WO2007105530A1

WO2007105530A1 - Related term acquiring device, related term acquiring method, technology trend information creating device, technology trend information creating method, and program

Info

Publication number: WO2007105530A1
Application number: PCT/JP2007/054257
Authority: WO
Inventors: Hidetsugu Nanba
Original assignee: Hiroshima City
Priority date: 2006-03-10
Filing date: 2007-03-06
Publication date: 2007-09-20
Also published as: JP5463494B2; JP5078164B2; JP2012226768A; JPWO2007105530A1

Abstract

[PROBLEMS] A related term acquiring device for acquiring a related term by using document citation relation. [MEANS FOR SOLVING PROBLEMS] The related term acquiring device comprises a document information storage section (11) storing document information, a term information receiving section (12) for receiving term information, a document information acquiring section (13) for acquiring a part of document information at least including cited document identification information for identifying other documents cited in the document information including term information, a cited document information acquiring section (14) for acquiring a part of the cited document information identified by the acquired cited document identification information and corresponding to a predetermined item from the document information storage section (11), a related term information acquiring section (15) for acquiring related term information related to the term information from the part of the cited document information, and a related term information output section (16) for outputting the related term information.

Description

Specification

Related term acquisition device, related term acquisition method, technology trend information creation device, technology trend information creation method, and program

Technical field

[0001] The present invention creates, for example, a related term acquisition device that acquires a related term related to a certain term, and technical trend information that is information that associates a technical term with a period related to a technical document including the technical term. The present invention relates to a technology trend information creation device and the like.

Background art

[0002] A conventional information processing apparatus searches a Web page on the Web and automatically collects related terms (for example, see Non-Patent Document 1, Non-Patent Document 2, Non-Patent Document 3, and Non-Patent Document 4). . In general, in order to collect terms related to a technical term t from the Web, it is necessary to first collect descriptions related to the term t and then extract terms related to t from there. Here, one of the points is to collect appropriate descriptions about the term t. For example, in Non-Patent Document 1, descriptions relating to the term t are collected by the method described below. For a certain term t, first enter four types of queries, “What is t”, “T”, “t is”, and “t”, into the search engine, and the top 100 pages of the obtained URLs. Get Next, the obtained page is formatted and divided into sentences, and only sentences containing the term t are extracted, and related terms are collected from there.

[0003] In addition, there is a survey paper creation support system that takes into account reference information between papers in the prior art (Non-Patent Document 5).

In recent years, research has been actively conducted to automatically collect terms related to a certain term from a text set (see Non-Patent Documents 1, 3, 4, and 6).

Non-patent document 1: Satoshi Sato, 1 other, "Automatic collection of related terms using the web", Information Processing Society of Japan, Natural Language Processing, NL-153, p. 57-64, 2003

Non-Patent Document 2: Yasuhiro Sasaki, two others, “Proposal of an index for measuring the degree of association between terms”, 10th Annual Conference of the Association for Natural Language Processing, p. 25-28, 2004

Non-Patent Document 3: Kiyoaki Shirai and 3 others, "Attempt to create portal site automatically", The Association for Language Processing 10th Annual Conference, p. 624—627, 2004

Non-Patent Literature 4: Keisuke Ohara, 3 others, “Gathering Related Terms Using the Web”, 3rd Information Science Technology Forum (FIT2004), 2004

Non-Patent Document 5: Eizo Namba and 1 other, “Development of survey paper creation support system considering reference information between papers”, Natural Language Processing, Vol. 6, No. 5, p. 43-62, 1999 Non-Patent Document 6: Ei Namba, “Automatic Collection of Related Terms Using Citation Information Between Papers”, The 11th Annual Conference of the Language Processing Society of Japan, 2005

Disclosure of the invention

Problems to be solved by the invention

[0004] However, conventional information processing devices do not focus on the citation relationship of documents, but collect related pages for each term using a Web search engine and extract related terms from there. Therefore, there is a problem that it takes time to collect related terms. In addition, conventional information processing apparatuses have a problem that the accuracy of collecting related terms is low because they do not focus on the citation relationship of documents.

[0005] In addition, in a research field, collecting and organizing information such as “what kind of technical power ^ has been used since! It is indispensable to give an overview of research trends. However, collecting such information has been problematic in that it requires a great deal of labor and time from a person familiar with the research field.

[0006] Further, in the above non-patent documents, as described above, terms related to a certain term can be automatically collected. However, in the above-mentioned non-patent documents, etc., it was difficult to create information indicating when technical terms were used.

[0007] The present invention has been made to solve at least one of the above problems, and a related term acquisition device or the like capable of acquiring appropriate related terms by using a citation relationship between documents is provided. The purpose is to provide.

[0008] The present invention has been made to solve at least one of the above-described problems, and creates technical trend information, which is information for associating a technical term with a period related to a technical document including the technical term. The purpose is to provide a technology trend information creation device, etc. that can do this. Means for solving the problem

[0009] In order to achieve at least one of the above objects, a related term acquisition device according to the present invention includes a reference information storage unit that stores two or more reference information that is information indicating a reference, and information indicating a term. A term information receiving unit that accepts certain term information, and document information having the term indicated by the term information accepted by the term information receiving unit in all or part of the document information is stored in the document information storage unit !, Search from two or more document information, and identify all the document information searched or a part of the document information searched, and other documents cited in the document information searched. A document information acquisition unit that acquires from the document information storage unit a portion having at least the document identification information for bow I that is information, and a bow included in all or part of the document information acquired by the document information acquisition unit Document identification information for I The document information for bow I, which is information indicating the document identified by (2), is searched for two or more document information stored in the document information storage unit, and is a part of the retrieved cited document information. A citation information acquisition unit that acquires a part corresponding to a predetermined item from the document information storage unit, and a part of the citation information acquired by the citation information acquisition unit, the term information reception unit Related term information acquisition unit that acquires related term information that is information indicating related terms related to the term indicated by the term information received by the term information, and related term information that outputs the related term information acquired by the related term information acquisition unit And an output unit.

With such a configuration, related term information related to term information can be acquired.

In particular, when the cited document information acquisition unit acquires a part of the cited document information, more appropriate related term information can be acquired.

[0011] In the related term acquisition device according to the present invention, the document information includes structure description information that is information describing a structure of the document information, and the cited document information acquisition unit acquires the document information acquisition. Is a part of cited document information indicating a cited document identified by the document identification information for bow I included in all or a part of the document information acquired by the department, and is determined in advance by the structure description information. You may retrieve the part associated with the associated item.

[0012] With such a configuration, since the document information includes the structure description information, the cited document information is acquired. The department can easily obtain the part corresponding to the item that has been determined in advance.

[0013] Further, in the related term acquisition apparatus according to the present invention, the cited document structure information acquisition is performed for acquiring the cited document structure information which is information indicating correspondence between one or more parts of the cited document information and items of the part. The cited document information acquisition unit is a part of the cited document information and is preliminarily determined using the cited document structure information acquired by the cited document structure information acquisition unit. You may acquire the part corresponding to an item.

With such a configuration, the cited document information acquisition unit can easily acquire a portion corresponding to a predetermined item using the cited document structure information acquired by the cited document structure information acquisition unit. It can be done.

[0015] Further, in the related term acquisition device according to the present invention, when the document information acquisition unit acquires a part of the document information, the document information acquisition unit includes at least the cited document identification information, The cited reference information acquisition unit is included in all or part of the reference information acquired by the reference information acquisition unit. In the information for bow I included in all or part of the document information acquired by the document information acquisition unit, which is a part of the cited document information indicating the document identified by the document identification information for bow I You can get the part corresponding to the item that is predetermined according to the citation format!

[0016] With such a configuration, the cited document information acquisition unit can acquire a portion corresponding to the item according to the citation format, and one of the cited document information corresponding to which item is determined according to the citation format. Appropriate setting of whether or not to acquire the part can enable more relevant terminology information to be acquired.

[0017] Further, in the related term acquisition device according to the present invention, the related term information acquisition unit is a related term that is information that is a candidate for a related term in a part of the cited document information acquired by the cited reference information acquisition unit. Related term candidate information acquiring means for acquiring candidate information, relevance level calculating means for calculating, for each related term candidate information, a relevance level of terms indicated by the related term candidate information acquired by the related term candidate information acquiring means, Related Term Candidate Information Acquisition Of related term candidate information acquired by the means, the related term candidate with the highest corresponding degree of relatedness Related term information determining means for determining information as related term information.

With such a configuration, related term information can be appropriately acquired from a part of the cited document information acquired by the cited document information acquiring unit.

[0018] Further, in the related term acquisition device according to the present invention, the document information storage unit stores at least a first type of document information and a second type of document information, and the document information acquisition unit The document information storage unit acquires all or part of the first type of document information from the first type of document information stored in the document information storage unit, and the cited document information acquisition unit includes the document information storage unit. A part of the cited document information may be acquired from the second type of document information stored in the above.

[0019] With such a configuration, it is possible to obtain related terms related to a certain term but in a different field from the term. For example, patent terms related to terms used in academic literature may be obtained.

[0020] In order to achieve at least one of the above objects, a technical trend information creation device according to the present invention includes a plurality of document information that is information indicating at least a part of a technical document, and a technical document indicated by the document information. A document information storage unit that stores at least timing information, which is information indicating a period of time, and is stored in the document information storage unit! All or one of at least some of the document information among the plurality of document information. A document information acquisition unit that acquires a part, a part or all of the document information acquired by the document information acquisition unit, a technical term extraction unit that extracts a technical term, and a technical term that the technical term extraction unit extracts The time information acquisition unit that acquires the time information corresponding to the document information stored from the document information storage unit, the technical terms extracted by the technical term extraction unit, and the time information acquired by the time information acquisition unit The technical trend information creation unit that creates technical trend information, which is information for associating technical terms with the timing of the technical literature including the technical terms, and the technical trend information created by the technical trend information creation unit. And an output unit for outputting.

[0021] With such a configuration, it is possible to create technical trend information, which is information for associating a technical term with a period related to a technical document including the technical term. As a result, by using the created technology trend information, it is possible to easily know the transition of the technology used in a certain research field. In addition, to create the technology trend information, There is also an advantage that it is not necessary to spend a great deal of labor and time for those who are familiar with the research field.

[0022] Further, in the technical trend information creation device according to the present invention, a search term receiving unit that receives a search term and a search unit that searches the document information storage unit using the search term received by the search term receiving unit. The document information acquisition unit may acquire all or part of the retrieved document information.

With such a configuration, it is possible to specify a research field in which technical trend information is created by using a search term.

[0023] Further, in the technical trend information creating device according to the present invention, any one of a search term storage unit storing two or more search terms and two or more search terms stored in the search term storage unit A search term selection accepting unit that accepts selection of the search term, and the search term accepting unit may accept the search term indicated by the selection accepted by the search term selection accepting unit.

[0024] With such a configuration, an appropriate search term (for example, a term indicating a research field) is stored in the search term storage unit so that an inappropriate search term is input. It can be avoided. As a result, an appropriate search can be performed and appropriate technical trend information can be created.

[0025] Further, in the technical trend information creation device according to the present invention, a technical term extraction unit that extracts technical information terminology stored in the literature information storage unit, and a suffix storage that stores a predetermined suffix And the technical term extracted by the technical term extraction unit is stored in the suffix storage unit, and the term with the suffix is included in the literature information stored in the literature information storage unit. In this case, a search term storage unit that stores the technical terms as search terms in the search term storage unit may be further included.

With such a configuration, the search terms can be automatically stored in the search term storage unit without the user performing processing for storing the search terms in the search term storage unit.

[0026] In the technical trend information creation device according to the present invention, the search unit searches for document information corresponding to a technical document whose search term received by the search term receiving unit is a main topic.

With this structure, technical trend information is created in the field whose main topic is search terms. Can be.

[0027] Further, in the technical trend information creation device according to the present invention, the technical trend information creation device further includes a specifying unit that specifies document information having the same field as the document information searched by the searching unit, and the document information acquiring unit includes the specifying unit All or a part of the document information specified by may be acquired from the document information storage unit.

[0028] With such a configuration, it is document information that cannot be acquired by a search using a search term, but other document information that has the same field as the document information acquired by the search can be acquired. sell. As a result, more literature information can be collected, and more appropriate technology trend information can be created.

[0029] Further, in the technical trend information creation device according to the present invention, the specifying unit is information that identifies another technical document cited in the document information from the document information searched by the search unit. A certain cited document identification information may be acquired, and using the cited document identification information, the document information having the same field as the document information searched by the search unit may be specified.

With such a configuration, it is possible to specify document information using citation relationships.

[0030] Further, in the technical trend information creation device according to the present invention, the specifying unit describes a description of another technical document cited in the document information from the document information searched by the search unit. The citation information, which is the information to be shown, is also acquired, and the citation format indicated by the citation information is cited. Reference information having the same field as the document information searched by the search unit may be specified using cited document identification information for identifying the technical document being searched.

[0031] With such a configuration, it is possible to specify document information using citation information as well. In particular, when the citation format is a problem-pointing reference format that points out the problem of the cited technical document, the fields of the cited document information and the cited document information are similar. Therefore, it is possible to identify appropriate literature information.

[0032] Further, in the technical trend information creation device according to the present invention, the technical term extraction unit includes at least one A clue phrase storage means for storing a clue word phrase, a manual power S phrase search means for searching for a clue phrase in all or part of the document information acquired by the document information acquisition unit, Technical term extraction means may be provided that extracts, as technical terms, terms that have a predetermined relationship with the hand-strengthening phrase searched by the hand-strengthening phrase search means. With such a configuration, technical terms can be extracted from all or a part of the acquired document information using the clue words.

[0033] In the technical trend information creation device according to the present invention, the technical term extraction unit includes clue word storage means for storing one or more clue words, and all or all of the document information acquired by the document information acquisition unit. In some cases, the hand S-phrase searching means for searching for a powerful phrase, the search term received by the search term receiving unit, and the hand searched by the clue phrase searching means by a powerful phrase Technical term extraction means for extracting the associated term as a technical term.

With such a configuration, it is possible to extract technical terms from all or part of the acquired document information by using hand-power phrases and search terms.

[0034] Further, in the technical trend information creation device according to the present invention, the technical term extraction unit includes clue word storage means for storing one or more clue words, and all or all of the document information acquired by the document information acquisition unit. In some cases, the hand searches for a powerful phrase, a power S phrase search means, a technical term storage means for storing two or more technical terms, and a hand searched by the clue phrase search means. Technical terms extraction means for extracting the technical terms as technical terms when the technical terms stored in the technical term storage means are included in the terms having a predetermined relationship with the phrase. .

With such a configuration, it is possible to avoid that the technical term extraction means extracts general nouns and non-technical terms as technical terms.

[0035] Also, in the technical trend information creation device according to the present invention, the technical term extraction unit includes clue word storage means for storing one or more clue words, and all or all of the document information acquired by the document information acquisition unit. In some cases, the technical term is a term that has a predetermined relationship with the hand-powered phrase search means for searching for a powerful phrase by the hand and the hand searched by the hand-held phrase searching means. Technical term candidate extraction means for extracting as a candidate, and for the technical Technical term selection means for selecting all or part of the technical term candidates extracted by the word candidate extraction means as technical terms.

With such a configuration, first, a technical term candidate is extracted by using a hand-held phrase, and thereafter, an appropriate technical term can be selected for the technical term candidate power.

[0036] Further, in the technical trend information creating device according to the present invention, the technical term extraction unit further includes technical term suffix storage means for storing one or more suffixes that the technical term can take. The technical term selection means may select a technical term candidate having a suffix stored in the technical term suffix storage means as a technical term.

[0037] With such a configuration, a term having a predetermined suffix is considered appropriate as a technical term. By selecting a technical term using the suffix, an appropriate technical term is selected. Can be selected.

[0038] Further, in the technical trend information creation device according to the present invention, the technical term selection means is stored in the literature information storage unit, and is used as a main topic according to any literature information. You can select technical term candidates as technical terms!

[0039] With such a configuration, a term that is not used as a main topic in any document information is considered to be unsuitable as a technical term, but is used as a main topic in any document information. By selecting a technical term candidate as a technical term, an appropriate technical term can be selected.

[0040] Further, in the technical trend information creation device according to the present invention, the technical term extraction unit includes literature information specifying means for specifying the literature information in which the technical field candidates are extracted, and literature information having the same field. A technical term suffix storage unit that stores one or more suffixes that can be taken by the technical term, and the literature information acquisition unit also includes all or part of the literature information identified by the literature information identification unit. The technical term selecting means identifies the whole or a part of the one piece of literature information obtained by the literature information obtaining unit and the field information and the field are the same as the one piece of literature information. When at least one of technical term candidates extracted from all or a part of the document information is stored in the suffix storage means and has a suffix, all or one of the one document information is stored. Part The extracted technical terms candidate be selected as the technical terms! / ヽ. With such a configuration, it is possible to select an appropriate technical term.

[0041] Further, in the technical trend information creating device according to the present invention, the technical trend information is an image indicating a timing indicated by timing information corresponding to document information including the technical term for each technical term, and the output unit May display and output the technical trend information.

With such a configuration, it is possible for the user to easily grasp the technology trend by viewing the image of the technology trend information displayed and output.

[0042] Further, in the technical trend information creation device according to the present invention, the technical trend information includes, for each technical term, a reference graphic corresponding to the reference information including the technical term corresponding to the reference information. It is an image that is displayed according to the time indicated by the time information, and relates to a document selection accepting unit that accepts selection of a document graphic in the technology trend information, and document information corresponding to the document graphic that the graphic selection accepting unit has accepted the selection. A display information acquisition unit that acquires from the document information storage unit display information that is information and information to be displayed on an image of the technical trend information. The technical trend information creation unit acquires the display information. Technical trend information for displaying the display information acquired by the department may be created.

[0043] With such a configuration, for example, the user who is viewing the technical trend information image can easily know the predetermined information about the document information including the technical term displayed in the technical trend information image. It will be possible to improve user convenience. The invention's effect

[0044] According to the related term acquisition device and the like according to the present invention, related term information related to term information can be acquired. In addition, for example, it is possible to acquire more appropriate related term information by acquiring a portion corresponding to an item corresponding to the citation format and acquiring related term information.

[0045] According to the technical trend information creating apparatus and the like according to the present invention, it is possible to create technical trend information that is information for associating technical terms with times related to technical documents including the technical terms. Therefore, by using the technology trend information, it is possible to easily know the changes in technology used in a certain research field.

BEST MODE FOR CARRYING OUT THE INVENTION

[0046] Hereinafter, the related term acquisition device and the technical trend information creation device according to the present invention, This will be described using an embodiment. In the following embodiments, components and steps denoted by the same reference numerals are the same or equivalent, and the description thereof may be omitted.

[Embodiment 1]

A related term acquisition apparatus according to Embodiment 1 of the present invention will be described with reference to the drawings.

FIG. 1 is a block diagram showing a configuration of a related term acquisition device 1 according to this embodiment. In FIG. 1, a related term acquisition device 1 according to the present embodiment includes a document information storage unit 11, a term information reception unit 12, a document information acquisition unit 13, a cited document information acquisition unit 14, and a related term information acquisition unit. 15 and a related term information output unit 16.

[0048] The document information storage unit 11 stores two or more document information. Here, the document information is information indicating a document. The document may be any document as long as it is a collection of articles, patent documents (for example, application publications, patent bulletins, etc.), Web pages, official gazettes, books, etc. One document information includes information (data) of the corresponding one document. However, one piece of document information may only include information in a range necessary for later processing. For example, in the case of document information of an academic paper, when only the reference document and title of the academic paper are used in the subsequent processing, the document information stored in the document information storage unit 11 includes only the reference document and title. It may be information. The bibliographic information may be a text file or a file of a unique format such as word processing software. If the document information is a text file, the text file may be described in a markup language that uses tags to describe the document. In some cases, the content of the corresponding document is simply text data. May be shown. Bibliographic information shall have a structure at least in part. Here, the structure may or may not be specified by a tag or a heading. In the latter case, for example, by reading a paragraph in the literature indicated by the literature information, you can see that the summary is written there, and by reading the other paragraph, the purpose is written there. It may be understood that it is. When the structure is specified, the structure is information that the document information has, and information that describes the structure of the document information. It may or may not be indicated by the structure description information. Here, the structure description information is, for example, a heading tag used in a Japanese patent specification or a tag used in an HTML file. As a case where the structure of the document information is described by other than the structure description information, for example, the text data of the heading such as “summary” or “reference document” may be included in the document information as in a normal paper. is there. It is assumed that the two or more document information stored in the document information storage unit 11 includes at least document information indicating a document that cites another document. Other documents cited in a certain document information are called cited documents. Cited document identification information, which is information for identifying a cited document, is included in the document information indicating a document cited by citing another document. Here, the content of the cited document identification information is not limited as long as it is information that can identify the cited document. Cited reference identification information may be, for example, an author's name, title, date of publication, which may be an ID for identifying a cited reference such as a patent number, an application publication number of a patent application, or a PMID (Pub Med Identifier). It may be bibliographic information of a document that can identify a cited document such as information on a medium (journal name, publisher name, URL, etc.). The document information storage unit 11 can be realized by a predetermined recording medium (for example, a semiconductor memory, a magnetic disk, an optical disk, etc.). The process in which the user attribute correspondence information is stored in the document information storage unit 11 does not matter. For example, document information transmitted via a communication line or the like may be stored in the document information storage unit 11 even if document information is stored in the document information storage unit 11 via a recording medium. Alternatively, the document information input via the input device may be stored in the document information storage unit 11.

The term information receiving unit 12 receives term information. Here, term information is information indicating a term. This term information is generally information indicating the text of the term, but may be other information as long as it indicates the term. In the related term acquisition device 1, a related term that is a term related to the term indicated by the term information received by the term information receiving unit 12 is acquired. For example, the term information receiving unit 12 may receive information input from an input device (for example, a keyboard, a mouse, a touch panel, etc.) or may be transmitted via a wired or wireless communication line. Accepts information read from a given recording medium (for example, optical disk, magnetic disk, semiconductor memory, etc.) that can receive information. May be. The term information receiving unit 12 may or may not include a device for receiving (for example, a modem or a network card). Further, the term information receiving unit 12 may be realized by hardware or may be realized by software such as a driver that drives a predetermined device.

Note that the term information receiving unit 12 may receive information other than the term information. For example, when a search is performed using related term information acquired by the related term acquisition device 1, a search key used in the search (for example, an international patent classification used in the search) may be received together with the term information. . Even in such a case, the following processing such as acquisition of document information is performed using the term information received by the term information receiving unit 12.

[0051] The document information acquisition unit 13 has two or more documents stored in the document information storage unit 11 having document information having the terms indicated by the term information received by the term information receiving unit 12 in all or part of the document information. Search from information. The document information having the term in all the document information means that the term is included in any part of the document information. On the other hand, bibliographic information having a term as part of the document information includes the term in a partial area of the bibliographic information, for example, a predetermined area such as a title or a claim. Let's say. When the document information acquisition unit 13 searches for document information having the term indicated by the term information as part of the document information, for example, information indicating an item corresponding to a part of the document information is stored in a recording medium (not shown). The document information acquisition unit 13 that has been stored may read the information indicating the item of the recording medium power and perform the above search.

The document information acquisition unit 13 acquires all of the searched document information or a part of the searched document information from the document information storage unit 11. When the document information acquisition unit 13 acquires part of the retrieved document information, the part of the document information is information that identifies other documents cited in the retrieved document information. It is the part that has at least the document identification information for Bow I. Therefore, all or a part of the document information including at least the cited document identification information is acquired by the document information acquisition unit 13. When the document information acquisition unit 13 acquires a part of the document information, for example, the document information acquisition unit 13 may include a reference column or a patent that is considered to include at least reference text identification information. You can get the column of literature and non-patent literature, or use technology such as no-turn matching. It is also possible to identify a region where the cited document identification information exists and acquire a part of the document information including the region. In the former case, for example, information indicating an item corresponding to a part to be acquired is not illustrated, and is stored in a recording medium. The document information acquiring unit 13 receives information indicating an item from the recording medium. A part of the literature information corresponding to the item may be acquired by reading. In the latter case, for example, information indicating a pattern used for pattern matching or the like is stored in a recording medium (not shown), and the document information acquisition unit 13 reads the pattern and the like to read the pattern. A part of the document information may be acquired by performing matching or the like. When the document information acquisition unit 13 searches for document information having a term indicated by the term information as part of the document information, and the document information acquisition unit 13 acquires a part of the searched document information, The part of the document information used in the search and the part of the document information to be acquired may be the same part of the document information or different parts of the document information.

The cited document information acquisition unit 14 retrieves the cited document information from two or more document information stored in the document information storage unit 11. Here, the cited document information is document information indicating the document identified by the document identification information for bow I included in all or part of the document information acquired by the document information acquiring unit 13. Then, the cited document information acquisition unit 14 acquires a part of the retrieved cited document information from the document information storage unit 11. A part of the cited document information acquired by the cited document information acquiring unit 14 is a part of the cited document information corresponding to the item that has been determined in advance. The part that corresponds to the item that has been determined is the part that describes the item. An item is an area that can be classified in a document. For example, a title, a title of an invention, an abstract (abstract), a claim, a claim, a premise part (preamble) of a claim, which is described first. Claims (hereinafter referred to as “first claim”), claims subordinate to the first claim, the object of the invention, the effects of the invention, and the like. The predetermined items may be a single item or two or more items. The item may or may not be manifested in the cited reference information. The fact that an item is manifested means that the part corresponding to that item is clearly indicated in the cited document information. For example, the item name may be displayed as text and the item may be actualized, or the tag may be used. In other words, the item may be manifested. If the item is not actualized, the part corresponding to the item is clearly indicated in the cited document information, as in the case where the item is actualized, V, and so on. For example, a case where a document is described without setting items is applicable. Even in such a case, the cited document information acquisition unit 14 can know what items are described in a predetermined part of the document.

Here, a process in which the cited document information obtaining unit 14 obtains a portion of the cited document information corresponding to a predetermined item will be described. In the case where information indicating items that have been determined in advance is stored in a recording medium (not shown) that can be accessed by the cited document information acquiring unit 14, the cited document information acquiring unit 14 Access to and read the information indicating the item. Then, when the item is actualized in the cited document information, the cited document information acquisition unit 14 acquires a portion of the cited document information corresponding to the read item. On the other hand, when the item is not manifested in the cited document information, the cited document information acquiring unit 14 specifies the cited document information part corresponding to the item, and acquires the specified cited document information part. Next, specification of the portion of the cited document information corresponding to the item will be described. For example, the cited document information acquisition unit 14 stores the condition information indicating the condition corresponding to each item to be specified! On the recording medium. Then, when specifying the cited document information part corresponding to a certain item, the cited document information acquiring unit 14 acquires the condition information corresponding to the item, and the reference information of the bow I document information corresponding to the condition information is acquired. Identify the part.

[0055] When the structure description information is included in the document information, the cited document information acquisition unit 14 identifies the document identification for the bow I included in all or part of the document information acquired by the document information acquisition unit 13. A part of cited document information indicating a cited document identified by information, which is associated with an item that has been determined in advance, may be acquired by structure description information.

[0056] If the cited document information acquiring unit 14 can acquire a part of the cited document information as described above as a result, the process is not limited. For example, when the document information acquisition unit 13 acquires information including the title of the cited document as the cited document identification information, and the cited document information acquisition unit 14 acquires a part of the cited document information corresponding to the item “title” In The cited document information acquiring unit 14 may acquire a part of the cited document information by acquiring a part corresponding to the title of the cited document information from the cited document identification information acquired by the document information acquiring unit 13. Good.

The related term information acquisition unit 15 acquires related term information from a part of the cited document information acquired by the cited document information acquisition unit 14. Here, the related term information is information indicating related terms related to the term indicated by the term information received by the term information receiving unit 12. The detailed configuration of the related term information acquisition unit 15 will be described later with reference to FIG.

The related term information output unit 16 outputs the related term information acquired by the related term information acquisition unit 15. Here, this output is output from a speaker that can be displayed on a display device (for example, a CRT or a liquid crystal display) or transmitted via a communication line to a predetermined device or printed by a printer. It may be stored in a recording medium or by audio output.

. The related term information output unit 16 may or may not include an output device (for example, a display device or a printer). The related term information output unit 16 may be realized by hardware, or may be realized by software such as a driver for driving these devices.

FIG. 2 is a block diagram showing a configuration of the related term information acquisition unit 15. In FIG. 2, the related term information acquisition unit 15 includes a related term candidate information acquisition unit 21, a relevance degree calculation unit 22, and a related term information determination unit 23.

[0060] The related term candidate information acquisition means 21 is configured so that the cited reference information acquisition unit 14 obtains related term candidate information, which is information that is a candidate for a related term in a part of the cited reference information acquired by the cited reference information acquisition unit 14. A part of the acquired cited document information is also acquired. The related term candidate information acquisition means 21 may not store the acquired related term candidate information and may store it in a recording medium. Here, various methods for acquiring the related term candidate information will be described here.

[0061] [Method for Acquiring Related Term Candidate Information 1]

The related term candidate information acquisition means 21 performs morphological analysis on a part of the cited reference information acquired by the cited reference information acquisition unit 14, and acquires information indicating a single noun and Z or compound noun as related term candidate information. May be. Related term candidate information acquisition means 21 acquires information indicating unknown words as related term candidate information in addition to information indicating single nouns, etc. May be. Here, the morpheme analysis is a process of dividing a natural language document into morphemes and recognizing the parts of speech of the morphemes. As a software for performing morphological analysis, “ChaSen” (http: ZZch _aS en. Nai st. Jp) developed at the Nara Institute of Science and Technology is known in Japan. By using a tea bowl, for example, information indicating nouns can be obtained. Here, nouns are simple nouns, unknown words, or compound nouns that are connected together. In addition, software that gives parts of speech to English words includes “TnT” (http: Z / www. Coll. Uni—saarland. DeZ to thorstenz tntZ) and “Brili TaggerJ (http: // www. Cs. Jhu. ~ BrillZ) etc. The method of acquiring information indicating a single noun as related term candidate information has been disclosed in the above-mentioned Non-Patent Document 4 etc. Therefore, detailed description thereof is omitted.

[0062] [Related Term Candidate Information Acquisition Method 2]

The related term candidate information acquisition means 21 may acquire information indicating technical terms as related term candidate information from a part of the cited reference information acquired by the cited reference information acquisition unit 14. Here, a method for acquiring information indicating technical terms will be described. First, the related term candidate information acquisition means 21 performs a simple noun, etc. from a part of the cited reference information acquired by the cited reference information acquisition unit 14 in the same manner as in the above-mentioned “Related Term Candidate Information Acquisition Method 1”. Extract information that indicates. Then, scoring indicating the possibility of being a technical term for each single noun is performed, and information indicating a single noun with a high score is acquired as related term candidate information. Here, a plurality of types are known as methods for assigning scores.

[0063] (Scoring based on coined word ability)

The word-making ability is a scale indicating the ease of composing a single noun compound word. A high score is given to information indicating single nouns including nouns with high word-making ability. Here, the connection frequency may be used as an index indicating the coined word ability. The concatenation frequency is the number of different words connected to a word, and the number of types of words that appear immediately before or after a word. In other words, articulation frequency is a measure of how many words are included in a compound noun, in other words, how easy it is to compose a compound noun. In this way, a score can be given to each single noun or the like based on the coined word ability. In compound nouns, the compound noun score is the geometric mean of the scores of the constituent single nouns. May be given.

[0064] (Scoring based on appearance frequency)

Let t be the single noun of interest. The number of constituent words of t is n. In that case, the score corresponding to t is calculated as follows.

score of t = (frequency of occurrence of t) Z (average frequency of occurrence of single nouns with n as the number of words) [0065] Here, "single noun etc." in the above formula means related term candidate information acquisition means 21 Are simple nouns extracted. Here, the appearance frequency of t and the average appearance frequency of single nouns and the like with n as the number of words are calculated in a part of the cited document information acquired by the cited document information acquisition unit 14. Note that “t occurrence frequency” may be simply used as the score of t.

[0066] In addition, scoring may be performed using a method other than the above description, and information indicating technical terms may be acquired as related term candidate information using a method other than the above description.

. Methods for acquiring information indicating technical terms as related term candidate information are disclosed in Non-Patent Document 1, Non-Patent Document 3, and the following documents, and are well known in the past. Detailed description thereof is omitted.

[0067] Literature: Hiroshi NaKagawa ^ “Automatic Term Recognition based on S tatistics of Compound NounsJ, Terminology, Vol. 6, No. 2, p. 195— 2

10, 2000

[0068] Literature: Hirokazu Ohata, Hiroshi Nakagawa, “Extraction of technical terms by different number of connected words”, Information Processing Society of Japan, 2000-NL-136, p. 119- 126

Literature: Hiroshi Nakagawa, Yasunori Mori, Yasuaki Yumoto, “Extraction of technical terms based on appearance frequency and connection frequency”, Natural Language Processing, Vol. 10 No. l, p. 27-45, January 2003

[0069] [Method for Acquiring Related Term Candidate Information 3]

The related term candidate information acquisition means 21 analyzes the structure of a part of the cited reference information acquired by the cited reference information acquisition unit 14 to identify a group of nouns, and includes single nouns included in the specified noun group. May be acquired as related term candidate information. Here, a group of nouns is a group including one or more single nouns. For example, it is assumed that a part of the cited document information acquired by the cited document information acquiring unit 14 is a claim of a patent application document as shown below. [0070] In a working machine that performs a desired work by driving the actuator by the operation means, a load detection means for detecting a load created in the work mechanism of the work described above, and a frequency corresponding to the detection value of the load detection means A first frequency converter that outputs a first frequency signal, a second frequency converter that outputs a pulse of a frequency corresponding to the detection value of the load detecting means, and the first frequency modulation output signal. Is provided with a modulation means for intermittently outputting the first frequency change pulse during the output period and a vibration generation means for generating a vibration in accordance with the output of the modulation means. Virtual vibration generator for machine operation o J

[0071] In the claims, there are generally the following structural features: The first feature is that there is a “group of nouns” at the end of the claim. In the above example, “virtual vibration generating device for operating a work machine” corresponds to the group of nouns. The second is that when the claim is divided into the first half and the second half by a character string such as “in”, “that is”, immediately before “in” and “in”. Is also characterized by the existence of a “group of nouns” similar to that at the end. In the above example, “work machine” corresponds to a group of the nouns. Therefore, the related term candidate information obtaining means 21 obtains a group of nouns at the end of the claim and a group of immediately preceding nouns such as `` Ode, '' and a single name included in the group of these nouns. Information indicating lyrics etc. may be acquired as related term candidate information. The related term candidate information acquisition means 21 can specify the location of a group of nouns immediately before “in” as a clue with “in”. Although the claims of patent application documents have been described here, a group of nouns can be specified in the same way in documents with other structures, and related term candidate information can be acquired. it can.

[0072] A method for analyzing a document structure to identify a group of nouns and obtaining information indicating single nouns included in the group of identified nouns is disclosed in the following documents. Since the conventional force is also known, detailed description thereof is omitted.

[0073] Literature: Akihiro Niimori, Manabu Okumura, Yuzo Marukawa, Makoto Iwayama, “Structural analysis of patent claims using clue phrases”, Transactions of Information Processing Society of Japan, Vol. 45, No. 3, p. 891— 905, 2004 Literature: JP 2004-164054

It should be noted that the related term candidate information acquisition means 21 stores information indicating common nouns that frequently appear. The related term candidate information power may be excluded. For example, the related term candidate information acquisition means 21 holds one or more pieces of information indicating nouns to be excluded in a recording medium (not shown), and indicates the nouns to be excluded in the information acquired as the related term candidate information. If any information power is included, the related term candidate information power may be excluded from the information. Examples of nouns to be excluded include methods, descriptions, publications, and literature.

The degree-of-association calculating unit 22 calculates the degree of association of terms indicated by the related term candidate information acquired by the related term candidate information acquiring unit 21 for each piece of related term candidate information. The degree-of-association calculating unit 22 may store the calculated degree of association and the related term candidate information acquired by the related term candidate information acquiring unit 21 in association with each other, not shown in the drawing.

Here, a method for calculating the degree of association will be described. The degree-of-relevance calculating means 22 indicates the degree of relevance of the related term candidate information, and the term indicated by the related term candidate information is a part of the cited reference information acquired by the cited reference information acquisition unit 14 ( If one or more of them are acquired, it may be the frequency of appearance in the set). Also, the degree-of-association calculation means 2 2 has, for each related term candidate information, described in “Related Term Candidate Information Acquisition Method 2”, a score indicating the possibility of being a technical term, for example, a score based on word-making ability A score based on the frequency or a score based on the connection frequency may be calculated, and the score may be used as the relevance level. In this case, if the score is already calculated by the related term candidate information acquisition unit 21, the relevance degree calculation unit 22 may acquire the score from the related term candidate information acquisition unit 21. Alternatively, a new score may be calculated. Accordingly, the calculation of the relevance by the relevance calculation means 22 includes acquisition of the relevance. Further, the degree-of-association calculating unit 22 may calculate the degree of association using both the appearance frequency of the term indicated by the related term candidate information and the above score. For example, the degree of association may be calculated by adding the two, or the degree of association may be calculated by multiplying the two.

[0077] The related term information determining unit 23 determines related term candidate information having a higher corresponding degree of related term candidate information from the related term candidate information acquired by the related term candidate information acquiring unit 21 as related term information. For example, the related term information determining means 23 may include, for example, a certain quantity of related terms candidate information acquired by the related term candidate information acquiring means 21 (for example, 30) or a certain percentage ( (For example, 30%) It is also possible to determine related term candidate information that has a corresponding relevance level equal to or higher than a predetermined threshold value as related term information, or to increase the corresponding relevance level by other methods. The related term candidate information may be determined as related term information. More specifically, the related term information determination unit 23 sorts the relevance levels calculated by the relevance level calculation unit 22, selects related term candidate information corresponding to the higher rank of the sorted relevance levels, and does not illustrate it. The related term information is determined by storing the related term information on the recording medium. The related term information stored in the recording medium (not shown) is the related term information output by the related term information output unit 16. The related term information determining means 23 may store the related term information in a recording medium (not shown). In this case, the stored related term information is read and output by the related term information output unit 16.

Next, the operation of the related term acquisition device 1 according to the present embodiment will be described using a flowchart. FIG. 3 is a flowchart showing the overall operation of the related term acquisition device 1.

(Step S101) The term information receiving unit 12 determines whether or not the term information is received.

If the term information is received, the process proceeds to step S102. If not, the process of step S101 is repeated until the term information is received.

(Step S102) The document information acquiring unit 13 stores the document information having the term indicated by the term information received by the term information receiving unit 12 in all or part of the document information in the document information storage unit 11. Two or more document information capabilities that have been searched and all the document information retrieved or a part of the retrieved document information, which is referred to in the retrieved document information. A portion having at least the document identification information for bow I that is information for identifying the document is acquired from the document information storage unit 11. Details of this process will be described later using the flowchart of FIG.

(Step S103) The cited document information acquisition unit 14 is cited document information that is information indicating a document identified by the cited document identification information included in all or part of the document information acquired by the document information acquisition unit 13. Is retrieved from two or more document information stored in the document information storage unit 11, and a part of the retrieved cited document information corresponding to a predetermined item is stored in the document information. Obtained from Part 11. See Figure 5 for details of this process. This will be described later with reference to the flowchart.

(Step S104) The related term information acquisition unit 15 uses related terms related to the term indicated by the term information received by the term information reception unit 12 from a part of the cited reference information acquired by the cited reference information acquisition unit 14. Related term information, which is information indicating Details of this processing will be described later using the flowchart of FIG.

(Step S 105) The related term information output unit 16 outputs the related term information acquired by the related term information acquisition unit 15. Then, the process returns to step S101.

In the flowchart of FIG. 3, the process ends when the power is turned off or the process is terminated.

FIG. 4 is a flowchart showing details of the document information acquisition process in step S 102 in the flowchart of FIG.

(Step S201) The document information acquisition unit 13 includes document information including all or part of the term information received by the term information reception unit 12, and is stored from the two or more document information stored in the document information storage unit 11. Search for.

(Step S 202) The document information acquisition unit 13 sets a counter i to 1.

(Step S203) The document information acquisition unit 13 determines whether or not the i-th document information searched in Step S201 exists. If it exists, the process proceeds to step S204. If it does not exist, the series of processing ends, and the steps in the flowchart of FIG.

Proceed to S103.

(Step S 204) The document information acquisition unit 13 acquires all or a part of the searched i-th document information. When acquiring a part of the retrieved document information of the cell, as described above, a part including at least the cited document identification information is acquired. When the retrieved i-th document information does not include any cited document identification information, the document information acquisition unit 13 does not have to acquire anything!

(Step S205) The literature information acquisition unit 13 increments the counter i by 1 and returns to Step S203.

FIG. 5 is a flowchart showing details of the cited document information acquisition process of step S103 in the flowchart of FIG. (Step S301) The cited document information acquisition unit 14 sets the counter i to 1.

(Step S302) The cited document information acquisition unit 14 determines whether or not the i-th document information acquired by the document information acquisition unit 13 exists. If it exists, the process proceeds to step S303. If it does not exist, the series of processing ends, and the process proceeds to step S104 in the flowchart of FIG.

(Step S303) The cited document information acquisition unit 14 acquires all the document identification information for bow I included in the i-th document information acquired by the document information acquisition unit 13.

(Step S304) The cited document information acquisition unit 14 sets the counter j to 1.

(Step S 305) The cited document information acquisition unit 14 determines whether or not the j-th cited document identification information acquired in Step S 303 exists. And if present, step

Proceed to step S307, and if it does not exist, proceed to step S306.

(Step S306) The cited document information acquisition unit 14 increments the counter i by one. Then, the process returns to step S302.

[0091] (Step S307) The cited document information acquisition unit 14 searches the document information storage unit 11 for the document information for the bow I identified by the jth reference document identification information acquired in step S303, and performs the search. A predetermined part of the cited reference information obtained is acquired from the reference information storage unit 11.

(Step S308) The cited document information acquisition unit 14 determines whether a part of the cited document information acquired in Step S307 has already been acquired. If it has already been acquired, the process proceeds to step S310, and if not, the process proceeds to step S309.

(Step S309) The cited document information acquisition unit 14 temporarily stores a part of the cited document information acquired in step S307. A part of the cited document information added in step S309 becomes a part of the cited document information finally acquired by the cited document information acquiring unit 14.

(Step S310) The cited document information acquisition unit 14 increments the counter j by 1. Then, the process returns to step S305.

FIG. 6 shows the related term information acquisition process of step S 104 in the flowchart of FIG. It is a flowchart shown about a detail.

(Step S401) The related term candidate information acquisition means 21 uses a part of the cited document information acquired by the cited document information acquisition unit 14 (if two or more of the cited document information are acquired, Two or more sets of part of cited reference information), that is, partial power of cited reference information temporarily stored in step S309.

(Step S 402) Relevance calculation means 22 sets counter i to 1.

(Step S403) The degree-of-association calculating unit 22 determines whether there is related term candidate information of the cells for which the related term candidate information acquiring unit 21 has also acquired the partial power of the cited document information. If it exists, the process proceeds to step S404. If it does not exist, the process proceeds to step S407.

[0096] (Step S404) The degree-of-association calculating unit 22 calculates the degree of association of the related term candidate information of the cells for which the related term candidate information acquiring unit 21 has also acquired partial power of the cited document information.

(Step S405) The related term information determining means 23 temporarily stores the degree of association calculated in step S404 in association with the corresponding related term candidate information. Here, the related term candidate information corresponding to the degree of relevance calculated in step S404 is the i-th related term candidate information acquired by the related term candidate information acquisition means 21 as part of the cited reference information. is there.

(Step S406) The degree-of-association calculating means 22 increments the counter i by 1. Then, the process returns to step S403.

(Step S407) The related term information determining means 23 sorts the relevance temporarily stored in Step S405.

[0099] (Step S408) The related term information determining means 23 determines related term candidate information corresponding to the higher relevance degree sorted in step S407 as related term information. Then, the series of processing ends, and the process proceeds to step S105 in the flowchart of FIG.

[0100] Next, experimental examples showing specific effects obtained by the related term acquisition device 1 according to the present embodiment will be described. In this experimental example, the sentence acquired by the document information acquisition unit 13 The donation information is an academic paper. On the other hand, it is assumed that the cited document information acquired by the cited document information acquiring unit 14 is document information related to a patent. Therefore, by inputting the term information indicating the academic paper term into the related term acquisition device 1, the related term information indicating the patent term related to the academic paper term is output. Here, academic paper terms are terms that are used relatively frequently in academic papers (for example, specific subordinate terms such as DRAM and word processor), and patent terms are used relatively frequently in patent documents. It is a term (for example, an abstract high-level term such as a semiconductor storage device or a document editing device).

[0101] In this experimental example, the information of the patent publication (1993 to 2002) is included in the document information stored in the document information storage unit 11. Also, the bibliographic information of about 85,000 bibliographic information of cited papers in the patent publication is included in the bibliographic information stored in the bibliographic information storage unit 11. The method disclosed in the following document was used as a method for extracting the bibliographic information of the paper cited in the patent publication from the patent publication.

[0102] Literature: Natsumi Anzen, Hideaki Namba, Teruaki Aizawa, Manabu Okumura, “Construction of a Search Environment that Integrates Patents and Article Databases”, Information Processing Society of Japan Research Report, NL—168, p. 21—26, 2005

First, term information received by the term information receiving unit 12 will be described. The nouns are extracted from the information of the patent publications stored in the document information storage unit 11. Then, the extracted nouns are arranged in order of frequency, and the 25 most frequently used articles are selected manually. Specifically, “CPU”, “semiconductor laser”, “DRAM”, “memory cell”, “word processor”, “novolak resin”, “CD”, etc. were selected.

In this experimental example, the pattern of the portion of the cited document information acquired by the cited document information acquiring unit 14 is as follows.

(Pattern 1) Information indicating the first claim of the cited document, that is, the first described claim is acquired as a part of the cited document information.

(Pattern 2) All the claims of the cited document, that is, information indicating all claims described in the claims is acquired as a part of the cited document information.

[Pattern 3] Information indicating the first claim of the cited document, and claims dependent on the first claim Information indicating a dependent claim that is a term is acquired as part of the cited document information. Where

Claims dependent on one claim include claims dependent on the first claim through other claims, not just on the claims directly dependent on the first claim.

In this experimental example, the pattern in which the related term candidate information acquisition unit 21 acquires the related term candidate information is as follows.

(Pattern Related Term Candidate Information Acquisition Method 1 As described in Method 1, a morphological analysis is performed on a part of cited document information, and a noun is acquired as a related term candidate.

[0110] (Pattern B) As described in Method 3 for acquiring related term candidate information, identify a group of nouns from a part of cited reference information, and acquire nouns included in the group of nouns as related term candidates. To do.

[0111] It should be noted that the related term candidate information acquisition unit 21 does not acquire a related term candidate that matches a phrase included in the unnecessary phrase list by using a predetermined unnecessary phrase list. Terms such as “method” and “description” appear in many claims regardless of the field, so that such terms are excluded from the related term candidates. In the unnecessary word list, the nouns included in the patent publications for 10 years are arranged in order of appearance frequency, and the words to be included in the unnecessary word list are selected manually from the most frequently used ones. For example, a total of 350 unnecessary words such as method, description, publication, literature, use, use, details, manufacturing, proposal, manufacturing method, and data are included in the unnecessary word list.

[0112] Also, in this experimental example, in order to verify the effect of acquiring a part of cited document information, the relevance calculation means 22 does not calculate the relevance! . Further, the related term information determining unit 23 determines the related term candidate information acquired by the related term candidate information acquiring unit 21 as the related term information as it is.

[0113] Under such circumstances, the term information receiving unit 12 receives each of the 25 term information items described above, and the related term information output unit 16 outputs related term information related to the term information. Executed. The related term information output unit 16 stores the related term information in a predetermined recording medium. After that, the related term information was used for verification.

[0114] In this verification, whether the related term information is correct or not was determined according to the following criteria.

(Standard 1) Only the term that is conceptually closest is correct For example, for the term information “word processor”, the related term information “document editing device” is the correct answer, and the related term information “display device” that is a component of the word processor is incorrect.

[0115] (Standard 2) Frequency of appearance in patent database

If the frequency of occurrence of a term was extremely low in the patent database, it was considered incorrect because the term was not useful for obtaining patent related terms.

[0116] (Criteria 3) Comparison with the one selected in Criteria 1

Even if a term does not meet the above (Criteria 2)! / ヽ, if it is judged that the term is conceptually almost equal to the one selected above (Criteria 1), the correct answer will be given even if it is infrequent. did. For example, for the term information “word processor”, it is assumed that the related term information “document creation device” that is conceptually almost equivalent to the related term information “document editing device” is also correct. For fluctuations such as “Laser” and “Laser I”, if the related term information is determined to be correct, the other is also correct.

[0117] In this verification, the following evaluation scale ε was used. This is an extension of the MRR (mean reciprocal rank) generally used in the evaluation of question answering systems, and is disclosed in the following document.

[0118] Literature: Yoji Kiyota, Ikuo Kurohashi, Toko Kido, “Resolving Dependency Displacement Using Automatically Extracted Metaphoric Expressions”, Natural Language Processing, Vol. 11, No. 4, p. 127—145 , 2004

[Number 1]

∑,…, "})

[0119] where n is the number of correct answers for the input. R is the set of correct answer rank numbers in the output list. ε takes a maximum value of 1 when all correct answers are ranked at the top.

FIG. 7 is a table showing the results of this experimental example. In Fig. 7, the ID is set to identify each experimental example. The ID6 experiment example is a baseline experiment example in other experiment examples, in which nouns that co-occur with the term information frequently are extracted and the nouns are used as related terms. ID6 experimental example that is the baseline Acquisition of related terms from the past This is the method used in As can be seen from the table in Fig. 7, when comparing the experimental example of ID1 with the experimental example of ID2, it is better to obtain a noun from a group of nouns in the claim than simply acquiring a noun. I understand that. Also, comparing the experimental example of ID3 with the experimental example of ID4, it is better to obtain a noun from a group of nouns in a claim that simply needs to obtain a noun. From this, it is clear that it is effective to obtain nouns from a group of nouns in a claim that simply obtains nouns.

Next, it is examined whether it is effective to consider the relationship between claims. Comparing the experimental results of IDs 2, 4, and 5, the experimental result of ID5 using the first claim and its dependent claims is the best, and the experimental result of ID2 is the worst when only the first claim is used. The result was. The reason why ID2's experimental results are bad is that the number of correct answers that can be obtained by reducing the noise is too small, and the number of correct answers that can be obtained is reduced. The ID3 experiment example using all the claims is inferior to the ID5 experiment example because the number of correct answers extracted is larger than the ID2 experiment example, but many incorrect answers are extracted. It is becoming a result.

[0122] In each method, when extracting the noun from one patent publication, the number of claims used was investigated, and the result shown in Fig. 8 was obtained. The ID5 experimental example is higher than the D4 experimental example even though the ID4 experimental example is less than the power of the claims to be acquired compared to the ID4 experimental example. It is difficult to say that a term and its dependent claims are high!

[0123] As described above, according to the related term acquisition device 1 according to the present embodiment, it is possible to acquire effective related term information by acquiring a part of the cited document information. Therefore, it is possible to provide the related term acquisition device 1 that can appropriately acquire the related term information related to the accepted term information.

[0124] It should be noted that a part of the cited document information acquired by the cited document information acquiring unit 14 may be any part as long as the related term information can be appropriately acquired. For example, the cited document information is information indicating a patent document, and the cited document information part corresponding to the predetermined item acquired by the cited document information acquiring unit 14 is a part of the independent claim. May be. An independent claim is a claim that is not dependent on other claims. The cited document information acquisition unit 14 may determine whether a certain claim is an independent claim, for example, as follows. The cited document information acquisition unit 14 determines whether or not there is a description referring to another claim in the claim of interest, that is, the description of “Claim N”. It is determined that the current claim is not an independent claim, and if it does not exist, it is determined that the target claim is an independent claim. Here, “N” is an arbitrary integer of 1 or more. Further, for example, the cited document information is information indicating a patent document, and the portion of the cited document information corresponding to the item decided by the cited document information acquisition unit 14 that has been determined in advance has the effect of the invention. The described part may be used. The portion describing the effect of the invention may be, for example, the portion corresponding to the item “effect of the invention” or the content of the document. Good. In the latter case, as a method of specifying the portion describing the effect of the invention, for example, “as above” or “in this way” force starts, “effect”, “possible”, “can” For example, there is a method of identifying a paragraph including any of the above words as a part describing the effect of the invention. In addition, the cited document information is information indicating a patent document, and the cited document information part corresponding to the item that is determined in advance by the cited document information acquiring unit 14 is other than the premise part of the claims. It may be a part. The premise part of a claim is a part called a preamble of a claim, and is generally a part described before “in” or “in” in a claim. Accordingly, the part other than the premise part of the claim is a part in which the characteristic description of the claim is made, and is generally later than “to” or “to” in the claim. It is a part that is described. If the preamble is described in the claim, the entire claim becomes a part other than the premise part.

[0125] (Embodiment 2)

A related term acquisition apparatus according to Embodiment 2 of the present invention will be described with reference to the drawings. The related term acquisition device according to the present embodiment further includes a cited document structure information acquisition unit.

FIG. 9 is a block diagram showing a configuration of the related term acquisition device 2 according to the present embodiment.

In FIG. 9, the related term acquisition device 2 according to the present embodiment includes a document information storage unit 11, The term information receiving unit 12, the document information acquiring unit 13, the cited document information acquiring unit 14, the related term information acquiring unit 15, the related term information output unit 16, and the cited document structure information acquiring unit 31 are provided. Configurations and operations other than the cited document structure information acquisition unit 31 are the same as those in the first embodiment, and a description thereof will be omitted.

The cited document structure information acquisition unit 31 obtains cited document structure information that is information indicating correspondence between one or more parts of the cited document information stored in the document information storage unit 11 and items of the parts. get. The cited document structure information may be any information structure as long as the item can be associated with a portion of the cited document information corresponding to the item. For example, the cited document structure information may indicate an item by a tag and a portion corresponding to the item. That is, in the cited document information, a region sandwiched between <effect> and <Z effect> may be a portion corresponding to the item “effect”. In this case, the cited document structure information may be stored in the document information storage unit 11. Further, for example, the cited document structure information may have information indicating the portion of the cited document information corresponding to the item “effect” in association with the item “effect”. In this case, the cited document structure information may be held in the document information storage unit 11 in association with the cited document information, or the cited document structure information acquisition unit 31 and other components are illustrated. No, you can hold it on the recording medium!ヽ. In the latter case, it is preferable to store the cited document structure information in association with the cited document identification information. The information indicating the cited document information part may be information indicating the position of the leading end and the position of the trailing end of the cited document information part, for example. The positions of the leading edge and trailing edge may be indicated by, for example, the number of bytes of the leading force of the cited document information, or may be indicated by the number of pages and the number of lines.

[0128] Here, how to specify a part corresponding to an item in the cited document structure information acquisition unit 31 will be described. For example, the cited document structure information acquisition unit 31 holds the condition information indicating the condition corresponding to each item to be specified in a not-shown recording medium. Then, the portion of the cited document information corresponding to the condition information is specified, and the cited document structure information is acquired by associating the item with the portion. For example, the condition information corresponding to the item “Effect” starts with a paragraph starting from “As above” or “Like this”, and the word “Effect”, “Possible”, or “Yes” appears in the paragraph. To be included To do. Then, the cited document structure information acquisition unit 31 can acquire the cited document structure information by specifying a paragraph that satisfies the condition and associating the paragraph with the item “effect”. In addition, for example, the condition information corresponding to the item “characteristic description of claim” is a part included in the claim, which is a part that follows “is” and “in”. ”. Then, the cited document structure information acquisition unit 31 can acquire the cited document structure information by specifying a portion that meets the condition and associating the portion with the item “characteristic description of claim”. Regarding the method of obtaining the characteristic description of claims, the above-mentioned documents “Akihiro Niimori, Manabu Okumura, Yuzo Marukawa, Makoto Iwayama,“ Structural analysis of patent claims using clue phrases ”, Information Processing Society of Japan Journal, Vol. 45, No. 3, p. 891-905, 2004 ”[This is listed!

Next, the overall operation of the related term acquisition apparatus 2 according to the present embodiment will be described using the flowchart of FIG. The processes other than steps S501 and S502 are the same as those in the flowchart of FIG. 3 in the first embodiment, and a description thereof will be omitted. However, in step S103, the cited document information acquisition unit 14 uses the cited document structure information acquired by the cited document structure information acquisition unit 31, and is a part of the cited document information that is determined in advance. The part corresponding to is acquired.

(Step S501) The cited document structure information acquisition unit 31 determines whether or not the cited document structure information has already been acquired. If it has not been acquired, the process proceeds to step S502. If it has already been acquired, the process proceeds to step S102.

(Step S502) The cited document structure information acquisition unit 31 acquires the cited document structure information for all of the cited document information stored in the document information storage unit 11. Here, in the document information stored in the document information storage unit 11, it is insignificant until the document information is acquired as to whether V or the deviation is the cited document information. The obtaining unit 31 acquires the cited document structure information for all the document information stored in the document information storage unit 11.

[0132] In the flowchart of Fig. 10, the case where the cited document structure information is acquired collectively has been described. However, in the case where a part of the cited document information is acquired, the bow of the cited document information is obtained. In the case where the literature structure information for I has not yet been acquired, Only the cited document structure information may be acquired. In this way, unnecessary reference document structure information is not acquired, and the processing load is reduced.

[0133] Further, the citation structure information is acquired when the related term acquisition device 2 does not perform related term acquisition processing, that is, when the processing load on the related term acquisition device 2 is large. Go ahead and do it! /.

As described above, according to the related term acquisition device 2 according to the present embodiment, since a part of the cited document information is acquired using the cited document structure information, the structure of the document is manifested in the cited document information. Even if there is not, it is possible to easily obtain a desired portion of the cited document by using the cited document structure information.

[Embodiment 3]

A related term acquisition apparatus according to Embodiment 3 of the present invention will be described with reference to the drawings. The related term acquisition device according to the present embodiment acquires a part of cited document information corresponding to an item corresponding to the cited format of the cited document in the document information.

The configuration of the related term acquisition device according to the present embodiment is the same as that shown in FIGS. 1 and 2 of Embodiment 1, and the description thereof is omitted. In addition, when acquiring a part of the document information, the document information acquisition unit 13 acquires a portion having at least cited reference identification information and at least including reference information. In addition, the cited document information acquisition unit 14 is a piece of cited document information that is information indicating a document identified by the document identification information for bow I included in all or part of the document information acquired by the document information acquisition unit 13. The part corresponding to the item that is decided according to the quotation format in the information for bow I included in all or part of the document information acquired by the document information acquisition unit 13 is acquired. To do. In addition, when the cited document information acquisition unit 14 acquires a part corresponding to an item determined according to the citation format, the citation document is a predetermined format. In some cases, no information is obtained.

Here, the citation information is information indicating a description of the document identified by the cited document identification information. In the document information, for example, the citation information may exist in the same area as the cited document identification information, and the citation information may exist in a different area from the cited document identification information. In the former case, for example, cited document identification information is described in the background art area. In this case, the cited document is cited by the cited document identification information itself. Such citations may be made in patent specifications and the like. On the other hand, in the latter case, for example, the cited document identification information is collectively described in the reference column, and corresponds to the cited document identification information described in the reference column in the text of the document. This is the case where the cited reference is used for the bow I by the given index. In academic literature, such citations are often made. Here, the index is, for example, 1, 2, 3 ... or 1), 2), 3) ... ゝ [1], [2], [3] ... ゝ [A], [B], [C ] ..., patent document 1, patent document 2, patent document 3, ..., non-patent document 1, non-patent document 2, non-patent document 3, ..., etc., which can identify cited document identification information Anything can be used. When a cited document is cited by the cited document identification information itself, the cited information is information including the cited document identification information. The information including cited document identification information is, for example, information on a predetermined area including cited document identification information. The predetermined area may be, for example, a sentence or a noragraph, or a group of other documents. When a cited document is cited by a predetermined index corresponding to the cited document identification information, the cited information is information including the index. The information including the index is, for example, information on a predetermined area including the index. The predetermined area may be, for example, a sentence or a noragraph, or a group of other documents. In the literature information, when the citation information and the cited document identification information exist in different areas and the literature information acquisition unit 13 acquires a part of the literature information, the literature information acquisition unit 13 It is possible to acquire a part of a set of document information including “”, or to acquire two or more parts of document information including both of them. Further, when the document information acquisition unit 13 acquires all or a part of the document information having the citation information, the reference information may be manifested in all or a part of the document information, or may be manifested. It does not have to be converted. In the former case, the portion of the reference information can be easily saved in all or part of the literature information.

Next, the citation format in the citation information will be described. The citation format includes, for example, a problem-pointing citation format (hereinafter also referred to as “type C” citation format) that points out the problem of the cited document, and a format that incorporates the cited document as the basis of the editorial. An editorial basis type There are citation formats (hereinafter also referred to as “Type B” citation formats) and other citation formats (hereinafter also referred to as “Type 0” citation formats). The type B citation format is a citation format used when a new theory is proposed or a system is constructed using existing research results. It should be noted that other citation formats may be used. The cited document information acquisition unit 14 holds, for example, one or more hands according to each citation format in a recording medium (not shown), and the hand has a force phrase at a predetermined position of the quote information. Depending on whether it is included, each citation format may be determined. The predetermined position may be, for example, all of the citation information that may be at the beginning of the citation information or at the end of the citation information. Note that other methods may be used as long as the citation format can be determined from the citation information.

Next, the operation of the related term acquisition device 1 according to the present embodiment will be described using a flowchart. The overall operation of the related term acquisition apparatus 1 according to the present embodiment is the same as that of the flowchart of FIG. The flowchart shown in detail in the flowchart of FIG. 3 for obtaining the document information in step S102 is also the same as the flowchart of FIG. 4 of the first embodiment, and a description thereof will be omitted. However, it is assumed that the document information acquisition unit 13 also acquires citation information in step S204 of FIG. Also, the flowchart showing the details of the related term information acquisition process of step S104 in the flowchart of FIG. 3 is the same as the flowchart of FIG. 6 of the first embodiment, and a description thereof will be omitted.

[0140] FIG. 11 is a flowchart showing details of the cited document acquisition processing in step S103 in the flowchart of FIG. The processes other than steps S601 to S603 are the same as those in the flowchart of FIG. 5 of the first embodiment, and the description thereof is omitted.

[0141] (Step S601) The cited document information acquisition unit 14 includes all the cited document identification information included in the i-th document information acquired by the document information acquisition unit 13 and the cited information corresponding to the cited document identification information. And get. If the citation information part is not obvious in all or part of the literary information acquired by the literary information acquisition unit 13, it is the same as described in the citation information acquisition process by the literary information acquisition unit 13. Thus, the cited document information acquisition unit 14 can identify the portion of the cited information. [0142] (Step S602) The cited document information acquisition unit 14 determines the citation format in the cited information corresponding to the j-th cited document identification information. The citation format may be determined, for example, by storing the j-th cited document identification information and information indicating the bow I format in association with each other in a not-shown recording medium. Details of this processing will be described later using the flowchart of FIG.

[0143] (Step S603) The cited document information acquisition unit 14 searches the document information storage unit 11 for the document information for the bow I identified by the jth reference document identification information acquired in Step S601. A part corresponding to the citation format determined in step S602 is acquired from the document information storage unit 11 as a part of the cited document information.

FIG. 12 is a flowchart showing details of the citation format determination process in step S602 in the flowchart of FIG. As described above, it is assumed that the cited document information acquisition unit 14 holds one or more hands corresponding to each citation format in a recording medium (not shown).

(Step S 701) The cited document information acquisition unit 14 sets a counter k to 1.

(Step S702) The cited document information obtaining unit 14 determines whether or not the k-th hand whose citation information is type C includes a force phrase. If so, the process proceeds to step S703, and if not, the process proceeds to step S704.

(Step S 703) The cited document information acquisition unit 14 determines the citation format as type C. Then, the series of processing ends, and the process proceeds to step S603 in the flowchart of FIG.

(Step S704) The cited document information acquisition unit 14 increments the counter k by 1.

(Step S 705) The cited document information acquisition unit 14 determines whether or not the k-th type C cue phrase exists. If it exists, the process returns to step S702. If it does not exist, the process proceeds to step S706.

(Step S706) The cited document information acquisition unit 14 sets the counter k to 1.

(Step S707) The cited document information acquisition unit 14 determines whether or not the k-th hand whose citation information is type B includes a power phrase. If it is included, the process proceeds to step S708; otherwise, the process proceeds to step S709.

(Step S 708) The cited document information acquisition unit 14 determines the citation format as type B. And Thus, the series of processing ends, and the process proceeds to step S603 in the flowchart of FIG.

(Step S709) The cited document information acquisition unit 14 increments the counter k by 1.

[0150] (Step S710) The cited document information acquisition unit 14 determines whether or not the k-th type B manual strength phrase exists. If it exists, the process returns to step S707. If it does not exist, the process proceeds to step S711.

(Step S711) The cited document information acquisition unit 14 determines the citation format as type O. Then, the series of processing ends, and the process proceeds to step S603 in the flowchart of FIG.

[0152] Next, the operation of the related term acquisition apparatus 1 according to the present embodiment will be described using a specific example. In this specific example, the bibliographic information storage unit 11 stores about 12000 full-text papers (bibliographic information) centered on natural language processing fields in Postscript and PDF format. Of these, approximately 8,000 are included in ACL Anthology provided by ACL, and the remaining approximately 4,000 are also collected from the web pages of natural language processing researchers and natural language processing laboratories in Japan and overseas. And paper data (bibliographic information) extracted from the proceedings of the international conference (CD-ROM). Thus, the document information stored in the document information storage unit 11 in this specific example is an academic paper and! /, Another kind of document information.

[0153] Also, in this specific example, the document information acquisition unit 13 obtains information in the column of the reference document of the document information from the document information in which the term indicated by the term information received by the term information reception unit 12 is included in the title And the corresponding citation information.

[0154] Also, in this specific example, the cited document information acquisition unit 14 uses the hand phrase corresponding to type C, which is information having a clue phrase corresponding to type C, and the hand corresponding to type B. A type B hand, which is information having phrases, holds a force phrase dictionary on a recording medium (not shown). FIG. 13 is a diagram showing an example of a type C clue phrase dictionary. FIG. 14 is a diagram showing an example of a type B cue phrase dictionary. The cited document information acquisition unit 14 determines that the citation format is type C when any of the clue phrases in the type C clue phrase dictionary is included in the citation information, and the citation information is for type B. If the hand contains any clue phrase in the force phrase dictionary, the citation form is determined to be type B.

[0155] In this specific example, the cited document information acquiring unit 14 acquires the title of the cited document as a part of the cited document. First, it is assumed that the user inputs the term information “ _term i _no l ₀ gy” to the related term acquisition device 1.

. Then, the term information "t _er minol ₀ gy" are accepted by the term information receiving section 12 (scan Tetsupu S101). Then, the document information acquisition unit 13 acquires the reference field and reference information of each document information including the term information “terminol ₀ gy” in the title (steps S 102, S 201 to S 201). S205).

Specifically, the document information acquiring unit 13 searches each document information including the term information “terminology” in the title, and acquires the bibliographic information of the searched document information (step S201). FIG. 15 is a diagram showing an example of the bibliographic information of the acquired document information. As shown in Fig. 15, the bibliographic information includes "author", "title", and "other". “Author” is information about the author (s) of the paper, “Title” is information about the title of the paper, and “Other” is information such as the name and year of the journal. Note that in FIG. 15, “ID” is associated with each record. This “ID” exists for record management in the table.

[0157] The document information acquisition unit 13 uses the document information identified in each record shown in Fig. 15 to determine the reference document (Reference) column part and the I document identification information included in the reference document column. Information for bow I corresponding to the information is acquired (step S204).

[0158] Here, a method of acquiring citation information in this specific example will be described. As described above, the document information acquiring unit 13 acquires a predetermined index corresponding to the cited document identification information described in the reference column from the reference column, and searches for a sentence including the index. . Next, the document information acquisition unit 13 extracts sentences (1) to (6) that are deeply connected to the sentence including the index using the following power phrases. In other words, the document information acquisition unit 13 3 culls the hand if the sentence following the sentence including the index includes the following clue phrases (1) to (6)! The sentence containing the phrase is extracted as a sentence closely related to the sentence containing the index. The document information acquisition unit 13 acquires the sentence including the index, the sentence including the index, the depth of connection, and the sentence as citation information.

[0159] (1) Manual power for anaphor S: In this, On this, Such

(2) Skills related to conjunctions S: But, However, Although

(3) First person clues: We, we, Our, our, us ゝ I (4) Third person clues: They, they, Their, their, them

(5) clues about adverbs: additionally additionally, Still

(6) Other clues: In particular, follow, For example

Next, the cited document information acquisition unit 14 is based on a part of the document information acquired by the document information acquisition unit 13 (that is, the citation information corresponding to the reference document part and each cited document identification information). Then, the citation format is determined, and the portion of the cited document corresponding to the citation format is acquired (step S103, flowcharts of FIGS. 11 and 12).

[0161] When determining the citation format, as described above, if any hand in the type C cue phrase dictionary shown in Figure 13 contains a force phrase, the citation format is changed to type C. If the citation information includes a force phrase in one of the hand phrase dictionary type B shown in Fig. 14, the citation format is determined as type B, type C, type B If it is neither of these, the citation format is determined as type O (steps S701 to S711). Then, when the citation format is type C, the cited document information acquisition unit 14 acquires information indicating the title of the cited document information as a part of the cited document information. On the other hand, when the citation format is type B, the cited document information acquisition unit 14 acquires information indicating a summary (abstract) of the cited document information as part of the cited document information. The cited document information acquisition unit 14 does not acquire a part of the cited document information when the citation format is type O.

[0162] Thereafter, the related term information output unit 16 acquires related term information from a partial set of cited reference information acquired by the cited reference information acquisition unit 14 (step S104, flowchart of FIG. 6). The related term information output unit 16 outputs the acquired related term information (step S105).

[0163] Needless to say, the method for obtaining the citation information is not limited to the specific description described above. Here, another method for acquiring citation information will be described. For example, as described above, the document information acquisition unit 13 acquires a predetermined index corresponding to the cited document identification information described in the reference column from the reference column, and reads a sentence including the index. Search and identify the sentence that contains the index. Then, the literature information acquisition unit 13 uses the sentence including the index and the sentence closely related to the sentence as citation information. And get. Here, we explain how to identify sentences that are closely related to the sentence that contains the index.

It is assumed that the document information acquisition unit 13 can access the following two types of hand-powered phrases stored on a recording medium (not shown).

(A) Hands for front extension

In this, On this, ¾uch, But, However-

(B) Post expansion clue phrases

We, we, They, they, Our, our, In this, On this, Such, But, However---

[0165] First, the document information acquisition unit 13 sets a sentence including an index as a candidate sentence for citation information. Then, if the first sentence of the candidate sentence contains (A) at least one of the previous extension hand and the phrase is included, the sentence one sentence before the candidate sentence is included in the candidate sentence. The document information acquisition unit 13 repeats the process of extending the candidate sentence before the first sentence of the candidate sentence does not include (A) the previous extension handwriting and all of the phrases. In addition, the document information acquisition unit 13 adds (B) an extension hand to the next sentence after the candidate sentence (a sentence that is adjacent to the candidate sentence and not included in the candidate sentence). Is included, the next sentence of the candidate sentence is included in the candidate sentence. The document information acquisition unit 13 repeats the process of extending the candidate sentence later until the next sentence after the candidate sentence does not include all of the words (B). The candidate sentence at the time when the process of extending the candidate sentence is completed becomes the citation information. The literature information acquisition unit 13 acquires the citation information. Note that (A) the pre-extension hand phrase is an example, and the (B) post-extension clue phrase is an example, so long as it is possible to appropriately extract sentences closely related to the sentence containing the index. Other clue words may be used. Here, we focused on the sentence that contains the index, but in the technical literature that directly refers to the cited document by the cited document identification information, the sentence that contains the cited document identification information is replaced with the sentence that contains the index. Will be used instead of.

[0166] Needless to say, the method of determining the citation format is not limited to the specific description described above. Here, another method for determining the citation format will be described. For example, the document information acquisition unit 13 considers the position of the cue phrase included in the citation information that does not determine the citation format only based on whether or not the predetermined hand is included in the citation information. The citation format may be determined. More specifically, for example, in the type C clue phrase dictionary, as shown in FIG. 20, the type C hand is a power phrase (in FIG. 20, “cue phrase”) and the hand is strong. Assume that the position of the phrase is associated. The “position of the clue phrase” in FIG. 20 is information indicating the number of sentences in the citation information, with the sentence including the index and the cited document identification information as a reference (0). For example, if the hand is in the position “1-3” of the force phrase, the citation information starts with the index or the sentence after the sentence containing the index or cited document identification information (cue phrase position = 1). It means three sentences from the sentence containing the cited document identification information to the third backward sentence (hand is the position of the force phrase = 3). If the position of the clue phrase is negative, it means the sentence before the sentence that contains the index or cited document identification information. The document information acquisition unit 13 determines that the type of citation information is type C when the type C hand is included in the sentence indicated by the position of the corresponding hand. You may judge. More specifically, the document information acquiring unit 13 selects any one of the citation information from the next sentence (first sentence) to the third sentence after the sentence including the index and the cited document identification information. If “However” is included in the sentence, the citation format of the citation information may be determined to be type C. Although the method for determining whether the citation format is type C has been described here, the method for determining whether the citation format is type B is the same.

Thus, according to the related term acquisition device 1 according to the present embodiment, it is possible to acquire a part of the cited document information corresponding to the item according to the cited format of the cited document. Accordingly, it is possible to obtain related term information with higher accuracy by appropriately setting which part of the cited document information corresponding to which item is to be obtained.

[0168] In the present embodiment, as in the above specific example, when the citation format is S type C, information indicating the title of the cited document information is acquired, and the citation format is type B. In this case, the case where information indicating a summary of cited document information is acquired has been described, but this may be another setting. For example, the cited document information acquisition unit 14 may refer to the cited document in the information for the bow I included in all or part of the document information acquired by the document information acquisition unit 13 S. A portion having background items in the information is acquired and included in all or a part of the document information acquired by the document information acquisition unit 13. If the citation format in the citation information is an editorial-based citation format, a portion having characteristic items in the citation information may be acquired. Here, the background items are, for example, patent documents, “conventional technology”, “background technology”, etc., and academic documents that may be “introduction”, “related research”, etc. There may be. The characteristic items are, for example, patent documents, “embodiments”, “effects”, etc. There may be. The method described in the first and second embodiments can be used as a method for obtaining the portion of the reference document information corresponding to these items.

Needless to say, the related term acquisition device 2 according to the second embodiment may execute the process of acquiring the cited document information part according to the citation format! /.

[0169] Also, in each of the above embodiments, the document information stored in the document information storage unit 11 may be of two or more types. For example, in the document information storage unit 11, at least a first type of document information and a second type of document information are stored, and the document information acquisition unit 13 is stored in the document information storage unit 11. !, All or part of the first type of document information is acquired from the first type of document information, and the cited document information acquisition unit 14 stores the second type of information stored in the document information storage unit 11. A part of the cited document information may be acquired from the type of document information. For example, the first type of document information may be information on academic papers, and the second type of document information may be patent document information or vice versa. In general, users who are familiar with academic papers are often not familiar with the terms used in patent documents, but by using such a related term acquisition device, the terms used in academic papers Related terms used in patent documents related to terms can be obtained. The first type of document information may be information of the first type of language, and the second type of document information may be information of the second type of language. The first type language and the second type language may be any language such as English, Japanese, Chinese, French, German, and the like. In this way, for example, it may be possible to obtain English related terms related to Japanese terms.

[Embodiment 4]

Regarding the technical trend information creation device according to the fourth embodiment of the present invention, refer to the drawings. Will be explained.

FIG. 16 is a block diagram showing the configuration of the technology trend information creation device according to this embodiment. In FIG. 16, the technical trend information creation device 1001 according to the present embodiment includes a search term reception unit 1011, a document information storage unit 1012, a search unit 1013, a specification unit 1014, a document information acquisition unit 1015, a technology A term extraction unit 1016, a time information acquisition unit 1017, a technology trend information creation unit 1018, and an output unit 1019 are provided.

[0171] The search term receiving unit 1011 receives a search term. The search term is information used as a search keyword in a search by the search unit 1013 described later. The search term accepted by the search term receiving unit 1011 is actually information indicating the search term, but is simply referred to as a search term. The technical trend information creation device 1001 searches for technical documents based on the search terms received by the search term receiving unit 1011, acquires information indicating the searched technical documents, and based on the information, acquires the technical trends. Information will be created. As described above, this search term is used to determine a field or the like in which technical trend information is created. This search term may be force or other information that is typically text data. Further, this search term may be information indicating the period of the technology trend information to be created, for example, information indicating the field of the technology trend information to be created. When the search term is information indicating a technical trend information field, the search term may be, for example, a symbol associated with the field or the name of the field. Examples of symbols associated with the fields include IPC (international patent classification) and us class (US patent classification). In the present embodiment, a case will be described in which search term receiving unit 1011 receives a search term indicating the name of the field of technology trend information.

[0172] Here, the search term accepting unit 1011 accepts the search term using, for example, a wired or wireless communication line that accepts information input from an input device (eg, keyboard, mouse, touch panel, etc.). It is also possible to accept information read from a predetermined recording medium (for example, an optical disk, a magnetic disk, a semiconductor memory, etc.) by receiving information transmitted through the network. The search term receiving unit 1011 may or may not include a device (for example, a modem or a network card) for receiving. The search term acceptance unit 1011 may be implemented by hardware. Alternatively, it may be realized by software such as a driver that drives a predetermined device.

[0173] In the document information storage unit 1012, a plurality of document information and a plurality of time information are stored at least. Here, the literature information is information indicating at least a part of the technical literature. The technical literature includes, for example, technical papers, patent 'utility model publications, published technical bulletins, technical documents and articles, technical web pages, and the like. One document information includes at least part of information (data) of the corresponding one technical document. The part of the technical document is a part of the technical document that includes at least a range necessary for subsequent processing. For example, when the title of a technical document and a reference document are used in later processing, the document information may be information indicating the title of the technical document and the reference document. The document information may be information indicating all technical documents. Moreover, time information is information which shows the time regarding the technical literature which literature information shows. The time information may be, for example, information indicating the time when the document information was created, or information indicating the time when the document information was released. Also good. The time information may be, for example, information indicating the year related to the literature information, information indicating the appropriate date, information indicating the correct date, or information indicating other time. It is assumed that the document information and the time information are directly or indirectly associated with each other so that it can be understood which technical document is at which time. In the former case, for example, document information and time information corresponding to each other may be included in the same record. In the latter case, for example, document information and time information may be associated with each other through a document ID for identifying a technical document. The document information and the time information may be a text file, or may be a file of a unique format such as a professional software. The document information and the time information may be separate data or may be integrated as data.

It goes without saying that other information may be stored in the document information storage unit 1012. For example, bibliographic information such as author name, publisher name, media name (eg, journal name, book name, etc.), technical literature field (eg, IPC), technical literature summary, etc. It may be stored in the storage unit 1012. Further, the document information may include, for example, cited document identification information and cited information. Cited reference identification information refers to reference information. This is information for identifying other technical documents (hereinafter, this technical document may be referred to as “cited document”). Cited information is information indicating the description of other technical documents cited in the document information including the cited information. In the technical literature, the description is, for example, a description for pointing out the problems of the technical literature, a description for proposing a new theory or constructing a system based on the technical literature. Etc.

. Here, the cited document identification information may be any information as long as it is information that can identify the cited document. Cited reference identification information includes, for example, the author's name, title, date of publication, and medium, which may be an ID for identifying a cited reference such as a patent number, an application publication number of a patent application, or a PMID (PubMed Identifier). It may be bibliographic information of a document that can identify a cited document such as information (journal name, publisher name, URL, etc.). In the present embodiment, it is assumed that the document information includes at least a title, cited document identification information, and cited information.

Here, the cited document identification information and the cited information will be described in more detail. In the document information, for example, the citation information may exist in the same area as the cited document identification information, and the citation information may exist in a different area from the cited document identification information. In the former case, for example, the cited document identification information is described in the background art area, and the cited document is cited by the cited document identification information itself. Such citations may be made in patent specifications. On the other hand, in the latter case, for example, the cited document identification information is collectively described in the column of the reference, and corresponds to the cited document identification information described in the column of the reference in the text of the document. This is a case in which a cited document is cited by a predetermined index. In academic literature, such citations are often made. Here, the index is, for example, 1, 2, 3 ... or 1), 2), 3) ... ゝ [1], [2], [3] ... ゝ [A], [B], [C ], Patent document 1, patent document 2, patent document 3, ..., non-patent document 1, non-patent document 2, non-patent document 3, ..., etc., which can identify the cited document identification information. Anything may be used. When a cited document is cited by the cited document identification information itself, the cited information is information including the cited document identification information. The information including the cited document identification information is, for example, information on a predetermined area including the cited document identification information. The predetermined area can be a sentence, for example. It may be a noragraph or some other group of documents. When a cited document is cited by an index corresponding to the cited document identification information, the cited information is information including the index. The information including an index is, for example, information on a predetermined area including an index. The predetermined area may be, for example, a group of documents other than a sentence or a noragraph. The predetermined area may be determined based on a predetermined rule, as will be described later.

[0176] Next, the citation format of the cited document in the citation information will be described. The citation format includes, for example, a problem-pointing citation format (hereinafter also referred to as “type C” citation format), which is a format that points out the problem of the cited document, and a format that incorporates the cited document as the basis of the editorial. There are certain citation forms (hereinafter referred to as “Type B” citation forms) and other citation forms (hereinafter also referred to as “Type 0” citation forms). The type B citation format is a citation format used when a new theory is proposed or a system is constructed using existing research results. In addition, it may be classified by other citation formats. Here, the citation form of the above description is described in the following document.

[0177] Literature: Eizo Namba, Manabu Okumura, “Development of Survey Paper Creation Support System Considering Reference Information Between Papers”, Natural Language Processing, Vol. 6, No. 5, p. 43-62, 1999

Note that the document information storage unit 1012 can be realized by a predetermined recording medium (for example, a semiconductor memory, a magnetic disk, an optical disk, or the like). The document information storage unit 1012 may store any document information. For example, document information transmitted via a communication line or the like may be stored in the document information storage unit 1012 even if document information or the like is stored in the document information storage unit 1012 via a recording medium. Alternatively, document information input via an input device may be stored in the document information storage unit 1012.

The search unit 1013 searches the document information storage unit 1012 using the search term received by the search term receiving unit 1011. It is preferable that the search unit 1013 searches for document information corresponding to the technical document whose search term received by the search term receiving unit 1011 is the main topic. “Document information corresponding to a technical document” means document information indicating at least a part of the technical document. The main topic is the name of a research field. Wide range Narrowness can vary depending on the area of interest. For example, “morphological analysis” can be a main topic, but “natural language processing” including it can also be a main topic.

[0180] For such a search, the search unit 1013 may search a part of each piece of document information stored in the document information storage unit 1012 (for example, only the title etc.). ) Or information other than literature information may be searched. When searching for a part of the document information, the document information has a structure capable of specifying a part of the document information. For example, the item name may be described for each part of the document information, or the item may be specified using a markup language tag or the like. “Information other than bibliographic information” may be, for example, time information or other bibliographic information.

[0181] In addition, in order to search for document information corresponding to the technical document whose search term is the main topic, the search unit 1013 searches, for example, document information in which the search term is described more than a predetermined number of times. Alternatively, literature information in which the search term is described in a plurality of predetermined areas (for example, a title and a summary) may be searched. As described above, a method for searching for document information corresponding to a technical document having a certain search term as a main topic is already known in the following documents, and the detailed description thereof is omitted.

[0182] Literature: Ricardo Baeza—Yates, Berthier Ribeiro—Neto, “Modem Information Retrieval, Addison—Wesley Pub, ISBN: 020139829X, 1999

[0183] Literature: Takenobu Tokunaga, “Information Retrieval and Language Processing”, University of Tokyo Press, ISBN: 413065405 5, 1999

[0184] Article: Nitin Indurkhya, Tong Zhang, Fred J. Damerau, “Text Mining: Predictive Methods For Analyzing Unstructured Information j, Springer, ISBN: 0387954333, 2004

[0185] Also, when the document information is information including at least the title of the technical document, the search unit 1013 finds the main topic in the title of the technical document indicated by the document information stored in the document information storage unit 1012. The document information including the search term received by the search term receiving unit 1011 may be searched for in the indicated area. By doing so, it is considered that the literature information corresponding to the technical literature whose search term is the main topic can be searched. In the title The area indicating the main topic may be, for example, the last area of the title in a Japanese title, or the first area of the title in an English title.

[0186] Note that the search processing itself performed by the search unit 1013 is already known, and thus detailed description thereof is omitted. As a result of the search by the search unit 1013, one or more document information is generally specified as the search result. The identification may be performed, for example, by accumulating information for identifying the document information in a recording medium such as a temporary storage memory, or by setting a flag in association with the document information. .

[0187] The identifying unit 1014 identifies document information that has the same field as the document information retrieved by the retrieval unit 1013. By specifying by the specifying unit 1014, the reference information that the search unit 1013 has not searched for is used. However, the document information that has the same field as the reference information searched by the search unit 1013 is also created. Can be used. Here, as the identification method, there are, for example, (1) a method using citation relations, and (2) a method using document classification and document clustering.

[0188] (1) Method using citation relationship

In the method using the citation relationship, the document information corresponding to the technical document cited in the document information searched by the search unit 1013 is assumed to have the same field as the document information searched by the search unit 1013. It is a method of specifying. In specifying the document information, there are, for example, (11) a method using only cited document identification information and (12) a method using cited document identification information and a format for bow I.

[0189] (1-1) Method using only cited document identification information

The identifying unit 1014 acquires the document identification information for bow I, which is information for identifying other technical documents cited in the document information, from the document information searched by the search unit 1013. Then, the document information is specified by the acquired cited document identification information.

[0190] In acquiring the cited document identification information, the specifying unit 1014 acquires the columns of the patent document and the non-patent document that may acquire the column of the reference that is considered to include the cited document identification information. Alternatively, the area where the cited document identification information exists may be acquired by using a technique such as pattern matching. Obtain references and patent documents In this case, for example, information indicating an item corresponding to the part to be acquired is stored in a recording medium (not illustrated), and the specifying unit 1014 reads information indicating the recording medium force item and corresponds to the item. An area of literature information may be acquired. In addition, when acquiring cited document identification information using a technique such as pattern matching, for example, information indicating a pattern used in pattern matching or the like is stored in a recording medium without being illustrated, The specifying unit 1014 may acquire an area including the cited document identification information in the document information by reading a pattern or the like from the recording medium and performing pattern matching or the like. The cited document identification information acquired by the specifying unit 1014 may be temporarily stored in a recording medium (not shown).

[0191] (1-2) Method of using cited document identification information and citation format

The identifying unit 1014 acquires the cited document identification information from the document information searched by the search unit 1013, and also acquires citation information that is information indicating a description of another technical document cited in the document information. To do. Then, if the citation format indicated by the obtained citation information is the problem indication type I format (type C bow I format), which is a format that points out the problem of the technical document to be cited, The document information is specified by the document identification information for Bow I that identifies the technical document described in the information.

[0192] For example, when technical document B is cited in a certain technical document A, and technical document B is cited in a format that points out the problem of technical document B (format for type C I) Inventor's research has shown that technical literature A and technical literature B are likely to be in the same field (the above-mentioned literature, “Survey Paper Creation Support System Considering Reference Information Between Papers”). Development ").

[0193] Accordingly, if the citation format of the technical document indicated by the citation information is a citation format of type C, the literature information is specified by the cited document identification information that identifies the technical document, and if not, It is not necessary to specify information.

[0194] The identification unit 1014 holds, for example, one or more clue words / phrases corresponding to the type C citation format in a recording medium (not shown), and the hand moves to the predetermined position of the citation information. Whether the citation form is type C may be determined by whether the phrase is included. The predetermined position is, for example, the end of the citation information which may be the beginning of the citation information. Sentences that are all citation information or sentences that are cited in the citation information (for example, sentences that include cited document identification information or sentences that include an index corresponding to the cited document identification information) May be within a predetermined range. The predetermined position may be set for each clue word. As long as the citation information ability can determine the citation format, other methods may be used.

[0195] In the acquisition of citation information, for example, the specifying unit 1014 specifies an area referring to the cited document identification information using the cited document identification information, and acquires the citation information including the specified area. Alternatively, the index corresponding to the cited document identification information is referred to, and the area to be identified is identified using the index corresponding to the document identification information for Bow I, and the identified area is included. Citation information may be acquired. The citation information acquired by the specifying unit 1014 may be temporarily stored in a recording medium (not shown).

[0196] The identifying unit 1014 obtains the citation information, and when it is determined that the citation format in the citation information is type, the citation information is used to identify the technical document described in the citation information. Document information will be specified. For example, in the cited information, when the cited document is referred to by the cited document identification information, the document information may be specified by the cited document identification information. On the other hand, in the cited information, when the cited document is referred to by the index, the document identification information for the bow I corresponding to the index is identified, and the document is identified by the identified document identification information for the bow I. Identify the information.

[0197] In obtaining the cited document identification information and the cited information in the above (11) and (12), the specifying unit 1014 may obtain the cited document identification information from the document information storage unit 1012. Or, when the document information acquisition unit 1015 described later acquires document information including cited document identification information, etc., even if the reference information is acquired from the document information acquired by the document information acquisition unit 1015 Good. In the present embodiment, the former case will be described.

[0198] (2) Method using document classification and document clustering

Methods for classifying and clustering a plurality of document information have been conventionally known. For example, the above-mentioned documents “Modern Information Retrieval”, “Information Retrieval and Language Processing”, “Text Mining: Predictive Methods For Analyzing Unstructured” Information "etc. In this method, literature information that is classified into the same group or clustered is assumed to be literature information in the same field, and the literature information is specified. More specifically, the document information classified into the same group as the document information searched by the search unit 1013 or clustered is specified, and the specifying unit 1014 has the same field as the document information searched by the search unit 1013. Identify bibliographic information. In this case, the document information may be specified by, for example, a document ID for identifying the document information or bibliographic information of the document information (title, publication year, first author name, name of the medium on which the document is published, etc.). .

[0199] The document information acquisition unit 1015 acquires all or a part of at least a part of the document information among the plurality of document information stored in the document information acquisition unit 1015. The document information acquisition unit 1015 acquires all or part of the document information searched by the search unit 1013. When the document information acquisition unit 1015 acquires a part of the document information, a part of the document information may be, for example, a title or a summary of the document information. For example, information indicating an item corresponding to the part to be acquired is stored in a recording medium (not shown), and the document information acquiring unit 1015 reads information indicating the item of the recording medium power and a document corresponding to the item. The area of information may be acquired as part of the literature information. When the document information acquisition unit 1015 acquires part of the document information and the search unit 1013 searches for part of the document information, a part of the document information to be acquired and a part of the document information used in the search May be the same part of the document information or different parts of the document information.

[0200] The document information acquisition unit 1015 also acquires all or part of the document information specified by the specification unit 1014 from the document information storage unit 1012. For example, when the document information is specified by the cited document identification information, the document information acquisition unit 1015 searches the document information storage unit 1012 using the cited document identification information, and all of the retrieved document information. Or get some. Here, the document information area acquired by the document information acquiring unit 1015 using the specified result by the specifying unit 1014 is the same as the document information area acquired by the document information acquiring unit 1015 using the search result by the searching unit 1013. Suppose there is. For example, when the document information acquisition unit 1015 acquires the title of the document information using the search result, the document information acquisition unit 1015 acquires the title of the specified document information. The document information acquisition unit 1015 may temporarily store all or a part of the document information acquired according to the search result or the specific result on the recording medium! .

[0201] The technical term extraction unit 1016 extracts all or part of the technical information of the literature information acquired by the literature information acquisition unit 1015. The document information acquired by the document information acquisition unit 1015 is the document information acquired by the document information acquisition unit 1015 partially or entirely. Here, the technical term is a term used in the technical literature field searched by the search unit 1013. This technical term is preferably a technical term that is an element in the technical literature field searched by the search unit 1013. By looking at the transition of this technical term, it is possible to know the technical trend. The technical terms extracted by the technical term extraction unit 1016 are actually information indicating technical terms, but are simply referred to as technical terms. A method by which the technical term extraction unit 10 16 extracts technical terms will be described later. The technical term extraction unit 1016 may temporarily store the extracted technical terms on a recording medium without illustration.

[0202] The timing information acquisition unit 1017 acquires the timing information corresponding to the literature information including the technical terms extracted by the technical term extraction unit 1016 from the literature information acquisition unit 1015. For example, when the time information acquisition unit 1017 acquires time information corresponding to the document information acquired by the document information acquisition unit 1015, the time information acquisition unit 1017 can acquire the above-described time information. In this case, if the technical power of a document is not extracted, it is not necessary to acquire the time information corresponding to the document information, or the time information corresponding to the document information is described later. Do not use it to create technical trend information.

[0203] The technical trend information creation unit 1018 creates technical trend information using the technical terms extracted by the technical term extraction unit 1016 and the time information acquired by the timing information acquisition unit 1017. Here, the technology trend information is information that associates a technical term with a period related to technical literature including the technical term. In other words, it is possible to know when a certain technical term was used by the technology trend information. In the technical trend information, the time associated with the technical term may be the time information itself (for example, the numerical value itself such as year or month) or different from the time information (for example, corresponding to the year, month, etc.). Figure etc.). In the latter case, for example, the time associated with the technical information may be indicated using a coordinate axis indicating the time. This technical trend information If the technical term extracted by is associated with the time information acquired by the time information acquisition unit 1017, the data format is not limited. For example, the file may be a text file, a spreadsheet file, an image file, or another file. This technical trend information may be, for example, an image indicating the time indicated by the time information corresponding to the document information including the technical term for each technical term. The technical trend information may include the search terms accepted by the search term acceptance unit 1011.

[0204] The output unit 1019 outputs the technology trend information created by the technology trend information creation unit 1018. Here, this output is output to a recording medium that can be displayed on a display device (for example, a CRT or a liquid crystal display) or transmitted via a communication line to a predetermined device or printed by a printer. May be accumulated. The output unit 1019 may or may not include an output device (for example, a display device or a printer). Further, the output unit 1019 may be realized by hardware, or may be realized by software such as a driver that drives these devices. For example, when the technology trend information is an image, the output unit 1019 displays and outputs the technology trend information.

Note that the language used in the technical trend information creation device 1001 is not limited. For example, it may be in Japanese, English, French, Chinese, Chinese or Korean.

Next, the operation of the technical trend information creation device 1001 according to this embodiment will be described using the flowchart of FIG.

(Step S1101) The search term receiving unit 1011 determines whether or not the search term is received. If the search term is accepted, the process proceeds to step S1102, and if not, the process of step S1101 is repeated until the search term is accepted.

(Step S1102) The search unit 1013 searches the document information storage unit 1012 with the search terms received by the search term receiving unit 1011. For example, the search unit 1013 may acquire a document ID for identifying the searched document information.

(Step S1103) The identifying unit 1014 identifies the document information that has the same field as the document information searched by the search unit 1013. Details of this process will be described later. (Step S 1104) The document information acquisition unit 1015 displays all or part of the document information searched by the search unit 1013 and all or part of the document information specified by the specifying unit 1014. Get from. Details of this process will be described later.

[0210] (Step S1105) The technical term extraction unit 1016 extracts technical terms from all or part of the document information acquired by the document information acquisition unit 1015. Details of this process will be described later.

[0211] (Step S1106) The time information acquisition unit 1017 acquires the time information corresponding to the document information including the technical term extracted by the technical term extraction unit 1016 from the document information storage unit 1012.

[0212] (Step S1107) The technical trend information creation unit 1018 creates technical trend information using the technical terms extracted by the technical term extraction unit 1016 and the timing information acquired by the timing information acquisition unit 1017. .

(Step S 1108) The output unit 1019 outputs the technical trend information created by the technical trend information creation unit 1018. Then, the process returns to step S1101. If the technology trend information can be output continuously as in the case of display output, the output may be terminated after a certain period of time, or an instruction to terminate, interrupt processing, etc. The output may be terminated with the receipt of the message as a trigger.

In the flowchart of FIG. 17, the process ends when the power is turned off or the process is terminated.

[0214] In the search process (step S1102), the literature information acquisition process (step S1104), the technical term extraction process (step S1105), the time information acquisition process (step S1106), etc. in the flowchart of FIG. If nothing is searched for or no document information is obtained, it is possible to return to step S1101 as an error.

[0215] Further, in the document information specifying process (step S1103), even if the document information is not specified, the process may return to step S1101 regardless of whether the process proceeds to step S1104. In the present embodiment, the former case will be described.

[0216] Further, the order of processing in the flowchart of Fig. 17 is arbitrary to some extent. For example, time The process of acquiring information may be performed before the process of acquiring the document information or the process of extracting the technical terms as long as it is after the process of specifying the document information.

Next, detailed processing of the document information identification processing (step S1103) in the flowchart of FIG. 17 will be described using the flowchart of FIG. As described above, there are various methods for identifying document information. Here, a method for identifying document information using cited document identification information and a cited format will be described.

(Step S 1201) The identifying unit 1014 sets the counter i to 1.

(Step S1202) The identifying unit 1014 acquires all the cited document identification information and the cited information corresponding to each cited document identification information from the i-th document information searched by the search unit 1013. As described above, the cited document identification information may or may not be included in the cited information. Also, in this step, if the i th document information searched by the search unit 1013 does not contain any cited document identification information, the process proceeds to step S 1203 without obtaining the cited document identification information. .

[0219] (Step S1203) The identifying unit 1014 sets the counter j to 1.

(Step S1204) The identifying unit 1014 determines whether or not the j-th cited document identification information acquired from the searched i-th document information exists. If it exists, go to step S 1205; if not, go to step S 1208.

[0220] (Step S1205) The identifying unit 1014 determines whether or not the citation form power S type C of the citation information corresponding to the j-th citation identification information. If it is type C, go to step S1206, and if not, go to step S1207.

(Step S1206) The identifying unit 1014 temporarily stores the j-th cited document identification information in a recording medium (not shown). The document information identified by the temporarily stored cited document identification information becomes the identified document information.

(Step S1207) The identifying unit 1014 increments the counter j by 1. Then, return to step S1204.

(Step S1208) The identifying unit 1014 increments the counter i by 1.

(Step S1209) The identifying unit 1014 determines whether or not the i-th document information searched by the search unit 1013 exists. If it exists, return to step S1202. If not, the series of processes for specifying the document information ends, and the process proceeds to step S1104.

Next, detailed processing of the document information acquisition processing (step S1104) in the flowchart of FIG. 17 will be described with reference to the flowchart of FIG.

(Step S 1301) The document information acquisition unit 1015 acquires all or part of each document information indicated by the search result by the search unit 1013. Details of this processing will be described later.

(Step S1302) The document information acquiring unit 1015 determines whether the document information is identified by the specifying unit 1014. If the document information is specified, the process proceeds to step S1303. If not, the series of processes for acquiring the document information ends, and the process proceeds to step S1105.

(Step S 1303) The document information acquisition unit 1015 acquires all or part of the document information specified by the specification unit 1014. Details of this process will be described later. When this process ends, the series of processes for obtaining the document information ends, and the process proceeds to step S1105.

Next, the process of acquiring all or part of each piece of document information indicated by the search result in the flowchart of FIG. 19 will be described using the flowchart of FIG.

(Step S1401) The literature information acquisition unit 1015 sets the counter i to 1.

(Step S1402) The document information acquisition unit 1015 acquires all or part of the document information indicated by the i-th search result.

(Step S 1403) The document information acquisition unit 1015 temporarily stores all or part of the document information acquired in step S 1402 on a recording medium, not shown. This recording medium may be included in other constituent elements that the document information acquisition unit 1015 may have.

(Step S1404) The literature information acquisition unit 1015 increments the counter i by 1.

(Step S 1405) The document information acquisition unit 1015 determines whether or not the i-th search result exists. If it exists, the process returns to step S 1402. If not, the series of processes for acquiring all or part of each document information indicated by the search result ends, and the process proceeds to step S 1302.

[0231] Next, all or part of the specified document information in the flowchart of FIG. The obtaining process will be described with reference to the flowchart of FIG.

(Step S1501) The literature information acquisition unit 1015 sets the counter i to 1.

(Step S 1502) The document information acquiring unit 1015 determines whether all or a part of the i-th document information specified by the specifying unit 1014 has not yet been acquired. If it has not been acquired, the process proceeds to step S 1503, and if it has been acquired, the process proceeds to step S 1505. This determination can be made, for example, by referring to a recording medium (not shown) in which the document information acquired by the document information acquisition unit 1015 in step S1403 is temporarily stored.

(Step S 1503) The document information acquisition unit 1015 acquires all or part of the i-th document information specified by the specifying unit 1014.

(Step S1504) The document information acquisition unit 1015 temporarily stores all or part of the document information acquired in Step S1503 on a recording medium, not shown. This recording medium may be included in other constituent elements that the document information acquisition unit 1015 may have.

(Step S1505) The literature information acquisition unit 1015 increments the counter i by 1.

(Step S 1506) The document information acquiring unit 1015 determines whether or not the i-th document information specified by the specifying unit 1014 exists. If it exists, the process returns to step S1502. If not, the series of processes for acquiring the specified document information ends, and the process proceeds to step S1105.

[0235] Next, a method of extracting technical terms from all or part of the document information acquired by the document information acquisition unit 1015 will be described.

First, the basic principle of extracting technical terms will be described. It is assumed that all or part of the document information acquired by the document information acquisition unit 1015 includes technical terms in the field of the main topic that has been searched and identified. In general, the technical terms are likely to correspond to a specific phrase. In particular, if the name of the main topic is also included in all or part of the document information acquired by the document information acquisition unit 1015, the technical term corresponds to the name of the main topic via a predetermined effort. There are many things that are attached!

[0236] For example, in the case of "name of main topic ^ sentence extraction", the document information acquisition unit 1015 Assuming that part of the literature information “sentence extraction using SVM” is acquired, the name of the main topic “sentence extraction” and the technical term “SVM ^” in that field are used via the clue phrase “using”. It can be seen that they are associated with each other. Also, for example, if the main topic name power ^ caption generation ", and the document information acquisition unit 1015 acquires a part of the document information" Short sentence for subtitle generation ", the main topic name" It can be seen that “caption generation” is associated with the technical term “sentence shortening” in the field via the clue phrase “for”. Even if all or part of the document information acquired by the document information acquisition unit 1015 does not include the name of the main topic, it is possible to specify technical terms by using hand-powered phrases. It is thought that.

[0237] Therefore, those hands specify a powerful phrase, and the literature information acquisition unit 1015 searches for all or a part of the literature information using the clue phrase, and the searched hand is a powerful word. A term corresponding to a phrase can be extracted as a technical term. Note that with such a method, it is possible that technical terms that are not appropriate may be extracted, so the inventors are also considering measures to improve accuracy. The configuration and operation of the technical term extraction unit 10 16 will be specifically described below.

[0238] [Pattern 1]

FIG. 22 is a block diagram showing the configuration of the technical term extraction unit 1016 in Pattern 1. In FIG. 22, the technical term extraction unit 1016 includes a clue phrase storage unit 1021, a clue phrase search unit 1022, and a technical term extraction unit 1023. It should be noted that all or part of the document information acquired by the document information acquisition unit 1015 is stored in the document information temporary storage unit 1020. The document information temporary storage means 1020 may be included in the technical term extraction unit 1016, which may be included in the document information acquisition unit 1015, or may be included in other constituent elements, for example.

[0239] The clue word storage means 1021 stores one or more clue words. As described above, this hand-powered phrase is a hand-held phrase that is used in the extraction of technical terms, and is determined in advance so that appropriate technical terms can be extracted. It is what. Note that this clue word is information that actually indicates a hand-held word, but is simply called a clue word. The clue word storage means 1021 is a predetermined recording medium. (For example, it can be realized by a semiconductor memory, a magnetic disk, an optical disk, etc.). There is no limitation on the process in which words are stored by hand in the word storage means 1021. For example, hand-powered words transmitted through a communication line or the like may be stored in the word-and-phrase storage means 1021. The clue phrase storage means 1021 may store the clue word or phrase input via the input device, or the clue phrase storage means 1021 may store the clue phrase.

[0240] The manual action phrase search means 1022 uses the hand stored in the manual action S phrase storage means 1021 in all or part of the literature information acquired by the literature information acquisition section 1015. Search for.

[0241] The technical term extraction unit 1023 extracts, as the technical term, a term having a predetermined relationship with the hand-powered phrase searched by the hand-powered phrase searching unit 1022. The term having a predetermined relationship with the clue word / phrase is, for example, a term before the clue word / phrase or a term after the clue word / phrase. This relationship may be determined for each attribute of the clue word, even if it is determined for each word. The attribute of the clue word / phrase may be, for example, a relationship in which the clue word / phrase relates the technical term to the main topic. For example, there are “Method”, “Goal”, and the like as attributes of the clue word. For example, “by”, “based on”, “using”, and the like exist as hand-written words having the attribute “Method”. Examples of clue words having the attribute “Goal” include “for” and “toward”. The technical term extraction means 1023 temporarily stores the extracted technical terms in a recording medium (not shown).

[0242] The technical term extraction means 1023 may extract, for example, a continuous noun phrase having a predetermined relationship with a clue word phrase as a technical term, or a candidate for a term that can be used as a technical term. May be stored in a recording medium (not shown), and a term that has a predetermined relationship with the clue word and that matches the candidate technical term may be extracted as a technical term.

[0243] Next, the operation of the technical term extraction unit 1016 in Pattern 1 will be described using the flowchart in FIG. The process of the flowchart of FIG. 23 corresponds to the technical term extraction process (step S 1105) in the flowchart of FIG. (Step S1601) The technical term extraction unit 1016 sets the counter i to 1, and sets the counter j to 1.

[0244] (Step S1602) The hand-powered phrase search unit 1022 stores the j-th stored in the clue phrase storage unit 1021 in all or part of the i-th document information acquired by the document information acquisition unit 1015. Search for words and phrases. If it is found, the process proceeds to step S1603. If not, the process proceeds to step S1606.

[0245] (Step S1603) The technical term extraction means 1023 extracts, as a technical term, a term in which the searched hand has a predetermined relationship with the force phrase. The technical term extraction means 1023 may temporarily store the extracted technical terms in a recording medium without illustration.

(Step S1604) The technical term extraction unit 1016 increments the counter i by 1, and sets the counter j to 1.

(Step S1605) The technical term extraction unit 1016 determines whether or not the i-th document information acquired by the document information acquisition unit 1015 exists. If it exists, the process returns to step S1 602. If not, the series of processes for extracting technical terms ends, and the process proceeds to step S1106.

(Step S1606) The technical term extraction unit 1016 increments the counter j by 1.

(Step S1607) The technical vocabulary extraction unit 1016 determines whether or not the hand-powered phrase storage unit 1021 includes the j-th manual phrase S phrase. If it exists, go back to step S1602, and if not, go to step S1604.

[0248] In this flowchart, the case is described in which a hand extracts a technical term using only a force word, but even if a hand extracts a technical term using a search term together with the force word. Good. By doing so, the extraction accuracy of technical terms can be improved. For example, if a technical term is extracted from a part of the literature information “sentence extraction using SVM” and the search term is “sentence extraction”, the search term “sentence extraction” and the manual search term “ The term “SVM” associated with “used” can be appropriately extracted. On the other hand, if the search term is “SVM”, the term to be extracted (the term before the clue phrase “using”) and the search term are the same, so it is considered inappropriate. Term extraction can be avoided. Note that the document information area including the search term searched by the search unit 1013 is If at least it is acquired by the document information acquisition unit 1015, it is possible to extract the technical terms using the search terms, but the document information area including the search terms searched by the search unit 1013 Extraction of technical terms using search terms when the information acquisition unit 1015 does not acquire it or when the reference information specified by the specification unit 1014 does not include the search terms. May not be possible. It should be noted that technical terms can be extracted using search terms, and the same applies to the following patterns!

In this way, technical terms can be extracted.

[0249] [Pattern 2]

FIG. 24 is a block diagram showing the configuration of the technical term extraction unit 1016 in Pattern 2. In FIG. 24, the technical term extraction unit 1016 includes clue phrase storage means 1021, clue phrase search means 1022, technical term storage means 1024, and technical term extraction means 1025. The configurations and operations other than the technical term storage unit 1024 and the technical term extraction unit 1025 are the same as those in the pattern 1, and the description thereof is omitted.

[0250] The technical term storage means 1024 stores two or more technical terms. Here, technical terms are terms that can be technical terms in one or more research fields and can be technical terms. This terminology is actually information indicating a terminology, but is simply called a terminology. This technical term may be determined by a person or may be obtained mechanically from a plurality of technical documents. In the latter case, for example, singular nouns etc. are extracted by morphological analysis of technical literature, scoring is given to indicate the possibility that each noun etc. is a technical term, and a high score is given. Single nouns may be acquired as technical terms. Here, as a method for assigning a score, a plurality of types such as scoring based on word-making ability and scoring based on appearance frequency are known. Further, other methods may be used. The method for obtaining technical terms is disclosed in the following documents and the like, and its conventional power is also known. TermExtract is also available as a tool for creating a terminology list (http: ZZ gensen. Di. Itc. U—tokyo. Ac. JpZ termextract. Htm 1). [0251] Literature: Hiroshi Nakagawa, “Automatic Term Recognition based on Statistics of Compound NounsJ, Terminology, Vol. 6, No. 2, p. 195— 2 10, 2000

[0252] Article: Hirokazu Ohata, Hiroshi Nakagawa, “Extraction of technical terms based on the number of connected words,” Information Processing Society of Japan, 2000-NL-136, p. 119-126

[0253] Literature: Hiroshi Nakagawa, Masanori Mori, Yasuaki Yumoto, “Extraction of technical terms based on appearance frequency and connection frequency”, Natural Language Processing, Vol. 10 No. l, p. 27-45, January 2003

Note that the technical term storage means 1024 can be realized by a predetermined recording medium (for example, a semiconductor memory, a magnetic disk, an optical disk, etc.). Further, the process of storing the technical terms in the technical term storage means 1024 is not limited. For example, technical terms transmitted via a communication line or the like may be stored in the technical term storage means 1024 even if the technical terms are stored in the technical term storage means 1024 via the recording medium. Alternatively, the terminology input via the input device may be stored in the terminology storage means 1024.

[0255] The technical term extraction means 1025 uses the terminology stored in the technical term storage means 1024 as a term having a predetermined relationship with the hand-strength phrase searched by the hand-strength phrase search means 1022. If included, the technical term is extracted as a technical term. In this way, technical terms other than the technical terms stored in the technical term storage means 1024 are not extracted as technical terms. The situation of extracting non-technical terms such as “method” can be avoided.

[0256] Next, the operation of the technical term extraction unit 1016 in Pattern 2 will be described using the flowchart in FIG. The process of the flowchart of FIG. 25 corresponds to the technical term extraction process (step S 1105) in the flowchart of FIG. In this flowchart, the processes other than steps S 1701 to S 1706 are the same as those in the flowchart of FIG. 23 except that the technical term extracting means 1023 is replaced with the technical term extracting means 1025, and the description thereof is omitted.

[0257] (Step S1701) The technical term extraction means 1025 extracts a term in which the searched hand has a predetermined relationship with the force phrase. (Step S1702) The technical term extraction means 1025 sets the counter k to 1.

(Step S1703) The technical term extraction means 1025 determines whether or not the term extracted in step S1701 includes the k-th technical term stored in the technical term storage means 1024. If it is included, the process proceeds to step S1704. If not, the process proceeds to step S1705.

[0259] (Step S1704) The technical term extraction means 1025 extracts the k-th technical term included in the term extracted in step S1701 as a technical term.

(Step S1705) The technical term extraction means 1025 increments the counter k by 1.

[0260] (Step S1706) The technical term extraction means 1025 determines whether or not the k-th technical term exists in the technical term storage means 1024. If it exists, the process returns to step S1703, and if not, the process proceeds to step S1604.

In this way, technical terms can be extracted.

[0261] [Pattern 3]

FIG. 26 is a block diagram showing the configuration of the technical term extraction unit 1016 in Pattern 3. The technical term extraction unit 1016 in this pattern extracts technical term candidates, and the technical term candidate power also selects technical terms. In FIG. 26, the technical term extraction unit 1016 includes clue word / phrase storage means 1021, hand / phrase word / phrase search means 1022, technical term candidate extraction means 1026, and technical term selection means 1027. The configuration and operation other than the technical term candidate extraction means 1026 and the technical term selection means 1027 are the same as those in pattern 1 and will not be described.

[0262] The technical term selection unit 1027 extracts, as technical term candidates, terms having a predetermined relationship with the hand-powered phrase searched by the hand-powered phrase searching unit 1022. This technical term candidate extraction method is the same as the technical term extraction method described in patterns 1 and 2, and a description thereof will be omitted.

[0263] The technical term selection means 1027 selects all or part of the technical term candidates extracted by the technical term candidate extraction means 1026 as technical terms. The specific selection method will be described later in patterns 4 and 5. [0264] Next, the operation of the technical term extraction unit 1016 in Pattern 3 will be described using the flowchart in FIG. The process of the flowchart of FIG. 27 corresponds to the technical term extraction process (step S1105) in the flowchart of FIG. In this flow chart, the processes other than steps S1801 and S1802 are the same as those in the flowchart of FIG.

[0265] (Step S1801) The technical term candidate extraction means 1026 extracts a term in which the searched hand has a predetermined relationship with the strong phrase as a technical term candidate. The technical term candidate extraction means 1026 may temporarily store the extracted technical term candidates on a recording medium, not shown.

(Step S 1802) Technical term selection means 1027 selects a technical term from the technical term candidates selected by technical term selection means 1027. The technical term selection means 1027 may temporarily store the selected technical term in a recording medium without illustration.

[0267] In step S1802, the technical term selection means 1027 stores, for example, technical terms that are stored in the literature information storage unit 1012, but are not used as the main topic even if they are in the misplaced literature information! Candidates may not be selected as technical terms, but technical terms that are used as main topics in any document information may be selected as technical terms. This is because a term selected as a technical term is considered to be treated as a main topic in any technical document and is considered to be highly likely.

[0268] Note that, as a specific method, for example, terms indicating the main topic are also collected and stored in the recording medium, and among the technical term candidates, the recording medium is selected. May be selected as a technical term that matches one of the main topic terms, or whether a technical term candidate is used as a main topic term. Alternatively, the determination may be made by searching a plurality of document information stored in the document information storage unit 1012. Whether or not a certain term is used as a term indicating the main topic in the literature information can be determined as described in the search processing in the search unit 1013 using the search term, for example. Specifically, if a term is described in the literature information a predetermined number of times or more, it may be determined that the term is a main topic, or a term is defined in a plurality of predetermined areas (for example, , Title and summary, etc.), the term is considered the main topic. May be. Needless to say, the determination may be made by other methods. For example, the structure of the document information may be analyzed to determine that the term existing in the area where the main topic is described is the main topic. Further, the method of selecting technical terms by the technical term selecting means 1027 is not limited to this and may be other methods. Other methods will be described later in patterns 4 and 5.

In this manner, the technical terms can be extracted by selecting the technical terms from the technical term candidates.

[0269] [Pattern 4]

FIG. 28 is a block diagram showing the configuration of the technical term extraction unit 1016 in Pattern 4. Here, an example of selecting technical terms in the technical term extraction unit 1016 for pattern 3 will be described. In FIG. 28, the technical term extraction unit 1016 includes a clue phrase storage unit 1021, a clue phrase search unit 1022, a technical term candidate extraction unit 1026, a technical term selection unit 1027, and a technical term suffix storage. Means 1028. The configuration and operation other than the technical term suffix storage means 1028 are the same as those in the pattern 3, and the description thereof is omitted.

[0270] The technical term suffix storage means 1028 stores one or more suffixes that can be taken by the technical term. Suffixes stored in the technical term suffix storage means 1028 can be technical terms such as “model”, “law”, “algorithm”, and the like. This suffix is actually information indicating a suffix, but is simply called a suffix. Technical Term The suffix storage means 1028 can be realized by a predetermined recording medium (for example, a semiconductor memory, a magnetic disk, an optical disk, etc.). The technical term suffix storage means 1028 does not matter how the suffix is stored. For example, a suffix transmitted via a communication line or the like may be stored in the technical term suffix storage means 1028 even if the suffix is stored in the technical term suffix storage means 1028 via a recording medium. Alternatively, the suffix input via the input device may be stored in the technical term suffix storage means 1028.

The technical term selection unit 1027 selects a technical term candidate having the suffix stored in the technical term suffix storage unit 1028 as a technical term.

[0271] The operation of the technical term extraction unit 1016 in this pattern is the same as the flowchart of FIG. It is like. FIG. 29 is a flowchart showing details of the technical term selection process (step S 1802) in the flowchart of FIG. 27.

(Step S1901) The technical term selecting means 1027 sets the counter i to 1 and sets the counter j to 1.

[0272] (Step S1902) The technical term selection means 1027 uses the j th suffix stored in the technical term suffix storage means 1028 as the i th technical term candidate extracted by the technical term candidate extraction means 1026. Judge whether you have. If so, the process proceeds to step S1903; otherwise, the process proceeds to step S1906.

(Step S 1903) Technical term selection means 1027 selects the i-th technical term candidate as a technical term. The technical term selection means 1027 may temporarily store the selected technical term on a recording medium (not shown)!

(Step S1904) The technical term selection means 1027 increments the counter i by 1 and sets the force counter j to 1.

[0274] (Step S1905) The technical term selecting means 1027 judges whether or not the i th technical term candidate exists. If it exists, the process returns to step S1902, and if it does not exist, the series of processes for selecting the technical term ends, and the process proceeds to step S1106.

(Step S1906) The technical term selection means 1027 increments the counter j by 1.

(Step S 1907) The technical term selection unit 1027 determines whether or not the j th suffix exists in the technical term suffix storage unit 1028. If it exists, go back to step S 1902, and if not, go to step S 1904.

[0276] [Pattern 5]

FIG. 30 is a block diagram showing the configuration of the technical term extraction unit 1016 in Pattern 5. Here, an example of selecting technical terms in the technical term extraction unit 1016 for pattern 3 will be described. In FIG. 30, the technical term extraction unit 1016 includes a clue phrase storage unit 1021, a clue phrase search unit 1022, a technical term candidate extraction unit 1026, a technical term selection unit 1027, and a technical term suffix storage. Means 1028 and literature information identification means 1029 Yeah. Except as described below, the configuration and operation other than the document information specifying unit 1029 are the same as those in the pattern 4, and the description thereof is omitted.

[0277] In Pattern 5, the document information acquisition unit 1015 also acquires all or part of the document information specified by the document information specifying means 1029. Further, the technical term selection means 1027 stores at least one of the technical term candidates extracted from all or part of the group of literature information acquired by the literature information acquisition unit 1015 in the technical term suffix storage means 1028. If a technical term candidate is selected, a predetermined technical term candidate is selected as a technical term from technical term candidates extracted from all or part of the group of document information. Here, “a group of document information” refers to one document information searched by the search unit 1013 or specified by the specifying unit 1014 (this is referred to as “document information N”), This is a set of document information including one document information and one or more document information specified by the document information specifying means 1029 that the field is the same. The “predetermined technical term candidate” selected by the technical term selection means 1027 as the technical term is a technical term candidate in which all or part of the literature information N is extracted.

[0278] The document information specifying method by the document information specifying means 1029 is the same as the document information specifying method by the specifying unit 1014. The document information specifying unit 1029 may specify, for example, document information N and document information having a citation relationship. Here, the citation relationship may be a relationship in which the document information N cites other document information or a relationship in which the document information N is cited in other document information. A relationship including Further, the document information that is a problem-pointing citation format in which the format for bow I in the citation relationship is a format for quoting and pointing out a problem of the technical document may be specified. Regarding the specific operation of this document information specifying means 1029, the force similar to the operation of the specifying unit 1014 or the operating force of the specifying unit 1 014 can be easily considered, and detailed description thereof will be omitted.

[0279] The operation of the technical term extraction unit 1016 in this pattern is the same as the flowchart of FIG. FIG. 31 is a flowchart showing details of the technical term selection process (step S 1802) in the flowchart of FIG. In this flowchart, the processes other than step S11001 are the same as those in the flowchart of FIG. 29, and the description thereof is omitted. (Step SI 1001) Technical term selection means 1027 selects technical term candidates using the literature information identified by literature information identification means 1029. Details of this processing will be described later.

Next, detailed processing of the technical term candidate selection processing (step S11001) in the flowchart of FIG. 31 will be described using the flowchart of FIG.

[0282] (Step S11101) The document information specifying means 1029 specifies document information having the same field as the document information including the i-th technical term candidate. For example, when specifying document information that is cited in the document information including the i-th technical term candidate and that has the citation form power S type C, the flowchart of FIG. It can be done by the process shown in. Note that the document information specifying unit 1029, for example, if the document information temporary storage unit 1020 includes a document ID or the like for identifying the document information, the document information including the technical term candidate of the cell using the document ID or the like. Can be specified.

(Step S11102) The document information acquiring unit 1015 acquires all or part of each document information specified by the document information specifying unit 1029. This acquisition process can be performed in the same manner as the process of step S1104, for example. When all or a part of the document information specified by the document information specifying unit 1029 has already been acquired, the document information acquisition unit 1015 acquires all or a part of the document information. The document information may be acquired from a recording medium in which all or part of the document information is stored, or may be acquired from the document information storage unit 1012.

(Step S11103) Technical term candidate extraction means 1026 extracts technical term candidates from all or part of the literature information acquired in step S11102. This extraction process can be performed, for example, in the same manner as the process before step S1802 in the flowchart of FIG.

(Step S11104) Technical term selecting means 1027 sets counter m to 1 and sets counter n to 1.

[0285] (Step S11105) The technical term selection means 1027 stores the mth technical term candidate extracted by the technical term candidate extraction means 1026 in step S11103 in the technical term suffix storage means 1 028. Determine if it has a suffix. And if you have If this is not the case, go to step SI 1110. If not, go to step SI1110.

(Step S11106) Technical term selecting means 1027 increments counter m by 1.

(Step S11107) The technical term selection unit 1027 determines whether or not the m-th suffix exists in the technical term suffix storage unit 1028. If it exists, go back to step S11105, and if not, go to step S11108.

(Step S11108) Technical term selecting means 1027 increments counter η by 1, and sets counter m to 1.

(Step S11109) The technical term selecting means 1027 judges whether or not the nth technical term candidate exists. If it exists, the process returns to step S11105. If it does not exist, the series of processes for selecting a technical term using the specified document information ends, and the process proceeds to step S1904.

(Step SI 1110) Technical term selecting means 1027 selects the i-th technical term candidate as a technical term. The technical term selection means 1027 may temporarily store the selected technical term on a recording medium (not shown).

In the flowcharts of FIGS. 31 and 32, first, technical term candidates related to the document information N are selected, and then technical terms related to the document information identified as having the same field as the document information N. The case where candidate selection is performed has been described, but this is only an example. As a result, selection of technical term candidates related to document information N and technical terms related to document information identified as having the same field as document information N Any method can be used if it can be selected.

[0290] In the above patterns 1 to 5, the technical term extraction unit 1016 explained the variation in which the technical term is extracted, but it goes without saying that the technical term may be extracted using a method other than the above explanation. Yes. The extracted technical term is a term used in the technical literature field searched by the search unit 1013, and is preferably a technical term that is an element in the technical literature field. Street. Above putter As a method of extracting technical terms other than 1 to 5, for example, the technical information may be extracted by analyzing all or part of the literature information acquired by the literature information acquisition unit 1015. Briefly explain how to extract technical terms by analyzing all or part of the literature information.

It is assumed that the technical term extraction unit 1016 holds information associating the structure tag shown in FIG. 33 with the clue phrase. Then, it is assumed that “sentence extraction using SVM” is acquired by the document information acquisition unit 1015 as part of the document information. Then, the technical term extraction unit 10 16 searches the clue phrase shown in FIG. 33 in a part of the obtained document information “sentence extraction using SVM”, and the hand has a structure corresponding to the crawling phrase. Replace with a tag. In other words, “SVM Extraction using Skill Method clue phrase =” is obtained. Next, the technical term extraction unit 1016 sandwiches the character string immediately before the structure tag (in the case of English, the character string immediately after) between the structure tags. In other words, the result of the analysis is “SVM K ZMethod> Sentence Extraction” using “Method Method S phrasing =”. The technical term extraction unit 1016 can extract the term “SVM” corresponding to the “Method” tag from this analysis result as a technical term. In the case of the “Method” tag, the term sandwiched between the tags may be extracted. In the case of the “Goal” tag, the term sandwiched between the tag and the hand of “Goal” are extracted. You will extract the term (usually the term after the “Goal” tag) that is matched by the force phrase. For example, if the document information acquisition unit 1015 acquires “Sentence shortening for subtitle generation in a news program”, as a result of the structural analysis, the subtitle “ `` Generate ZGoal> Sentence shortened '', and the technical term extraction unit 1016 uses the term `` caption generation '' and `` Goal '' clue phrase `` for '' that are interleaved between `` Goal '' tags. "Sentence shortening" is extracted as a technical term. Note that structure tags other than those described in FIG. 33 may be used. However, the “Method” tag and “Goal” tag are generally used to extract technical terms. Further, the technical term extraction unit 10 16 may extract technical terms using the search terms. For example, if the result of the analysis is “Method Method uses force phrase => SVM / ZMethod> Sentence Extraction” and the search term is “Sentence Extraction”, the technical term extraction unit 1016 This is a term corresponding to the search term “sentence extraction”, and the term “SVM” sandwiched between “Method” tags is extracted as a technical term. To do. On the other hand, if the result of the analysis is “SVM Ku ZMethod> Sentence Extraction” using “K Method clue phrase =” and the search term is “SVM”, the term corresponding to the search term “SVM” Because there is no term sandwiched between “Method” tags, technical terms will not be extracted. Thus, by extracting technical terms using search terms as well, it is possible to improve the accuracy of extracting technical terms.

[0292] Next, the operation of the technology trend information creation device 1001 according to the present embodiment will be described using a specific example. In this specific example, it is assumed that the technology trend information creation device 1001 is a stand-alone device.

In this specific example, it is assumed that the document information and the like stored in the document information storage unit 1012 is as shown in FIG. In FIG. 34, a document ID for identifying a technical document, time information, and document information are associated with each other. The document information “D001” or the like is data indicating each document information, and at least the title area can be specified in each document information.

First, it is assumed that the user inputs a search term “morpheme analysis” to the technology trend information creation apparatus 1001 by operating a keyboard, a mouse, or the like. Then, the search term “morpheme analysis” is received by the search term receiving unit 1011 (step S1101) and passed to the search unit 1013. The search unit 1013 searches for literature information in which the search term “morpheme analysis” is included in the title area (step S1102). As a result of the search, the search unit 1013 obtains a document ID “00 1, 003, 010...” Corresponding to the document information in which the search term “morphological analysis” is included in the title area, and the specifying unit 1014 And the document information acquisition unit 1015.

[0295] The identifying unit 1014 identifies document information having the same field as the document information identified by the document ID received from the search unit 1013 (step S1103). In this specific example, it is assumed that the document information cited in the type C citation format is specified in the document information identified by the document ID received by the search unit 1013. The process will be specifically described.

First, the identifying unit 1014 acquires cited document identification information and citation information from the document information identified by the first document ID “001” received from the search unit 1013 (steps S1201 and S1202). . Here, when the document information identified by the document ID “001” is an academic paper, the specifying unit 1014 reads the “reference document” column of the document information from the document information storage unit 1012. The bibliographic information (title, date of publication, author, publication medium, etc.) of the documents described in is acquired as cited reference identification information. The bibliographic information includes, for example, 1, 2, 3 ..., 1), 2), 3) ..., [1], [2], [3] ...] [A], [B], [ C] ... etc. are added, so that index is also acquired. Next, the specifying unit 1014 performs a search using the acquired index in the document information, and specifies a sentence including the index. Then, the sentence including the index and the sentence closely related to the sentence are acquired as citation information. Here, we explain how to identify sentences that are closely related to the sentence that contains the index.

[0297] The identification unit 1014 presumably holds the following two types of clue words on a recording medium (not shown).

(A) Hands for front extension

In this, On tnis, Such, But, However-

(B) Post expansion clue phrases

We, we, They, they, Our, Our, In this, Ontnis, Such, But, However---[0298] First, the specifying unit 1014 sets a sentence including an index as a candidate sentence of citation information. Then, if the first sentence of the candidate sentence contains at least one of the (A) pre-extension manpower S words, the sentence one sentence before the candidate sentence is included in the candidate sentence. The identification unit 1014 repeats the process of expanding the candidate sentence before the candidate sentence does not include (A) all of the preceding extension clue words. In addition, the specifying unit 1014 adds (B) a post-extension hand to the next sentence after the candidate sentence (a sentence adjacent to the candidate sentence and not included in the candidate sentence). If included, the next sentence after the candidate sentence is included in the candidate sentence. The identification unit 1014 repeats the process of expanding the candidate sentence later until the sentence after the candidate sentence (B) does not include all of the phrasing words. The candidate sentence at the time when the process of expanding the candidate sentence is completed becomes the citation information. The identification unit 1014 acquires the citation information. Note that the (pre-extended cue word / phrase and (B) post-extended cue word / phrase are examples, and if the sentence containing the index is closely related to the sentence, the other hand can be extracted. In this example, we focused on the sentence that contains the index, but in the technical literature that directly refers to the cited document by the cited document identification information, The sentence containing the document identification information is used instead of the sentence containing the index.

[0299] Next, the identifying unit 1014 determines whether or not the citation form power type C is obtained using the acquired citation information. Here, the specifying unit 1014 holds the information that associates the type C clue phrase shown in FIG. 35 with the position of the hand clue phrase on the recording medium, not shown. To do. The “position of clue phrase” in FIG. 35 is information indicating the number of sentences in the citation information, with the sentence including the index and the cited document identification information as a reference (0). For example, in the case of manual S scale phrase position “1-3”, in the citation information, from the sentence following the sentence that contains the index or cited document identification information (manual S scale phrase position = 1), This means three sentences up to the third sentence (index of clue phrase = 3). If the position of the hand phrase is negative, the index means the sentence before the sentence containing the cited document identification information. If a type C cue word is included in the sentence indicated by the position of the corresponding cue word, the citation form of the citation information is determined to be type C. Specifically, in the citation information, any sentence from the next sentence (first sentence) to the third sentence after the sentence containing the index or cited document identification information contains “However”. In this case, it is determined that the citation information format for the bow I is type C (step S1205).

[0300] The identifying unit 1014 temporarily stores the cited document identification information corresponding to the cited information of the citation format determined to be type C (step S1206). For example, cited document identification information corresponding to an index included in citation information whose citation format is type C is temporarily stored. The identifying unit 1014 obtains citation information and cited document identification information for all document IDs received from the search unit 1013, and temporarily stores cited document identification information whose citation format is C type ( Steps S1201 to S1209). The temporarily stored cited document identification information is passed to the document information acquisition unit 1015.

[0301] The document information acquisition unit 1015 acquires the title of the document information identified by the document ID “001, 003, 010...” Received from the search unit 1013 from the document information storage unit 1012 (Step S1301). In addition, the document information acquisition unit 1015 searches the document information storage unit 1012 using the cited document identification information also received by the specifying unit 1014, and the citation is obtained. When the title of the document information identified by the document identification information has not been acquired, the title of the document information is acquired (steps S1302, S1303, S1501 to S1506). In this way, the document information acquisition unit 1015 acquires a part of the document information (step S 1104). FIG. 36 is a diagram showing an example of a part (title) of document information acquired in this way.

Next, extraction of technical terms by the technical term extraction unit 1016 will be described. Here, the case where extraction is performed using the method of pattern 1 will be described. Further, it is assumed that the information shown in FIG. 36 is stored in the document information temporary storage means 1020. It is assumed that the clue word phrase storage means 1021 stores the clue word phrase shown in FIG. In FIG. 37, the “$” is a symbol indicating the position of a technical term to be extracted. For example, if the title is acquired by the literature information acquisition unit 1015, the hand is a vocabulary phrase “by”, and the continuous noun phrase before the word “by” is extracted as a technical term. To do.

[0303] The first title “morphological analysis using context tree” shown in FIG. 36 does not include the clue phrases “by” and “based on”. It is determined that these clue words are not included in the second title (steps S1601, S1602, S1606, S1607). Next, the clue phrase search means 1022 searches for the clue phrase “using” in the first title “morphological analysis using context tree”. In this case, since “it used” is included in the title (step S 1602), the clue phrase “used” is searched, and the clue phrase search means 1022 uses the clue phrase “ To the technical term extraction means 1023 to extract the continuous noun phrase before “using”. Then, the technical term extraction means 1023 performs morphological analysis on the title “morphological analysis using context tree”, and extracts a continuous noun phrase “context tree” before the clue word “using” as a technical term ( In step S1603), the technical term “context tree” and the corresponding document ID “001” are stored in a recording medium (not shown). In this way, technical terms are extracted (step S110 5). FIG. 38 is a diagram showing an example of information associating technical terms extracted in this way with document IDs. Note that the technical term extraction unit 1016 passes the document ID of the information shown in FIG. 38 to the time information acquisition unit 1017. The technical term extraction unit 1016 passes the information shown in FIG. 38 to the technical trend information creation unit 1018. [0304] Upon receiving the document ID, the time information acquisition unit 1017 searches the document information storage unit 1012 using the document ID as a search key, and acquires the time information corresponding to the document ID (step S 1106). ). FIG. 39 is a diagram showing an example of information associating the time information thus obtained with the document ID. The time information acquisition unit 1017 shall pass the information shown in FIG. 39 to the technology trend information creation unit 1018.

[0305] The technical trend information creation unit 1018 receives the information shown in Fig. 38 from the technical term extraction unit 1016, and receives the information shown in Fig. 39 from the timing information acquisition unit 1017, the timing information is obtained for each technical term. Group. Each technical term is written vertically, the time is written on the horizontal axis, a circle is placed at the corresponding time for each technical term, and a line connecting the rightmost circle and the leftmost circle is written. An image is created (step S 1107). The image shall also contain the search terms received via routes not shown. In order to generate an image of technology trend information, the technology trend information creation unit 1018 holds a template or the like in a recording medium (not shown) and generates an image of technology trend information using the template or the like. Good.

[0306] The output unit 1019 displays an image of the technology trend information created by the technology trend information creation unit 1018 on the display (step S1108). FIG. 40 is a diagram showing an example of the image of the technical trend information displayed on the display as described above. In this way, the user can know the technical trend (technical flow) related to morphological analysis.

[0307] Although this specific example has been described in the case where the technical trend information is an image, the technical trend information may not be an image. For example, the information shown in FIG. 41 may be the information shown in FIG. 38 combined with the information shown in FIG. 39 using the document ID. The technology trend information shown in FIG. 41 may be spreadsheet data, for example.

[0308] In this specific example, as described in Pattern 2, technical terms may be extracted using technical terms. For example, the technical term storage means 1024 stores the technical terms shown in FIG. 42, and a term having a predetermined relationship with the manual skill S phrase searched by the manual skill S phrase search means 1022 is “Japanese. It is assumed that it is “Konos” or “Proposed method”. In this case, since the “Japanese corpus” includes the “corpus” stored in the technical term storage means 1024, the technical term extraction means 1025 extracts “corpus” as the technical term. To do something. In addition, since the “proposed method” does not include the “co-path” stored in the technical term storage means 1024, the technical term extracting means 1025 uses the “proposed method” that is a non-technical term as a technical term. It will not be extracted. By doing so, the technical term extraction means 1025 extracts an appropriate “corpus” as a technical term that does not extract “Japanese corpus” as a technical term. In addition, it is possible to avoid the situation where the technical term extraction means 1025 extracts general nouns and non-technical terms.

[0309] Further, the specific information used in this specific example is shown to explain the details of the operation of the technical trend information creation device 1001 according to the present embodiment. Including corpus power Not acquired.

[0310] As described above, the technical trend information creation apparatus 1001 according to the present embodiment extracts technical terms from the literature information, and acquires time information corresponding to the literature information from which the technical terms are extracted. The technology trend information can be created using the extracted technical terms and the acquired time information. As a result, by using the created technology trend information, it is possible to easily know the transition of the technology used in a certain research field. For example, it is possible to know the range of time when a technical term is described in the technical literature (from one to! /, The power that the technical term is used from). In addition, for example, it is possible to know the frequency with which a certain technical term is described in the technical literature. In addition, there is a merit that it is not necessary to spend a great deal of labor and time for those who are familiar with the research field to create the technology trend information.

[0311] In the above embodiment, a case has been described in which the document information acquisition unit 1015 acquires all or part of the document information searched by the search unit 1013. However, this need not be the case. For example, the document information acquisition unit 1015 may acquire all or a part of at least some document information among the plurality of document information stored in the document information storage unit 1012. For example, when only the literature information of a certain research field is stored in the literature information storage unit 1012, the literature information acquisition unit 1015 may select all of the literature information stored in the literature information storage unit 1012 or randomly. A predetermined number of documents selected in the above may be acquired. As described above, when the search by the search unit 1013 is unnecessary, the technology trend information creation device 1001 does not need to include the search term reception unit 1011 and the search unit 1013. [0312] Also, in the above embodiment, the specifying unit 1014 specifies the document information having the same field as the document information searched by the searching unit 1013, and the document information acquiring unit 1015 specifies the document specified by the specifying unit 1014. Although the case where all or a part of the information is acquired has been described, this need not be the case. That is, the document information acquisition unit 1015 may not acquire the document information specified by the specifying unit 1014. In this case, the technology trend information creation device 1001 may not include the specifying unit 1014.

In addition, when the document information is specified by the specifying unit 1014 and the cited document identification information or the cited information is not used, the document information may not include the cited document identification information or the cited information.

[0313] (Embodiment 5)

A technical trend information creation device according to Embodiment 5 of the present invention will be described with reference to the drawings. In the technical trend information creation device according to the present embodiment, the search terms accepted by the search term acceptance unit are selected.

FIG. 43 is a block diagram showing a configuration of the technical trend information creation device 1002 according to the present embodiment. In FIG. 43, the technology trend information creation device 1002 according to the present embodiment includes a search term acceptance unit 1011, a document information storage unit 1012, a search unit 1013, a specification unit 1014, a document information acquisition unit 1015, a technology Term extraction unit 1016, time information acquisition unit 1017, technology trend information creation unit 1018, output unit 1019, suffix storage unit 1031, technical term extraction unit 1032, search term storage unit 1033, and search term storage A section 1034 and a search term selection receiving section 1035 are provided. The configuration and operation other than the suffix storage unit 1031, the specialized term extraction unit 1032, the search term storage unit 1033, the search term storage unit 1034, and the search term selection reception unit 1035 newly added in the present embodiment are searched. The term accepting unit 1011 is the same as in the fourth embodiment except that it accepts the search term indicated by the selection accepted by the search term selection accepting unit 1035, and the description thereof is omitted.

[0315] The suffix storage unit 1031 stores a predetermined suffix. This suffix is used when selecting a search term from the technical terms extracted by the professional term extraction unit 1032 described later, and is, for example, “system”, “method”, “data”, and the like. It goes without saying that other appropriate suffixes may be used. The suffix stored in the suffix storage unit 1031 is actually information indicating a suffix, but is simply referred to as a suffix. Also, contact The acronym storage unit 1031 can be realized by a predetermined recording medium (for example, a semiconductor memory, a magnetic disk, an optical disk, etc.). Further, the process of storing the suffix in the suffix storage unit 1031 does not matter. For example, a suffix transmitted via a communication line or the like may be stored in the suffix storage unit 1031 even if the suffix is stored in the suffix storage unit 1031 via a recording medium. Alternatively, the suffix input via the input device may be stored in the suffix storage unit 1031.

[0316] The technical term extraction unit 1032 extracts technical terms from the literature information stored in the literature information storage unit 1012. Here, the terminology is a technical term in one or more research fields. This terminology is actually information indicating a terminology, but is simply called a terminology. The technical term extraction unit 1032 extracts single nouns, for example, by performing morphological analysis on the literature information, performs scoring to indicate the possibility of being a technical term for each single noun, etc. You can get a single noun and other words as technical terms. Here, as a method for assigning a score, a plurality of types such as scoring based on word-making ability and scoring based on appearance frequency are known. Other methods may be used.

. A method for extracting technical terms is disclosed in a plurality of documents shown in the fourth embodiment and the like, and its conventional power is also known.

[0317] The search term storage unit 1033 stores a term in which the technical term extracted by the technical term extraction unit 1032 is stored in the suffix storage unit 1031 and a suffix is added in the document information storage unit 1012. The technical term is stored in the search term storage unit 1034 as a search term. By appropriately selecting the suffix stored in the suffix storage unit 1031, it becomes possible to appropriately accumulate the search terms used to determine the field for creating the technical trend. For example, when the suffix “system” is stored in the suffix storage unit 1031 and the technical term extraction unit 1032 extracts “morpheme” and “morpheme analysis”, the “morpheme system” is included in the literature information. If the “morpheme analysis system” is included in the document information, “morpheme analysis” is stored as a search term, but “morpheme” is not stored.

[0318] The search term storage unit 1034 stores two or more search terms. This search term is stored by the search term storage unit 1033. The search term storage unit 1034 Recording medium (for example, semiconductor memory, magnetic disk, optical disk, etc.).

[0319] The search term selection accepting unit 1035 accepts selection of one of the two or more search terms stored in the search term storage unit 1034. In order to accept this selected term, two or more search terms stored in the search term storage unit 1034 may or may not be output. In the former case, for example, a search term may be displayed on a display or the like, and the user may click a desired search term by operating a mouse or the like, and the search term selection receiving unit 1035 may receive the operation. . In the latter case, for example, the user has a document or the like on which two or more search terms stored in the search term storage unit 1034 and an identification symbol corresponding to each search term are displayed. The user may input an identification symbol corresponding to a desired search term by operating a keyboard or the like, and the search term selection receiving unit 1035 may receive the input. The search term receiving unit 1011 receives the search term indicated by the selection received by the search term selection receiving unit 1035 as described above.

[0320] The search term selection accepting unit 1035 accepts information input from an input device (for example, a keyboard, mouse, touch panel, etc.), for example, and is transmitted via a wired or wireless communication line. Received information may be received. Note that the search word selection receiving unit 1035 may or may not include a device (for example, a modem or a network card) for receiving. The search term selection accepting unit 1035 may be realized by hardware or software such as a driver for driving a predetermined device.

[0321] Next, the operation for creating the technology trend information in the technology trend information creation device 1002 according to the present embodiment is the same as the flowchart of FIG. 17 except for the search term acceptance process (step S1101). The description is omitted. FIG. 44 is a flowchart showing a process replacing the search term acceptance process (step S1101) in the flowchart of FIG. That is, in the technology trend information creation device 1002 according to the present embodiment, the processing of steps S 11201 to S11203 shown in FIG. 44 may be performed instead of the processing of step S1101! /.

[0322] (Step S11201) Search term selection accepting unit 1035 accepts selection of a search term Judge whether it is power. If the selection is accepted, the process proceeds to step S11202. If not, the process of step S11201 is repeated until the selection is accepted.

(Step S11202) Search term selection receiving unit 1035 reads a search term indicated by the selection received by search term selection receiving unit 1035 from two or more search terms stored in search term storage unit 1034.

[0324] (Step S11203) The search term selection receiving unit 1035 inputs the search term read from the search term storage unit 1034 in Step S11202 to the search term receiving unit 1011. As a result, the search term is accepted by the search term acceptance unit 1011. Then go to step S1102.

[0325] In the flowchart of Fig. 44, the case where the search term selection receiving unit 1035 reads the search term stored in the search term storage unit 1034 and inputs it to the search term reception unit 1011 has been described. The search term reception unit 1011 reads the search term indicated by the selection received by the search term selection reception unit 1035 from the search term storage unit 1034.

Next, processing for storing search terms in the search term storage unit 1034 will be described with reference to the flowchart of FIG.

(Step S11301) The technical term extraction unit 1032 extracts technical terms from the literature information stored in the literature information storage unit 1012. The method for extracting this technical term is as described above, and a detailed description thereof is omitted. Note that the extracted technical terms are not shown.

V, may be temporarily stored in the recording medium!

(Step S11302) Search term storage section 1033 sets counter i to 1 and counter j to 1.

(Step S11303) The search term storage unit 1033 adds a term obtained by adding the jth suffix stored in the suffix storage unit 1031 to the i-th technical term extracted by the technical term extraction unit 1032 and the literature information storage unit. A search is performed in 1012 to determine whether the term is included in the document information stored in the document information storage unit 1012. If it is included, go to step S11304. If not, go to step S11307.

[0328] (Step S11304) The search term storage unit 1033 uses the i-th technical term as a search term. And stored in the search term storage unit 1034.

(Step S11305) The search term storage unit 1033 increments the counter i by 1, and sets the force counter j to 1.

(Step S11306) The search term accumulation unit 1033 determines whether or not the i-th term is extracted by the technical term extraction unit 1032. If it exists, the process returns to step S 11303; otherwise, the series of processes for accumulating search terms ends.

(Step S11307) The search term storage unit 1033 increments the counter j by 1.

(Step S11308) The search term storage unit 1033 determines whether or not the j-th suffix is stored in the suffix storage unit 1031. If it is stored, go back to step S11303, and if not, go to step S11305.

[0331] As described above, the technical trend information creation apparatus 1002 according to the present embodiment extracts technical terms, selects search terms from the technical terms, and accumulates them to extract the technical terms and search terms. Appropriate search terms indicating the research field can be received by the search term receiving unit 1011 by appropriately selecting the items. As a result, appropriate technology trend information can be created.

[0332] In the present embodiment, the search term storage unit 1034 stores the search terms stored in the search term storage unit 1034. However, the search term storage unit 1034 stores the search terms. Terminology may be accumulated by other methods. For example, the user or the like may select an appropriate search term and the search term may be stored in the search term storage unit 1034. As such, the process in which the search term is stored in the search term storage unit 1034 is not limited. For example, a search term transmitted via a communication line or the like may be stored in the search term storage unit 1034 even if the search term is stored in the search term storage unit 1034 via a recording medium. Alternatively, the search term input via the input device may be stored in the search term storage unit 1034. In such a case, the technology trend information creation device 1002 may not include the suffix storage unit 1031, the technical term extraction unit 1032, and the search term storage unit 1033.

[0333] (Embodiment 6) A technical trend information creation device according to Embodiment 6 of the present invention will be described with reference to the drawings. The technical trend information creating apparatus according to the present embodiment displays information regarding the document information in the displayed image of the technical trend information according to the selection of the document graphic corresponding to the document information.

FIG. 46 is a block diagram showing a configuration of the technical trend information creation device 1003 according to this embodiment. In FIG. 46, the technology trend information creation device 1003 according to the present embodiment includes a search term acceptance unit 1011, a document information storage unit 1012, a search unit 1013, a specification unit 1014, a document information acquisition unit 1015, a technology A term extraction unit 1016, a time information acquisition unit 1017, a technology trend information creation unit 1018, an output unit 1019, a graphic selection reception unit 1041, and a display information acquisition unit 1042 are provided. In the configuration and operation other than the figure selection reception unit 1041 and the display information acquisition unit 1042 newly added in the present embodiment, the technology trend information creation unit 1018 displays the display information acquired by the display information acquisition unit 1042. Except for creating the technology trend information, this is the same as in the fourth embodiment, and the explanation is omitted.

[0335] In the present embodiment, for each technical term, the technical trend information is a time when the document graphic corresponding to the document information including the technical term is indicated by the timing information corresponding to the document information. It is assumed that the image is displayed accordingly. The shape of the document figure is not important. For example, as shown in the technical trend information shown in FIG. 40, the document figure may be a circle, a triangle, a rectangle, or the like, or another shape.

[0336] The figure selection receiving unit 1041 receives selection of a document figure in the technology trend information.

This selection may be accepted, for example, using a GUI (Graphical User Interface) such as bringing the pointer over a reference figure by operating the mouse or the like (on mouse). Alternatively, in the technical trend information, each document graphic is associated with identification information (for example, a number or alphabet) for identifying the document graphic, and the user can operate the keyboard by operating the keyboard. Selection may be accepted such as inputting identification information.

[0337] The graphic selection accepting unit 1041 accepts, for example, an input device (eg, a keyboard, a mouse, a touch panel, etc.) and transmits it via a wired or wireless communication line that accepts input information. Received information may be received. In addition, figure selection reception The attachment unit 1041 may or may not include a device (for example, a modem or a network card) for reception. The graphic selection receiving unit 1041 may be realized by hardware, or may be realized by software such as a driver that drives a predetermined device.

[0338] Display information acquisition section 1042 acquires display information from document information storage section 1012. Here, the display information is information related to the document information corresponding to the document graphic accepted by the graphic selection receiving unit 1041, and is information displayed on the image of the technical trend information. Information related to document information is, for example, bibliographic information of document information. More specifically, it may be the title of the document information, the author, the publication year of the document, or the like. The technical trend information creation unit 1018 creates technical trend information for displaying the display information acquired by the display information acquisition unit 1042. For example, the display information may be displayed in the vicinity of the reference graphic that the graphic selection receiving unit 1041 has received the selection, or if the display information display area is set, the display information is displayed in that area. May be.

Next, the operation of creating technical trend information in technical trend information creating apparatus 1003 according to the present embodiment is the same as the flowchart of FIG. 17, and the description thereof is omitted. FIG. 47 is a diagram showing a process executed after the process of the technical trend information output process (step S 1108) in the flowchart of FIG. That is, in the technology trend information creation device 1003 according to the present embodiment, the processing in steps S11401 to S11406 shown in FIG. 47 may be performed after the processing in step S1108.

[0340] (Step S11401) The figure selection receiving unit 1041 determines whether or not the selection of a document figure has been received. If the selection of the document figure is accepted, the process proceeds to step S11402, and if not, the process proceeds to step S11405.

[0341] (Step S11402) The display information acquisition unit 1042 acquires display information, which is information related to the reference graphic accepted by the graphic selection receiving unit 1041, from the reference information storage unit 1012.

(Step S11403) The technology trend information creation unit 1018 creates technology trend information including the display information acquired by the display information acquisition unit 1042.

(Step S11404) The output unit 1019 is a display created by the technology trend information creation unit 1018. Outputs technical trend information including information. Then, the process returns to step S11401.

(Step S11405) The output unit 1019 determines whether or not to end the output of the technology trend information. For example, when the technical trend information is output and a predetermined time elapses, an instruction to end the output of the technical trend information is received, or an instruction to output other information is received The output unit 1019 may determine to end the output of the technology trend information. If the output of the technology trend information is to end, the process proceeds to step S11406. If not, the process returns to step S11401.

(Step S11406) The output unit 1019 ends the output of the technology trend information. Then, the process returns to step S1101.

[0345] Next, the operation of displaying the display information of the technology trend information creation device 1003 according to this embodiment will be specifically described. Here, as shown in FIG. 40, it is assumed that an image of the technology trend information is displayed on the display. Suppose that the mouse pointer is placed on the leftmost circle in the display (circle) corresponding to the minimum cost method. Then, the figure selection receiving unit 1041 determines that the selection of the document figure has been received (step S11401). Then, the graphic selection receiving unit 1041 accesses the technical trend information creating unit 1018 to acquire the document ID “003” for identifying the document information corresponding to the document pattern at the position of the mouse pointer, and obtains the display information acquiring unit. Pass to 1042.

The display information acquisition unit 1042 acquires the title of the document information identified by the document ID “003” received from the figure selection reception unit 1041 as display information from the document information storage unit 1012 (step S11402). The display information is passed to the technical trend information creation unit 1018. The technology trend information creation unit 1018 creates the technology trend information so that the display information received from the display information acquisition unit 1042 is displayed in association with the position of the mouse pointer at that time (step S 11403). Note that the technology trend information creation unit 1018 may receive the position of the mouse pointer from the figure selection reception unit 1041 or other component force.

[0347] The output unit 1019 outputs the technology trend information including the display information created as described above. As a result, the technology trend information shown in FIG. 48 is displayed on the display (step S 11404). [0348] When the user performs an operation to close the image of the technology trend information, the output unit 1019 determines that the output of the technology trend information is finished (step S11405), and the The output is ended (step S11406).

[0349] In this specific example, the case where the title of the document information is displayed as the display information has been described. However, as described above, other display information may be displayed. For example, the display information may include the author's name and the announcement time. The announcement time may be time information.

[0350] As described above, in the technical trend information creation device 1003 according to the present embodiment, when a document graphic in the image of the technical trend information is selected, display information that is information related to the document information corresponding to the document graphic Is acquired, and an image of technical trend information including the display information is created and output. Therefore, for example, it becomes possible for a user to easily know predetermined information about document information including technical terms displayed in the technical trend information image by looking at the technical trend information image. User convenience has been improved.

[0351] Here, an improvement in a method for extracting technical terms and experimental results will be described. In the fourth embodiment, various methods for extracting technical terms have been described. Here, methods (Method 1 and Method 2) that improve the extraction accuracy by incorporating machine learning will be described.

[0352] First, the technical term extraction unit 1016 applies the “Method” tag and the “Goal” tag to at least a part of the document information acquired by the document information acquisition unit 1015 in the same manner as described above. Is granted. In addition, “Re _S trict” tags that correspond to clue words related to limitations such as “in” and “related”, and “and”, “or”, and other connections related to the corresponding words “ Add “Conj” tag and so on. Note that tags other than the “Method” tag, “Goal” tag, and “Head” tag described later are referred to as “Other” tags. Here, the case where the document information acquisition unit 1015 acquires the title of the technical document as part of the document information will be described. In addition, this time, a “Head” tag indicating the subject of the document information is also added. The “Head” tag is attached to a noun phrase to which no “Method” tag or “Goal” tag is attached. In many cases, a “Head” tag is added to the noun phrase at the end of the acquired title. It becomes.

[0353] Here, a method for extracting technical terms using a title such as a "Head" tag will be briefly described. The technical term extraction unit 1016 extracts a term having a “Method” tag as a technical term from a title to which the “Head” tag is added to the search term received by the search term receiving unit 1011. In addition, the technical term extraction unit 1016 extracts a term that is given a “Heal” tag from a title that is assigned a “Goal” tag to the search term accepted by the search term acceptance unit 1011 as a technical term. By doing so, it is possible to extract technical terms indicating elemental technologies for the search terms.

[0354] However, it may be inappropriate to add a "Head" tag to the noun phrase at the end of the title acquired by the literature information acquisition unit 1015. For example, if the title power is a comparison experiment between SVM and the least cost method for Chinese morphological analysis, then the last comparison title is not the subject but SVM or the least cost method. It is thought that. Therefore, we will explain the methods (Method 1 and Method 2) that can add the “Head” tag appropriately even in such a case.

[0355] First, Method 1 will be described. In Method 1, terms that are inappropriate as the subject (for example, “research” “examination” “development” “impact” “analysis” “consideration” “evaluation” “consideration” “experimental research” “examination” “application” A list of “effects”, “suggestions”, etc.) (herein called “unnecessary word list”) is prepared. A method of creating this unnecessary word list will be described later. First, the technical term extraction unit 1016 adds a “Head” tag, a “Method” tag, and the like to the title acquired by the document information acquisition unit 1015. Then, it is determined whether the term with the “Head” tag is included in the unnecessary word list. If the term to which the “Head” tag is attached is not included in the unnecessary word list, the process of assigning the “Head” tag ends. On the other hand, if a term with the “Head” tag is included in the unnecessary word list, the ¾ ^ (1) tag is removed from the term, and a noun phrase existing before the term is deleted. If the “Method” tag is added with the “Goal” tag, the “Head” tag is added to the noun phrase, and the term with the “Head” tag is added to the unnecessary word list. In this way, an appropriate “Head” tag will be assigned.In this example, the processing for Japanese is explained, but it is not possible to Is grammatically word order In the case of a different language, when a term to which the “Head” tag is added is included in the unnecessary word list, a “Head” tag is newly added to a noun phrase existing after the term.

[0356] Next, method 2 will be described. In Method 2, data (teacher data) with appropriate “Head” tags is prepared and machine learning is performed. In this case, machine learning is similarly performed for “Method” tags and “Goal” tags other than the “Head” tag. In addition, by including information on whether or not each word is included in the unnecessary word list in the teacher data, the “Head” tag is not added to the term included in the unnecessary word list. Conceivable. For example, SVM (support vector machine) may be used as a machine learning tool. By performing such machine learning, it is considered that inappropriate “Head” tags are not assigned.

Next, a method for creating an unnecessary word list used in Method 1 above will be described.

When the “Head” tag is added formally, the “Head” tag is added to inappropriate terms such as “Experiment” and “Consideration”, and the appropriate “Morphological analysis” is added. The term “Hea d” tag is also attached to the term. However, only the papers in the natural language processing field are given the “Head” tag for terms such as “morphological analysis”, but the “Head” tag is given to terms such as “experiment” and “one consideration”. It is believed that it will cover a wide range of technical fields. Therefore, after formally assigning the “Head” tag and sorting the terms with the “Head” tag in order of frequency, unnecessary words such as “experiment” and “one consideration” are ranked higher. Become. An unnecessary word list can be created by manually excluding technical terms from unnecessary words ranked higher.

Finally, the experimental results when the “Head” tag and the like are formally added, when Method 1 is used, and when Method 2 is used will be described. In this experiment, we used data from NTCIR Workshop 1 and 2 cross-language search task. This data is an abstract database from 1988 to 1997, and contains about 450,000 papers presented by 65 academic societies in Japan. We conducted experiments by manually assigning “Head” tags to 1000 Japanese paper titles that were randomly selected and using them as teacher data.

FIG. 49 shows the results when tags are formally added, FIG. 50 shows the results when Method 1 is used, and FIG. 51 shows the results when Method 2 is used. In addition, in those results Precision is a value indicating accuracy (accuracy rate) and serves as an index of accuracy. It is calculated by the following formula.

Precision = number of morphemes whose system output matches the correct tag / number of morphemes with system tag

[0360] Recall is a value indicating the recall, and serves as an index of completeness. It can be calculated by the following formula.

Recall = number of morphemes whose system output matches correct tag Z number of morphemes with human subject power ^s tag

[0361] The F value is a harmonic average of Precision and Recall, and is obtained by the following equation.

F value = 2 Recall water Precision / (Recall + Precision;

[0362] As can be seen from the experimental results in Figs. 49 to 51, when a formal tag is added, for example, the extraction accuracy of the "Head" tag is very low, about 44%. . On the other hand, the results of Methods 1 and 2 (Figs. 50 and 51) show that the extraction accuracy and recall of the “Head” tag have improved by 30% or more. From this, the effectiveness of Method 1 and Method 2 was confirmed. Therefore, it is possible to extract technical terms with higher accuracy by applying tags to at least a part of the document information acquired by the document information acquisition unit 1015 using these methods 1 and 2. It's a bit tricky to do with power.

[0363] Here, the improvement related to the display of the technology trend information will be described. In the fourth embodiment, etc., the technology trend information has been described. However, when a large number of technical terms are included in the technology trend information, the technology trend information may be difficult for the user. Therefore, this section explains how to create technical trend information by collecting technical terms for each classification.

[0364] FIG. 52 is a block diagram showing a configuration of a technology trend information creation device 1004 that creates technology trend information in which technical terms are grouped for each classification. In FIG. 52, the technology trend information creation device 1004 further includes a classification result information storage unit 1051, except that the technology trend information is created using the classification result information stored in the classification result information storage unit 10 51, This is the same as the technology trend information creation device 1001 of the fourth embodiment.

[0365] In the classification result information storage unit 1051, the classification result information is stored. Where classification result Information is information indicating the result of classification of technical terms. This technical term is a technical term that the technical term extraction unit 1016 may extract. For example, as shown in Fig. 53, in the classification result information, technical terms are grouped by classification. In FIG. 53, a classification name such as “algorithm” is given to the classification, but the classification name is given! The classification result information may be created manually or automatically.

[0366] The classification result information storage unit 1051 can be realized by a predetermined recording medium (for example, a semiconductor memory, a magnetic disk, an optical disk, or the like). The process of storing the classification result information in the classification result information storage unit 1051 is not limited. For example, classification result information transmitted via a communication line or the like may be stored in the classification result information storage unit 1051 even if the classification result information is stored in the classification result information storage unit 1051 via the recording medium. Alternatively, the classification result information input via the input device may be stored in the classification result information storage unit 1 051! /.

[0367] The technical trend information creation unit 1018 creates technical trend information in which technical terms are classified using the classification result information stored in the classification result information storage unit 1051. The technical trend information is the same as in the fourth embodiment, etc., except that technical terms are classified. Specifically, the technology trend information creation unit 1018 refers to the classification result information, and classifies the technical terms extracted by the technical term extraction unit 1016 for each classification. For example, when the technical terms “minimum cost”, “neural net”, “HMM”, “tagged corpus”, and “untagged cornos” are extracted, the technical trend information creation unit 1018 displays the classification results shown in FIG. By referring to the information, these technical terms are divided into the classification “algorithm” and the classification “data”. As such, for each group of technical terms that have been classified, the technical trend information creation unit 1018 creates technical trend information in the same manner as described above. FIG. 54 is a diagram showing an example of the technology trend information created as described above. In FIG. 54, since the technical terms are classified for each category, the user can easily grasp the technical trend for each category. This is particularly effective when a large number of technical terms are extracted. After creating technical trend information in the same way as in Embodiment 4, etc., classify technical terms using classification result information. [0368] In each of the above embodiments, each process or each function may be realized by centralized processing by a single device or a single system, or a plurality of devices. Alternatively, it may be realized by distributed processing by a plurality of systems.

[0369] Also, in each of the above embodiments, the related term acquisition device and the technical trend information creation device may be a stand-alone device or may be a server device constituting a server 'client system. . In the latter case, the related term acquisition device may receive the term information transmitted from the client, or transmit the related term information to the client.

[0370] Also, in each of the above embodiments, each component may be configured by dedicated hardware, or a component that can be realized by software may be realized by executing a program. Good. For example, each component can be realized by a program execution unit such as a CPU reading and executing a software program recorded on a recording medium such as a hard disk or a semiconductor memory.

[0371] The software that realizes the related term acquisition apparatus according to Embodiments 1 to 3 described above is the following program. That is, this program has a term information receiving step for receiving term information, which is information indicating terms, in a computer, and a term indicated by the term information received in the term information receiving step in all or part of the document information. The document information is searched from two or more document information stored in the document information storage unit in which two or more document information that is information indicating the document is stored, and all or all of the searched document information is searched. A document which is a part of the document information and which has at least a document identification information for bow I which is information for identifying other documents cited in the retrieved document information from the document information storage unit Information indicating a document identified by the document identification information for bow I included in all or part of the document information acquired in the information acquisition step and the document information acquisition step. The document information for the bow I is stored in the document information storage unit and is searched for two or more document information, and corresponds to a predetermined item that is a part of the retrieved cited document information. Related to the term indicated by the term information accepted by the term information accepting step from a part of the cited reference information obtained in the cited reference information obtaining step and the cited reference information obtaining step obtained from the reference information storage unit. You A related term information acquisition step for acquiring related term information, which is information indicating related terms, and a related term information output step for outputting related term information acquired in the related term information acquisition step. is there.

[0372] The software that realizes the technical trend information creation device in the above embodiment is the following program. In other words, this program stores, in a computer, a plurality of document information that is information indicating at least a part of the technical document, and a document that stores at least time information that is information indicating a time related to the technical document indicated by the document information Of the plurality of document information stored in the information storage unit, at least a part of the document information acquisition step for acquiring all or a part of the document information, and all or one of the document information acquired at the document information acquisition step. The technical term extracting step for extracting the technical term, the timing information acquiring step for acquiring the timing information corresponding to the document information including the technical term extracted in the technical term extracting step, from the document information storage unit, Using the technical terms extracted in the technical term extraction step and the time information acquired in the time information acquisition step, the technical terms and And executing a technology trend information creating step for creating technology trend information, which is information associating a period related to a technical document including the technical term, and an output step for outputting the technology trend information created in the technology trend information creating step. Is for.

[0373] Further, in this program, a search term acceptance step for accepting a search term in a computer, a search step for searching the literature information storage unit using the search term accepted in the search term acceptance step, The document information acquisition step may acquire all or part of the retrieved document information.

[0374] In the above program, in the reception step for receiving information and the output step for outputting information, processing that is not performed by hardware, such as a modem or an interface card in the output step, is performed. Processing is not included at least.

[0375] In addition, this program is recorded on a predetermined recording medium (for example, an optical disk such as a CD-ROM, a magnetic disk, a semiconductor memory, etc.) that can be executed by being downloaded by force such as a server. The program may be executed by being read. [0376] Further, the computer that executes this program may be singular or plural. That is, centralized processing or distributed processing may be performed.

FIG. 55 is a schematic diagram showing an example of the appearance of a computer that executes the program and realizes the related term acquisition device and the technical trend information creation device according to the embodiment. The above-described embodiment is realized by computer hardware and a computer program executed on the computer hardware.

In FIG. 55, the computer system 100 includes a computer 101 including a CD-ROM (Compact Disk Read Only Memory) drive 105, an FD (Flexible Disk) drive 106, a keyboard 102, a mouse 103, and a monitor. 104.

FIG. 56 is a diagram showing a computer system. In FIG. 56, a computer 101 includes a CD-ROM drive 105 and an FD drive 106, a CPU (Central Processing Unit) 111, and a ROM (Read Only Memory) 112 for storing a program such as a bootup program. The CPU 111 is connected to the CPU 111 to temporarily store the instructions of the application program, and to provide a temporary storage space. And a bus 115 for mutually connecting the ROM 112 and the like. Note that the computer 101 may include a network card (not shown) that provides connection to the LAN.

[0380] A program that causes the computer system 100 to execute the functions of the related term acquisition device and the technical direction information creation device according to the above-described embodiment is stored in the CD-ROM 121 or FD 122, and the CD-ROM drive 105, or It may be inserted into the FD drive 106 and transferred to the hard disk 114. Instead, the program may be transmitted to the computer 101 via a network (not shown) and stored in the hard disk 114. The program is loaded into RAMI 13 when executed. The program may be loaded directly from the CD-ROM 121, the FD 122, or the network.

[0381] The program does not necessarily include an operating system (OS) or a third-party program that causes the computer 101 to execute the functions of the related term acquisition device and the technical trend information creation device according to the above-described embodiment. May be. Program controlled May contain only the part of the instruction that calls the appropriate function (module) in the aspect and achieves the desired result. How the computer system 100 operates is well known and will not be described in detail.

[0382] Further, the present invention can be variously modified without being limited to the above embodiments, and it goes without saying that these are also included in the scope of the present invention.

Industrial applicability

[0383] As described above, according to the related term acquisition device and the like according to the present invention, the related term information related to the accepted term information can be acquired, and the device etc. that acquires the related term related to a certain term Useful as.

[0384] Further, according to the technical trend information creation device or the like according to the present invention, it is possible to create technical trend information that is information for associating technical terms with the timing related to the technical literature including the technical terms. This is useful in devices that create technical trend information from Brief Description of Drawings

FIG. 1 is a block diagram showing a configuration of a related term acquisition device according to Embodiment 1 of the present invention.

FIG. 2 is a block diagram showing a configuration of a related term information acquisition unit according to the embodiment

FIG. 3 is a flowchart showing the operation of the related term acquisition apparatus according to the embodiment.

FIG. 4 is a flowchart showing the operation of the related term acquisition apparatus according to the embodiment.

FIG. 5 is a flowchart showing the operation of the related term acquisition apparatus according to the embodiment.

FIG. 6 is a flowchart showing the operation of the related term acquisition apparatus according to the embodiment.

FIG. 7 is a diagram for explaining an experimental example in the embodiment.

FIG. 8 is a diagram for explaining an experimental example in the embodiment.

FIG. 9 is a block diagram showing a configuration of a related term acquisition apparatus according to Embodiment 2 of the present invention.

FIG. 10 is a block diagram showing the configuration of a related term information acquisition unit according to the embodiment

FIG. 11 is a block diagram showing a configuration of a related term information acquisition unit according to the embodiment

FIG. 12 is a flowchart showing the operation of the related term information acquisition unit according to the third embodiment of the present invention.

FIG. 13 is a diagram showing an example of a type C hand-warming phrase dictionary according to the embodiment.

FIG. 14 is a diagram showing an example of a type B hand-powered phrase dictionary according to the embodiment. [15] A diagram showing an example of bibliographic information of bibliographic information in the embodiment

圆 16] Block diagram showing the configuration of the technology trend information creation device according to Embodiment 4 of the present invention. 圆 17] Flow chart showing the operation of the technology trend information creation device according to the embodiment. 圆 18] Technology trend according to the embodiment. Flowchart showing the operation of the information creation device 圆 19] Flowchart showing the operation of the technology trend information creation device according to the embodiment 圆 20] Flowchart showing the operation of the technology trend information creation device according to the embodiment 圆 21] The flowchart which shows operation | movement of the technical trend information preparation apparatus by form

FIG. 22 is a block diagram showing a configuration of a technical term extraction unit in the embodiment.

[23] A flowchart showing the operation of the technical term extraction unit in the embodiment

FIG. 24 is a block diagram showing a configuration of a technical term extraction unit in the embodiment.

FIG. 25 is a flowchart showing the operation of the technical term extraction unit in the embodiment.

FIG. 26 is a block diagram showing a configuration of a technical term extraction unit in the embodiment.

[27] A flowchart showing the operation of the technical term extraction unit in the embodiment

FIG. 28 is a block diagram showing a configuration of a technical term extraction unit in the embodiment.

FIG. 29 is a flowchart showing the operation of the technical term extraction unit in the embodiment.

FIG. 30 is a block diagram showing a configuration of a technical term extraction unit in the embodiment.

圆 31] Flow chart showing the operation of the technical term extraction unit in the embodiment 圆 32] Flow chart showing the operation of the technical term extraction unit in the embodiment 圆 33] Structure tag and hand in the same embodiment Showing an example of correspondence with

FIG. 34 is a diagram showing an example of information stored in the document information storage unit in the embodiment.

FIG. 35 is a diagram showing an example of correspondence between type C clue words and positions of clue words in the embodiment.

圆 36] A diagram showing an example of document information acquired by the document information acquisition unit in the embodiment. [FIG. 37] An example of a hand-powered phrase stored in the clue phrase storage unit in the embodiment. Illustration

圆 38] A diagram showing an example of extracted technical terms in the embodiment

[39] A diagram showing an example of acquired time information in the embodiment 圆 40] A diagram showing an example of the technology trend information output in the embodiment

圆 41] Diagram showing an example of technology trend information in the embodiment

FIG. 42 is a diagram showing an example of technical terms stored in the technical term storage means in the embodiment.

圆 43] Block diagram showing the configuration of the technology trend information creation device according to Embodiment 5 of the present invention 圆 44] Flow chart showing the operation of the technology trend information creation device according to the embodiment 圆 45] Technology trend according to the embodiment Flowchart showing the operation of the information creation device 圆 46] Block diagram showing the configuration of the technical trend information creation device according to Embodiment 6 of the present invention 圆 47] Flowchart showing the operation of the technical trend information creation device according to the embodiment 圆 48 ] A diagram showing an example of the technology trend information output in the embodiment

[Fig.49] Diagram showing experimental results

[Fig.50] Diagram showing experimental results

[Fig.51] Diagram showing experimental results

圆 52] Block diagram showing the configuration of a technical trend information creation device according to another embodiment

[53] A diagram showing an example of classification result information in another form

圆 54] A figure showing an example of the output technical trend information in another form

FIG. 55 is a schematic diagram showing an example of the external appearance of a computer system.

FIG. 56 is a diagram showing an example of the configuration of a computer system

Claims

The scope of the claims

[1] A document information storage unit that stores two or more document information that is information indicating a document;

A term information accepting unit that accepts term information that is information indicating a term;

The document information searched for the document information having the term indicated by the term information received by the term information receiving unit in all or part of the document information from the two or more document information stored in the document information storage unit. Or a part having at least cited document identification information which is a part of the retrieved document information and is information identifying other documents cited in the retrieved document information. A literature information acquisition unit acquired from the department;

The document information storage unit stores the document information for bow I, which is information indicating the document identified by the document identification information for bow I included in all or part of the document information acquired by the document information acquisition unit. Search from two or more document information, and obtain a portion corresponding to the item that has been determined in advance from the retrieved document information storage unit, which is a part of the retrieved cited document information. An acquisition unit;

Related term information for acquiring related term information, which is information indicating a related term related to the term indicated by the term information received by the term information receiving unit, from a part of the cited reference information acquired by the cited reference information acquiring unit. An acquisition unit;

A related term acquisition device comprising: a related term information output unit that outputs related term information acquired by the related term information acquisition unit.

[2] The document information includes structure description information that is information describing a structure of the document information. The cited document information acquisition unit includes all or part of the document information acquired by the document information acquisition unit. A part of cited document information indicating an I document identified by the included I document identification information, which is associated with an item that has been decided according to the structure description information, is obtained. The related term acquisition device according to claim 1.

[3] A reference structure information acquisition unit for bow I that acquires reference document structure information that is information indicating correspondence between one or more parts of the cited document information and items of the part,

The cited document information acquisition unit is a cited document acquired by the cited document structure information acquisition unit. 2. The related term acquisition apparatus according to claim 1, wherein the related information acquisition unit acquires a part of the cited document information corresponding to an item that has been decided by using structural information.

[4] The cited document information is information indicating a patent document,

4. The related term acquisition apparatus according to claim 1, wherein a part of cited reference information corresponding to an item that is determined in advance is a part of an independent claim.

[5] The cited document information is information indicating a patent document,

The related term acquisition apparatus according to any one of claims 1 to 3, wherein the portion of the cited document information corresponding to the predetermined item is a portion describing an effect of the invention.

[6] The cited document information is information indicating a patent document,

The related term acquisition device according to any one of claims 1 to 3, wherein the part of the cited document information corresponding to the preliminarily determined item is a part other than the preamble of the claim.

[7] When the document information acquisition unit acquires a part of the document information, the document information acquisition unit is a part having at least the cited document identification information and identified by the cited document identification information. A portion having at least the information for bow I, which is information indicating the description of the document, and the cited document information acquisition unit includes the document for bow I included in all or part of the document information acquired by the document information acquisition unit. It is a part of cited document information that is information indicating a document identified by the identification information, and is in the bow I format in the bow I information included in all or a part of the document information acquired by the document information acquisition unit. The related term acquisition device according to any one of claims 1 to 6, wherein the related term acquisition device acquires a portion corresponding to an item determined in advance according to the determination.

[8] The citation form includes at least a problem-pointing citation form that points out the problem of the cited document and an article-based citation form that incorporates the cited document into the basis of the article. The related term acquisition device described.

[9] The cited document information acquisition unit is a background when the citation format in the citation information included in all or part of the document information acquired by the document information acquisition unit is a problem-pointing citation format. The document information acquired by the document information acquisition unit is acquired. 9. The related term acquisition device according to claim 8, wherein when the citation format in the citation information included in all or part of the report is an editorial basis citation format, a portion having a characteristic item is acquired.

[10] The related term information acquisition unit includes:

Related term candidate information acquisition means for acquiring related term candidate information, which is information used as candidates for related terms in a part of the cited reference information acquired by the cited reference information acquisition unit, and acquired by the related term candidate information acquisition means Relevance calculation means for calculating the relevance level of the terms indicated by the related term candidate information for each related term candidate information;

A related term information determining unit that determines related term candidate information having a higher corresponding degree of related term candidate information as related term information from among the related term candidate information acquired by the related term candidate information acquisition means. The related term acquisition device according to any one of claims 1 to 9.

[11] The document information storage unit stores at least a first type of document information and a second type of document information,

The document information acquisition unit acquires all or part of the first type of document information from the first type of document information stored in the document information storage unit,

The cited document information acquisition unit acquires a part of the cited document information from the second type of document information stored in the document information storage unit. The related term acquisition device described.

[12] A document information storage unit that stores two or more document information, which is information indicating a document, a term information reception unit, a document information acquisition unit, a cited document information acquisition unit, a related term information acquisition unit, A related term acquisition method used in a related term acquisition device including a related term information output unit,

A term information receiving step for receiving term information, which is information indicating a term, and a term information receiving unit;

From the two or more document information stored in the document information storage unit, the document information acquisition unit stores the document information having the term indicated by the term information received in the term information reception step in all or part of the document information. Searched, all of the retrieved document information, or a part of the retrieved document information, cited in the retrieved document information A document information acquisition step of acquiring a part having at least cited document identification information that is information for identifying other documents from the document information storage unit;

The cited document information acquisition unit obtains the cited document information as information indicating the document identified by the document identification information for the bow I included in all or part of the document information acquired in the document information acquisition step. Stored in the information storage unit !, search from two or more document information, and select a part of the retrieved cited document information corresponding to a predetermined item from the document information. Cited reference information acquisition step acquired from the storage unit;

Related term information, which is related term information that the related term information acquisition unit indicates related terms related to the term indicated by the term information received by the term information receiving step, from a part of the cited reference information acquired in the cited reference information acquiring step. Related term information acquisition step to acquire

A related term information output method comprising: a related term information output unit that outputs related term information acquired in the related term information acquisition step.

On the computer,

A term information receiving step for receiving term information, which is information indicating a term,

The document information having the term indicated in the term information received in the term information receiving step in all or a part of the document information is stored in the document information storage unit in which two or more document information that is information indicating the document is stored. Searching from two or more document information, all of the retrieved document information, or a part of the retrieved document information, cited in the retrieved document information, etc. A document information acquisition step of acquiring from the document information storage unit a portion having at least the document identification information for bow I, which is information for identifying the document, and all or part of the document information acquired in the document information acquisition step. The document information for bow I, which is information indicating the document identified by the document identification information for bow I included, is searched for two or more documents information stored in the document information storage unit, and the retrieved cited document information Part of There are a cited document information acquisition step of acquiring a portion corresponding to the item are determined because Ji roughness force from the document information storage unit,

Information indicating related terms related to the term indicated by the term information received by the term information receiving step from a part of the cited reference information acquired in the cited reference information acquiring step. A related term information acquisition step for acquiring related term information,

And a related term information output step for outputting the related term information acquired in the related term information acquisition step.

[14] A document information storage unit that stores at least a plurality of document information that is information indicating at least part of the technical document, and time information that is information indicating a time related to the technical document indicated by the document information,

A document information acquisition unit that acquires all or part of at least some of the document information among the plurality of document information stored in the document information storage unit;

A technical term extraction unit that extracts all or part of the technical information obtained by the literature information acquisition unit;

A time information acquisition unit that acquires time information corresponding to document information including the technical terms extracted by the technical term extraction unit from the document information storage unit;

Technical trend information, which is information associating technical terms with the timing of technical documents including the technical terms, using the technical terms extracted by the technical term extraction unit and the timing information acquired by the timing information acquisition unit Technical trend information creation department to create

A technology trend information creation device comprising: an output unit that outputs the technology trend information created by the technology trend information creation unit.

[15] A search term reception unit for receiving search terms;

A search unit that searches the document information storage unit using the search term received by the search term reception unit,

15. The technical trend information creation device according to claim 14, wherein the literature information acquisition unit acquires all or a part of searched literature information.

[16] a search term storage unit in which two or more search terms are stored;

A search term selection accepting unit that accepts selection of one of the search terms among the two or more search terms stored in the search term storage unit,

16. The technical trend information creation device according to claim 15, wherein the search term reception unit receives a search term indicated by the selection received by the search term selection reception unit.

[17] Technical terms for extracting technical terms from the literature information stored in the literature information storage unit An extractor;

A suffix storage unit for storing a predetermined suffix;

When the terminology obtained by adding the suffix stored in the suffix storage unit to the technical term extracted by the technical term extraction unit is included in the document information stored in the document information storage unit, 17. The technical trend information creation device according to claim 16, further comprising: a search term storage unit that stores technical terms as search terms in the search term storage unit.

[18] The technical trend information according to any one of claims 15 to 17, wherein the search unit searches for document information corresponding to a technical document whose search term received by the search term receiving unit is a main topic. Creation device.

[19] The literature information is information including at least a title of technical literature,

The search unit is stored in the document information storage unit, and the document information including the search term received by the search term receiving unit is included in the area indicating the main topic in the title of the technical document indicated by the document information. 19. The technical trend information creation device according to claim 18, wherein the technical trend information creation device searches.

20. The technical trend information creating apparatus according to claim 19, wherein the area indicating the main topic is a last area of the title.

[21] The apparatus further comprises a specifying unit that specifies the document information having the same field as the document information searched by the search unit,

21. The technical direction information creation device according to claim 15, wherein the document information acquisition unit acquires all or part of the document information specified by the specification unit from the document information storage unit.

[22] The specifying unit acquires, from the document information searched by the search unit, the document identification information for bow I that is information for identifying other technical documents cited in the document information, The technical trend information creation device according to claim 21, wherein the cited document identification information is used to identify document information having the same field as the document information searched by the search unit.

[23] The specifying unit also includes information for bow I which is information indicating a description of other technical documents cited in the document information from the document information searched by the search unit. If the citation format obtained and indicated by the citation information is a problem-pointing citation format that points out the problem of the cited technical document, the technology described in the citation information 23. The technical trend information creation device according to claim 22, wherein the literature identification information for I that identifies a document is used to identify literature information having the same field as the literature information searched by the search unit.

[24] The technical term extraction unit includes:

A clue word storage means for storing one or more clue words,

A manual phrase search means for searching for a clue phrase by using all or a part of the reference information acquired by the reference information acquisition section;

The technical term extracting means for extracting, as a technical term, a term having a predetermined relationship with the hand-squeezed phrase searched by the hand-squeezed phrase searching means. The described technical trend information creation device.

[25] The technical term extraction unit includes:

A clue word storage means for storing one or more clue words,

The search term received by the search term receiving unit, and a technical term extraction unit that extracts a term associated with the clue phrase searched by the clue phrase search unit as a technical term. 24. The technical trend information creating device according to claim 23.

[26] The technical term extraction unit includes:

A clue word storage means for storing one or more clue words,

Terminology storage means for storing two or more terminology,

If the term retrieved by the hand-powered phrase search means includes a technical term stored in the technical term storage means in the term having a predetermined relationship with the hand-stretched phrase, the technical term is referred to as a technical term. 24. The technical trend information creating device according to claim 14, further comprising: a technical term extracting unit that extracts as a technical term.

[27] The technical term extraction unit includes: A clue word storage means for storing one or more clue words,

Technical term candidate extraction means for extracting, as a technical term candidate, a term having a predetermined relationship with the hand searched for by the hand force phrase search means;

The technical trend information creation according to any one of claims 14 to 23, further comprising technical term selection means for selecting all or part of technical term candidates extracted by the technical term candidate extraction means as technical terms. apparatus.

[28] The technical term extraction unit includes:

Technical term suffix storage means for storing one or more suffixes that can be taken by the technical term is further provided,

28. The technical trend information creating apparatus according to claim 27, wherein the technical term selection means selects a technical term candidate having a suffix as stored in the technical term suffix storage means as a technical term.

[29] The technical term selection means selects a technical term candidate as a technical term that is stored in the literature information storage unit and used as a main topic in any literature information! The technical trend information creation device according to claim 27.

[30] The technical term extraction unit includes:

Document information identifying means for identifying document information from which the technical term candidates are extracted, and document information having the same field,

Technical term suffix storage means for storing one or more suffixes that can be taken by the technical term, and further comprising:

The document information acquisition unit also acquires all or part of the document information specified by the document information specifying means,

The technical term selection means is specified by the reference information specifying means that all or a part of one reference information acquired by the reference information acquisition unit and the field are the same as the one reference information. If at least one of the technical term candidates extracted from all or part of the document information has the suffix stored in the suffix storage means, 28. The technical trend information creating apparatus according to claim 27, wherein the technical term candidates extracted from all or a part of the document information as described above are selected as technical terms.

[31] The technical trend information is an image indicating the time indicated by the time information corresponding to the document information including the technical term for each technical term.

31. The technical trend information creation device according to claim 14, wherein the output unit displays and outputs the technical trend information.

[32] The technical trend information is an image in which, for each technical term, a document graphic that is a graphic corresponding to the document information including the technical term is displayed according to the time indicated by the time information corresponding to the document information. Yes,

A graphic selection receiving unit that receives selection of a document graphic in the technical trend information; A display information acquisition unit that acquires certain display information from the document information storage unit,

32. The technical trend information creation device according to claim 31, wherein the technical trend information creation unit creates technical trend information for displaying the display information acquired by the display information acquisition unit.

[33] A document information storage unit that stores at least a plurality of document information that is information indicating at least part of the technical document, and time information that is information indicating a time related to the technical document indicated by the document information, and a document A technical trend information creation method that is executed using an information acquisition unit, a technical term extraction unit, a time information acquisition unit, a technical trend information generation unit, and an output unit, wherein the document information acquisition unit includes: A document information acquisition step of acquiring all or a part of at least a part of the document information among the plurality of document information stored in the document information storage unit;

A technical term extraction step in which the technical term extraction unit extracts all or part of the technical information of the literature information acquired in the literature information acquisition step;

A timing information acquisition step in which the timing information acquisition unit acquires timing information corresponding to the document information including the technical terms extracted in the technical term extraction step;

Technical terms extracted by the technical trend information creation unit in the technical term extraction step, Using the time information acquired in the time information acquisition step, a technical trend information creation step for creating technical trend information, which is information for associating a technical term with a time concerning a technical document including the technical term,

An output step in which the output unit outputs the technology trend information created in the technology trend information creation step.

[34] A technical trend information generation method that is executed by further using a search term reception unit and a search unit.

A search term receiving step in which the search term accepting unit accepts a search term; and a search step in which the search unit searches the literature information storage unit using the search term accepted in the search term accepting step. Prepared,

34. The technical trend information creation method according to claim 33, wherein in the document information acquisition step, all or a part of the retrieved document information is acquired.

[35] On the computer,

A plurality of document information that is information indicating at least a part of the technical document and a plurality of document information stored in the information storage unit that stores at least time information that is information indicating the time related to the technical document indicated by the document information. A document information acquisition step of acquiring all or a part of at least a part of the document information,

A technical term extraction step for extracting all or part of the technical information of the literature information acquired in the literature information acquisition step;

A time information acquisition step of acquiring time information corresponding to the document information including the technical terms extracted in the technical term extraction step from the document information storage unit;

Technical trend information, which is information for associating technical terms with the technical literature including the technical terms, using the technical terms extracted in the technical term extraction step and the time information acquired in the time information acquisition step. A program for executing a technology trend information creating step for creating a technology and an output step for outputting the technology trend information created in the technology trend information creating step.

[36] On the computer, A search term acceptance step for accepting a search term;

A search step of searching the document information storage unit using the search term received in the search term reception step, and

In the document information acquisition step, all or part of the retrieved document information is acquired.

36. The program according to claim 35.