Web text biased geographic information self-correction method and device based on context, storage medium and computer system

Abstract

The invention discloses a context-based web text biased geographic information self-correction method and device, a storage medium and a computer system.The method comprises the steps that to-be-corrected geographic information, specifically time information and space information, of paragraph target statements is obtained through analysis; screening and analyzing a plurality of pieces of time information and space information of the paragraph target statement, and performing self-correction of geographic information; performing geographic information screening judgment from the context adjacent statements of the paragraph, and determining time information and space information which can be self-corrected; and geographic information self-correction is carried out by utilizing a precise context. According to the method, the related geographic information content in the context information can be effectively utilized, the deviation of the geographic information in the target statement is reduced, the obtained target geographic information is more accurate, and the method is suitable for news, social media and other network texts containing the geographic information and better serves the utilization of network geographic information resources.

Description

Technical Field

[0001] The present invention relates to the fields of artificial intelligence and computational linguistics, and in particular to a context-based network text biased geographic information self-correction method, device, storage medium and computer system. Background Art

[0002] In the Internet age, massive amounts of text data are flooding various social media, news platforms and forums, and these texts contain rich geographic information. However, with the development of science and technology and the deepening of data application, the accuracy and reliability of geographic information in these online texts have become key issues. Geographic information is not only widely used in navigation, emergency response, urban planning and other fields, but also plays an important role in geographic data analysis and public opinion monitoring. However, the geographic information contained in online texts is often accompanied by inaccuracy and bias, which seriously affects the effectiveness and reliability of this information in practical applications.

[0003] Specifically, the problem of geographic information deviation in online texts is manifested in inconsistent descriptions of geographic locations, time point deviations, and large differences in information sources. For example, the location information of the "United Nations World Geographic Information Conference" presents completely different descriptions in different social media or news reports, such as "Deqing International Conference Center", "Novotel Hotel", "Deqing Geographic Information Town", etc. Although these place names are close to each other, the actual locations they point to are different. This difference in expression not only increases the difficulty of automatic parsing of geographic information, but also poses a huge challenge to subsequent applications. Another typical example is the reporting of typhoon events. When describing "Typhoon Lekima landed in Zhejiang in the early morning", some news did not accurately describe the specific location and time, and there was a large deviation compared with the actual situation. In fact, the exact location where Typhoon "Lekima" landed was Chengnan Town, Wenling City, at 1:45 a.m., while some media reports may generally describe it as "landing in Zhejiang". This deviation may lead to delayed emergency response or misjudgment.

[0004] These phenomena expose the major challenges faced in extracting and applying geographic information from online texts. Especially in scenarios that require accurate geographic information support, such as emergency management and disaster monitoring, inaccurate or biased geographic information may lead to serious consequences. Therefore, how to automatically and accurately correct the geographic information bias in online texts has become an urgent problem to be solved in current research and practical applications. Summary of the invention

[0005] In view of the above-mentioned deficiencies in the prior art, the present invention provides a method, device, storage medium and computer system for self-correcting biased geographic information in network texts based on contextual context, which solves the problem of correcting deviations in geographic information (especially time information and spatial location information) contained in network texts, and makes the geographic information obtained in network texts more accurate.

[0006] In a first aspect, the present application provides a method for self-correcting biased geographic information in network text based on context, and the technical solution adopted by the method includes the following steps: S1. Parse and obtain the specified paragraph Target sentence Geographic information elements to be self-corrected ; S2. Based on the target sentence According to the intra-sentence self-correction algorithm, the geographic information elements Perform self-correction; S3. From paragraph Contains context statements In the process, geographic information screening and judgment are performed according to the paragraph self-correction algorithm; S4. Use the context of the sentence and paragraph to calibrate geographic information elements .

[0007] Furthermore, step S1 includes the following sub-steps: S1-1. Use a time recognition method or a spatial position recognition method, not limited to a specific implementation method, to identify a specified paragraph. Target sentence To identify; S1-2. Obtaining geographic information elements to be self-corrected .in, is the time information to be self-corrected; is the spatial information to be self-corrected.

[0008] Furthermore, the specific method of step S2 includes the following sub-steps: S2-1. Use time identification method or spatial location identification method, not limited to specific implementation methods, to identify geographic information elements. The statement To identify; S2-2. Obtaining the sequential order of time elements within a sentence , where each time element in the sequence is arranged in the order of its appearance in the text, i represents the order in which the time element appears from the beginning to the end in the text; and the time elements with consecutive characters describe An additional record is required , which constitutes a sequential sequence ; S2-3. Obtaining the ordered sequence of spatial position elements within the sentence , where each spatial position element in the sequence is arranged in the order of its appearance in the text, i represents the order in which the spatial position element appears from the beginning to the end in the text; and the spatial position elements with continuous characters describe An additional record is required , which constitutes a sequential sequence ; S2-4, according to the sentence time self-correction function formula:

[0009] The time information to be self-calibrated Perform correction operation. Among them, is the input time information to be self-calibrated; Indicates the sequential sequence of continuous time element descriptions in step S2-2 The first value of ; Represents the serialization sequence in step S2-2 The first value of ; represents the intra-sentence temporal self-correction function; S2-5, according to the sentence spatial position self-correction function formula:

[0010] The spatial position information to be self-corrected Perform correction operation. Among them, is the input spatial position information to be self-corrected; Represents the sequential sequence of continuous spatial position element descriptions in step S2-3 The first value of ; Represents the self-correction function of the spatial position within the sentence.

[0011] Furthermore, the specific method of step S3 includes the following sub-steps: S3-1. Analyze the paragraphs one by one Contains context statements , and obtain the ordered sequence of time elements for each statement , and a sequential sequence of time elements with continuous characters .in, represents the kth sentence in paragraph P, and j represents the order in which the time element appears from the beginning to the end in sentence k.

[0012] S3-2. Analyze the paragraphs one by one Contains context statements , and obtain the ordered sequence of spatial position elements of each sentence , and the sequential sequence of continuous spatial position elements of characters .in, represents the kth sentence in paragraph P, and j represents the order in which the spatial position element appears from front to back in sentence k.

[0013] S3-3. Confirm and find the first continuous time element of characters in paragraph P, and filter it according to the following formula:

[0014] in, Indicates the time element of the first character continuation. represents the character continuous time element sequence in step S3-1, Indicates the time information from the first sentence of paragraph P to the tth sentence to be self-corrected .

[0015] S3-4. Confirm and find the spatial position element with the closest distance to the spatial position element to be corrected in paragraph P, with continuous characters, and select it according to the following formula:

[0016] in, Indicates the continuous spatial position element of the first character, represents the ordered sequence of continuous spatial position elements of characters in step S3-2, Indicates the distance from the first sentence of paragraph P to the tth sentence where the spatial position information to be self-corrected is located .

[0017] Furthermore, the specific method of step S4 includes the following sub-steps: S4-1. Self-correction formula based on the time element in the precise context:

[0018] The time information to be self-calibrated Perform correction operation. Among them, is the input time information to be self-calibrated; Represents the self-correction function of the time element in the context of accurate context; The time element representing the first character continuity in step S3-3; represents the result of the intra-sentence time self-correction function in step S2-4; S4-2. Self-correction formula based on spatial position elements in the precise context:

[0019] The spatial position information to be self-corrected Perform correction operation. Among them, is the input spatial position information to be self-corrected; Represents the self-correction function of the spatial position element in the precise context; The spatial position element representing the first character continuation in step S3-4; represents the result of the intra-sentence spatial position self-correction function in step S2-5; S4-3. Obtaining geographic information elements The results of self-correction in context .

[0020] In a second aspect, the present application provides a context-based network text biased geographic information self-correction device for implementing the above method, the device comprising the following modules: Analysis module: used to analyze and obtain the time and space information to be self-corrected; Intra-sentence self-correction module: self-corrects temporal and spatial information based on the context within the sentence; Paragraph self-correction module: information screening and correction based on the context of the paragraph; Context correction module: uses the double-layer context of sentence and paragraph to accurately correct geographic information elements; The synergistic effect of the above modules enables the device to efficiently realize accurate correction of geographic information in network texts, and is suitable for processing various types of text data containing geographic information.

[0021] In a third aspect, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a computer system, enables the computer system to implement the above-mentioned self-correction method. The storage medium may be in various forms such as a hard disk, a flash memory, an optical disk, or a cloud storage, so as to ensure that the program is executed in various environments.

[0022] In a fourth aspect, the present invention also provides a computer system for performing self-correction of geographic information based on context. The computer system includes a processor, a memory, and an interface module for data input and result output. By calling a program stored on a storage medium, the computer system can parse and correct geographic information, effectively eliminating the deviation of geographic information in the text.

[0023] The beneficial effects of the present invention are: 1. The present invention can improve the accuracy of geographic information by self-correcting biased geographic information in online texts in combination with context, and significantly improve the problems caused by inconsistent or inaccurate descriptions of geographic information. This is of great significance for ensuring the reliability of geographic information in applications such as navigation, emergency response and urban planning.

[0024] 2. The present invention uses context to conduct multi-level analysis, and can automatically identify and correct biased geographic information based on the overall semantics and background information of the text, thereby ensuring that the final geographic information is more in line with the actual situation. This can effectively reduce misjudgments and misuses caused by information bias, especially in the decision-making and management of major events.

[0025] 3. The present invention can flexibly adapt to different types of texts and scenes, and reduce the deviation of geographic information in complex or dynamic texts through an adaptive correction mechanism. For example, in texts with real-time and complex backgrounds such as social media and news reports, the present invention can effectively improve the accuracy of geographic information.

[0026] 4. The interpretability of the present invention provides users with a transparent understanding of the correction process. By explaining the basis for the correction of geographic information, users can clearly understand how the correction process comprehensively considers multiple factors of context and language, thereby increasing trust and reliance on the system. At the same time, this feature can provide scientific basis and decision support for researchers and policymakers, helping them better understand the sources of deviation and correction mechanism of geographic information in texts.

[0027] 5. The present invention can be widely applied to a variety of network text data sources, automatically correct biased geographic information in the text, effectively reduce the workload of manual correction, and thus improve the efficiency and accuracy of data processing. This will greatly promote the deep integration and application of geographic information systems (GIS) and natural language processing technology in multiple fields. Through these beneficial effects, the present invention provides an innovative method for efficient and accurate correction of network text geographic information, helps to improve the accuracy and practicality of geographic information, and promotes the intelligent development of data applications and decision support systems in related fields. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 The overall process diagram of this method is shown in FIG. Figure 2 Examples of web texts for implementation of this method; Figure 3 This is a schematic diagram of the structure of the self-correcting computer system proposed by the present invention. DETAILED DESCRIPTION

[0029] The specific implementation modes of the present invention are described below so that those skilled in the art can understand the present invention. However, it should be clear that the present invention is not limited to the scope of the specific implementation modes. For those of ordinary skill in the art, as long as various changes are within the spirit and scope of the present invention as defined and determined by the attached claims, these changes are obvious, and all inventions and creations utilizing the concept of the present invention are protected.

[0030] like Figure 1 As shown in the technical route, in one embodiment of the present invention, the steps include: target sentence parsing (parsing to obtain the geographic information elements to be self-corrected in the specified paragraph, including time and space information); sentence self-correction (self-correcting the geographic information elements based on the sentence context using a self-correction algorithm); paragraph self-correction (screening relevant geographic information from the paragraph context, and screening and judging in combination with the context of the paragraph); context correction (correcting the geographic information elements through the context of the sentence and paragraph level to ensure higher accuracy). Figure 2 The online news reports of are examples of implementation, such as Figure 2 As shown, it includes the following sub-steps: S11. The extractEntities parsing method in the HanLP open source package is used to parse the time information and spatial position of the target sentence "Recently, Xiang Changjun, a villager in Shilong Village, Liangping Township, Wushan County, Chongqing City, was busy in his own fields."

[0031] S12. Obtaining geographic information elements to be self-corrected .in, "Recently" is the time information to be self-calibrated; "My own field" is the spatial information to be self-corrected.

[0032] S21. Use the extractEntities method in the HanLP open source package to extract geographic information elements. The sentence "Recently, in Shilong Village, Liangping Township, Wushan County, Chongqing, villager Xiang Changjun was busy in his own field." is identified; S22. Obtaining the sequence of time elements in the sentence ; and the time elements of the characters are continuous to describe the sequence ; S23. Obtaining the ordered sequence of spatial position elements within the sentence , and the continuous spatial position elements of the characters describe the sequence ; S24, the time information to be self-corrected recently" Perform correction operation. Because, in step S22 is empty, so ; S25, perform correction operation on the spatial position information "my own field" to be self-corrected. is not empty, so ; S31. Analyze the paragraphs one by one Contains context statements "People's Daily Online, Chongqing, January 24th, "The weather has been very good these past two days, and our whole family has gone out to harvest radishes in the fields. We have harvested more than 10,000 kilograms, and there are still about 20,000 kilograms in the fields." "Recently, in Shilong Village, Liangping Township, Wushan County, Chongqing, villager Xiang Changjun was busy in his own fields." "Xiang Changjun was busy working while talking about how the big-headed radishes were growing well this season. After being pickled, the green radishes turned into "gold nuggets". " , , , , , ; S32. Analyze the paragraphs one by one Contains context statements "People's Daily Online, Chongqing, January 24th, "The weather has been very good these past two days, and our whole family has gone out to harvest radishes in the fields. We have harvested more than 10,000 kilograms, and there are still about 20,000 kilograms in the fields." "Recently, in Shilong Village, Liangping Township, Wushan County, Chongqing, villager Xiang Changjun was busy in his own fields." "Xiang Changjun was busy working while talking about how the big-headed radishes were growing well this season. After being pickled, the green radishes turned into "gold nuggets". " , , , , , ; S33, confirm and find the first character continuous time element in the paragraph ; S34, confirm and find the spatial position element with continuous characters that is closest to the spatial position element to be corrected in the paragraph ; S41, perform correction operation on the time information to be self-corrected "recent days", because ,therefore ; S42: The spatial position information to be self-corrected The correction calculation is done in the "own field" because ,therefore ; S43. Obtaining geographic information elements The results of self-correction in context .

[0033] In addition, the present application also proposes a context-based network text biased geographic information self-correction device, which is used to implement the above method and includes the following modules: Parsing module: used to parse the target sentence and extract the time and space information to be self-corrected; Self-correction module: Uses the information within the sentence to self-correct geographic information elements and generate a sequential sequence of time and space positions; Paragraph self-correction module: Filter relevant time and space information in the paragraph context, compare and confirm the optimal correction elements; Contextual Correction Module: Generates correction results based on the sentence and paragraph context to improve information accuracy.

[0034] At the same time, the present application proposes a storage medium for self-correction of biased geographic information of network text based on context. The storage medium stores program code executable in a computer system, which is suitable for implementing the self-correction method of biased geographic information of network text based on context of the present invention. The storage medium can be a non-volatile storage device such as a hard disk, SSD, or optical disk.

[0035] In addition, this application proposes a computer system for self-correcting biased geographic information in network text based on context, such as Figure 3 As shown, the system automatically implements the context-based network text biased geographic information self-correction method of the present invention by calling the program in the storage medium, and includes the following components: a processor M3: used to execute the context-based network text biased geographic information self-correction method; a memory M2: storing and reading the time and space information of the text to be corrected; an input interface module M1: receiving the text information to be corrected; an output interface module M4: outputting the corrected geographic information result for further processing or display.

[0036] In summary, the present invention can effectively use other clues in the text to judge the accuracy of geographic information through an adaptive correction mechanism. This method can not only identify biased geographic information in the text, but also perform adaptive correction based on contextual clues, thereby improving the accuracy and reliability of geographic information. Through multi-level semantic understanding of the text and cross-text information comparison, the self-correction method based on context can significantly reduce errors and improve the effectiveness of network text geographic information in various applications. This provides an important technical means for the future automated processing of geographic information in massive network texts, and also opens up new directions for research and application in related fields.

Claims

1. A method for self-correcting biased geographic information in network text based on context, characterized in that: The following steps are involved: S1. Parse and obtain the specified paragraph Target sentence Geographic information elements to be self-corrected ; S2. Based on the target sentence According to the intra-sentence self-correction algorithm, the geographic information elements Perform self-correction; S3. From paragraph Contains context statements In the process, geographic information screening and judgment are performed according to the paragraph self-correction algorithm; S4. Use the context of the sentence and paragraph to calibrate geographic information elements .

2. According to the context-based network text biased geographic information self-correction method of claim 1, it is characterized by: Step S1 includes the following sub-steps: S1-1. Use a time recognition method or a spatial position recognition method, not limited to a specific implementation method, to identify a specified paragraph. Target sentence To identify; S1-2. Obtaining geographic information elements to be self-corrected .in, is the time information to be self-corrected; is the spatial information to be self-corrected.

3. According to the context-based network text biased geographic information self-correction method of claim 1, it is characterized by: Step S2 includes the following sub-steps: S2-1. Use a time identification method or a spatial location identification method, not limited to a specific implementation method, to identify geographic information elements. The statement To identify; S2-2. Obtaining the sequential order of time elements within a sentence , where each time element in the sequence is arranged in the order of its appearance in the text, i represents the order in which the time element appears from the beginning to the end in the text; and the time elements with consecutive characters describe An additional record is required , which constitutes a sequential sequence ; S2-3. Obtaining the ordered sequence of spatial position elements within the sentence , where each spatial position element in the sequence is arranged in the order of its appearance in the text, i represents the order in which the spatial position element appears from the beginning to the end in the text; and the spatial position elements with continuous characters describe An additional record is required , which constitutes a sequential sequence ; S2-4, according to the sentence time self-correction function formula: The time information to be self-calibrated Perform correction operation. Among them, is the input time information to be self-calibrated; Indicates the sequential sequence of continuous time element descriptions in step S2-2 The first value of ; Represents the serialization sequence in step S2-2 The first value of ; represents the intra-sentence temporal self-correction function; S2-5, according to the sentence spatial position self-correction function formula: The spatial position information to be self-corrected Perform correction operation. Among them, is the input spatial position information to be self-corrected; Represents the sequential sequence of continuous spatial position element descriptions in step S2-3 The first value of ; Represents the self-correction function of the spatial position within the sentence.

4. The method for self-correcting biased geographic information in network text based on context according to claim 1, characterized in that: Step S3 includes the following sub-steps: S3-1. Analyze the paragraphs one by one Contains context statements , and obtain the ordered sequence of time elements for each statement , and a sequential sequence of time elements with continuous characters .in, represents the kth sentence in paragraph P, and j represents the order in which the time element appears from the beginning to the end in sentence k. S3-2. Analyze the paragraphs one by one Contains context statements , and obtain the ordered sequence of spatial position elements of each sentence , and the sequential sequence of continuous spatial position elements of characters .in, represents the kth sentence in paragraph P, and j represents the order in which the spatial position element appears from front to back in sentence k. S3-3. Confirm and find the first continuous time element of characters in paragraph P, and filter it according to the following formula: in, Indicates the time element of the first character continuation. represents the character continuous time element sequence in step S3-1, Indicates the time information from the first sentence of paragraph P to the tth sentence to be self-corrected . S3-4. Confirm and find the spatial position element with the closest distance to the spatial position element to be corrected in paragraph P, with continuous characters, and select it according to the following formula: in, Indicates the continuous spatial position element of the first character, represents the ordered sequence of continuous spatial position elements of characters in step S3-2, Indicates the distance from the first sentence of paragraph P to the tth sentence where the spatial position information to be self-corrected is located .

5. The method for self-correcting biased geographic information in network text based on context according to claim 1, characterized in that: Step S4 includes the following sub-steps: S4-1. Self-correction formula based on the time element in the precise context: The time information to be self-calibrated Perform correction operation. Among them, is the input time information to be self-calibrated; Represents the self-correction function of the time element in the context of accurate context; The time element representing the first character continuity in step S3-3; represents the result of the intra-sentence time self-correction function in step S2-4; S4-2. Self-correction formula based on spatial position elements in the precise context: The spatial position information to be self-corrected Perform correction operation. Among them, is the input spatial position information to be self-corrected; Represents the self-correction function of the spatial position element in the precise context; The spatial position element representing the first character continuation in step S3-4; represents the result of the intra-sentence spatial position self-correction function in step S2-5; S4-3. Obtaining geographic information elements The results of self-correction in context .

6. A context-based network text biased geographic information self-correction device, characterized in that: Includes the following modules: A parsing module, used for parsing a target sentence of a specified paragraph to obtain geographic information elements to be self-corrected; An intra-sentence self-correction module, which corrects the geographic information elements of the target sentence based on the intra-sentence self-correction algorithm mentioned in claim 3; A paragraph self-correction module, extracting key information from the context sentences of the paragraph, and using the paragraph self-correction algorithm mentioned in claim 4 to filter and correct the geographic information; The context self-correction module performs final correction on the geographic information elements based on the contextual context at the sentence and paragraph levels using any of the steps in claim 5.

7. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, enables the processor to execute the context-based biased geographic information self-correction method for network text as described in claims 1-5.

8. A computer system comprising: A processor, configured to execute instructions stored in a storage medium to implement the self-correction method of claims 1-5; A memory, used to store the network text to be self-corrected and the intermediate results generated during the calculation process; The input / output interface is used to receive a specified text paragraph or geographic information and output corrected geographic information elements.

Images