KR-20260065223-A - SERVER TO ANALYZE DOCUMENT AUTOMATIC BASED ON ARTIFICIAL INTELLIGENCE LEARNING MODEL AND METHOD OPERATION THEREOF

KR20260065223AKR 20260065223 AKR20260065223 AKR 20260065223AKR-20260065223-A

Abstract

According to various embodiments, a server for automatically performing analysis of a document based on an artificial intelligence model comprises: a communication interface; and a processor; wherein the processor acquires at least one document information from an external electronic device of a user through the communication interface, inputs at least one document information into the artificial intelligence model to output at least one predicted document information, and is configured to determine that the at least one predicted document information is document information that does not contain errors when the at least one predicted document information exceeds a preset first threshold value, and the artificial intelligence model is learned based on a plurality of document information, a plurality of predicted document information, information in which the plurality of predicted document information is determined to be accurate, and information in which the plurality of predicted documents are determined to be inaccurate.

Inventors

이상현

Assignees

호남대학교 산학협력단

Dates

Publication Date: 20260508
Application Date: 20241101

Claims (10)

In a server for automatically performing document analysis based on an artificial intelligence model, Communication interface; and Includes a processor; and The above processor is, Through the above communication interface, at least one document information is obtained from the user's external electronic device, and Input at least one document information into the artificial intelligence model to output at least one expected document information, and When the above at least one expected document information exceeds a preset first threshold value, the above at least one expected document information is determined to be document information that does not contain errors, and The above artificial intelligence model is, Learning based on multiple document information, multiple predicted document information, information where multiple predicted document information is judged to be accurate, and information where multiple predicted documents are judged to be inaccurate, Server.
In Article 1, The above at least one document information is, At least one word information composed of a word containing at least one document and/or text, at least one first PDF information composed of a PDF containing at least one document and/or text, and at least one image information composed of an image containing at least one document and/or text, Server.
In Article 2, The above processor is, Extracting key text and/or image information, such as title, author, and abstract, based on natural language processing (NLP) of at least one first PDF information, and The extracted core text and/or image information is automatically entered into a pre-set form information to output at least one second PDF information, and The above at least one second PDF information is configured to be input into the artificial intelligence model, and The above artificial intelligence model is, A plurality of at least one first PDF information and a plurality of at least two PDF information are additionally learned, Server.
In Paragraph 3, Including memory; further, The above processor is, Based on the above 2nd DPF information, regular expression definition, technical information extraction, section iteration, and match verification are performed, and In the above prediction model, output is provided to include at least one predicted document information with a preset number of characters to enable quick verification of the summary based on at least one second PDF information, and Set to automatically save at least one expected document information to the memory, Server.
In Paragraph 4, The above processor is, If the above at least one expected document information does not exceed the first threshold value, the above at least one expected document information is compared with a second threshold value set lower than the first threshold value, and If the above at least one expected document information exceeds the above second threshold value, it is determined that the above at least one expected document information is document information containing an error, and If the above at least one expected document information does not exceed the above second threshold value, it is determined that the above at least one expected document information is document information containing many errors, and A set to transmit at least one expected document information exceeding the first threshold value and/or the second threshold value to the user's external electronic device through the above communication interface, Server.
In a method for operating a server to automatically perform analysis of documents based on an artificial intelligence model, The above method is, Through a communication interface, at least one document information is obtained from a user's external electronic device, and Through a processor, at least one document information is input into the artificial intelligence model to output at least one predicted document information, and Through the above processor, if the at least one expected document information exceeds a preset first threshold value, the at least one expected document information is determined to be document information that does not contain errors, and The above artificial intelligence model is, Learning based on multiple document information, multiple predicted document information, information where multiple predicted document information is judged to be accurate, and information where multiple predicted documents are judged to be inaccurate, method.
In Article 6, The above at least one document information is, At least one word information composed of a word containing at least one document and/or text, at least one first PDF information composed of a PDF containing at least one document and/or text, and at least one image information composed of an image containing at least one document and/or text, method.
In Article 7, The above method is, Extracting key text and/or image information, such as title, author, and abstract, based on natural language processing (NLP) of at least one first PDF information, and The extracted core text and/or image information is automatically entered into a pre-set form information to output at least one second PDF information, and The above at least one second PDF information is configured to be input into the artificial intelligence model, and The above artificial intelligence model is, A plurality of at least one first PDF information and a plurality of at least two PDF information are additionally learned, method.
In Article 8, The above method is, Based on the above 2nd DPF information, regular expression definition, technical information extraction, section iteration, and match verification are performed, and In the above prediction model, output is provided to include at least one predicted document information with a preset number of characters to enable quick verification of the summary based on at least one second PDF information, and Set to automatically save at least one expected document information in memory, method.
In Article 9, The above method is, If the above at least one expected document information does not exceed the first threshold value, the above at least one expected document information is compared with a second threshold value set lower than the first threshold value, and If the above at least one expected document information exceeds the above second threshold value, it is determined that the above at least one expected document information is document information containing an error, and If the above at least one expected document information does not exceed the above second threshold value, it is determined that the above at least one expected document information is document information containing many errors, and A set to transmit at least one expected document information exceeding the first threshold value and/or the second threshold value to the user's external electronic device through the above communication interface, method.

Description

Server for automatically performing document analysis based on an artificial intelligence model and method of operating the same Various embodiments of the present invention relate to a server for automatically performing analysis of documents based on an artificial intelligence model and a method for operating the same. Recently, many patent applications based on numerous papers and authors are being filed, and in particular, a very large number of patents have been filed in Korea since the 2020s. To request such a patent from an agent, the application form is prepared in advance and sent to the agent. However, conventionally, drafting a patent application required researchers to manually extract information from papers and fill it out according to the format, which presented problems that could lead to errors and inefficiency. In particular, conventionally, based on the aforementioned issues, there were many problems with consistency, and furthermore, due to significant differences from the structure of the paper, it was difficult to distinguish using simple keywords and there was a problem where the context could be missed. Therefore, in order to overcome the aforementioned problems, there is a need for a system and method that can easily generate patent applications and requests by automatically inputting them based on papers and/or written documents. FIG. 1 illustrates a block diagram of a server and a network according to various embodiments of the present invention. FIG. 2 is a flowchart illustrating how a server operates according to various embodiments. FIG. 3 is a diagram illustrating, in exemplary terms, the operation of automatic document output based on PDF files between a server and an external electronic device according to various embodiments. FIG. 4 is an example diagram showing source code for a server to briefly generate text extracted from PDF information according to various embodiments. FIG. 5 is an example diagram showing a structure for outputting and storing at least one expected document information output by a server according to various embodiments. FIG. 6 is a specific example of at least one expected document information output by a server according to various embodiments. Hereinafter, various embodiments of this document are described with reference to the accompanying drawings. The embodiments and the terms used therein are not intended to limit the technology described in this document to specific embodiments and should be understood to include various modifications, equivalents, and/or substitutions of said embodiments. In relation to the description of the drawings, similar reference numerals may be used for similar components. A singular expression may include a plural expression unless the context clearly indicates otherwise. In this document, expressions such as "A or B" or "at least one of A and/or B" may include all possible combinations of items listed together. Expressions such as "first," "second," "first," or "second" may modify said components regardless of order or importance and are used only to distinguish one component from another and do not limit said components. When it is mentioned that a certain (e.g., 1st) component is "(functionally or telecommunicationally) connected" or "connected" to another (e.g., 2nd) component, said certain component may be directly connected to said other component or connected through another component (e.g., 3rd component). In this document, "configured to" may be used interchangeably with, depending on the context, for example, hardware- or software-wise, "suitable for," "capable of," "modified to," "made to," "capable of," or "designed to." In some cases, the expression "device configured to" may mean that the device is "capable of" in conjunction with other devices or components. For example, the phrase "processor configured to perform A, B, and C" may mean a dedicated processor for performing the corresponding operations (e.g., an embedded processor), or a general-purpose processor capable of performing the corresponding operations by executing one or more software programs stored in a memory device (e.g., a CPU or application processor). An electronic device according to various embodiments of the present document may include, for example, at least one of a smartphone, a tablet PC, a desktop PC, a laptop PC, a netbook computer, a workstation, and a server. Referring to FIG. 1, an electronic device (101) within a network environment (100) in various embodiments is described. The electronic device (101) may include a bus (110), a processor (120), a memory (130), an input/output interface (140), a display (150), and a communication interface (160). In some embodiments, the electronic device (101) may omit at least one of the components or additionally include other components. The bus (110) may include a circuit that connects the components (110-160) to each other and transmits communication (e.g., control messages or data)