development;

[0078] In this example, the following GIS databases were also collected to expand access to the Northeast hydrological elements and Changchun place name information databases, including:

[0079] The Northeast hydrological element database is constructed from data obtained from hydrological tests, observations and calculations;

[0080] The Changchun place name information database is constructed from the place name data of the Changchun Civil Affairs Bureau and the address data of the public security department;

[0081] According to the place name attributes of the above database, the segmented text is expanded.

[0082] The following are the specific implementation steps:

[0083] S1 Input text. The user inputs text for the identification of geographical units and the association with spatial views;

[0084] The user inputs the original text to be processed through the text box on the interactive page;

[0085] The system automatically generates a cache file of the original input text.

[0086] S2 Chinese word segmentation. Use natural language processing tools to perform Chinese word segmentation on the input text;

[0087] Text preprocessing:

[0088] Clean the text: Remove irrelevant characters such as HTML tags, punctuation marks, special symbols, redundant spaces, etc.;

[0089] Case conversion: Convert all the letters in the text to lowercase to avoid problems caused by inconsistent case;

[0090] Stop word removal: Remove stop words in the text, such as "de", "shi", "zai", etc. These words appear frequently but do not contain substantial information;

[0091] Chinese word segmentation processing:

[0092] Through the text segmentation tool, the text is reasonably segmented according to the grammar and semantic rules of the language, divided into meaningful words or phrases, and the effective minimum morphemes of the input text are obtained.

[0093] S3 Text matching. Through traversal and matching, match the segmented text with place names;

[0094] If the text matching is successful, obtain the place name attribute (a) and its mapped spatial attribute (b), and enter the association step;

[0095] If the text matching fails, it means that the text input is incorrect, there is ambiguity, or there is no corresponding place name attribute in the database. In this case, it is not processed according to geographical units.

[0096] S4 Association. According to the matching results, establish the association between geographical unit information and spatial elements. The user can choose to further edit and process the association relationship;

[0097] In this example, you can choose to use geocoding to establish the association between place name text and spatial element (b):

[0098] The system calls the application program interface of the geocoding service and uses the successfully matched geographic unit as an input parameter to initiate a geocoding request;

[0099] Convert the acquired spatial features (b) into digital code form and return it to the geocoding service;

[0100] The system stores the association codes between geographic units and spatial elements (b);

[0101] The system replaces the associated code text (1) of the text that has been successfully matched and established an associated relationship in real time to generate new output text;

[0102] In the example, the user may choose to further edit the relationship;

[0103] The user can choose whether to execute this part according to actual needs;

[0104] When there are temporal or spatial differences in the same geographic unit text in the text, the user can check and analyze the geographic unit information and further edit the associated code to ensure that the attribute information is consistent with the actual situation;

[0105] The system stores the association code edited by the user;

[0106] The system replaces the associated code edited by the user with the associated code text in real time (1) to generate new output text.

[0107] S5 outputs text. According to the result of the associated code text replacement, the system outputs the text and uses the map service to generate a real-time spatial view to display the geographic spatial location;

[0108] In the example:

[0109] User interaction outputs geographic units in text;

[0110] The system reads the geographic unit association code;

[0111] Use the map service to call the spatial elements (b), obtain the spatial location and range (2) information of each geographic unit through the spatial element data returned by the map service, and use the data visualization tool to generate a spatial view in real time;

[0112] The geographic unit is associated with the spatial view;

[0113] The map frame will automatically scale to the appropriate size based on the spatial view;

[0114] The spatial view can be interactively operated to zoom, drag, and view detailed information;

[0115] There can be multiple associations between geographic units and spatial elements on the same web page without any operational conflicts.

[0116] The above shows and describes the core principles, main features and advantages of the present invention. For those skilled in the art, it is obvious that the present invention is not limited to the details of the exemplary implementation, but can be implemented in other specific forms while maintaining the basic spirit of the present invention. Therefore, no matter from which angle, the exemplary examples should be regarded as illustrative rather than restrictive. The scope of the present invention depends on the claims, rather than the limitations described above. Therefore, the purpose of the present invention is to include all changes that meet the meaning and scope of the equivalent elements of the claims, and any figure mark should not be regarded as limiting the scope of the relevant claims.

[0117] Although the embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations may be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for associating a geographic unit with a spatial view in a document, characterized in that: Based on the support of GIS vector database, the system performs word segmentation and matching on the text input by the user, establishes the association between geographic units and spatial elements, generates a real-time spatial view, and displays the geographic spatial location, which is used for the visualization of the positioning of geographic units in document reading.

2. A method for associating a geographic unit with a spatial view in a document, further comprising the following steps: S1 input text, the user inputs text, which is used for the identification of geographic units and the association with the spatial view; S2 word segmentation processing: the system uses natural language processing tools to perform word segmentation on the input text; S3 text matching, by traversing and matching, matches the segmented text with the place name attribute (a); S4 association, based on the matching results, establishes the association between geographic unit information and spatial elements. Users can choose to further edit and process the association relationship; S5 outputs text. Based on the result of the associated code text replacement, the system outputs text and generates a real-time spatial view to display the geographic spatial location.

3. A method for associating geographic units and spatial views in a document according to claim 1, characterized in that: Support based on GIS vector database; The GIS vector database (A) includes place name attributes (a) and spatial elements (b); The place name attribute (a) is used to expand the segmented text; The place name attribute (a) is used to match text containing geographic units; The spatial element (b) includes latitude and longitude or a spatial element expressed using GIS data; There is a mapping relationship between place name attributes (a) and spatial elements (b).

4. The method for associating geographic units and spatial views in a document according to claim 2, characterized in that: The system in S2 performs word segmentation on the input text using natural language processing tools; The system uses text segmentation tools to reasonably divide the input text into meaningful words or phrases according to the grammatical and semantic rules of the language, and obtain the effective minimum morphemes of the input text.

5. The method for associating geographic units and spatial views in a document according to claim 2, characterized in that: In S3, the segmented text is matched with the place name attribute (a) through manual matching or related algorithms; If the text is successfully matched, the place name attribute (a) and its mapped spatial attribute (b) are obtained and the association step is entered; If the text matching fails, the text is incorrectly input, ambiguous, or there is no corresponding place name attribute in the database. In this case, it will not be processed as a geographic unit.

6. A method for associating geographic units and spatial views in a document according to claim 2, characterized in that: In S4, the association between the geographic unit information and the spatial elements is established according to the matching results; The system calls the geocoding service to associate the successfully matched geographic unit with the mapped spatial feature (b).

7. The method for associating geographic units and spatial views in a document according to claim 2, characterized in that: The user in S4 can choose to further edit and process the association relationship; The user can choose whether to execute this part according to actual needs; When there are temporal or spatial differences in the text of the same geographical unit in the text, the user further edits the association relationship.

8. The method for associating geographic units and spatial views in a document according to claim 2, characterized in that: In S5, according to the result of the associated code text replacement, the system outputs the text; The system replaces the associated code text with the associated text (1) to generate new output text.

9. The method for associating geographic units and spatial views in a document according to claim 2, characterized in that: In S5, map services are used to visualize spatial views; The system uses map services to call spatial features (b) to obtain spatial locations and ranges (2), and uses data visualization tools to interactively output textual geographic units to view the associated spatial views.

Images