KR20210039904A - Method and system for acquiring word set of patent document using image information - Google Patents

Abstract

Disclosed is a method for obtaining word sets of patent documents using image information. The method for obtaining the word sets of the patent documents includes steps of: obtaining, by a server, patent documents; obtaining, by the server, a plurality of word sets by analyzing morphemes on the basis of the patent documents; determining, by the server, an erroneous word set among the acquired plurality of word sets; correcting, by the server, the erroneous word set; and obtaining, by the server, at least one compound noun phrase set on the basis of a correlation between the plurality of word sets.

Description

Method and system for acquiring word set of patent documents using image information {METHOD AND SYSTEM FOR ACQUIRING WORD SET OF PATENT DOCUMENT USING IMAGE INFORMATION}

The present invention relates to a method and system for obtaining a word set of a patent document.

With the development of the fourth industry, the value of intellectual property rights is increasing. Accordingly, many people are trying to protect their own technology and acquire rights to technology, and interest in patent applications for technology is increasing.

On the other hand, for a patent application, a prior art search is performed to determine whether the own technology can be patented, and a prior art search may be performed by searching various patent documents published in the past.

However, due to the vast amount of patent documents and time constraints, it is virtually impossible to analyze all patent documents published in the past. The reality is that prior art investigations are being conducted.

Prior art research through search type input, etc., is often dependent on the ability of personnel to conduct prior art research, so there are cases in which it is not possible to guarantee stable results for prior art research.

Therefore, there is a need for a prior art research method that can guarantee stable results with a small time investment.

Registered Patent Publication No. 10-0481598, 2005.03.29

The problem to be solved by the present invention is to provide a method and system for obtaining a word set of a patent document.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems that are not mentioned will be clearly understood by those skilled in the art from the following description.

A method for obtaining a word set of a patent document according to an aspect of the present invention for solving the above-described problem includes the steps of: obtaining, by a server, the patent document; Obtaining, by the server, a morpheme based on the patent document to obtain a plurality of word sets; Determining, by the server, an error word set from among the acquired plurality of word sets; Modifying, by the server, the error word set; And obtaining, by the server, at least one compound noun phrase set based on a degree of association between the plurality of word sets.

In this case, obtaining the plurality of word sets may include obtaining sentences included in the patent document; Dividing the sentence into syllable units; Matching a part-of-speech tag to the divided syllables; And obtaining a morpheme included in the sentence based on the divided syllables. It may include.

In this case, the determining of the error word set may include matching semantic information for each of the obtained plurality of word sets; Obtaining an accuracy score for each of the plurality of word sets based on the matched meaning information and the patent document; And determining a word set whose accuracy score is less than or equal to a preset value as an error word set.

In this case, the step of correcting the error word set may include obtaining a plurality of semantic information for the error word; Obtaining a plurality of weights for each of the obtained plurality of semantic information; Obtaining a weight having the highest correlation with the patent document from among the plurality of weights; And matching semantic information corresponding to a weight having the highest association with the patent document to the error word set. It may include.

In this case, obtaining the at least one compound noun phrase set may include obtaining a plurality of word sets for sentences included in the patent document; Obtaining a plurality of compound noun phrase set candidates obtained by combining the plurality of word sets; Obtaining a frequency in which a plurality of obtained compound noun phrase sets and the same compound noun phrase set candidates are included in the patent document; And determining a composite noun phrase set candidate whose frequency is equal to or greater than a preset frequency as a composite noun phrase set. Including, the composite noun phrase set candidate may include order information and spacing information of word sets included in the composite noun phrase set candidate.

In this case, the obtaining of the composite noun phrase set candidate may include changing the positions of the plurality of word sets when the plurality of word sets satisfy a preset condition; Determining the changed plurality of word sets as a composite noun phrase set candidate; Including, the preset condition, a condition in which the plurality of word sets are adjacent, a condition in which a preset sign is included between the plurality of adjacent word sets, and a word set located to the right of the plurality of adjacent word sets includes parentheses. It may be a condition in which the plurality of word sets are in different languages.

In this case, obtaining the word set may include analyzing sentences included in the patent document; If the sentence has a preset structure, acquiring at least one word set from among the word sets included in the sentence excluding a word set corresponding to the preset structure; Obtaining semantic information of the at least one word set; And obtaining a word set corresponding to the semantic information. It may include.

In this case, the step of obtaining the word set may include: obtaining a plurality of identification item information and a template included in the patent document; Obtaining a plurality of sentences excluding the obtained template; Assigning a weight to each of the plurality of identification item information; Determining a priority of an identification item to perform morpheme analysis based on a weight of each of the plurality of identification item information; And obtaining a word set for a plurality of sentences from which the template is excluded according to the determined priority. It may include.

In this case, the obtaining of the word set may include determining whether an identification item adjacent to the image exists when the patent document contains an image; Obtaining text included in the image when the identification item is adjacent to the image; And obtaining a word set based on the obtained text. It may include.

Other specific details of the present invention are included in the detailed description and drawings.

According to various embodiments of the present invention described above, it is possible to obtain a word set for efficiently analyzing a patent document.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 is a system diagram for implementing a method of obtaining a word set of a patent document according to an embodiment of the present invention.
2 is a flowchart illustrating a method of obtaining a word set of a patent document according to an embodiment of the present invention.
3 is a flowchart illustrating a method of obtaining a plurality of word sets from a patent document according to an embodiment of the present invention.
4 is a flowchart illustrating a method of determining an error word set according to an embodiment of the present invention.
5 is a flowchart illustrating a method of correcting an error word set according to an embodiment of the present invention.
6 is a flowchart illustrating a method of obtaining a compound noun phrase set according to an embodiment of the present invention.
7 is a flowchart illustrating a method of obtaining a compound noun phrase set according to another embodiment of the present invention.
8 is a flowchart illustrating a method of obtaining a word set according to an embodiment of the present invention.
9 is a flowchart illustrating a method of obtaining a word set excluding a template of a patent document according to an embodiment of the present invention.
10 is a flowchart illustrating a method of obtaining a word set when an image exists in a patent document according to an embodiment of the present invention.
11 is a block diagram of an apparatus according to an embodiment of the present invention.

Advantages and features of the present invention, and a method of achieving them will become apparent with reference to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in a variety of different forms. It is provided to fully inform the skilled person of the scope of the present invention, and the present invention is only defined by the scope of the claims.

The terms used in the present specification are for describing exemplary embodiments and are not intended to limit the present invention. In this specification, the singular form also includes the plural form unless specifically stated in the phrase. As used herein, “comprises” and/or “comprising” do not exclude the presence or addition of one or more other elements other than the mentioned elements. Throughout the specification, the same reference numerals refer to the same elements, and "and/or" includes each and all combinations of one or more of the mentioned elements. Although "first", "second", and the like are used to describe various elements, it goes without saying that these elements are not limited by these terms. These terms are only used to distinguish one component from another component. Therefore, it goes without saying that the first component mentioned below may be the second component within the technical idea of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in the present specification may be used with meanings that can be commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, terms defined in a commonly used dictionary are not interpreted ideally or excessively unless explicitly defined specifically.

The term "unit" or "module" used in the specification refers to a hardware component such as software, FPGA or ASIC, and the "unit" or "module" performs certain roles. However, "unit" or "module" is not meant to be limited to software or hardware. The “unit” or “module” may be configured to be in an addressable storage medium, or may be configured to reproduce one or more processors. Thus, as an example, "sub" or "module" refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, Includes procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays and variables. Components and functions provided within "sub" or "modules" may be combined into a smaller number of components and "sub" or "modules" or into additional components and "sub" or "modules". Can be further separated.

Spatially relative terms "below", "beneath", "lower", "above", "upper", etc. It can be used to easily describe the correlation between a component and other components. Spatially relative terms should be understood as terms including different directions of components during use or operation in addition to the directions shown in the drawings. For example, if a component shown in a drawing is turned over, a component described as "below" or "beneath" of another component will be placed "above" the other component. I can. Accordingly, the exemplary term “below” may include both directions below and above. Components may be oriented in other directions, and thus spatially relative terms may be interpreted according to the orientation.

In the present specification, a computer means all kinds of hardware devices including at least one processor, and may be understood as encompassing a software configuration operating in the corresponding hardware device according to embodiments. For example, the computer may be understood as including all of a smartphone, a tablet PC, a desktop, a laptop, and a user client and application running on each device, and is not limited thereto.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

Each of the steps described herein is described as being performed by a computer, but the subject of each step is not limited thereto, and at least some of the steps may be performed by different devices according to embodiments.

1 is a system diagram for implementing a method of obtaining a word set of a patent document according to an embodiment of the present invention.

A system for obtaining a word set of a patent document according to the present invention includes a server 10 and an electronic device 20.

The server 10 is a component for acquiring a patent document and acquiring a word set from the acquired patent document.

Specifically, the server 10 may receive a patent document from the electronic device 20, obtain a patent document from an external server, and obtain a word set of the obtained patent document.

In this specification, the patent document may be a document on the technical content submitted by an applicant to obtain a patent registration at a national patent office. However, the present disclosure is not limited thereto, and a patent document may be understood as a concept including various documents including technical contents such as a job invention for a patent application, a thesis, and the like.

The electronic device 20 is a configuration for providing a patent document to the server 10. The electronic device 200 according to the present invention may be implemented as a smart phone, but this is only an example, and a smart phone, a tablet personal computer, a mobile phone, a video phone, E-book reader, desktop PC, laptop PC, netbook computer, workstation, server, personal digital assistant (PDA), portable multimedia (PMP) player) or a wearable device.

Hereinafter, the present invention will be described in detail through various embodiments of FIGS. 2 to 10.

2 is a flowchart illustrating a method of obtaining a word set of a patent document according to an embodiment of the present invention.

In step S110, the server 10 may obtain a patent document.

In one embodiment, the server 10 may obtain a job invention from the electronic device 20 as a patent document. In another embodiment, the server 10 may receive the patent publication or registration publication from an external server and obtain it as a patent document.

In step S120, the server 10 may obtain a word set by analyzing the morpheme based on the patent document.

In one embodiment, the server 10 may perform a morpheme analysis of a patent document using a Mecab morpheme analyzer. However, the present invention is not limited thereto, and of course, various morpheme analyzers such as Okt, Komoran, Hannanum, and Kkma morpheme analyzers may be used in some cases. Furthermore, it goes without saying that the server 10 can use various morpheme analyzers according to the language of the patent document to be analyzed.

In step S130, the server 10 may determine an error word set from among the acquired plurality of word sets.

In an embodiment, when the acquired plurality of word sets do not satisfy a preset condition, the server 10 may determine the corresponding word as an error word. A detailed description of this will be described later.

In step S140, the server 10 may correct the error word set.

In step S150, the server 10 may obtain at least one compound noun phrase set based on the degree of association between the plurality of word sets.

3 is a flowchart illustrating a method of obtaining a plurality of word sets from a patent document according to an embodiment of the present invention.

In step S210, the server 10 may obtain a sentence included in the patent document. Specifically, the server 10 may classify text included in the patent document into sentences, and perform morpheme analysis for each of the classified sentences.

In step S220, the server 10 divides the sentence into syllable units, in step S230, the server 10 matches the part-of-speech tag to the divided syllables, and in step S240, the server 10 is based on the divided syllables. As a result, the morpheme included in the sentence can be obtained.

In an embodiment, the server 10 may perform a syllable segmentation and part-of-speech tag matching process based on LSTM-CRFs and word2vec algorithms, but is not limited thereto.

4 is a flowchart illustrating a method of determining an error word set according to an embodiment of the present invention.

In step S310, the server 10 may match semantic information for each of the obtained plurality of word sets.

In this case, the semantic information may mean an intent for a word set. The server 10 may perform natural language processing using an artificial intelligence model to obtain semantic information for a word set.

Specifically, the artificial intelligence model includes a natural language understanding unit, and the natural language understanding unit can grasp the intent of an entity and a set of words included in the sentence based on the sentence analysis result, and further, the natural language understanding unit Sentence can be analyzed through structure and main component analysis, and sentence analysis can be performed using statistics/analysis.

In an embodiment, the server 10 may obtain semantic information about the apple by analyzing a sentence including'apple'. For example, it may be assumed that the word set acquired through sentence text is “apple.” In this case, the meaning information about an apple may be semantic information indicating one type of fruit as a noun, but another person as a verb. It may also be semantic information indicating that a mistake is spoken to the server 10. The server 10 may match semantic information determined to be suitable for a sentence among a plurality of semantic information for'apple' with'apple'.

In step S320, the server 10 may obtain an accuracy score for each of the plurality of word sets based on the matched semantic information and the patent document.

In this case, in step S310, semantic information for a word set acquired through one sentence is acquired, but the semantic information acquired through step S310 may be inaccurate. Accordingly, the server 10 may obtain an accuracy score of the semantic information matched to the word set based on the entire patent document including the sentence.

Accordingly, the server 10 may obtain an accuracy score for the semantic information of the word set obtained through sentence analysis, based on the semantic information for the same word set found in the entire patent document.

For example, meaning information on'apple' obtained by analyzing a sentence containing'apple' is information about apple representing fruit, but semantic information of'apple' searched in the entire patent document including the sentence is different. In the case of information about telling a person a mistake, the server 10 may set the previously matched semantic information to a low value.

In step S330, the server 10 may determine a word set having an accuracy score equal to or less than a preset value as an error word set.

That is, when the accuracy score is less than or equal to a preset value, the server 10 may determine that semantic information matched to the corresponding word set is incorrectly matched, and obtain the word set as an error word set.

5 is a flowchart illustrating a method of correcting an error word set according to an embodiment of the present invention.

In step S410, the server 10 may acquire a plurality of semantic information for the error word. Specifically, the server 10 may obtain a plurality of semantic information of the erroneous word from a plurality of patent documents.

In step S420, the server 10 may acquire a plurality of weights for each of the obtained plurality of semantic information.

In an embodiment, the server 10 may acquire weights based on a patent document including an erroneous word. Specifically, the server 10 may obtain at least one sentence including the error word from the patent document, and obtain semantic information on the same word as the error word included in the obtained at least one sentence. The server 10 may acquire weights for a plurality of semantic information based on semantic information for at least one word that is the same as the error word.

In step S430, the server 10 may obtain a weight having the highest correlation with the patent document among the plurality of weights.

In step S440, the server 10 may match semantic information corresponding to the weight having the highest correlation with the patent document to the error word set. That is, the server 10 may determine semantic information having the largest weight among a plurality of semantic information for an error word as semantic information for an error word, and correct the error word.

On the other hand, according to various embodiments of the present invention, the error word set may be a case where incorrect semantic information is matched with the word set as well as a case of a word set that is erroneously parsed as an error in a morpheme analysis process. In an embodiment, when the sentence for acquiring the word set is "Natural language processing using machine learning is performed", the server 10 may acquire machine, learning, use, natural language, and processing as a word set.

In this case, due to an error in morpheme analysis, a case of acquiring a word set such as machine, learning, using, natural language, and processing may occur. In this case, the server 10 may determine “use” as an error word set and correct it.

Specifically, after obtaining semantic information for each of the acquired word sets, the server 10 may determine whether or not an error word is based on a degree of association between the semantic information and the patent document. According to an embodiment, when the acquired word set is found in a patent document including a word set with a preset frequency or more, the server 10 may determine that the word set is an error-free word set. In another embodiment, when the word set is found to be more than a preset frequency in the entire patent document, the server 10 may determine that the word set is not an erroneous word set by determining that the word set is a commonly used word set. In another embodiment, when the server 10 does not find semantic information for a word set, the server 10 may determine the corresponding word set as an error word set. In another embodiment, when the semantic information matched with the word set is different from the patent document including the word set, the server 10 may determine the corresponding word set as an error word set.

Specifically, the server 10 may obtain a word set included in the entire patent document, match and store semantic information for each of the acquired word sets. The server 10 may obtain a cluster of a plurality of word sets having relevant semantic information by clustering the matched word set and semantic information. The server 10 may acquire a word set cluster in which the number of word sets included in the cluster is less than or equal to a preset number from among the plurality of word set clusters. In this case, the preset number may not mean the number of a plurality of identical word sets used in the patent document, but may mean the number of a plurality of word sets having different forms. For example, even if the word "use" is searched for multiple times in a patent document, since "use" is the same set of words, it can be determined as one word set. The server 10 may determine the word set included in the cluster acquired in the above step as the error word set.

However, the present invention is not limited thereto, and of course, the server 10 may determine a word set included in a cluster having a distance from another cluster equal to or greater than a preset distance among the plurality of word set clusters as an error word set. Specifically, the server 10 may obtain center points of a plurality of clusters and determine a distance between clusters based on the obtained center points. For example, the acquired word set cluster may be a first word set cluster to a fourth word set cluster. In this case, the server 10 includes the distance between the first word set cluster and the second word set cluster, the distance between the first word set cluster and the third word set cluster, the first word set cluster and the fourth word set cluster. Each of the distances of is obtained, and when all of the three obtained distances are equal to or greater than a preset distance, the first word set cluster may be determined as an error word set.

6 is a flowchart illustrating a method of obtaining a compound noun phrase set according to an embodiment of the present invention.

Specifically, the word set obtained through steps S110 to S150 relates to a single word, but when a compound noun phrase is formed by combining single words, the meaning may change. Accordingly, there is a need for the server 10 to obtain a set of compound noun phrases from a single word set. Accordingly, the server 10 may obtain a compound noun phrase set based on a plurality of word sets.

In step S510, the server 10 may obtain a plurality of word sets for sentences included in the patent document.

For example, as a result of analyzing the sentence "Natural language processing using machine learning" is analyzed, the server 10 may acquire a word set of machine, learning, use, natural language, and processing.

In step S520, the server 10 may obtain a plurality of compound noun phrase set candidates obtained by combining a plurality of word sets.

For example, the server 10 may obtain a candidate complex noun phrase set such as machine learning, learning use, user language, natural language processing, and the like from a combination of the obtained word sets.

In step S530, the server 10 may obtain a frequency in which a plurality of acquired compound noun phrase sets and the same compound noun phrase set candidates are included in the patent document.

In step S540, the server 10 may determine a composite noun phrase set candidate whose acquired frequency is equal to or greater than a preset frequency as the composite noun phrase set.

For example, the server 10 acquires information on the discovery of a total of 301 times for machine learning, a total of 1 for learning, 0 for a user language, and a total of 58 times for natural language processing, and the frequency of occurrence is preset. A composite noun phrase candidate set with a frequency or higher may be obtained as a composite noun phrase set.

In this case, the composite noun phrase set candidate may include order information and spacing information of word sets included in the composite noun phrase set candidate.

In one embodiment, the compound noun phrase set is determined as a combination of two or more adjacent word sets, but in the present invention, a combination of a word set in which words are spaced apart may also be obtained as a compound noun phrase set. For example, when the server 10 acquires a compound noun phrase set from a sentence containing "a first device among a plurality of devices, a second device among a plurality of devices, a third device among a plurality of devices", The first device among the devices, the second device among the plurality of devices, and the third device among the plurality of devices may be acquired as an independent compound noun phrase set, but the "(separated word 1) device" among the plurality of devices is a single compound noun phrase set Of course, it can also be obtained with. In this case, the compound noun phrase set may include spacing information. In the above-described embodiment, the spacing information may be information indicating that one word is included between the word "medium" and the word "device". It goes without saying that, according to various embodiments, a plurality of words may be included between a word and a word.

개이고, 단어 세트간의 순서가 변경되는 경우 획득되는 복합 명사구 세트의 수는

개이다. 따라서, 문장이 길어지면 길어질수록, 서버(10)는 복합 명사구 세트 검색을 위해 과도한 리소스를 투입하여야 한다. 따라서, 서버(10)는 복합 명사구 세트를 구성하는 단어 세트의 최대 개수를 결정하고, 결정된 개수 내의 복합 명사구 세트를 획득할 수 있다. 이때, 서버(10)는, 단어 세트 획득을 수행하는 특허문서와 동일한 기술 분야인 복수개의 특허문서를 획득하고, 획득된 특허문서에 포함된 복합 명사구 세트에 포함된 단어 세트의 최대 개수를 복합 명사구 세트를 구성하는 단어 세트의 최대 개수로 결정할 수 있다. In another embodiment, the server 10 may determine the maximum number of word sets constituting the compound noun phrase set, and obtain a compound noun phrase set within the determined number. Specifically, when the number of words included in the sentence for obtaining the compound noun phrase set is n and the order between the word sets is not changed, the number of compound noun phrase sets obtained is

And the number of compound noun phrase sets obtained when the order between word sets is changed is

It's a dog. Therefore, the longer the sentence is, the longer the server 10 has to put excessive resources to search for the complex noun phrase set. Accordingly, the server 10 may determine the maximum number of word sets constituting the compound noun phrase set, and obtain a compound noun phrase set within the determined number. At this time, the server 10 acquires a plurality of patent documents that are the same technical field as the patent document for acquiring the word set, and determines the maximum number of word sets included in the compound noun phrase set included in the obtained patent document. It can be determined as the maximum number of word sets constituting the set.

7 is a flowchart illustrating a method of obtaining a compound noun phrase set according to another embodiment of the present invention.

In step S610, when the plurality of word sets satisfy a preset condition, the server 10 may change the positions of the plurality of word sets.

In general, when trying to obtain a compound noun phrase from a sentence, it is unnecessary to change the order of the word sets included in the sentence. For example, in the sentence of "~~ using machine learning", the server 10 needs to obtain a set of complex noun phrases called "machine learning", but uses a complex noun phrase set called "running machine" that has changed the order of the word sets. You won't need to get it. Rather, in the case of acquiring a complex noun phrase set of a "treadmill", a complex noun phrase set having a completely different meaning is acquired, and thus there is room for deteriorating the performance to be achieved in the present invention.

However, as described in step S610, if a preset condition is satisfied, the server 10 may obtain a composite noun phrase set candidate by changing the order of the word sets included in the sentence. At this time, the preset condition is a condition in which a plurality of word sets are adjacent, a condition in which a preset sign is included between a plurality of adjacent word sets, a condition in which a word set located on the right of a plurality of adjacent word sets includes parentheses, and a plurality of words. It may be a condition that the set is in different languages.

For example, when the sentence to be analyzed includes "Machine Learning", the server 10 may acquire machine, learning, machine, and learning as a word set. Furthermore, the server 10 may acquire "Machine Learning Machine Learning" as a set of complex noun phrases. Furthermore, the server 10 may determine that the parenthesis sign, which is a preset condition, is included, and obtain "Machine Learning Machine Learning" as a complex noun phrase set. That is, when the server 10 is a compound noun phrase (or word) of "machine learning" and a compound noun phrase (Machine Learning) of another language for the compound noun phrase (or word) exist together, it is expressed in different languages, but has the same meaning. It is possible to acquire two compound noun phrases (or words) having a as one compound noun phrase, and also obtain one compound noun phrase by changing the order of the two compound noun phrases. This has the effect of increasing the efficiency of comparison when comparing patent documents written in different languages. That is, a patent document written in Korean is expressed as "Machine Learning", but a patent document written in English can be expressed as "Machine Learning". It can be obtained as a noun phrase set to increase the efficiency of the search.

Meanwhile, in the above-described embodiment, a condition in which the preset sign inclusion condition includes parentheses has been described, but the present invention is not limited thereto. According to various embodiments, the preset sign may be a sign such as a hyphen (-), a slash (/), a tilde (~), and a quotation mark ('or ").

In step S620, the server 10 may determine the changed plurality of word sets as a composite noun phrase set candidate.

8 is a flowchart illustrating a method of obtaining a word set according to an embodiment of the present invention.

In step S710, the server 10 may analyze the sentences included in the patent document.

In step S720, when the analyzed sentence has a preset structure, the server 10 may obtain at least one word set excluding a word set corresponding to the preset structure from among the word sets included in the sentence.

According to an embodiment, the preset structure may be a standardized structure such as “~ is defined as ~”. Specifically, in the patent document, "~ is defined as ~" and "hereinafter, ~ is referred to as ~." "~ can be understood as ~." Sentences with structures such as “to describe as” may be used to define terms that are not generally used in the technical field. Accordingly, the server 10 may determine a sentence defining a term that is not generally used in the technical field, and obtain a word set defined in the determined sentence.

For example, if the sentence to be analyzed is a sentence "Machine learning describes (or defines) as OOO.", the server 10 determines that the sentence is a preset structure, and You can acquire a word set.

In step S730, the server 10 may obtain semantic information of at least one word set.

Specifically, when the acquired word set of OOO has semantic information commonly used in the technical field, the server 10 may match semantic information corresponding to OOO with the OOO. However, when the OOO term is a term newly defined by the user and the semantic information is unclear, the server 10 may match semantic information corresponding to machine learning with the semantic information of OOO.

In step S740, the server 10 may obtain a word set corresponding to the semantic information.

However, the present invention is not limited thereto, and the server 10 may, of course, replace the word set of OOO with the word set of machine learning when the degree of association between machine learning and OOO is greater than or equal to a preset degree of association.

9 is a flowchart illustrating a method of obtaining a word set excluding a template of a patent document according to an embodiment of the present invention.

Specifically, a patent document is a standardized document, which is largely irrelevant to the core contents of the invention, but a paragraph describing necessary essential elements in a standardized manner may exist. Therefore, when the standardized paragraph is removed and a clue set is obtained, there is an effect of reducing the amount of computation of the server 10.

In step S810, the server 10 may obtain a plurality of identification item information and a template included in the patent document.

In an embodiment, the template may be set to a paragraph existing at a specific location. For example, in the template, from the sentence included in the line following the [Specific Contents for Carrying out the Invention] Identification Item included in the Patent Document, the Word of'Fig. 1'First in the [Specific Contents for Carrying out the Invention] It may be text up to before the searched sentence.

In another embodiment, the template may mean a part in common with other patent documents created by the creator of the patent document to be analyzed. That is, the server 10 determines the author of the patent document, obtains another patent document of the determined author, compares a plurality of obtained patent documents, and a paragraph determined to be similar by more than a preset ratio through the comparison result. Alternatively, the identification item can be obtained as a template. Since there is a high possibility that the structure of a patent document written by the same author will be similar, the server 10 may set the criteria for similarity determination as a paragraph or identification item rather than a sentence unit.

In another embodiment, the server 10 may obtain a text corresponding to a preset identification item as a template. For example, the server 10 may obtain text included in identification items such as [simple description of drawings] and [description of symbols] as a template.

In the above-described embodiment, a method of obtaining a template for a general identification item of a patent document for a domestic application has been described, but is not limited thereto. That is, the server 10 is used for various identification items such as identification items in Korean format for PCT applications, identification items in English format for PCT applications, and further, identification items in formats used in US, Japan, China, and Europe applications. Of course, you can obtain a template.

In step S820, the server 10 may acquire a plurality of sentences excluding the acquired template.

In step S830, the server 10 may assign a weight to each of the plurality of identification items.

In one embodiment, when the patent document has the same format and identification items as in this specification, the server 10 is the name of the invention, the technical field, the technology behind the invention, the problem to be solved, the means for solving the problem, the invention The effect of, a brief description of the drawings, specific contents for carrying out the invention, the description of the symbols, the claims, the summary, the representative diagram, it is possible to assign a weight to each of the drawing identification items.

In this case, the weight can be given by various methods. In one embodiment, the server 10 is a technical field, the technology behind the invention, the claims, the effect of the invention, the specific content for carrying out the invention, the description of the symbols, a brief description of the drawings, a summary, a task to be solved Higher weights can be given in the order of, the solution of the task, and the degree of representation.

In another embodiment, the weight is high in the identification item having a high importance score after obtaining the importance score for each of the word set (or compound noun phrase set) included in the patent document, and obtaining the importance score for each identification item based on this. Can be weighted. The importance score is an index indicating the importance of the corresponding word set (or compound noun phrase set) in the patent document, and the higher the importance score is the word set (or compound noun phrase set), the keyword of the corresponding patent document.

Meanwhile, the importance score for each identification item may mean a value obtained by dividing the number of word sets (or compound noun phrase sets) after summing the importance scores of the word set (or compound noun phrase set) included in the identification item. In this case, the word set (or compound noun phrase set) used to obtain the importance score for each identification item may be a set of all words (or a compound noun phrase set) included in the identification item, but is not limited thereto. For example, the word set (or compound noun phrase set) used to obtain the importance score for each identification item is a word set (or a compound noun phrase set) of a portion determined as a template among all the word sets (or compound noun phrase sets) included in the identification item. Of course, it may be a word set (or a compound noun phrase set) excluding a compound noun phrase set).

In step S840, the server 10 may determine the priority of the identification item to perform morpheme analysis based on the weight of each of the plurality of identification item information.

In step S850, the server 10 may obtain a word set for a plurality of sentences from which the template is excluded according to the determined priority.

That is, the server 10 may reduce the computation amount by first analyzing the identification item with a high probability of the presence of the keyword, and then analyzing the identification item of relatively low importance based on the analyzed content. Furthermore, when different semantic information for the same word set is matched, the server 10 may determine semantic information obtained from the identification item having a high priority as accurate semantic information.

10 is a flowchart illustrating a method of obtaining a word set when an image exists in a patent document according to an embodiment of the present invention.

In step S910, when an image is included in the patent document, the server 10 may determine whether an identification item adjacent to the image exists.

In one embodiment, when the identification item of [Equation] exists in the patent document and an image exists below the identification item, the server 10 may determine the image as an image for the equation. In the case of the equation, since it is highly likely that it is the core content of the patent document, the server 10 may obtain the equation text included in the image.

In another embodiment, when the identification item of [Chemical Formula] exists in the patent document and an image exists below the identification item, the server 10 may determine the image as an image for the chemical formula.

In step S920, when the identification item is adjacent to the image, the server 10 may analyze the image to obtain text included in the image. In this case, the image analysis may be performed by optical character recognition (OCR), but is not limited thereto. For example, when the image is a chemical formula image, it goes without saying that the server 10 can obtain a chemical formula corresponding to the image by analyzing the chemical structure.

In step S930, the server 10 may acquire a word set based on the acquired text.

Meanwhile, the server 10 may acquire an importance score of each word set through a method described later. In one embodiment, the server 10 may obtain a word set from which the importance score is calculated from the patent document. The server 10 includes a second detail of the word set in the patent classification information corresponding to the technical field information of the patent document including the first detailed importance and importance score of the word set in the entire patent document. One or more of the importance and the third detailed importance of the search patent document including the word set among the entire patent documents may be calculated.

Specifically, the server 10 may calculate the first detailed importance based on the first appearance rate and the second appearance rate. At this time, the first appearance rate refers to the number of appearances of the word set for which the importance score is to be obtained in the entire patent document compared to the total number of word sets in the entire patent document, and the second appearance rate is the number of word sets among the sentences of the entire patent document. The number of appeared sentences is counted, and it may mean the total number of sentences in the entire patent document compared to the number of sentences in which the word set appears among the sentences of the entire patent document.

Specifically, the server 10 may calculate the first detailed importance by using Equation 1 below.

Here, W1 is the first detailed importance, wpw is the number of occurrences of the word set in the entire patent document, WPW is the total number of word sets in the entire patent document, and wps is the appearance of the word set in the sentences of the entire patent document. Is the number of sentences, WPS is the total number of sentences in the entire patent document, and a1 is the adjustment constant of the second appearance rate.

In another embodiment, the server 10 may calculate the first detailed importance based on the first appearance rate and the second appearance rate. At this time, the third appearance rate refers to the number of appearances of the word set for which the importance score in the patent classification information is to be obtained relative to the total number of word sets in the patent classification information, and the fourth appearance rate is the number of word sets among the sentences of the entire patent document. It can mean the total number of sentences in the entire patent document compared to the number of appeared sentences.

Here, the patent classification information is a code capable of classifying a patent according to a technical field, and may be any one of IPC (International Patent Classfication), CPC (Cooperative Patent Classification), and F-Term.

Specifically, the server 10 may calculate the second detailed importance by using Equation 2 below.

Here, W ₂ is the second detailed importance, ipcw is the number of occurrences of the word set in the patent classification information, IPCW is the total number of word sets in the patent classification information, and ipcs is the word set in the sentences of the entire patent document. It is the number of sentences that appear, IPCS is the total number of sentences in the entire patent document, and a2 is the control constant of the fourth appearance rate.

In another embodiment, the server 10 searches for a search patent document including a set of words to be calculated for the importance score among all patent documents, and based on the reference information of each search patent document, the server 10 An influence value may be calculated, and a third detailed importance may be obtained based on the calculated influence value.

Specifically, the server 10 calculates an influence value based on the number of items that are the same as other patent documents by one or more of the applicant, inventor, and right holder as reference information of the search patent document, the number of citations and the number of citations as reference information. I can.

That is, the server 10 may calculate the degree to which the searched patent document is related to other patent documents as the influence value. For example, when the search patent document is cited from several patent documents, the server 10 may determine that the search patent document has an influence on the corresponding patent document and calculate the value of the search patent document as the influence value of the search patent document.

Furthermore, the server 10 may calculate an average of the calculated influence values for each search patent document, and calculate the calculated average as a third detailed importance.

11 is a block diagram of an apparatus according to an embodiment of the present invention.

The processor 102 may include one or more cores (not shown) and a graphic processing unit (not shown) and/or a connection path (eg, a bus) for transmitting and receiving signals with other components. .

The processor 102 according to an embodiment executes one or more instructions stored in the memory 104 to perform the method described with reference to FIGS. 2 to 10.

For example, the processor 102 acquires new training data by executing one or more instructions stored in the memory, performs a test on the acquired new training data using the learned model, and labels the test result. Extracting first learning data in which the obtained information is obtained with an accuracy equal to or higher than a predetermined first reference value, deleting the extracted first learning data from the new learning data, and removing the new learning data from which the extracted learning data is deleted. The learned model can be retrained by using.

Meanwhile, the processor 102 temporarily and/or permanently stores a signal (or data) processed inside the processor 102, and a RAM (Random Access Memory, not shown) and a ROM (Read-Only Memory). , Not shown) may further include. In addition, the processor 102 may be implemented in the form of a system on chip (SoC) including at least one of a graphic processing unit, RAM, and ROM.

The memory 104 may store programs (one or more instructions) for processing and controlling the processor 102. Programs stored in the memory 104 may be divided into a plurality of modules according to functions.

The steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or a combination thereof. Software modules include Random Access Memory (RAM), Read Only Memory (ROM), Erasable Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), Flash Memory, hard disk, removable disk, CD-ROM, or It may reside on any type of computer-readable recording medium well known in the art to which the present invention pertains.

Components of the present invention may be implemented as a program (or application) and stored in a medium in order to be combined with a computer as hardware to be executed. Components of the present invention may be implemented as software programming or software elements, and similarly, embodiments include various algorithms implemented with a combination of data structures, processes, routines or other programming components, including C, C++ , Java, assembler, or the like may be implemented in a programming or scripting language. Functional aspects can be implemented with an algorithm running on one or more processors.

In the above, embodiments of the present invention have been described with reference to the accompanying drawings, but those skilled in the art to which the present invention pertains can be implemented in other specific forms without changing the technical spirit or essential features. You will be able to understand. Therefore, the embodiments described above are illustrative in all respects, and should be understood as non-limiting.

10: server
20: electronic device

Claims (1)

In the method of obtaining a word set of a patent document,
Obtaining, by the server, a patent document;
Obtaining, by the server, a morpheme based on the patent document to obtain a plurality of word sets;
Determining, by the server, an error word set from among the acquired plurality of word sets;
Modifying, by the server, the error word set; And
Including, the server, obtaining at least one compound noun phrase set based on the degree of association between the plurality of word sets,
Obtaining the word set,
If the patent document contains an image, determining whether an identification item adjacent to the image exists;
Obtaining text included in the image when the identification item is adjacent to the image; And
Obtaining a word set based on the obtained text; A word set acquisition method comprising a.

Images