Device for standard word AI error correction and traceability interpretation

Abstract

The device comprises an RPA data acquisition module, a DLF file generation module, an AI intelligent training module, an AI intelligent error correction module, a traceability interpretation module and a combined bound volume generation module, and creates a brand-new device for standard word AI error correction and traceability interpretation. When the reading object content is subjected to error correction, internet resources are used as a knowledge base of the reading object content, and traceability comparison is realized; according to the GB / T39677-2020 national standard, the traceability object is archived, and it is guaranteed that the original edition and the original sample of the traceability object are real and complete in the current historical period; according to the method, the archived webpage is reassembled by adopting a DLF file technology to generate a dynamic layout file, so that the current historical original appearance of the webpage is freeze-frame, the current website effect can be reproduced vividly and can be stored for a long time, the scene of the current webpage can be reflected by tracing, and the webpage can be stored for a long time. And the user experience is greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of AI technology, and in particular to a device for AI error correction and source tracing interpretation of standardized terms. Background Art

[0002] In the era of information explosion, text is the main carrier of information transmission, and its accuracy and standardization are directly related to the effective communication and understanding of information. However, due to various factors, such as regional differences, education level, and the rise of Internet language, inappropriate wording and grammatical errors often appear in texts.

[0003] To solve this problem, artificial intelligence technology came into being. In particular, the rapid development of natural language processing (NLP) has enabled AI systems to deeply understand text content and identify and correct errors in word usage.

[0004] After training on a large number of standard words, we can mark out the wrong words during actual use. When combined with sentences, many standard words cannot be accurately identified. After a sentence is used incorrectly, there is no way to trace the source after the error is corrected. Summary of the invention

[0005] The purpose of the present invention is to provide a device for AI error correction and source tracing interpretation of standardized terms to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above-mentioned purpose, the present invention provides the following technical solution: a device for AI error correction and source tracing interpretation of standardized terms, comprising an RPA data collection module, a DLF file generation module, an AI intelligent training module, an AI intelligent error correction module, a source tracing interpretation module, and a combined bound volume generation module. The RPA data collection module is used to collect information from the set website and obtain the standard words in the web page according to regular expressions and semantics; The DLF file generation module obtains an offline web page file, converts the interface content corresponding to each level in the web page into an OFD file, and assembles the converted OFD file into a DLF file according to the web page level relationship; The AI ​​intelligent training module inputs the collected information into the training application system, extracts the list of 'standard words', calls the AI ​​extension model, and constructs sentences for the specified words in different situations; The AI ​​intelligent error correction module is used to infer the sentence input by the user that needs to be checked or corrected, and return whether there is an error in the sentence according to the inference result; The source tracing and interpretation module is used to parse the data structure returned by the AI ​​intelligent error correction module, render and display the parsed results, and mark the source button. The parsed results are linked to the original text; The combined bound volume generation module combines all linked files in the source tracing interpretation module with the DLF files generated by the DLF file generation module to generate a bound volume.

[0007] Preferably, the RPA data collection module collects information including standardized terms, basic meanings and developments, interpretations, historical backgrounds, corresponding URLs, and offline corresponding web page files.

[0008] Preferably, the DLF file is a compressed package file, which contains a navigation file and several OFD files, wherein the navigation file mainly records the association relationship between files, file entries, storage path of OFD files, and trigger locations and jump events between OFD and OFD.

[0009] Preferably, when the AI ​​intelligent training module constructs sentences for the specified words in different situations, the sentence patterns include simple sentences, parallel sentences, compound sentences, interrogative sentences, exclamatory sentences, declarative imperative sentences, and predicate inversion sentences. When constructing sentences, N sentences of each type are generated according to the correct content and the incorrect content, and the standardized words, correct sentences, and incorrect sentences are input into the model for sentence training.

[0010] Preferably, the AI ​​intelligent error correction module performs logical reasoning on the input sentences. If it is an erroneous sentence, it marks the erroneous information content: erroneous words, standard normative words, and the location of the error; when the reasoning result returns that there are multiple errors in the sentence, the erroneous content is displayed in the form of a queue, and the erroneous content is directly corrected and then sent to the model for secondary training.

[0011] Preferably, the traceability and interpretation module refers to querying the corresponding data information in the normative term storage system according to the normative term, the data information includes the normative term, basic meaning and development, interpretation, historical background, and website address. After querying the corresponding data information, the page is loaded and a link is established between the page and the original file content.

[0012] Preferably, the combined bound volume generation module combines all DLF files matched by the traceability interpretation into a bound volume, uses a DLF reader to open the specified DLF file, automatically jumps to the specific traceability location in each DLF, and displays multiple traceability jump directory addresses for each DLF file, which can be switched by clicking.

[0013] Preferably, the combined bound volume generation module supports displaying the specified standard terms, basic meanings and developments, interpretations, and historical backgrounds on the DLF file using different colors, icons, and styles, and extracting the content to form an outline; when the DLF file displays the traceability content, for the corresponding original text address, first check whether the original text address exists. If so, directly display the link to the original text on the DLF to achieve the final tracking and tracing of the original address.

[0014] The device for AI error correction and source tracing of standard terms according to claim 1 is characterized by: Step S1: The RPA data collection module collects information from the set website, including standardized terms, basic meanings and developments, interpretations, historical backgrounds, corresponding websites, and offline corresponding web page files; Step S2: The DLF file generation module obtains the offline web page file, converts the interface content corresponding to each level in the web page into an OFD file, and assembles the converted OFD file into a DLF file according to the web page level relationship; Step S3: The AI ​​intelligent training module inputs the collected information into the training application system, calls the AI ​​extension model, and constructs sentences for the specified words in different situations; Step S4: The AI ​​intelligent error correction module infers the sentence input by the user that needs to be checked or corrected, and returns whether there is an error in the sentence based on the inference result; Step S5: The source tracing interpretation module is used to parse the data structure returned by the AI ​​intelligent error correction module and render and display the parsed results; Step S6: The combined bound volume generation module combines all linked files in the source tracing interpretation module with the DLF files generated by the DLF file generation module to generate a bound volume.

[0015] Compared with the prior art, the present invention has the following beneficial effects: (1) The present invention creates a new AI error correction and source tracing interpretation device for standardized wording, which uses Internet resources as its knowledge base when correcting the content of the reading object and realizes source tracing comparison; (2) The present invention archives the traceability object in accordance with the national standard GB / T39677-2020, ensuring that the original version is authentic and complete in the current historical period; (3) The present invention uses DLF file technology to reassemble archived web pages and generate a dynamic layout file, thereby freezing the original historical appearance of the web page at that time, so that the website effect at that time can be vividly reproduced and can be preserved for a long time, realizing the traceability and reflecting the scene of the web page at that time, greatly improving the user experience; (4) The present invention adopts DLF dynamic layout file technology to localize the traceability content, thereby solving the problem of inaccessibility of the external network caused by the separation of the user's internal and external network, and does not affect the user's traceability comparison of the AI ​​error correction of standardized terms; (5) The present invention uses an AI intelligent error correction module to reason about sentences. After reasoning, secondary training can be performed for incorrect data, thereby achieving the purpose of continuous learning; (6) The present invention converts different web page sources into DLF files and then generates a DLF file binding book, so that different web pages can be viewed in the same reader, achieving the purpose of "one-stop search". DETAILED DESCRIPTION

[0016] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solution of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] A device for AI error correction and source tracing interpretation of standardized terms consists of an RPA data acquisition module, a DLF file generation module, an AI intelligent training module, an AI intelligent error correction module, a source tracing interpretation module, and a combined bound book generation module. The RPA data collection module is used to collect information from the set URLs and obtain the standardized words in the web pages based on regular expressions and semantics; The DLF file generation module obtains the offline web page file, converts the interface content corresponding to each level in the web page into an OFD file, and assembles the converted OFD file into a DLF file according to the web page level relationship; The AI ​​intelligent training module inputs the collected information into the training application system, extracts the list of "standard words", calls the AI ​​extension model, and constructs sentences for the specified words in different situations; The AI ​​intelligent error correction module is used to infer the user input statements that need to be checked or corrected, and returns whether there are errors in the statements based on the inference results; The source tracing interpretation module is used to parse the data structure returned by the AI ​​intelligent error correction module, render and display the parsed results, and mark the source button. The parsed results are linked to the original text; The combined bound volume generation module combines all linked files in the source tracing interpretation module with the DLF files generated by the DLF file generation module to generate a bound volume.

[0018] The working steps of a device for AI error correction and source tracing of standardized words are as follows: Step S1: The RPA data collection module collects information from the set website, and obtains the standard words in the web page according to regular expressions and semantics. The collected content includes standard words, basic meanings and developments, interpretations, historical backgrounds, corresponding websites, and offline corresponding web page files; Step S2: The DLF file generation module obtains the offline web page file, converts the interface content corresponding to each level in the web page into an OFD file, and assembles the converted OFD file into a DLF file according to the web page level relationship, wherein the DLF file is a compressed package file, and the DLF file contains a navigation file and several OFD files, wherein the navigation file mainly records the association relationship between files, the entry of the file, the storage path of the OFD file, and the triggering position and jump event between OFD and OFD; Step S3: The AI ​​intelligent training module inputs the collected information into the training application system, calls the AI ​​extension model, and constructs sentences for the specified words in different situations. The sentence patterns include simple sentences, parallel sentences, compound sentences, interrogative sentences, exclamatory sentences, declarative imperative sentences, and predicate inversion sentences. When constructing sentences, N sentences of each type are generated according to the correct content and the incorrect content, and the standardized words, correct sentences, and incorrect sentences are input into the model for sentence training.

[0019] Step S4: The AI ​​intelligent error correction module infers the sentences input by the user that need to be checked or corrected, and returns whether there are errors in the sentences based on the inference results. For the erroneous sentences, the erroneous information content is marked: the erroneous words, the standard normative words, and the location of the error; When the inference result returns that there are multiple errors in the sentence, the erroneous content is displayed in the form of a queue, and the erroneous content is directly corrected, and then sent to the model for secondary training; Step S5: The source tracing interpretation module is used to parse the data structure returned by the AI ​​intelligent error correction module, render and display the parsed results, and query the corresponding data information in the normative word storage system according to the normative word. The data information includes the normative word, basic meaning and development, interpretation, historical background, and website. After the corresponding data information is queried, the page is loaded and a link is established between the page and the original file content; Step S6: The combined bound volume generation module combines all linked files in the source tracing interpretation module with the DLF file generated by the DLF file generation module to generate a bound volume, and uses the DLF reader to open the specified DLF file. Each DLF automatically jumps to the specific source tracing location and displays multiple source tracing jump directory addresses of each DLF file. Click to switch. The combined bound volume generation module supports displaying the specified standard terms, basic meanings and developments, interpretations, and historical backgrounds on the DLF file with different colors, icons, and styles, and extracts the content to form an outline. When the DLF file displays the source tracing content, it first verifies whether the corresponding original text address exists. If it exists, the link to the original text is directly displayed on the DLF to achieve the tracking and tracing of the final original address.

[0020] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. Therefore, the embodiments should be considered exemplary and non-restrictive in all respects, and the scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims be included in the present invention.

Claims

1. A device for AI error correction and source tracing of standardized terms, characterized by: It includes RPA data collection module, DLF file generation module, AI intelligent training module, AI intelligent error correction module, source tracing interpretation module, and combined bound book generation module. The RPA data collection module is used to collect information from the set website and obtain the standard words in the web page according to regular expressions and semantics; The DLF file generation module obtains an offline web page file, converts the interface content corresponding to each level in the web page into an OFD file, and assembles the converted OFD file into a DLF file according to the web page level relationship; The AI ​​intelligent training module inputs the collected information into the training application system, extracts the list of 'standard words', calls the AI ​​extension model, and constructs sentences for the specified words in different situations; The AI ​​intelligent error correction module is used to infer the sentence input by the user that needs to be checked or corrected, and return whether there is an error in the sentence according to the inference result; The source tracing and interpretation module is used to parse the data structure returned by the AI ​​intelligent error correction module, render and display the parsed results, and mark the source button. The parsed results are linked to the original text; The combined bound volume generation module combines all linked files in the source tracing interpretation module with the DLF files generated by the DLF file generation module to generate a bound volume.

2. According to claim 1, the device for AI error correction and source tracing interpretation of standard terms is characterized by: The RPA data collection module collects information including standardized terms, basic meanings and developments, interpretations, historical backgrounds, corresponding URLs, and offline corresponding web page files.

3. The device for AI error correction and source tracing of standard terms according to claim 1 is characterized by: The DLF file is a compressed package file, which contains a navigation file and several OFD files. The navigation file mainly records the association relationship between files, file entries, storage paths of OFD files, and trigger locations and jump events between OFD and OFD.

4. The device for AI error correction and source tracing of standard terms according to claim 1 is characterized by: When the AI ​​intelligent training module constructs sentences for the specified words in different situations, the sentence patterns include simple sentences, parallel sentences, compound sentences, interrogative sentences, exclamatory sentences, declarative imperative sentences, and predicate inversion sentences. When constructing sentences, N sentences of each type are generated according to the correct content and the incorrect content, and the standardized words, correct sentences, and incorrect sentences are input into the model for sentence training.

5. The device for AI error correction and source tracing of standard terms according to claim 1 is characterized by: The AI ​​intelligent error correction module performs logical reasoning on the input sentences. If it is an erroneous sentence, it marks the erroneous information content: erroneous words, standard normative words, and the location of the error. When the reasoning result returns that there are multiple errors in the sentence, the erroneous content is displayed in the form of a queue, and the erroneous content is directly corrected and then sent to the model for secondary training.

6. The device for AI error correction and source tracing of standard terms according to claim 1 is characterized by: The traceability and interpretation module refers to querying the corresponding data information in the normative word storage system according to the normative word. The data information includes the normative word, basic meaning and development, interpretation, historical background, and website. After querying the corresponding data information, the page is loaded and a link is established between the page and the original file content.

7. The device for AI error correction and source tracing of standard terms according to claim 1 is characterized by: The combined bound volume generation module combines all DLF files matched by the traceability interpretation into a bound volume, uses a DLF reader to open the specified DLF file, automatically jumps to the specific traceability location in each DLF, and displays multiple traceability jump directory addresses of each DLF file, which can be switched by clicking.

8. The device for AI error correction and source tracing of standard terms according to claim 1 is characterized by: The combined bound volume generation module supports displaying the specified standardized terms, basic meanings and developments, interpretations, and historical backgrounds on the DLF file using different colors, icons, and styles, and extracting the content to form an outline; when the DLF file displays the traceability content, for the corresponding original text address, first check whether the original text address exists. If so, directly display the link to the original text on the DLF to achieve the tracking and tracing of the final original address.

9. The device for AI error correction and source tracing of standard terms according to claim 1 is characterized by: Step S1: The RPA data collection module collects information from the set website, including standardized terms, basic meanings and developments, interpretations, historical backgrounds, corresponding websites, and offline corresponding web page files; Step S2: The DLF file generation module obtains the offline web page file, converts the interface content corresponding to each level in the web page into an OFD file, and assembles the converted OFD file into a DLF file according to the web page level relationship; Step S3: The AI ​​intelligent training module inputs the collected information into the training application system, calls the AI ​​extension model, and constructs sentences for the specified words in different situations; Step S4: The AI ​​intelligent error correction module infers the sentence input by the user that needs to be checked or corrected, and returns whether there is an error in the sentence based on the inference result; Step S5: The source tracing interpretation module is used to parse the data structure returned by the AI ​​intelligent error correction module and render and display the parsed results; Step S6: The combined bound volume generation module combines all linked files in the source tracing interpretation module with the DLF files generated by the DLF file generation module to generate a bound volume.