The present disclosure relates to a method and device for providing patent document information based on natural language processing of patent documents. A method for visualizing patent documents implemented by a computer according to the present disclosure includes: receiving information about a target patent; and allowing a user interface to be displayed, wherein the user interface includes a first panel for classifying cores defining at least one component information extracted from the input target patent according to determined colors, and a second panel for classifying similarity assessment results of the target patent with respect to similar patents according to the determined colors. According to the present disclosure, by providing, in the form of a GUI, an interface for inputting patent information to be analyzed, users can easily request analysis of patent documents.

A highly accurate document search, particularly a search for a document relating to intellectual property, is achieved with an easy input method. A document search system includes a processing portion. The processing portion has a function of extracting a keyword included in text data, a function of extracting a related term of the keyword from words included in a plurality of pieces of first reference text analysis data, a function of giving a weight to each of the keyword and the related term, a function of giving a score to each of a plurality of pieces of second reference text analysis data on the basis of the weight, a function of ranking the plurality of pieces of second reference text analysis data on the basis of the score to generate ranking data, and a function of outputting the ranking data.

A request may be received from a user through a user interface an issued independent claim of a patent may be automatically compared to a pre-allowance published independent claim of an application of the patent to identify a unique keyword present in the issued independent claim but not present in the pre-allowance published independent claim. The unique keyword may be flagged to the user by highlighting the unique keyword in the user interface. A first prior art document may be retrieved using the flagged unique keyword. A unique keyword overlap score may be calculated for the first prior art document based on occurrences of the unique keyword in the first prior art document. A graphical representation of an identity of the first prior art document, the unique keyword, and the unique keyword overlap score may be generated for display in the user interface. The graphical representation may be displayed along with a graphical timeline based on a priority date of the first prior art document.

An information retrieval system that is capable of retrieving a similar application and value information of the similar application for a designated application is provided. An information retrieval system is provided that receives a designated application, calculates a first degree of similarity between a specification of the designated application and each of specifications of a plurality of applications, extracts a plurality of first similar applications from the plurality of applications on the basis of the first degree of similarity, calculates a second degree of similarity between a support drawing corresponding to the scope of claims of at least one of the plurality of first similar applications and at least one drawing of the designated application, extracts at least one drawing similar to the support drawing of at least one of the plurality of first similar applications from the drawings of designated application on the basis of the second degree of similarity, and outputs value information, the support drawing, and the similar drawing for at least one of the plurality of first similar applications. Related product information or the like can be given as the value information.

A system and method are provided for automatically proofing the patent specification of a granted patent issued on a patent application. The method comprises the steps of scanning amendments made to the patent application during prosecution; assembling the most recent claims, based on the scanned amendments, to create a test claim set of the claims; comparing the test claim set to the claims of the issued patent as published; and identifying any differences between the compared sets of claims and communicating the differences to a user.

The present invention relates to a terminal for providing a patent search and a control method therefor, a server for providing patent search and a control method therefor, and a patent search system and a control method therefor, and, to a terminal for providing a patent search and a control method therefor, a server for providing patent search and a control method therefor, and a patent search system and a control method therefor, all of which enable anyone to easily search for an idea that is looked for.

A computer-implemented method includes determining a set of identigens for each word of patent claim elements to produce sets of identigens and interpreting pairs of adjacent identigens of adjacent sets of identigens to determine a most likely meaning of the claim elements and produce a claim entigen group. The method further includes determining a level of match between the claim entigen group and a comparison matter entigen group. When the level of match between the claim entigen group and the comparison matter entigen group is greater than a threshold level, the method further includes indicating potential utilization of the claim by the comparison matter or potential prior art status of the comparison matter.

A computer includes a computing entity (CE) processing core section, a technology level (TL) co-processor section, a system database section, and a memory section. The database section stores TL data operands regarding quantified technologies and the memory section stores a CE operating system, a TL operating system, TL system applications, and TL user applications. The CE processing core section executes the TL operating system and the CE operating system. The TL co-processor section executes one or more TL system applications, in accordance with control of the TL operating system and the CE operating system, to produce TL data operands regarding a quantified technology from a large number of MSBTP documents.

A system and computer implemented method of patent mapping are provided. The method comprises maintaining a database of patent portfolios and a database of patents, each patent stored in the database of patents associated. with one or more patent portfolios stored in the database of patent portfolios; maintaining a database of ontologies, the ontologies including one or more patent concepts in defined groups; receiving a search query associated with a first patent portfolio; searching the first portfolio as a function of the search query; generating search results, the search results including one or more patent claims associated with the search query; and mapping the one or more patent claims to a patent concept in a defined group.

A system and method for patent mapping are provided. The system comprises a database of patent sets and a database of patents, each patent stored in the database of patents associated with one or more patent sets stored in the database of patent sets; and one or more modules to perform a portion of one or more of the following: receive input identifying a set of keyword source claims associated with a first patent set; automatically extract at least one keyword from the source claims; receive or formulate a search query associated with the first patent set, the search query including the at least one keyword; search the entire first patent set as a function of the search query; generate search results, the search results including one or more patent claims associated with the search query; and map the one or more patent claims to a patent concept.