JP2021043677A - Dictionary construction device, map creation device, search device, dictionary construction method, map creation method, search method, and program - Google Patents

Abstract

To provide a dictionary construction device, a map creation device, a search device, a dictionary creation method, a map creation method, a search method, and a program, that easily construct a term dictionary which excludes terms not belonging to a predetermined class but includes more of related words for the terms.SOLUTION: A dictionary construction device 1 in an information system includes a processing unit 13, comprising: a term classification section 131 for, to each of two or more terms, determining whether or not they are terms belonging to a predetermined class; a restriction processing section 132 for, by using a classification result, excluding terms not belonging to the predetermined class from the two or more terms; a document search section 133 for searching a document group by using each of remained one or more terms as at least keys, and obtaining a document corresponding to each one or more terms; and an expansion processing section 134, for obtaining one or more related words relating to the terms from information of predetermined locations, which is information within the obtained document, for obtaining a term dictionary having a plurality of pairs associated with the corresponding terms, and for accumulating thereof.SELECTED DRAWING: Figure 1

Description

The present invention relates to a dictionary construction device or the like for constructing a term dictionary of technical terms and the like.

Conventionally, when constructing a term dictionary of word categories, there has been a computer system that finds words to be registered without omission from newly added texts and efficiently performs the work (see, for example, Patent Document 1).

This computer system performs morphological analysis of text data and acquires token string data, and a morphological analysis unit that discriminates each token of the token string data using a category dictionary and extracts uncategorized words. The uncategorized word collation unit that collates the extracted uncategorized words with the uncategorized word collation rule and extracts the uncategorized words that match the uncategorized word collation rule as registration candidate words, and the uncategorized word collation unit. The token string of the token string data is matched with the token string matching rule, and the token string matching unit that extracts the token string matching the token string matching rule as a registration candidate word is included, and the registration candidate word is added to the category dictionary. It consists of a permission unit that allows the user to choose whether or not to register.

Japanese Unexamined Patent Publication No. 2010-157178

However, in a conventional computer system, complicated processing such as matching an uncategorized word with an uncategorized word matching rule and matching a token string with a token string matching rule is required, and the user selects whether or not to register a registration candidate. I needed it. Therefore, the conventional computer system does not include terms that do not belong to a predetermined class, and it is not possible to easily construct a term dictionary containing more related words of terms.

The dictionary construction device of the first invention has an initial terminology storage unit that stores an initial terminology that is a set of two or more terms, and terms belonging to a predetermined class for each of the two or more terms. Exclude terms that do not belong to a predetermined class from two or more terms using the term classification section that determines whether the term is a term that does not belong to a predetermined class and the classification result in the term classification section. A reduction processing unit that performs reduction processing, which is a process, and a document search unit that searches a group of documents using at least one or more terms remaining as a result of the reduction processing as a key, and acquires documents corresponding to each of one or more terms. And, it is the information in the document acquired by the document search unit, and one or more related words related to the term are acquired from the information of the predetermined location, and one or more related words are associated with the corresponding terms. This is a dictionary construction device including a term dictionary having a plurality of pairs of terms and one or more related words associated with the terms, and an expansion processing unit for performing expansion processing for accumulating the terms.

With such a configuration, it is possible to easily construct a term dictionary containing more related words of terms without including terms that do not belong to a predetermined class.

Further, the dictionary construction device of the second invention relates to the term from the information of the first predetermined place in the document acquired by the document search unit in the extended processing unit with respect to the first invention. Acquire one or more synonyms, associate one or more synonyms with corresponding terms, acquire a term dictionary having a plurality of pairs of terms and one or more synonyms associated with the terms, and accumulate them. This is a dictionary construction device that performs the first expansion process.

With such a configuration, it is possible to easily construct a term dictionary containing more synonyms of terms without including terms that do not belong to a predetermined class.

Further, the dictionary construction device of the third invention is based on the first or second invention, and the extension processing unit is based on the information of the second predetermined position in the document acquired by the document search unit. Acquire one or more hypernyms related to a term, associate one or more hypernyms with the corresponding terms, and acquire a term dictionary having a plurality of pairs of terms and one or more hypernyms associated with the terms. It is a dictionary construction device that performs the second expansion processing that accumulates.

With such a configuration, it is possible to easily construct a term dictionary containing more hypernyms of terms without including terms that do not belong to a predetermined class.

Further, in the dictionary construction apparatus of the fourth invention, with respect to the third invention, the document search unit searches the document group using the hypernym acquired by the extension processing unit in the second extension processing as a key, and one or more. The document corresponding to each hypernym of is acquired, and the extended processing unit is the information in the document corresponding to the hypernym acquired by the document search unit, and from the information in the second place, one or more related to the hypernym. It is a dictionary construction device further comprising a control unit that acquires the hypernym of the above and controls the processing of the document retrieval unit and the second expansion processing of the extension processing unit once or twice or more.

With such a configuration, a term dictionary including the upper terms of the hypernyms can be easily constructed.

Further, the dictionary construction device of the fifth invention stores the highest-level term, which is a set of the highest-level terms, which is one or more terms of the highest-level concept, for the fourth invention. The collection and storage unit is further provided, and the control unit processes and extends the document search unit until the term acquired by the second expansion processing of the expansion processing unit becomes one of the top-level terms included in the top-level glossary. It is a dictionary construction device that controls so as to repeat the second expansion process of the processing unit.

With such a configuration, a term dictionary containing terms of two or more layers up to the highest level can be easily constructed.

Further, the dictionary construction device of the sixth invention is a dictionary construction device, which is a class of technical terms, in a predetermined class for any one of the first to fifth inventions.

With such a configuration, it is possible to easily construct a dictionary of technical terms, which does not include terms other than technical terms and contains more related words of technical terms.

Further, the dictionary construction device of the seventh invention is a dictionary construction device in which a predetermined class is a class of a company name for any one of the first to fifth inventions.

With such a configuration, it is possible to easily construct a dictionary of company names, which does not include terms other than the company name and contains more related words of the company name.

Further, the dictionary construction device of the eighth invention is a dictionary construction device which is the class of the inventor for any one of the first to fifth inventions.

With such a configuration, it is possible to easily construct a term dictionary that is a dictionary of the inventor's name, does not include terms other than the inventor's name, and contains more related words of the inventor's name.

Further, the map creation device of the ninth invention stores a term dictionary storage unit for storing a term dictionary configured by the dictionary construction device of any one of the first to eighth inventions, and two or more patent information. The patent information storage unit, the term acquisition unit that acquires terms from each of two or more patent information, and the term acquisition unit acquires related words common to each of the two or more terms acquired from the term dictionary. The upper part of the term summary and the original two or more patent information from which each of the two or more terms acquired by the term acquisition department corresponding to the related word acquired by the upper part of the term summary are acquired, and the related words acquired by the upper part of the term summary. It is a map creation device including a related word correspondence unit to be associated and a map output unit that outputs the related words and two or more patent-related information related to each of the two or more original patent information in association with each other.

With such a configuration, an accurate map can be created from two or more patent information by using the term dictionary constructed by the dictionary construction device of any one of the first to eighth inventions.

Further, in the mapping device of the tenth invention, for the ninth invention, the term acquisition unit acquires two or more different classes of terms from each of two or more patent information, and the upper part of the term summary is The summarization process is performed for each of two or more different classes, and the related word correspondence section is for each of the two or more different classes acquired by the term acquisition section corresponding to the related word acquired by the upper part of the term summary. The original two or more patent information from which the term was acquired is associated with the related word acquired by the upper part of the term summary, and each of the two or more different classes is related to the related word and each of the two or more original patent information. A map configuration unit that constitutes a map associated with the above patent-related information is further provided, and the map output unit is a map creation device that outputs a map configured by the map configuration unit.

With such a configuration, a multidimensional map can be generated.

In addition, the map creation device of the eleventh invention refers to a map reception unit that accepts terms and one or more related words related to the terms accepted by the map reception unit for the ninth or tenth invention. A map processing unit that obtains search results by searching for two or more patent information stored in the patent information storage unit using each of the acquired one or more related words as a key is further provided. The output unit is a map creation device that outputs search results.

With such a configuration, an accurate patent search can be performed using the constructed term dictionary.

Further, in the map creating apparatus of the twelfth invention, for the eleventh invention, the search result is identification information which is a set of identification information for identifying one or more patent information including related terms. It is a group, the map output unit delivers the identification information group to the term acquisition unit, and the term acquisition unit is a map creation device that acquires terms from one or more patent information corresponding to the identification information group.

With this configuration, a child population, which is a set of one or more patent information including related words of accepted terms, is acquired from a parent population, which is a set of two or more stored patent information, and constructed. An accurate map can be created from the offspring using the term dictionary.

Further, the search device of the thirteenth invention stores a term dictionary storage unit for storing a term dictionary configured by the dictionary construction device of any one of the first to eighth inventions, and two or more patent information. The patent information storage unit, the reception unit that accepts terms, and one or more related words related to the terms accepted by the reception department are acquired from the term dictionary, and the patent information is stored using each of the acquired one or more related words as a key. It is a search device including a processing unit that searches two or more patent information stored in the unit and acquires the search result, and an output unit that outputs the search result by the processing unit.

With such a configuration, an accurate patent search can be performed using the constructed term dictionary.

According to the dictionary construction device according to the present invention, it is possible to easily construct a term dictionary containing more related words of terms without including terms that do not belong to a predetermined class. In addition, using the constructed term dictionary, it is possible to create an accurate map from two or more patent information, which has less noise and summarizes more related words. Furthermore, using the constructed term dictionary, it is possible to perform an accurate patent search with few omissions.

Block diagram of the information system in the embodiment Flow chart explaining a part of the operation of the dictionary construction device (reduction processing, etc.) A flowchart explaining another part (search / enlargement processing) of the operation of the dictionary construction device. Flowchart explaining an example of search / extension processing when constructing a hypernym dictionary Flowchart explaining hypernym correspondence (recursive processing) Flow chart explaining the operation of the map creation device Diagram showing an example of the unnecessary word group Diagram showing an example of the end group of the same sentence Diagram showing an example of the initial glossary Diagram showing an example of the same top-level terminology The figure which shows an example of the article summary corresponding to the same "CPU" A diagram showing an example of an article summary corresponding to the "minidisc" Diagram showing an example of the same clue phrase group Figure showing an example of the sentence group immediately after the summary Structural diagram of the table (Table 1) constructed from the same "jawiki-latest-page.SQL" Structural diagram of the table (Table 2) constructed from the same "jawiki-latest-redirect.SQL" Structural diagram of the table constructed from Tables 1 and 2 (Table 3: Synonymous dictionary) Structural diagram of the table (Table 4) constructed from the same "jawiki-latest-page.SQL" Structural diagram of the table (Table 5) constructed from the same "jawiki-latest-categorylinks.SQL" Structural diagram of the table constructed from Tables 4 and 5 (Table 6: Hypernym dictionary) Hierarchical diagram in which Table 6 is configured in a tree shape Diagram showing an output example of the map creation device A block diagram of a search device, which is a modification of the map creation device. Flow chart explaining the operation of the search device External view of the computer system Diagram showing an example of the internal configuration of the computer system

Hereinafter, embodiments of the dictionary construction device and the like will be described with reference to the drawings. In addition, since the components with the same reference numerals perform the same operation in the embodiment, the description may be omitted again.

FIG. 1 is a block diagram of the information system A according to the present embodiment. The information system A includes a dictionary construction device 1 and a map creation device 2. The dictionary construction device 1 is communicably connected to the map creation device 2 via, for example, a network such as a LAN or the Internet, a wireless or wired communication line, or the like. Each of the dictionary construction device 1 and the map creation device 2 may be connected to one or more terminal devices (not shown) via, for example, a network or the like. Further, the dictionary construction device 1 is usually connected to a server (not shown) that stores a group of documents described later. However, the dictionary construction device 1 and the map creation device 2 may be stand-alone.

The dictionary construction device 1 and the map creation device 2 are, for example, servers of an organization such as a company or an organization that provides patent information regarding patents. The server is, for example, a cloud server, an ASP server, or the like, but the type does not matter. The terminal device (not shown) is, for example, a PC, but may be a mobile terminal of a user who uses patent information, and the type is not limited. The mobile terminal is, for example, a smartphone, a tablet terminal, a mobile phone, a notebook PC, or the like, but the type is not limited.

The dictionary construction device 1 includes a storage unit 11, a reception unit 12, a processing unit 13, and an output unit 14. The storage unit 11 includes an initial terminology storage unit 111 and a top-level terminology storage unit 112. The initial terminology storage unit 111 includes a term classification unit 131. The processing unit 13 includes a reduction processing unit 132, a document retrieval unit 133, an expansion processing unit 134, and a control unit 135.

The map creation device 2 includes a map storage unit 21, a map reception unit 22, a map processing unit 23, and a map output unit 24. The map storage unit 21 includes a term dictionary storage unit 211 and a patent information storage unit 212. The map processing unit 23 includes a term acquisition unit 231, a term summary upper part 232, a related word correspondence unit 233, and a map configuration unit 234.

The storage unit 11 constituting the dictionary construction device 1 can store various types of information. The various types of information include, for example, initial glossary information. Other information will be explained in a timely manner.

The initial terminology storage unit 111 stores the initial terminology. The initial glossary is an early glossary. An initial glossary is a pre-stored set of two or more terms. The two or more terms that make up the initial glossary are, for example, technical terms, company names, inventor names, and other general terms.

Technical terms are terms related to technology. Technology is usually science and technology, and science and technology are, for example, technologies related to natural science, social science, humanities, etc., but the field is not limited. The technical terms are, for example, "CPU", "storage device", "display", etc., but may be anything.

The company name is the name of the company. The company name is usually the name recorded in the register, but it may be a common name, an abbreviation, or the like, and any name that can identify the company may be used.

The inventor's name is the name of the inventor. The inventor's name is usually the name written in the family register, but it may be a common name.

Other general terms are terms that do not fall under any of the technical terms, company names, and inventor names. It can be said that the general term is a term that is not necessary for the term dictionary that the dictionary construction device 1 intends to construct. Specifically, the general term is, for example, "Hatenai Monogatari", "Children's Literature", etc., but can be anything.

It is preferable that the two or more terms that make up the initial glossary are layered. Hierarchy means that the upper term and the lower term are at least associated with each other. The number of layers may be, for example, three or more, and the number of layers does not matter. Hierarchical means, for example, that hierarchical information corresponds to each of two or more terms. Hierarchical information is information about the hierarchy. The hierarchical information is information indicating the order of two or more layers such as "top layer (first layer)", "second layer", and "third layer", but the format is not limited.

Alternatively, the two or more terms constituting the glossary may have, for example, a tree structure, and the mode of layering thereof does not matter. However, layering is not essential, and the glossary may be a flat set of terms.

Specifically, the initial glossary may be, for example, all redirect titles of Wikipedia (registered trademark: the same shall apply hereinafter). Wikipedia is an electronic encyclopedia accessible on the Internet. Wikipedia includes, for example, two or more pages, and two or more redirect titles. The page has an article title, an article summary, an article, etc., but its structure does not matter.

In Wikipedia, for example, parts such as pages, article titles, article summaries, etc. are specified by predetermined tags. For example, a page is a portion sandwiched between a pair of tags <page> and </ page>. The article title is a part of the page sandwiched between a pair of tags <title> and </ title>. In addition, the article summary is the part of the page where the same character string as the article title sandwiched between <title> and </ title> appears first sandwiched between "'''" and "'''". From to the first punctuation mark "." (In the following, the tag that specifies such a part may be described as ""'''" to "." "). However, the part sandwiched between <title> and </ title> and the part sandwiched between the first "'''" and "'''" may be partially matched or judged by pattern matching. May be good. Furthermore, the article is the part from immediately after the first punctuation mark to immediately before the tag </ text>. However, the structure of the tag does not matter.

An article is a document that explains a term. The article title is the title of the article and is a term usually explained by the article. An article summary is a document that summarizes an article.

The redirect title is a title to be redirected. A title is a term. It can be said that redirect is a function that when an article of one term is accessed, it is transferred to the page of the article of another term. The redirect title is, for example, a pair of a transfer source term and a transfer destination term, but the format does not matter. The pair of the transfer source term and the transfer destination term is, for example, a pair of "CPU" and "central processing unit", but the combination of terms does not matter.

The term of the transfer destination is usually a synonym of the term of the transfer source, but it may be a hypernym, a hyponym, or any other related word. Related words, synonyms, hypernyms, and hyponyms will be described later.

However, the initial glossary may be, for example, the title of all articles on Wikipedia, and its structure does not matter.

The highest-level terminology storage unit 112 stores the highest-level terminology. A top-level glossary is a set of one or more top-level terms. The top-level term is a term of the top-level concept defined in advance in the present embodiment. The top-level term may be, for example, a term associated with hierarchical information indicating "top layer", a term arranged at the top of the tree structure, or a term belonging to the top-level group. In the following, the hypernym may be referred to as "hypernym".

Specifically, for example, in Wikipedia, the highest level of the hierarchy is "major category", but the subcategory of this "major category" is "classification by subject" (for example, "natural science", "social science". , "Humanities", etc.), which belong to the lower categories (for example, "Business Science" and "Engineering" under "Natural Science", and "Economics" and "Archology" under Social Science. , "Computer science", "dental science", etc., which are lower than "humanities") are the highest-level terms in the term dictionary (for example, higher-level word dictionary described later) constructed by the dictionary construction device 1.

Therefore, the top-level terms are, for example, "business science", "engineering", "economics", "archeology", "computer science", "dentistry", etc. Any term that belongs to the subcategory of "" may be used.

The reception unit 12 receives various types of information. The various types of information include, for example, a transmission instruction of a term dictionary. The term dictionary transmission instruction is an instruction to transmit the term dictionary constructed by the dictionary construction device 1 to the map creation device 2. The reception unit 12 receives the transmission instruction of the term dictionary via an input device such as a keyboard, but may receive it from a terminal device (not shown), and the mode of reception is not limited.

The terminal device usually transmits information such as a transmission instruction to the terminal identifier, and the reception unit 12 receives information such as a transmission instruction to the terminal identifier. The terminal identifier is information that identifies the terminal device. The terminal identifier is, for example, a MAC address, an IP address, an ID, or the like, but may be a user identifier, or any information that can identify the terminal device. The user identifier is information that identifies the user of the terminal device. The user identifier is, for example, an e-mail address, a telephone number, an ID, or the like, but any information that can identify the user may be used. However, when the number of terminal devices is only one, the terminal identifier does not have to be transmitted or received.

The processing unit 13 performs various processes. The various processes are, for example, processes such as a term classification unit 131, a reduction processing unit 132, a document retrieval unit 133, an expansion processing unit 134, and a control unit 135. The various processes also include various discriminations described in the flowchart. Other processes will be described in a timely manner.

The term classification unit 131 refers to each of the two or more terms stored in the initial glossary storage unit 111, and the term belongs to a predetermined class or does not belong to a predetermined class. Determine if it is a term and obtain a classification result that is information about the two or more determination results.

A class is a type or division of terms. The class is, for example, "technical term class", "company name class", "inventor name class", etc., but may also be "other term class", and is information indicating the type or classification of terms. Anything is fine as long as it is available.

The term belonging to a predetermined class is, for example, a technical term. And there are many related terms in technical terms. A related word is a word related to the term. Related words are, for example, synonyms, hypernyms, and hyponyms, but the types are not limited. It should be noted that the related words of a certain term may be considered to include the term itself.

Synonyms are words with the same concept. For example, the synonym for "CPU" is "central processing unit" or the like, but it may be "processor" or any word that includes the same concept. In addition, the synonymous word in this embodiment also includes, for example, a word in which notational fluctuation occurs. The word in which the notation fluctuates occurs is, for example, "processor", "processor", etc., but the type thereof does not matter. Further, the synonyms in the present embodiment may be considered to include, for example, synonyms, and can be widely understood. Synonyms are words with similar concepts. Synonyms are, for example, "CPU", "MPU", "GPU", etc., but the types are not limited. However, synonyms may be excluded from the synonyms referred to in this embodiment.

Hypernym is a term of a higher concept. For example, the hypernym of "CPU" is "hardware", "computer", "computer science", etc., but it may be "processing unit", "control unit", etc., and any term of a superordinate concept may be used. ..

Hyponyms are terms of subordinate concepts. For example, the subordinate term of "CPU" is "CPU socket", "microprocessor", etc., but any term of the subordinate concept may be used.

However, the term belonging to the predetermined class may be, for example, a company name or an inventor name, and the class to which the term belongs does not matter. Related words such as synonyms usually also exist in company names. The synonyms of the company name are, for example, common names and abbreviations, but may be the product names of the main products. The hypernym of the company name may be, for example, a parent company name, a group name, or the like, and the hyponym of the company name may be, for example, a subsidiary name, a product name, or the like. In addition, there are synonyms and the like in the inventor's name. The synonym for the inventor's name may be, for example, a pen name or a common name. The hypernym of the inventor's name may be, for example, the name of an organization such as a company or an organization to which the inventor belongs.

Whether the term belongs to a predetermined class or does not belong to a predetermined class can be determined, for example, by using a classification method. In the following, a process of determining whether a term belongs to a predetermined class or a term that does not belong to a predetermined class may be referred to as a determination process.

The determination process may be, for example, a process of classifying two or more terms constituting the initial glossary into terms included in the term dictionary and terms not included in the term dictionary. A term that is not included in the term dictionary may be called an unnecessary word, for example.

For example, if the initial glossary is the title of all Wikipedia articles (for example, "Hatenai Monogatari", "CPU", "Minidisc", etc.), the storage unit 11 stores unnecessary words and sentence endings. It may have been. An unnecessary word group is a set of one or more unnecessary words. The unnecessary words are, for example, "novel", "TV drama", "music unit", etc., but the type is not limited. The unnecessary word may be considered as a hypernym of the unnecessary word, for example. A sentence end group is a set of one or more sentence ends. The end of the sentence is, for example, "is.", "One of.", "Koto.", Etc., but the type does not matter.

For example, when the article summary of the page explaining a certain term (article title) ends with "" unnecessary word "+" end of sentence "", the article title corresponding to the article summary is determined to be an unnecessary word. Specifically, for example, the article title "The Neverending Story" has the corresponding article summary ""'''The Neverending Story'''" (The Neverending Story, {{de |''Die unendliche Geschichte' '}}) Is a [[Children's Literature | Children's]] [[Fantasy]] novel by [[Writer]] [[Michael Ende]] of [[Germany]]. Since it ends with "+" is. "", It is judged to be an unnecessary word.

The class classification method is, for example, a method by machine learning using a learning device in addition to the method by pattern matching as described above, but the type is not limited.

The classification method is a known technique, and detailed description thereof will be omitted. Regarding the classification of terms, for example, "Annotation of meaning classes and roles of terms in information science papers" (Yuka Tateishi et al., Natural Language Processing Society, Proceedings of the 22nd Annual Conference, March 2016), "Wikipedia" It is described in "Inherent expression classification of ambiguous expressions using articles" (Yuya Fujii et al., Natural Language Processing Society, Proceedings of the 16th Annual Conference, March 2010).

The determination result is, for example, a flag indicating "1" indicating that the term belongs to a predetermined class or "0" indicating that the term does not belong to a predetermined class. May be good. However, the format of the decision result does not matter.

The classification result is, for example, a set of pairs of terms and decision results. Alternatively, the classification result may be, for example, a set of one or more terms determined to belong to a predetermined class. Alternatively, the classification result is determined to be, for example, a first set which is a set of one or more terms determined to belong to a predetermined class and a term which does not belong to a predetermined class. It may include a second set, which is a set of one or more terms. Alternatively, the classification result may include, for example, only the second set and not the first set. However, the format of the classification result does not matter.

Specifically, for example, when a predetermined class is a "class of technical terms", in the term classification unit 131, each of two or more terms stored in the initial glossary storage unit 111 is a technical term. Determine whether a term belongs to a class or a term that does not belong to a technical term class using a class classification method such as pattern matching, and obtain a classification result that is a set of pairs of terms and decision results. .. The acquired classification result may be accumulated in the storage unit 11 by, for example, the processing unit 13.

Or, for example, when the predetermined class is the "class of the company name", the term classification unit 131 indicates that each of the two or more stored terms belongs to the class of the company name or the company name. Determine if the term does not belong to the class of, and obtain the classification result. When the predetermined class is the "inventor name class", the same determination process is performed and the classification result is acquired.

Alternatively, the term classification unit 131 can, for example, repeat the above-mentioned determination process two or more times to obtain the stored two or more terms in the "technical term class", "company name class", and "company name class". You may classify into three or more classes including "inventor name class" and obtain the classification result. The classification result obtained may be, for example, a set of pairs of terms and class identifiers. The class identifier is information that identifies the class to which the term belongs. The class identifier is, for example, a class name such as "technical term", "company name", or "inventor name", but an ID corresponding to the class name may be used, and the format is not limited. In addition, the format of the classification result does not matter.

Specifically, for example, the term classification unit 131 initially belongs to the technical term class or the technical term class for each of the two or more terms stored in the initial glossary storage unit 111. Determine whether the term does not belong, and associate the class identifier "technical term" with the term determined to belong to the technical term class.

Next, the term classification unit 131 refers to each of one or more terms determined to be a term that does not belong to the technical term class, for example, a term that belongs to the company name class or a term that belongs to the company name class. It is determined whether the term does not belong, and the class identifier "company name" is associated with the term determined to belong to the class of the company name.

Next, the term classification unit 131 refers to each of one or two or more terms determined to be a term that does not belong to the company name class, for example, a term that belongs to the inventor name class or an inventor name. It is determined whether the term does not belong to the class, and the class identifier "inventor name" is associated with the term determined to belong to the class of the inventor name.

Then, the term classification unit 131 associates, for example, the class identifier “class of other terms” with the term determined to be a term that does not belong to the class of the inventor's name. As a result, each of the two or more stored terms is associated with a class identifier indicating one of the above four classes, thereby obtaining a classification result which is a set of pairs of terms and class identifiers. Will be done.

The reduction processing unit 132 performs the reduction processing using the classification result in the term classification unit 131. The reduction process is a process for removing terms that do not belong to a predetermined class from two or more terms stored in the initial glossary storage unit 111.

The reduction processing unit 132 uses, for example, the classification result, which is a set of pairs of terms and determination results, as described above, and “predetermines” from two or more terms stored in the initial glossary storage unit 111. Processing may be performed excluding one or more terms that are paired with the determination result that "the term does not belong to the specified class". As a result of such reduction processing, only one or two or more terms belonging to a predetermined class remain among the two or more terms stored in the initial glossary storage unit 111.

For example, a copy of the initial terminology of the initial terminology storage unit 111 may be created in the storage unit 11, and the reduction process may be performed on the initial terminology of the storage unit 11.

Alternatively, the process of excluding the terms that do not belong to the predetermined class may be, for example, the process of extracting only the terms that belong to the predetermined class. That is, the reduction processing unit 132 uses, for example, a classification result which is a set of pairs of terms and a determination result, and uses two or more terms stored in the initial glossary storage unit 111 to obtain a “predetermined class”. A process of extracting one or more terms that are paired with the determination result of "a term belonging to" may be performed. The extracted one or more terms are accumulated in the storage unit 11 by, for example, the processing unit 13.

As a result of the reduction processing by the reduction processing unit 132, the document search unit 133 searches the document group using each of the remaining one or more terms as a key, and acquires the document corresponding to each of the one or more terms.

A document group is a set of one or more documents. The document referred to here is an electronic document. The electronic document is, for example, a document such as HTML or XML, but the format does not matter. The document group may be, for example, all the pages of Wikipedia described above (for example, "jawiki-latest-pages-articles.XML.bz2": hereinafter, may be simply referred to as "Wikipedia").

The document search unit 133 searches Wikipedia stored in a server (not shown) using each of the one or more terms remaining as a result of the reduction processing as a key, and acquires the Wikipedia page corresponding to each of the one or more terms. You may.

Alternatively, the document group may be, for example, a web page group existing on a specific server. The web page group may be, for example, a set of pages of one or more papers existing on the server of the academic society, a set of pages of one or more patent documents existing on the server of the patent office, or SNS. It may be a set of one or more blog pages existing on the server of, and the type does not matter.

However, the document group is not limited to the server, and may be stored in a local recording medium in the dictionary construction device 1, such as a storage unit 11, a detachable CD-ROM, or a memory card, and its location. And type does not matter.

Further, the document search unit 133 searches a document group using, for example, one or more hypernyms acquired by the extension processing unit 134 described later as a key, and the document corresponding to each of the one or more hypernyms. The process of acquiring the above may be performed once or twice or more.

The expansion processing unit 134 performs expansion processing on one or more terms remaining as a result of the reduction processing by the reduction processing unit 132 by using one or more documents acquired by the document retrieval unit 133. In the expansion process, for each one or more terms remaining as a result of the reduction process, one or more related words related to the term are acquired from the document acquired by the document search unit 133, and the term and one or more related words are acquired. By acquiring a plurality of pairs of and, it is a process of constructing a term dictionary containing only terms belonging to a predetermined class and related words without including terms not belonging to a predetermined class.

The term dictionary may include, for example, one or more of the synonym dictionaries described later or the hypernym dictionaries described later. The term dictionary may be, for example, a single dictionary that also serves as a synonym dictionary and a hypernym dictionary. That is, one or more synonyms and one or more hypernyms may correspond to one term.

Specifically, the expansion processing unit 134 refers to the first term among the one or more terms remaining as a result of the reduction processing, in the first document acquired by the document retrieval unit 133 for the first term. From the information of the predetermined portion, one or more related words related to the first term are acquired.

The predetermined location is a location where related words frequently appear, for example, when the document group is Wikipedia, an article summary described later, a redirect title described later, and the like. However, the location of a predetermined location does not matter.

The expansion processing unit 134 also performs the same processing as above for each of the second and subsequent terms, and acquires one or more related words related to the first term. Then, for each one or more terms, by associating the term with the acquired one or more related words, a plurality of pairs of the terms and one or more related words associated with the terms are acquired. The expansion processing unit 134 acquires a term dictionary having a plurality of pairs of terms and one or more related words associated with the terms acquired in this way, and stores them in, for example, the storage unit 11.

In particular, for each one or more terms remaining in the reduction processing, the expansion processing unit 134 is related to the term from the information of the first predetermined location in the document acquired by the document search unit 133. By acquiring the above synonyms and associating the one or more synonyms with the term, a term dictionary having a plurality of pairs of the term and one or more synonyms associated with the term (for example, a synonym dictionary). It may be called), and the first expansion process of accumulating may be performed.

The predetermined first place is, for example, the part of the article summary in the page (for example, "jawiki-latest-abstract") when the document group is Wikipedia. Alternatively, the first place may be, for example, a description based on a redirect title (for example, "jawiki-latest-redirect.scl", "jawiki-latest-page.skl", etc.), and its location does not matter.

Specifically, the article summary is, for example, a summary of an article related to the term "CPU", "CPU (Central Processing Unit), central processing unit (Chuo Shori Sochi) is the central processing in a computer. "Device (processor).", But the content does not matter.

Specifically, the description based on the redirect title is, for example, "... (transferred from the central processing unit)" based on "(CPU, central processing unit)", but the content does not matter.

For example, the extended processing unit 134 acquires "CPU", "Central Processing Unit", "central processing unit", and "chuo-shori-sochi" as synonyms for the term "CPU" from the above article summary. Further, the expansion processing unit 134 may acquire "central processing unit" as a synonym for "CPU" from the redirect title, for example.

Specifically, for example, a tag that identifies the first location is stored in the storage unit 11. The tag that identifies the first location is, for example, a predetermined array of one or more characters or symbols. Specifically, the tag that specifies the first portion is, for example, the tag "" "" to "." "that specifies the part of the article summary. However, the tag that specifies the first location may be, for example, "[bbb]" or "$ ccc_", and its format does not matter. Alternatively, the tag that identifies the first location may be, for example, a flag indicating whether the article title is a redirect title (for example, "1" indicating that the article title is a redirect title, or "0" indicating that the article title is not a redirect title). Good. The expansion processing unit 134 acquires one or more synonyms from the first location specified by the above tag in the acquired document.

The extended processing unit 134 acquires an article summary from the acquired document by using, for example, the tags "" "" to "." ". Then, the extension processing unit 134 performs morphological analysis on the acquired article summary, identifies one or more nouns, and excludes the term (that is, the article title) from the specified one or more nouns. The above noun may be acquired as a synonym for the term.

Alternatively, in the article summary, for each of the term and one or more synonyms thereof, for example, a predetermined tag (for example, a pair of tags "'''" and "'''" sandwiching the term or the like, etc. ) Is attached, and such a tag is also stored in the storage unit 11, and the expansion processing unit 134 may acquire one or more terms specified by the tag. For example, in the above article summary, a pair of tags "'''" and "'''" are associated with each of the "CPU" and the "central processing unit", and the expansion processing unit 134 has the pair of tags. You may acquire the "CPU" associated with the "CPU" and the "central processing unit" associated with the pair of tags. However, the type of pair of tags does not matter. Then, the expansion processing unit 134 acquires each of the acquired one or more terms other than the acquired term as a synonym for the term.

Further, the expansion processing unit 134 may acquire one or more terms included in the portion between "(" and ")" immediately after each of the acquired one or more words as synonyms. Good. For example, when the part between "(" and ")" contains one or more predetermined symbols (for example, a punctuation mark "," or a space "_"), the extension processing unit 134 may acquire each character string included in two or more sections separated by the symbol as a synonym.

In addition, for example, a predetermined array of characters or symbols (for example, a clue phrase such as "English:") is stored in the storage unit 11, and is sandwiched between "(" and ")". When such an array is included, the expansion processing unit 134 may acquire a character string specified by the array (for example, "Central Processing Unit" following the clue phrase "English:").

However, the sequence serving as a clue phrase may be, for example, "[[English]]:" or "{{language-en-short | *******}}", and the format is not limited. In the former case, the expansion processing unit 134 may acquire, for example, the character string of the part sandwiched between the array "[[English]]:" and the latest ")" or "," as synonyms. In the latter case, the expansion processing unit 134 may acquire, for example, the part of "*****" constituting the array "{{language-en-short | ***}}" as a synonym. Good.

In this way, from the above article summary, "CPC", "Central Processing Unit", "Central processing unit", and "Chuo-shori-sochi" are acquired as synonyms for the term "CPU".

Alternatively, for example, the storage unit 11 stores a predetermined condition regarding the end of the sentence following the article summary, and the extension processing unit 134 determines whether or not the end of the sentence following the article summary satisfies the condition. If it is determined that the condition is satisfied, the noun included at the end may be acquired as a synonym.

Specifically, for example, the predetermined condition may be, for example, the condition that "the end of the sentence following the article summary is" a predetermined sentence end including a noun "". "A predetermined sentence end including a noun". Is, for example, "also called XX." Or "abbreviation is XX.", And if the end of the sentence following the article summary satisfies the condition, the extension processing unit 134 is synonymous with "XX". It may be acquired as a word.

Specifically, for example, the article summary regarding the term "minidisc" is "a minidisc is ... a medium.", Followed by the sentence "abbreviation is MD." If so, the expansion processing unit 134 may determine that the condition of the predetermined condition is satisfied, and may acquire "MD" and "MD" as synonyms from the sentence. From the article summary, "minidisc" and "MiniDisc" are obtained as synonyms in the same procedure as described above.

Further, the extension processing unit 134 is included in the redirect title corresponding to the article title when, for example, referring to the flag attached to the article title corresponding to the term and indicating that the flag is the redirect title. The term of the transfer source may be acquired as a synonym for the term. As a result, "central processing unit" is acquired as a synonym for the term "CPU" from the description based on the redirect title.

Further, the expansion processing unit 134, for example, for each of the one or more terms remaining in the reduction processing, is related to the term from the information of the second predetermined position in the document acquired by the document search unit 133. By acquiring the above hypernyms and associating the one or more hypernyms with the terms, a term dictionary having a plurality of pairs of the terms and one or more hypernyms associated with the terms (for example, a hypernym dictionary). It may be called), and the second expansion process of accumulating may be performed.

The predetermined second place is, for example, when the document group is Wikipedia, category data (for example, “jawiki-latest-category.skl”) or category link information (for example, “jawiki-latest-categorylinks.skl”). "), But its location does not matter. Category data is information about the category of an article. For example, an article with the term "CPU" includes the category data "CPU". Then, the category link information "computer architecture | computer mechanism | hardware" corresponds to this category data "CPU".

Specifically, for example, a tag for specifying the second location is stored in the storage unit 11. The tag that identifies the second location is, for example, a predetermined array of one or more characters or symbols. Specifically, the tag that specifies the second location may be, for example, "Category:". However, the tag that specifies the second location may be, for example, "<ddd>", "[eee]", "$ fff_", or the like, and its format does not matter. The extension processing unit 134 identifies the second place in the acquired document by using such a tag, and acquires the hypernym from the information of the second place. As a result, the "CPU" following the tag "Category:" is acquired as category data, and the category link information "computer architecture | computer mechanism | hardware" corresponding to this "CPU" is acquired.

For example, the expansion processing unit 134 acquires "computer architecture" and "hardware" as hypernyms of the term "CPU" from the above category data. Specifically, the extended processing unit 134 first extracts three terms, for example, "computer architecture", "computer mechanism", and "hardware" from the above category data, and each term is stored in the initial term storage unit 111. Determine if it is stored. Then, the expansion processing unit 134 acquires only the term determined to be stored in the initial term storage unit 111 as a hypernym, and does not acquire the term determined to be not stored.

Here, for example, two terms "computer architecture" and "hardware" are stored, and "computer mechanism" is not stored. Therefore, the extension processing unit 134 stores "computer architecture" and "hardware". Acquire "ware" as a hypernym. However, it is not essential to determine whether or not each term is stored in the initial term storage unit 111, and the expansion processing unit 134 may acquire, for example, all the terms included in the category data.

The expansion processing unit 134 acquires, for example, one or more subordinate words related to the term from the documents acquired by the document search unit 133 for each of the one or more terms remaining in the reduction processing, and the one By associating the above hyponyms with the terms, the hypernym dictionary acquired by the second expansion process may be further expanded. That is, the hypernym dictionary may also include a term and a set of one or more hyponyms.

Hyponyms obtained from a document explaining a term may be, for example, a term containing the term or a term containing a synonym for the term. Specifically, for example, when the document includes the term "CPU socket" including the term "CPU" and the term "microprocessor" including the synonym "processor" of the term "CPU", it is extended. The processing unit 134 may acquire the two terms "CPU socket" and "microprocessor" as subordinate terms from the document. Alternatively, for example, "○○" may be acquired as a subordinate word from a sentence such as "for example, ○○." Following the article summary. In this way, a plurality of pairs of terms and one or more subordinate words are acquired, and the extension processing unit 134 constructs a term dictionary (for example, may be called a subordinate word dictionary) including the acquired plurality of pairs.

However, since the relationship between the hypernym and the hyponym is relative, for example, it may be considered that the above-mentioned hypernym dictionary is a hyponym dictionary or also serves as a hyponym dictionary. In that case, it is not necessary to acquire the subordinate words from the acquired document.

The expansion process by the expansion processing unit 134 is usually performed after the reduction processing by the reduction processing unit 132, but the reduction processing may be performed after the expansion processing. However, it is preferable to perform the expansion process after the reduction process because the processing speed is high.

The control unit 135 controls that the processing of the document retrieval unit 133 and the second expansion processing of the expansion processing unit 134 are performed once or twice or more. The control unit 135 repeatedly executes the search process of the document search unit 133 and the second expansion process of the extension processing unit 134 until, for example, a predetermined stop condition is satisfied. The predetermined stop condition may be, for example, "the number of times the search and the second extension process are executed has reached the predetermined number of times". Alternatively, the stop condition may be, for example, "the document could not be acquired by the search or the hypernym could not be acquired by the second extension process".

It is particularly preferable that the stop condition is, for example, "the hypernym has been acquired by the second extension process". That is, the control unit 135 processes and expands the document search unit 133 until, for example, the term acquired by the second expansion process of the extension processing unit 134 becomes one of the top-level terms included in the top-level terminology. It is preferable to control the processing unit 134 so as to repeat the second expansion process.

Specifically, for example, in response to the expansion processing unit 134 acquiring one or two or more hypernyms with respect to one hypernym, the control unit 135 receives the acquired one or more hypernyms. It is determined whether or not it is stored in the uppermost glossary storage unit 112, and if it is determined that it is not stored, the search process by the document search unit 133 and the second acquisition process by the extension processing unit 134 are executed again. When it is determined that the document is stored, the search process by the document search unit 133 and the second acquisition process by the extension processing unit 134 are stopped.

Specifically, for example, in response to the expansion processing unit 134 acquiring the two hypernyms "computer architecture" and "hardware" of the term "CPU", the control unit 135 of the two hypernyms Determine if the hypernym is included in it. For example, if the top-level terms are "business science", "engineering", "economics", "archeology", "computer science", and "dentistry" mentioned above, the discrimination result here is NO. , The control unit 135 causes the document search unit 133 to execute the search process and the extension processing unit 134 to execute the second acquisition process again. As a result, for example, the page of "hardware" is acquired, and the hypernym "computer" is acquired from the category data "computer | ..." corresponding to the category data "hardware" included therein.

In response to the acquisition of the hypernym "computer" of the hypernym "hardware" in this way, the control unit 135 determines whether or not the acquired hypernym is the hypernym. The determination result here is also NO, and the search process by the document search unit 133 and the second acquisition process by the extended processing unit 134 are executed again. As a result, the page of "computer" is acquired, and the higher-level word "computer science" is acquired from the category data "computer science | ..." corresponding to the category data "computer" included therein.

In response to the acquisition of the hypernym "computer science" of the hypernym "computer" in this way, the control unit 135 determines whether or not the acquired hypernym is the hypernym. The determination result here is YES, and the control unit 135 stops the search process by the document search unit 133 and the second acquisition process by the extension processing unit 134.

In this way, for the term "CPU", one or more hypernyms "hardware", "computer", and "computer science" leading to the hypernym are acquired.

The output unit 14 outputs various information. The various types of information are, for example, a term dictionary. The output unit 14 usually stores the term dictionary in the storage unit 11 or a detachable recording medium. Further, the output unit 14 transmits the term dictionary stored in the storage unit 11 or the like to, for example, the map creation device 2. However, the output unit 14 may display information such as a term dictionary on a display, deliver it to another program, or transmit it to another device, regardless of the output mode.

The other device may be, for example, a terminal device that has transmitted a transmission instruction of a term dictionary. That is, the reception unit 12 may receive the transmission instruction of the term dictionary in pair with the terminal identifier, and the output unit 14 may transmit the term dictionary to the terminal device identified by the received terminal identifier.

The map storage unit 21 that constitutes the map creation device 2 can store various types of information. The various types of information are, for example, a term dictionary.

The term dictionary storage unit 211 usually stores a term dictionary configured by the dictionary construction device 1. The stored term dictionary is, for example, the one received from the dictionary construction device 1 by the map reception unit 22, but may be read from the recording medium. However, the term dictionary may be stored in the term dictionary storage unit 211 in advance.

Two or more patent information is stored in the patent information storage unit 212. The patent information storage unit 212 is usually located inside the map creating device 1, but may be located outside. Patent information is information about a patent. The patent information is, for example, a patent document such as a published patent gazette, a patent gazette, or a utility model gazette. Patent information such as published patent gazettes is received from, for example, a server of the Japan Patent Office, but may be received from another server or read from a recording medium. However, the patent information may be, for example, a non-patent document such as a published technical report, and the type of information is not limited as long as it is information related to a patent. In addition, the provider of patent information does not matter.

Patent information includes, for example, one or more pieces of information such as a specification, claims, and abstract. Further, the patent information may include, for example, bibliographic information in which the name or name of the applicant, the name of the inventor, and the like are written. When the applicant is a company, it goes without saying that the name of the applicant included in the bibliographic information is the above-mentioned company name.

The map reception unit 22 receives various types of information. The various types of information are, for example, various instructions such as a map creation instruction. Further, the map reception unit 22 may accept, for example, a term designation, an axis selection, and the like together with a map creation instruction. The designation of terms, selection of axes, etc. will be described later. The map reception unit 22 receives various types of information via an input device such as a keyboard, for example. The map reception unit 22 may receive a map creation instruction from, for example, a terminal device (not shown) in pairs with the terminal identifier. Further, the map reception unit 22 may, for example, receive the term dictionary from the dictionary construction device 1 or read it from the recording medium. The type of information received by the map reception unit 22 and the mode of reception are not limited.

The map processing unit 23 performs various processes. The various processes are, for example, processes of the term acquisition unit 231, the term summary upper part 232, the related word correspondence unit 233, the map configuration unit 234, and the like. In addition, the map processing unit 23 also performs processing such as various determinations described in the flowchart.

The term acquisition unit 231 acquires terms from each of two or more patent information stored in the patent information storage unit 212. The term obtained is usually a term that belongs to a predetermined class. The predetermined class is, for example, a class of technical terms, but may be a class of a company name, a class of an inventor name, or any class. As a result, two or more terms belonging to a predetermined class are acquired.

The acquired term may be, for example, a related word (for example, a subordinate word) of the term specified at the time of receiving the map creation instruction. That is, the term acquisition unit 231 uses, for example, the term dictionary stored in the term dictionary storage unit 211, and is related to the designated terms from the two or more patent information stored in the patent information storage unit 212. You may get the word. As a result, two or more related words of the specified term, which are terms belonging to the predetermined class, are acquired.

It is preferable that terms belonging to the class of technical terms are obtained from information belonging to one or more items of patent documents such as published patent gazettes, particularly "abstract" or "claims". However, it may be obtained from the full text including the "statement". Alternatively, the term belonging to the technical term class may be acquired from the information belonging to "Abstract" of the treatise, for example, and the acquisition source does not matter.

The term belonging to the company name class or the inventor name class is obtained from, for example, the bibliographic information of the patent document, but may be obtained from the information such as the author name and affiliation following the title of the treatise, and the acquisition source thereof. Does not matter.

Alternatively, the predetermined class may be two or more different classes. The term acquisition unit 231 acquires terms of two or more different classes from, for example, a technical term class, a company name class, and an inventor name class from each of the two or more stored patent information. Is suitable. The term acquisition unit 231 is of a class of technical terms, for example, from information belonging to one or more items of "abstract" or "claims" for each of two or more stored patent documents. The term to which the term belongs may be acquired, and the term belonging to each class of the company name and the inventor name may be acquired from the "name or name of the applicant" and the "name of the inventor" in the bibliographic information. However, the number and combination of classes does not matter.

The technical terms can be obtained from the abstract or the like by using, for example, a method such as morphological analysis or machine learning (for example, "TermExtract" by Professor Hiroshi Nakagawa of the University of Tokyo). Acquisition of terms by morphological analysis, machine learning, etc. is a known technique, and detailed explanations will be omitted. Regarding this type of technology, for example, "Extraction of technical terms from patent documents by deep learning" (Keisuke Iwamoto, Japan YEAR BOOK 2017, p.242-246), "Extraction of semi-supervised terms using Web documents" ( It is described in Mitsumasa Kondo et al., Proceedings of the 13th Annual Conference of the Natural Language Processing Society, 2007).

The term summary upper part 232 performs a summary process on two or more terms acquired by the term acquisition unit 231. The summarization process is a process of acquiring related words common to each of the two or more terms acquired by the term acquisition unit 231 from the term dictionary stored in the term dictionary storage unit 211. The related word may be a term acquired by the term acquisition unit 231.

The terminology upper part 232 acquires, for example, synonyms common to each of the two or more terms acquired by the term acquisition unit 231 from the synonym dictionary stored in the term dictionary storage unit 211. Alternatively, the terminology upper part 232 may, for example, acquire the hypernym common to each of the two or more acquired terms from the stored hypernym dictionary. In addition, the term summary upper part 232 may acquire, for example, a synonym and a hypernym.

For example, the term summary upper part 232 may perform a summary process for each of two or more different classes to acquire a plurality of pairs of class identifiers and related words.

The related word correspondence part 233 is a term corresponding to the related word acquired by the upper part 232 of the term summary, and the original two or more patent information and the term from which each of the two or more terms acquired by the term acquisition unit 231 was acquired. Corresponds to the related words acquired by the upper part 232 of the summary.

The related word correspondence unit 233 is, for example, a term corresponding to the related word acquired by the upper part 232 of the term summary for each of two or more different classes, and each of the two or more terms acquired by the term acquisition unit 231 is acquired. The original two or more patent information may be associated with the related words acquired by the upper part 232 of the glossary.

The map configuration unit 234 configures a map in which related words and two or more patent-related information related to each of the original two or more patent information are associated with each of one or more different classes. The patent-related information includes the patent number (including the publication number), calendar year (for example, filing date or publication date), company name, inventor name, etc. of each of the two or more original patent information from which the term was acquired. Therefore, the two or more patent-related information to be acquired is, for example, a set of two or more patent numbers, a set of two or more calendar years, a set of two or more company names, a set of two or more inventor names, and the like. , The number of occurrences of the related word may be used, the number of original patent information paired with the related word may be used, or the frequency of occurrence of the related word may be used. Any information can be used.

The frequency of appearance of one related word may be, for example, a value obtained by dividing the number of occurrences of the related word by the total number of stored patent information, or the original patent information paired with the one related word. It may be a value obtained by dividing the number of patent information by the total number of stored patent information. However, the denominator of the frequency of appearance is not limited to the total number of stored patent information, and may be, for example, the total number of words or the total number of pages of one or more stored patent information. Absent.

Alternatively, the patent-related information may be, for example, the importance of the related word. The map configuration unit 234 provides information such as, for example, the number of original patent information paired with one related word, the number of occurrences of the term corresponding to the related word in each patent information, the total number of stored patent information, and the like. It may be acquired, and based on the acquired information, the importance of the related word may be acquired by using an algorithm such as tf-idf.

The map is, for example, a two-dimensional map. The two-dimensional map referred to in this embodiment is a map having two axes on which terms of different classes are arranged. In a two-dimensional map, for example, two or more technical terms are arranged on one of the horizontal axis or the vertical axis, and two or more company names are arranged on the other, and the positions corresponding to one technical term and one company name are arranged. , It may be a map in which figures (for example, circles) having a size corresponding to the number of original patent information are arranged.

However, the map may be a map having three or more dimensions. A three-dimensional or higher map is a map having three or more axes on which terms of different classes are arranged. For example, a three-dimensional map has two or more technical terms on one of the horizontal, vertical, or height axes, and two or more companies on the other. Place the name, place two or more calendar years on the other axis, and place one technical term, one company name, and one calendar year in a position corresponding to the number of original patent information. It may be a map in which the figures of are arranged.

The direction of each axis, the class of terms arranged on each axis, and the type of information represented by the figure do not matter.

Further, it is preferable that two or more terms arranged on one axis are arranged in an order according to, for example, frequency of appearance or importance. For example, when two or more technical terms are arranged on the vertical axis and two or more company names are arranged on the horizontal axis, the map configuration unit 234 selects two or more technical terms with the highest frequency or importance. As the highest position, from top to bottom in descending order of frequency of appearance or importance, and with two or more company names, the one with the highest frequency of appearance is the leftmost position, and the one with the highest frequency of appearance is on the left in descending order of frequency of appearance. You may line up from to the right. However, the relationship between the frequency of appearance and the direction of the arrangement may be opposite to the above.

Further, the two or more terms arranged on one axis may be, for example, two or more subordinate words that are paired with a term designated by a person. That is, for example, the map reception unit 22 accepts the designation of one term (for example, "hardware") via an input device such as a keyboard, and the map configuration unit 234 is stored in the term dictionary storage unit 211. Using a term dictionary, two or more hyponyms that are paired with the one accepted term (for example, hyponyms such as "processor", "storage device", and "firmware" that are paired with "hardware"). And the two or more subordinate words may be arranged on the one axis. At that time, it is preferable that the map constituent unit 234 arranges the two or more subordinate words in an order according to their occurrence frequency or importance.

A map of 4 dimensions or more is a map in a virtual space of 4 dimensions or more. For example, by selecting 3 or less axes out of 4 or more axes, the map is converted into a map in a real space of 3 dimensions or less. Is output.

The map output unit 24 outputs related words in association with two or more patent-related information related to each of the two or more original patent information.

The map output unit 24 normally outputs a map configured by the map configuration unit 234. However, when a map having four or more dimensions is configured, the map output unit 24 may output, for example, a map having three or less dimensions selected from four or more axes and having three or less axes. The selection of the output axis is usually performed according to a person's instruction, but it may be performed automatically.

The map output unit 24 may output, for example, a set of related words and one or more patent numbers. That is, the information output by the map output unit 24 may be one-dimensional, and it is not essential that the map has two or more dimensions.

Further, in the map configured by the map configuration unit 234, when the number of terms arranged on one axis exceeds a predetermined number (hereinafter, default number: for example, 7 or 10). , The map output unit 24 performs exclusion processing excluding the number of terms corresponding to the excess amount exceeding the specified number from the two or more terms arranged on the one axis.

Specifically, for example, two or more pairs of axis identifiers that identify axes and a specified number (for example, {vertical axis, 7 pieces}, {horizontal axis, 10 pieces}, etc.) are stored in the map storage unit 21. The term map configuration unit 234 acquires the number of terms arranged on the axis for each of two or more axis identifiers, and the acquired number exceeds the default number paired with the axis identifier. It is determined whether or not the axis is present, and the removal process is performed on the axis for which it is determined whether or not the number exceeds the predetermined number. As a result, a map in which a predetermined number or less of terms are arranged on each of two or more axes (for example, 7 technical terms are arranged on the vertical axis and 10 company names are arranged on the horizontal axis). (Two-dimensional map, etc.) is output.

When performing the exclusion process as described above, it is preferable that the map output unit 24 removes the terms in order from, for example, the terms having a low appearance frequency or importance. As a result, a map is output in which a predetermined number or less of terms are arranged in order of appearance frequency or importance on each of the two or more axes.

The map output unit 24 normally outputs the map configured by the map configuration unit 234 via a display, but it can be printed out by a printer, stored in a recording medium, handed over to another program, or another device. It may be transmitted to, and the mode of its output does not matter.

The other device may be, for example, a terminal device that has transmitted a map output instruction. That is, the map reception unit 22 may receive a map output instruction in pairs with the terminal identifier, and the output unit 14 may transmit the map to the terminal device identified by the received terminal identifier.

The storage unit 11, the initial glossary storage unit 111, the top-level glossary storage unit 112, the map storage unit 21, the term dictionary storage unit 211, and the patent information storage unit 212 are non-volatile recording media such as a hard disk and a flash memory. Is preferable, but it can also be realized with a volatile recording medium such as RAM.

The process in which the information is stored in the storage unit 11 or the like does not matter. For example, information may be stored in the storage unit 11 or the like via a recording medium, or information transmitted via a network, a communication line, or the like may be stored in the storage unit 11 or the like. Well, or the information input via the input device may be stored in the storage unit 11 or the like. The input device may be, for example, a keyboard, a mouse, a touch panel, or the like.

The reception unit 12 and the map reception unit 22 may or may not include the input device. The reception unit 12 and the like can be realized by the driver software of the input device or by the input device and its driver software.

Processing unit 13, term classification unit 131, reduction processing unit 132, document search unit 133, expansion processing unit 134, control unit 135, map processing unit 23, term acquisition unit 231, term summary upper part 232, related word correspondence unit 233, And the map configuration unit 234 can usually be realized from an MPU, a memory, or the like. The processing procedure of the processing unit 13 and the like is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, the processing procedure may be realized by hardware (dedicated circuit).

The output unit 14 and the map output unit 24 may or may not include output devices such as displays and speakers. The output unit 14 and the like can be realized by the driver software of the output device, or by the output device and its driver software.

Next, the operation of the information system A will be described with reference to the flowcharts of FIGS. 2 to 6. 2 and 3 are flowcharts for explaining the operation of the dictionary construction device 1. FIG. 2 mainly shows the reduction process which is a part of the operation, and FIG. 3 mainly shows the search / expansion process which is another part of the operation. In the flowcharts of FIGS. 2 and 3, the output of the term dictionary by the output unit 14 is usually transmission to the map creation device 2.

(Step S201) The processing unit 13 determines whether or not to construct a term dictionary. For example, when the reception unit 12 receives an instruction to create a term dictionary, the processing unit 13 determines that the term dictionary is to be constructed. Alternatively, for example, the storage unit 11 stores timing information regarding the timing for constructing the term dictionary, and the processing unit 13 indicates the current time acquired from the built-in clock of the MPU, the NTP server, or the like. If it matches the timing, it may be judged that the dictionary is constructed. The timing information includes, for example, a cycle such as "9:00 am on the first day of every month", but may be a set of one or two or more times such as "17:00 on August 1, 2019".

If it is determined that the term dictionary is to be constructed, the process proceeds to step S202, and if it is determined that the dictionary is not to be constructed, the process proceeds to step S217.

(Step S202) The term classification unit 131 sets the initial value 1 in the variable i. The variable i is a variable for sequentially selecting unselected terms from the two or more terms stored in the initial glossary storage unit 111.

(Step S203) The term classification unit 131 determines whether or not there is an i-th term. If it is determined that the i-th term exists, the process proceeds to step S204, and if it is determined that there is no term, the process proceeds to step S207.

(Step S204) The term classification unit 131 determines whether the i-th term belongs to a predetermined class or does not belong to a predetermined class. The predetermined class is, for example, a "technical term class", but may be a "company name class" or an "inventor name class". If it is determined that the i-th term belongs to a predetermined class, the process proceeds to step S206, and if it is determined that the term does not belong to the predetermined class, the process proceeds to step S205.

(Step S205) The reduction processing unit 132 performs reduction processing excluding the i-th term among the two or more terms stored in the initial terminology storage unit 111.

(Step S206) The term classification unit 131 increments the variable i. After that, the process returns to step S213.

(Step S207) The document retrieval unit 133 sets the initial value 1 in the variable j. The variable j is a variable for sequentially selecting unselected terms from the one or more terms remaining as a result of the reduction processing in step S205.

(Step S208) The document retrieval unit 133 determines whether or not there is a j-th term. If it is determined that there is a j-th term, the process proceeds to step S209, and if it is determined that there is no term, the process proceeds to step S214.

(Step S209) The document search unit 133 searches the document group using the j-th term as a key, and acquires the document corresponding to the j-th term.

(Step S210) The expansion processing unit 134 acquires related words from a predetermined portion of the document acquired in step S209.

(Step S211) The expansion processing unit 134 determines whether or not one or more related words have been acquired in step S210. If it is determined in step S210 that one or more related words have been acquired, the process proceeds to step S212, and if it is determined that the related words have not been acquired, the process proceeds to step S213.

(Step S212) The expansion processing unit 134 associates the j-th term with one or more related words acquired in step S210, and acquires a set of the term and one or more related words.

(Step S213) The expansion processing unit 134 increments the variable j. Then, the process returns to step S208.

(Step S214) The expansion processing unit 134 determines whether or not a set has been acquired. If it is determined that the pair has been acquired, the process proceeds to step S215, and if it is determined that the pair has not been acquired, the process returns to step S201.

(Step S215) The expansion processing unit 134 acquires a term dictionary having the acquired set.

(Step S216) The expansion processing unit 134 stores the term dictionary acquired in step S215 in, for example, the storage unit 11. Then, the process returns to step S201.

(Step S217) The processing unit 13 determines whether or not to transmit the stored term dictionary to the map creation device 2. For example, when the reception unit 12 receives the transmission instruction of the term dictionary, the processing unit 13 determines that the term dictionary is transmitted to the map creation device 2. Alternatively, for example, the map processing unit 23 may determine that the stored term dictionary is transmitted to the map creation device 2 in response to the accumulation of the term dictionary in step S216. If it is determined that the stored term dictionary is transmitted to the map creation device 2, the process proceeds to step S218, and if it is determined that the stored term dictionary is not transmitted, the process returns to step S201.

(Step S218) The output unit 14 transmits the stored term dictionary to the map creation device 2. Then, the process returns to step 201.

In the flowcharts of FIGS. 2 and 3, the process starts when the power of the dictionary construction device 1 is turned on or the program is started, and the process ends when the power is turned off or an interrupt for the end of the process occurs. However, the trigger for the start or end of processing does not matter.

Further, in the flowcharts of FIGS. 2 and 3, the two steps S217 and S218 may be omitted. That is, if NO in step S201, the process may return to step S201.

Further, in the flowcharts of FIGS. 2 and 3, the processing of steps S203 to S206 is, for example, for each of two or more classes of "technical term class", "company name class", and "inventor name class". May be executed.

Further, in the flowcharts of FIGS. 2 and 3, the type of term dictionary constructed does not matter. For example, when a synonym dictionary is constructed, "term dictionary" should be read as "synonymous dictionary", "predetermined part of the document" should be read as "predetermined first part of the document", and " "Related word" should be read as "synonymous word".

Similarly, when a hypernym dictionary is constructed, "term dictionary" should be read as "hypernym dictionary", and "predetermined part of the document" should be read as "predetermined second part of the document". "Related words" should be read as "hypernyms".

However, the search / extension process for constructing the hypernym dictionary may be performed recursively, for example, as shown in FIG. FIG. 4 is a flowchart illustrating an example of search / extension processing when constructing a hypernym dictionary.

In the flowchart of FIG. 3, in the flowchart of FIG. 3, steps S209 to S212 are replaced with steps S208a, steps S214 to S216 are replaced with steps S216a, and in step S208, if YES, the process proceeds to step S209, and NO. In the case of, it is changed so as to proceed to step S216a.

(Step S208a) The document retrieval unit 133 and the extension processing unit 134 recursively perform hypernym association using the j-th term. The hypernym correspondence using the j-th term will be described with reference to the flowchart of FIG.

(Step S216a) The extension processing unit 134 stores, for example, the hypernym dictionary acquired by recursively executing the hypernym association in step S208a in the storage unit 11. Then, the process returns to step S201.

FIG. 5 is a flowchart illustrating hypernym correspondence using the j-th term.

(Step S501) The document search unit 133 searches the document group using the j-th term as a key, and acquires the document corresponding to the j-th term.

(Step S502) The expansion processing unit 134 acquires a hypernym from a predetermined second location of the document acquired in step S501.

(Step S503) The expansion processing unit 134 determines whether or not one or more hypernyms have been acquired in step S502. If it is determined in step S502 that one or more higher-order words have been acquired, the process proceeds to step S504, and if it is determined that the higher-order words have not been acquired, the process returns to the higher-level processing.

(Step S504) The control unit 135 sets the initial value 1 in the variable k. The variable k is a variable for sequentially selecting unselected terms from the one or more acquired terms in step S502.

(Step S505) The control unit 135 determines whether or not there is a k-th term. If it is determined that the k-th term exists, the process proceeds to step S506, and if it is determined that the term does not exist, the process returns to higher-level processing.

(Step S506) The expansion processing unit 134 associates the j-th term with the k-th term and stores them in, for example, the internal memory of the CPU.

(Step S507) The control unit 135 determines whether or not the k-th term is the hypernym. When the k-th term matches any of the hypernyms stored in the top-level glossary storage unit 112, the control unit 135 determines that the k-th term is the top-level word. If it is determined that the k-th term is the hypernym, the process proceeds to step S509, and if it is determined that the term is not the hypernym, the process proceeds to step S508.

(Step S508) The control unit 135 performs hypernym association using the kth term. The hypernym association using the k-th term is a recursive process of the hypernym association using the j-th term.

(Step S509) The control unit 135 increments the variable k. Then, the process returns to step S505.

FIG. 6 is a flowchart illustrating the operation of the map creating device 2. In this flowchart, the reception of the term dictionary by the map reception unit 22 is usually reception from the dictionary construction device 1.

(Step S601) The map processing unit 23 determines whether or not the map receiving unit 22 has received the term dictionary from the dictionary construction device 1. If it is determined that the map reception unit 22 has received the term dictionary from the dictionary construction device 1, the process proceeds to step S602, and if it is determined that the term dictionary has not been received, the process proceeds to step S603.

(Step S602) The map processing unit 23 stores the term dictionary received in step S601 in the term dictionary storage unit 211. Then, the process returns to step S601.

(Step S603) The map processing unit 23 determines whether or not to create a map. For example, when the map receiving unit 22 receives the map creation instruction, the map processing unit 23 determines that the map is created. Alternatively, for example, the map processing unit 23 may determine that the map is created according to the fact that the term dictionary is received in step S601 or the term dictionary is accumulated in step S602. If it is determined that the map is to be created, the process proceeds to step S604, and if it is determined that the map is not created, the process proceeds to step S609.

(Step S604) The term acquisition unit 231 acquires terms from each of two or more patent information stored in the patent information storage unit 212.

(Step S605) The term summary upper portion 232 acquires related words common to each of the two or more terms acquired in step S604 from the term dictionary stored in the term dictionary storage unit 211.

(Step S606) The related word correspondence unit 233 associates the original two or more patent information for which the term was acquired in step S604 with the related word acquired in step S605.

(Step S607) The map configuration unit 234 associates the related words acquired in step S605 with two or more patent-related information related to each of the two or more original patent information from which the terms were acquired in step S604. Configure the map.

(Step S608) The map configuration unit 234 stores the map configured in step S607 in, for example, the map storage unit 21. Then, the process returns to step S601.

(Step S609) The map processing unit 23 determines whether or not to output the map. For example, when the map receiving unit 22 receives the map output instruction, the map processing unit 23 determines that the map is output. Alternatively, for example, the map processing unit 23 may determine that the map is output depending on whether the map is configured in step S607 or the map is accumulated in step S608. If it is determined that the map is to be output, the process proceeds to step S610, and if it is determined that the map is not output, the process returns to step S601.

(Step S610) The map output unit 24 outputs the map stored in the map storage unit 21 via an output device such as a display. Then, the process returns to step S601.

In the flowchart of FIG. 5, the process starts when the power of the map creation device 2 is turned on or the program is started, and the process ends when the power is turned off or the process ends. However, the trigger for the start or end of processing does not matter.

Further, in the flowchart of FIG. 5, the two steps S501 and S502 may be omitted.

Hereinafter, a specific operation example of the information system A in the present embodiment will be described. The following description can be changed in various ways and does not limit the scope of the present invention.

In this example, the document group is Wikipedia, and Wikipedia is stored in a server (not shown).

The storage unit 11 of the dictionary construction device 1 stores information that a predetermined class is a "class of technical terms". The predetermined class may be changed to, for example, a "company name class" or an "inventor name class" according to a person's instruction.

Further, the storage unit 11 also stores a tag for specifying the page, a tag for specifying the first place, a tag for specifying the second place, and the like. The tag for specifying the page is "<page>, </ page>". The first place is an article summary, a redirect title, etc., and the tag that identifies the first place is ""'''" to". "" That specifies the article summary, a flag that indicates whether or not it is a redirect title, and the like. .. The second place is category data, category link information, etc., and the tag that specifies the second place is, for example, "Category:".

Further, in the storage unit 11, for example, an unnecessary word group as shown in FIG. 7 and a sentence end group as shown in FIG. 8 are also stored. The unnecessary word group includes "novel", "TV drama", "music unit" and the like. The sentence end group is, for example, ".", "Is.", "One of.", "One of.", "One of.", "One of.", ". , "It's about.", "Members of.", Etc. are included.

The initial terminology storage unit 111 stores all Wikipedia article titles, for example, as shown in FIG. All article titles include terms such as "CPU", "central processing unit", "processing unit", "minidisc", and "endless story".

The top-level terminology storage unit 112 stores, for example, the top-level terminology as shown in FIG. In Wikipedia, each one or more top-level terms that make up the top-level glossary are subcategories of "major categories", "classification by subject", and further subcategories, "natural science" and "social science". It is a term that belongs to "humanities" and the like. The top-level glossary in this example is, for example, "business science", "engineering", "economics", "archeology", "computer science" (in this example, it may be referred to as "computer engineering"), And includes "dentistry" and the like.

For example, a map template is stored in the map storage unit 21 of the map creation device 2. The template is information about the composition of the map. The template includes, for example, information about the directions of the two or more axes that make up the map, and the arrangement of the two or more terms on each axis. However, the data structure of the template does not matter.

The term dictionary storage unit 211 stores a term dictionary (in this example, a synonym dictionary and a hypernym dictionary) constructed by the dictionary construction device 1. Two or more patent documents (for example, JP-A-2017-aaaa, JP-A-2010-bbbb, etc.) are stored in the patent information storage unit 212.

When the reception unit 12 receives an instruction to create a terminology dictionary via an input device such as a keyboard in the dictionary construction device 1, the processing unit 13 stores a copy of the initial terminology stored in the initial terminology storage unit 111. For each of the two or more terms (article titles) generated in the section 11 and constituting the initial glossary, the term belongs to the "technical term class" which is a predetermined class. Performs a determination process to determine whether the term is a term or a term that does not belong to the "class of technical terms".

The determination process in this example is a process of determining whether or not each term is an unnecessary word by using an unnecessary word group and a tail group. Specifically, the term classification unit 131 acquires an article summary of a page explaining the term for each one or more stored article titles (terms), and the acquired article summary is "" unnecessary word "+. It is determined whether or not the article ends with "end of sentence", and if it ends with "" unnecessary word "+" end of sentence "", the article title corresponding to the article summary is determined as an unnecessary word.

The term classification unit 131 is, for example, regarding the article title "CPU", the article summary "CPU (CPU (Central Processing Unit)" specified by the tags "'''" to ".", And the central processing unit (Chu). The article acquires the central processing unit (processor) in the computer, and determines whether or not the "CPU" is an unnecessary word. Since the article summary of "CPU" does not end with "" unnecessary word "+" end of sentence "", the term classification unit 131 determines that "CPU" is not an unnecessary word.

Similarly, the article titles "central processing unit", "processing unit", and "minidisc" are also judged to be not unnecessary words. However, regarding the article title "Hatenai Monogatari", the corresponding article summary ""'''Hatenai Monogatari'''" ... is a novel." Is "" Novel "+" is. "" Since it ends with, it is judged to be an unnecessary word.

In this way, among the above two or more terms, "CPU", "central processing unit", "processing unit", and "minidisc" are determined to belong to the technical term class, and "the endless story". Is determined to be a term that does not belong to the class of technical terms.

When the article summary of the page explaining one term contains two or more sentences, the term classification unit 131 states that, for example, for each of the two or more sentences, the sentence is "" unnecessary word "+" sentence end ". It is determined whether or not it ends with "". Then, for example, when it is determined that all of two or more sentences end with "" unnecessary word "+" end of sentence "", the term classification unit 131 May determine that one term is an unnecessary word, or, for example, when it is determined that at least one sentence ends with "" unnecessary word "+" end of sentence "", the term classification unit 131 may determine that the one term is an unnecessary word, or, for example, the determination result that the term ends with "unnecessary word" + "end of sentence" satisfies a predetermined condition. When a large number is obtained, the term classification unit 131 may determine the one term as an unnecessary word. The predetermined condition ends with, for example, "" unnecessary word "+" end of sentence "". The number of judgment results indicating that the sentence is being performed may be greater than or equal to the threshold value or greater than the threshold value, or the number of judgment results indicating that the sentence ends with "" unnecessary word "+" end of sentence "" is determined by the sentence. The value divided by the number (that is, the number of determinations) may be greater than or equal to the threshold value or greater than or equal to the threshold value.

Next, the reduction processing unit 132 performs reduction processing on the initial glossary copied to the storage unit 11 except for the "endless story" that is determined to be a term that does not belong to the "class of technical terms". Do. As a result, the "CPU", "central processing unit", "processing unit", and "minidisc" remain in the initial terminology of the storage unit 11.

Next, the document search unit 133 searches Wikipedia for each of the one or more terms remaining as a result of the reduction processing using the term as a key, and performs an acquisition process to acquire a document corresponding to the term. The search target is two or more article titles specified by the tags "<page>, </ page>". As a result, for example, the page of "CPU" in Wikipedia is acquired.

Next, the extended processing unit 134 has one or more synonyms for each of the one or more documents acquired by the document retrieval unit 133 from the first part (article summary, sentence immediately after the article summary, redirect title, etc.) of the document. Perform the first extension process to get the word. For example, synonyms such as "central processing unit" are acquired from the article summary (described above) on the acquired "CPU" page.

However, the article summary corresponding to the "CPU" includes, for example, a pair of tags "'''" and "'''" as shown in FIG. 11 and "{{language-en-short | *** | It may have a format including clues such as "*}}". Similarly, the article summary corresponding to the "minidisc" may have, for example, the format shown in FIG. In such a case, the storage unit 11 stores, for example, a group of clues as shown in FIG. A clue phrase group is a set of one or more clue phrases. The clue phrase is, for example, "{{language-en-short | *******}}", "{{language-en | ***}}", and the like.

In addition, the storage unit 11 also stores a group of sentences immediately after summarization, as shown in FIG. 14, for example. Immediately after summarization sentence group is a set of one or more immediately after summarization sentences. The sentence immediately after the summary is the sentence immediately after the article summary. Immediately after the abstract, the sentence is, for example, "*****", "abbreviation is ***.", Etc.

From the article summary of FIG. 11, for example, the expansion processing unit 134 includes a "CPU" sandwiched between a pair of tags "'''" and "'''" and a pair of tags "'''" and "''. Acquire the "central processing unit" sandwiched between "'". Next, the expansion processing unit 134 acquires "CPU" from the portion sandwiched between "(" and ")" immediately after the acquired "CPU", and further, the stored clue phrase "{{language". -En-short | ***}} "is also used to acquire the character string" Central Production Unit "corresponding to the clue phrase" *** ". Next, the expansion processing unit 134 acquires the "chuo-shori-sochi" from the portion sandwiched between the "(" and ")" immediately after the acquired "central processing unit".

Thus, from the article summary of FIG. 11, five synonyms "CPU", "CPU", "Central Production Unit", "Central Processing Unit", and "Chuo Shori Sochi" are obtained. Some of these five synonyms (here, "CPU", "Central Production Unit", and "Chuo Shori Sochi") were not included in the initial glossary. It is a term.

Similarly, the extension processing unit 134 obtains a "mini disk" sandwiched between a pair of tags "'''" and "'''" from the article summary of FIG. 12, and also stores a clue phrase. Using "{{range-en | *******}}", the character string "MiniDisc" corresponding to the clue phrase "*****" is also acquired. Further, the extension processing unit 134 uses the stored sentence immediately after the summary "abbreviation is ********." To correspond to the character string "MD" corresponding to the sentence "*****" immediately after the summary. And the character string "MD" sandwiched between "(" and ")" immediately after the "MD" is also acquired. Some of the acquired synonyms (here, "CPU", "Central Production Unit", and "Chuo Shori Sochi") are terms that were not included in the initial glossary.

In this way, the four synonyms "minidisc", "MiniDisc", "MD", and "MD" are obtained from the article summary of FIG. In addition, some of these four synonyms (here, three words "MiniDisc", "MD", and "MD") are terms that were not included in the initial glossary.

Further, the "central processing unit" is also acquired from the description "... (transferred from the central processing unit)" based on the redirect title "(CPU, central processing unit)" on the "CPU" page.

In acquiring the synonym from the redirect title, the extension processing unit 134 may refer to the table of FIG. 15 constructed from, for example, "jawiki-latest-page.sql" (hereinafter, may be referred to as "Table 1"). , And the table of FIG. 16 (hereinafter, “Table 2”) constructed from “jawiki-latest-redirect.SQL” can be linked to construct the table of FIG. 17 (hereinafter, “Table 3”). Good.

In FIG. 15, “page_id” is a number assigned to each article. “Page_namespace” is information indicating whether the page is an article page or a category page (for example, “0” is an article page and “14” is a category page). “Page_title” is an article title name, a redirect title name, or a category name. “Page_is_redirect” is information indicating whether or not the title is a redirect title (for example, “0” is the article title and “1” is the redirect title). Further, in FIG. 16, “rd_from” is a number associated with “page_id”, and “rd_title” is displayed when the page of “page_id” associated with “rd_from” is searched for by “page_title”. The title of the article.

The table of FIG. 15 is constructed by, for example, the expansion processing unit 134 from “jawiki-latest-page.SQL” and stored in the storage unit 11, but may be pre-built and stored in the storage unit 11. .. Similarly, the table of FIG. 16 is constructed, for example, by the expansion processing unit 134 from “jawiki-latest-redirect.SQL” and stored in the storage unit 11, but even if it is pre-built and stored in the storage unit 11. Good.

When constructing the two tables of FIGS. 15 and 16, for example, the article page of one or more article pages is redirected to "jawiki-latest-redirect.SQL" for each page_title of one or more article pages. Contains page_id for one or more article pages. The extension processing unit 134 uses the "jawiki-latest-redirect.sql" to redirect to the article page of the page_title "CPU", and the page_id of one or more article pages (for example, "47825", "621929"). , Etc.), and the page_id of each acquired article page is accumulated in association with the page_title “CPU” to construct the table of FIG.

Further, for example, "jawiki-latest-page.sql includes a set of pairs of page_id, page_namespace, page_tile, and page_is_redirect. The expansion processing unit 134 includes such" jawiki-date-page.sql. For each page_id of one or more of the acquired article pages, the page_tile corresponding to the page_id of the article page (for example, the "central processing unit" corresponding to "47825" and "621929" corresponding to "621929" Central processing unit "etc.) is acquired. Then, the expansion processing unit 134 stores the page_id of the article page, the page_namespace "0", and the page_is_redirect "1" in the acquired page_title in association with each other.

Further, the expansion processing unit 134 stores the page_id "2387", the page_namespace "0", and the page_is_redirect "0" of the corresponding article page in association with the page_title "CPU". As a result, the table of FIG. 15 is constructed. However, the procedure for constructing the two tables shown in FIGS. 15 and 16 does not matter.

In Wikipedia, if page_name (Table 1) = 0 and page_tile (Table 1) included in the record corresponding to page_is_redirect (Table 1) = 0 is searched, the article of page_tile (Table 1) is displayed. To. On the other hand, when the search is performed by page_tile (Table 1) included in the record corresponding to page_namespace (Table 1) = 0 and page_is_redirect (Table 1) = 0, page_id (Table 1) = rd_from (Table 2). The article of rd_tile (Table 2) included in the record of) is displayed.

Therefore, the expansion processing unit 134 associates two records in which the value of page_id (Table 1) and the value of rd_from (Table 2) match (that is, the column "page_tile" in Table 1 and the value in Table 2 are linked. By associating with the column "rd_tile"), a table (Table 3) which is a set of a set of page_id (Table 1) = rd_from (Table 2), title (word), and page_tile (synonymous word) is constructed. However, the terms (words, synonyms) corresponding to the article titles determined by the term classification unit 131 to be non-terms are usually excluded from Table 3. Then, the expansion processing unit 134 may acquire the constructed table (Table 3) as a term dictionary (synonymous word dictionary).

In addition, the expansion processing unit 134 also performs a second expansion processing for acquiring one or more hypernyms from the category data of the document for each of the acquired one or more documents. For example, one or more of the category data "CPU" in the acquired "CPU" page, and the category data "computer architecture | computer mechanism | hardware" corresponding to the "CPU", such as "hardware". The superordinate word of is acquired.

Next, the control unit 135 determines whether or not the acquired one or more hypernyms include the highest-order word, and the document search unit 133 performs search processing and the extension processing unit 134 continues until the determination result is YES. The second extension process is repeatedly executed. As a result, for the term "CPU", one or more hypernyms "hardware", "computer", and "computer science" leading to the highest-level word are acquired. The process until the hypernym "computer science" is acquired is not repeated because it has been described above.

Next, the expansion processing unit 134 associates one or more acquired synonyms with each of the one or more terms remaining as a result of the reduction processing, and sets a pair of the term and one or more synonyms. get. As a result, for example, a pair of the term "CPU" and one or more synonyms "central processing unit", "central processing unit", and the like is acquired. Then, the expansion processing unit 134 acquires the synonym dictionary having the acquired plurality of sets and stores it in the storage unit 11.

Further, the expansion processing unit 134 associates the acquired one or more hypernyms with each of the remaining one or more terms, and acquires a set of the terms and one or more hypernyms. As a result, for example, a pair of the term "CPU" and one or more hypernyms "hardware", "computer", and "computer science" is acquired. Then, the expansion processing unit 134 also acquires the hypernym dictionary having the acquired plurality of sets and stores it in the storage unit 11.

In acquiring the hypernym from the category data, the extension processing unit 134 may refer to the table of FIG. 18 constructed from, for example, "jawiki-latest-page.sql" (hereinafter, may be referred to as "Table 4"). , And the table of FIG. 19 (hereinafter, “Table 5”) constructed from “jawiki-latest-categorylinks.SQL” can be linked to construct the table of FIG. 20 (hereinafter, “Table 6”). Good.

In FIG. 18, “page_id”, “page_namespace”, and “page_title” are the same information as in FIG. 15 described above. Further, in FIG. 19, "cl_from" is a number associated with "page_id", "cl_to" is a category name of a category including "cl_from", and "cl_type" is associated with "cl_from". Information indicating whether the "page_id" page is an article page or a category page (for example, "page" is an article page and "subcat" is a category page).

The table of FIG. 18 is, for example, constructed by the expansion processing unit 134 from “jawiki-latest-page.SQL” and stored in the storage unit 11, but may be pre-built and stored in the storage unit 11. .. Similarly, the table of FIG. 19 is constructed by, for example, the expansion processing unit 134 from “jawiki-latest-categorylinks.SQL” and stored in the storage unit 11, but even if it is pre-built and stored in the storage unit 11. Good.

When constructing the two tables of FIGS. 18 and 19, for example, in "jawiki-latest-categorylinks.skl", for each page_title of one or more article pages, the page_id of the category page to which the page_title belongs and One or two or more page_titles of each category page corresponding to the page_id are included. The expansion processing unit 134 acquires the page_id "184440" of the category page to which the page_title "CPU" belongs by using such "jawiki-latest-categorylinks.sql", and further corresponds to the acquired page_id "184440" 1. Or, acquire the page_title (for example, "computer mechanism", "computer architecture", "hardware", etc.) of each of two or more category pages. Then, the expansion processing unit 134 stores the acquired page_titles of one or more category pages in association with the page_id "184440" and the cl_type "subcat".

In addition, the expansion processing unit 134 also acquires the page_id "2387" of the article page of the page_title "CPU", and stores the page_title "CPU" in association with the acquired page_id "2387" and the cl_type "page". To do. Further, the same processing as described above is performed for the page_tile "hardware", "computer architecture", etc., whereby the table of FIG. 19 is constructed.

Next, the expansion processing unit 134 uses, for example, the above-mentioned “jawiki-latest-page.sql” to obtain a category page corresponding to the page_titl for each page_titl of one or more category pages acquired as described above. (For example, "24360" corresponding to "computer mechanism", "249507" corresponding to "computer architecture", "140804" corresponding to "hardware", etc.) is acquired, and the page_titl is acquired. The page_id of the category page, the page_namespace "14", and the page_is_redirect "0" are stored in association with each other.

Further, the expansion processing unit 134 stores the category page page_titl "CPU" in association with the category page page_id "184440", page_name "14", and page_is_redirect "0". Further, the expansion processing unit 134 stores the page_titl "CPU" of the article page in association with the page_id "2387" of the article page, the page_namespace "0", and the page_is_redirect "0".

Further, the same processing as described above is performed for the page_titl "computer science" on the category page, the page_titl "hardware" on the article page, and the like, whereby the table shown in FIG. 18 is constructed. However, the procedure for constructing the two tables shown in FIGS. 18 and 19 does not matter.

In Wikipedia, the article page or category page of page_tile (Table 4) is included in the category name category of cl_to (Table 5) of cl_from (Table 5) associated with the corresponding page_id (Table 4).

Therefore, the expansion processing unit 134 associates two records in which the value of page_id (Table 4) and the value of cl_from (Table 5) match (that is, the column “page_id” in Table 4 and the value in Table 5). By associating with the column "cl_from"), a table that is a set of a set of page_id (Table 4) = cl_from (Table 5), cl_to (hyponymm), page_tile (hyponym), and cl_type (Table 5). Build Table 6). However, the terms (hypernyms, hyponyms) corresponding to the article titles determined by the term classification unit 131 to be non-terms are usually excluded from Table 6.

Then, the expansion processing unit 134 acquires the constructed table (Table 6) as a term dictionary (hypernym dictionary). Alternatively, the expansion processing unit 134 may acquire a hierarchical diagram of FIG. 21 in which the constructed table (Table 6) is configured in a tree shape.

After that, for example, in response to the reception unit 12 receiving the transmission instruction of the term dictionary, the output unit 14 transmits the synonym dictionary and the hypernym dictionary stored in the storage unit 11 to the map creation device 2.

In the map creation device 2, the map reception unit 22 receives the above two types of term dictionaries, and the map processing unit 23 stores the two types of received term dictionaries in the term dictionary storage unit 211.

After that, it is assumed that the map reception unit 22 receives the map output instruction together with the designation of the term "hardware". The term "hardware" may be specified, for example, by inputting characters or by specifying "hardware" in the hierarchical diagram of FIG. 21. In the latter case, for example, the map output unit 24 may display the hierarchical diagram of FIG. 21 on the display, and the map reception unit 22 may accept the designation of “hardware” with a mouse or the like.

In response to this, the term acquisition unit 231 acquires terms related to the designated term from each of the two or more patent documents stored in the patent information storage unit 212. Here, for example, the technical term "CPU" and the company name "AA Co., Ltd." are acquired from JP-A-2016-aaaa, and the technical term "central processing unit" and the company are obtained from JP-A-2010-bbbb. Suppose that the name "BB Co., Ltd." is acquired.

The term summary upper part 232 refers to the related words common to the two or more terms belonging to the technical term class (that is, "CPU" and "central processing device") among the two or more related words thus acquired. It is acquired from two types of term dictionaries stored in the storage unit 211. Specifically, for example, for the term "CPU" acquired from JP-A-2016-aaaa, synonyms such as "CPU", "central processing unit" and "central processing unit" are acquired from the synonym dictionary. , And higher-level words such as "hardware", "computer", and "computer science" are obtained from the higher-level word dictionary.

Similarly, for the term "central processing unit" acquired from Japanese Patent Application Laid-Open No. 2010-bbbb, synonyms such as "central processing unit", "CPU" and "central processing unit" are acquired from the synonym dictionary. Also, assume that hypernyms such as "processing unit", "computer", and "computer science" are obtained from the hypernym dictionary.

The upper part 232 of the glossary is the related word groups "CPU", "central processing unit", "central processing unit", "hardware", "computer", and "computer science" obtained from JP-A-2016-aaaa. And the related terms "central processing unit", "CPU", "central processing unit", "processing unit", "computer", and "computer science" obtained from JP-A-2010-bbbb. Detects common related terms "CPU", "central processing unit", and "computer science".

Of the above three related words detected, "CPU" and "central processing unit" are synonymous with each other. Therefore, the upper part 232 of the glossary is either "CPU" or "central processing unit". (For example, "CPU") is adopted. Then, the upper part 232 of the glossary acquires two common related words, "CPU" and "computer science".

For each of the two acquired related words "CPU" and "computer science", the related word correspondence part 233 describes the original patent document (that is, JP-A-2016-aaaa) and the special publication in which it was acquired. Open 2010-bbbb (Ab. 2010) is associated. Thereby, for example, for each of the two related terms "CPU" and "computer science", the publication number "Japanese Patent Laid-Open No. 2016-aaaa" and the company name, which are patent-related information related to JP-A-2016-aaaa, and the company name. "AA Co., Ltd." is associated with the publication number "Japanese Patent Laid-Open No. 2010-bbbb", which is patent-related information related to Japanese Patent Application Laid-Open No. 2010-bbbb, and the company name "BB Co., Ltd.".

The map configuration unit 234 acquires the two acquired related words and the corresponding terms by using the result of the association by the related word correspondence unit 233 and the template stored in the map storage unit 21. A two-dimensional map is constructed in which two or more patent-related information (for example, a company name) related to each of the two or more original patent information is associated with each other.

As a result, for example, a related information group including the above two related words "CPU" and "computer science" is arranged on one of the two axes (for example, the vertical axis), and the other of the two axes (for example, the horizontal axis) is arranged. ), A group of company names including the above two company names "AA Co., Ltd." and "BB Co., Ltd." is placed, and at positions corresponding to the pair of related words and company names, depending on the number of original patent information. A map with circles of the same size is obtained.

When constructing the map, the above two company names may be replaced with synonyms such as abbreviations. For example, in the term dictionary storage unit 211, a synonym dictionary for a company name (for example, a pair of a company name "AA Co., Ltd." and a synonym "AA Co., Ltd.", and a company name "BB Co., Ltd." and a synonym "BB" (Pairs with "Co., Ltd., etc.") are stored, and the map component unit 234 replaces the company name "AA Co., Ltd." with the synonym "AA Co., Ltd." using a synonym dictionary for the company name. The company name "BB Co., Ltd." may be replaced with the synonym "BB Co., Ltd.". The map configuration unit 234 stores the map thus configured in the map storage unit 21.

The map output unit 24 outputs the map stored in the map storage unit 21 via the display. As a result, for example, a map as shown in FIG. 22 is displayed on the display of the map creation device 2. In this map, 7 technical terms ("processor", "storage device", etc.) are arranged on the vertical axis, and 10 company names "AA Co., Ltd.", "BB Co., Ltd.", etc. are arranged on the horizontal axis. Is placed. Each technical term on the vertical axis is a subordinate term of the designated term "hardware". The company name on the horizontal axis is an abbreviation. In this map, the number of original patent information (number of cases) is also displayed in association with each circle, but the number of cases may not be displayed.

As described above, according to the present embodiment, the initial glossary, which is a set of two or more terms, is stored in the initial glossary storage unit 111, and the dictionary construction device 1 determines in advance for each of the two or more terms. A term classification is performed to determine whether the term belongs to a given class or a term that does not belong to a predetermined class, and the classification result in the term classification is used to determine a predetermined class from two or more terms. A reduction process that excludes terms that do not belong to is performed, and as a result of the reduction process, a document group is searched using at least one or more remaining terms as a key, and a document corresponding to each one or more terms is acquired. It is the information in the acquired document after processing, and one or more related words related to the term are acquired from the information of the predetermined location, and one or more related words are associated with the corresponding terms. By acquiring a term dictionary having a plurality of pairs of terms and one or more related words associated with the terms and performing extended processing to accumulate them, terms that do not belong to a predetermined class are not included and the terms are related. You can easily build a term dictionary that contains more words.

In the above configuration, the document group is Wikipedia, and in Wikipedia, since the freshness of information is always maintained by updating volunteers, a dictionary containing many latest terms and related words can be constructed at low cost. In addition, Wikipedia can also acquire English notation as a synonym, so it is possible to build a dictionary that coexists with English and Japanese.

Further, the dictionary construction device 1 acquires one or more synonyms related to a term from the information of the first predetermined location in the acquired document, and associates one or more synonyms with the corresponding terms. By acquiring a term dictionary having a plurality of pairs of terms and one or more synonyms associated with the terms and performing the first expansion process of accumulating them, terms that do not belong to a predetermined class are not included. , You can easily build a term dictionary that contains more synonyms for terms.

Further, the dictionary construction device 1 acquires one or more higher-order words related to a term from the information of a predetermined second place in the acquired document, and associates one or more higher-order words with the corresponding terms. By acquiring a term dictionary having a plurality of pairs of terms and one or more higher-level words associated with the terms and performing the second extension process of accumulating the terms, terms that do not belong to a predetermined class are not included. , You can easily build a term dictionary that contains more high-level terms.

Further, the dictionary construction device 1 searches a group of documents using the hypernym acquired by the second expansion process as a key, acquires a document corresponding to each of one or more hypernyms, and among the documents corresponding to the acquired hypernyms. By acquiring one or more hypernyms related to the hypernyms from the information in the second place and controlling that the search process and the second extension process are performed once or twice or more. You can easily build a term dictionary that includes the hypernyms of the hypernyms.

Further, the highest-level glossary storage unit 112 stores the highest-level glossary, which is a set of the highest-level terms, which is one or more terms of the highest-level concept, and the dictionary construction device 1 is acquired by the second expansion process. A term dictionary containing two or more layers of terms up to the top by controlling the search process and the second extension process to be repeated until the term becomes one of the top terms included in the top-level glossary. Can be easily constructed.

Further, in the above configuration, since the predetermined class is a class of technical terms, the dictionary construction device 1 is a dictionary of technical terms, does not include terms other than technical terms, and contains related terms of technical terms. You can easily build a dictionary that contains more.

Further, in the above configuration, since the predetermined class is a dictionary construction device which is a class of the company name, the dictionary construction device 1 is a dictionary of the company name and does not include terms other than the company name. You can easily build a dictionary that contains more related words of names.

Further, in the above configuration, since the predetermined class is the inventor's class, the dictionary construction device 1 is a dictionary of the inventor's name, does not include terms other than the inventor's name, and is the inventor's name. You can easily build a term dictionary that contains more related words.

Further, the term dictionary configured by the dictionary construction device 1 is stored in the term dictionary storage unit 211, two or more patent information is stored in the patent information storage unit 212, and the map creation device 2 stores two or more patent information. The terms are acquired from, and the related words common to each of the acquired two or more terms are acquired from the term dictionary. The summarization process is performed, and the two or more terms corresponding to the related words acquired by the summarization process are acquired. The original two or more patent information is associated with the related word acquired by the summarization process, and the related word is associated with the two or more patent-related information related to each of the original two or more patent information and output. By doing so, it is possible to create an accurate map from two or more patent information with less noise and a collection of more related words by using the term dictionary constructed by the dictionary construction device 1.

In addition, the map creation device 2 acquires terms of two or more different classes from each of two or more patent information, performs grouping processing for each of two or more different classes, and acquires each of two or more different classes. The original two or more patent information in which each of the two or more terms corresponding to the related words was acquired is associated with the acquired related words, and for each of the two or more different classes, the related words and the original two or more each. A multidimensional map can be generated by constructing a map in which two or more patent-related information related to patent information are associated with each other and outputting the constructed map.

Further, the processing in the present embodiment may be realized by software. Then, this software may be distributed by software download or the like. Further, this software may be recorded on a recording medium such as a CD-ROM and disseminated.

The software that realizes the dictionary construction device 1 in the present embodiment is, for example, the following program. That is, this program puts a computer that can access the initial glossary storage unit 111 that stores the initial glossary, which is a set of two or more terms, into a predetermined class for each of the two or more terms. Using the term classification unit 131 for determining whether the term belongs to the term or the term does not belong to the predetermined class and the classification result in the term classification unit 131, the term is predetermined from the two or more terms. A reduction processing unit 132 that performs a reduction processing that is a process excluding terms that do not belong to the class, and a document group is searched using at least one or more terms remaining as a result of the reduction processing as a key, and one or more terms are used. Information in the document search unit 133 that acquires the corresponding document and the document acquired by the document search unit 133, and one or more related words related to the term are acquired from the information of the predetermined portion. , An extension process for acquiring a term dictionary having a plurality of pairs of a term and one or more related words associated with the term by associating the one or more related words with the corresponding terms and performing an extension process for accumulating the terms. It is a program for functioning as a part 134.

Further, the software that realizes the map creation device 2 in the present embodiment is, for example, the following program. That is, this program uses two or more computers that can access the term dictionary storage unit 211 that stores the term dictionary configured by the dictionary construction device 1 and the patent information storage unit 212 that stores two or more patent information. A term acquisition unit 231 that acquires terms from each of the patent information of the above, and a term summary upper portion 232 that performs a summarization process for acquiring related words common to two or more terms acquired by the term acquisition unit 231 from the term dictionary. , The original two or more patent information from which each of the two or more terms acquired by the term acquisition unit 231 corresponding to the related words acquired by the term summary upper part 232, and the related words acquired by the term summary upper part 232. A program for functioning as a map output unit 24 that outputs the related word corresponding unit 233 and the two or more patent-related information related to the original two or more patent information in association with each other. Is.

The map creation device 2 in the present embodiment creates a map using the term dictionary constructed by the dictionary construction device 1, but patent search may also be performed. In the patent search, for example, a term is accepted, one or more related words related to the accepted term are acquired from the term dictionary of the term dictionary storage unit 211, and each of the acquired one or more related words is used as a key to obtain a patent. It can be said that this is a process of searching for two or more patent information stored in the information storage unit 212 and outputting the search result.

Specifically, the map creation device 2 may have two or more functions including, for example, a map creation function for creating a map and a search function for performing a patent search. When one of the functions is selected via an input device such as a keyboard, the map receiving unit 22 accepts the selection, and the map processing unit 13 or the like executes a process corresponding to the selection. For example, when the map creation function is selected, the map processing unit 23 and the like perform the above-mentioned processing.

When the search function is selected, the following processing is performed. That is, the map reception unit 22 accepts terms. The accepted term is a keyword for patent search, for example, a technical term, but it may be a company name, an inventor name, or the like, and the type thereof does not matter.

The map processing unit 23 acquires one or more related words related to the terms received by the map reception unit 22 from the term dictionary stored in the term dictionary storage unit 211. Then, the map processing unit 23 searches for two or more patent information stored in the patent information storage unit 212 using each of the acquired one or more related words as a key, and acquires the search result. The search result is information about the result of such a search. The search result is, for example, a set of identification information (hereinafter, "identification information group") that identifies one or more patent information including related words.

For example, when the patent information is a patent document, the identification information may be a publication number, a patent number, or the like, but may be an ID, and the type thereof does not matter. The search result in this case may be, for example, a set of publication numbers and the like described in one or more patent documents including related words. Alternatively, the search result may be, for example, a set of a set of a public number or the like and one or more pieces of information among the company name or the inventor name, and the structure is not limited.

Specifically, for example, the map processing unit 23 has one or more predetermined columns (for example, "public number", "name or name") for each one or more patent documents including related words. You may obtain the description items of "name", "name", "name of invention", etc.). Then, the map processing unit 23 may acquire a search result including one or two or more sets of the acquired one or more description items (the related words may be added).

The map output unit 24 outputs the search result acquired by the map processing unit 23 via an output device such as a display. As a result, for example, a group of identification information corresponding to one or more patent information including related words of the accepted term is displayed on the display.

As a result, the map creation device 2 can perform an accurate patent search with little omission by using the term dictionary constructed by the dictionary construction device 1.

The identification information group acquired by the patent search function is handed over to the map creation function, and even if the map creation function creates a map for one or more patent information corresponding to the identification information group. Good. That is, the patent search function searches for a "parent population", which is a set of two or more patent information stored in the patent information storage unit 212, using the accepted term and the stored term dictionary. It can also be considered that it is a function of narrowing down to a "child population" which is a set of one or more patent information including related words of.

Specifically, the map output unit 24 may deliver the acquired identification information group to the term acquisition unit 231. The term acquisition unit 231 acquires terms from one or more patent information corresponding to the identification information group. The subsequent processing is the same as described above. That is, the term summary upper part 232 performs a summarization process for acquiring the related words common to each of the two or more acquired terms from the term dictionary, and the term acquisition unit 231 corresponding to the related words acquired by the term summary upper part 231 performs the summarization process. The original two or more patent information from which each of the acquired two or more terms has been acquired is associated with the related word acquired by the upper part 232 of the term summary, and the map output unit 24 has the related word and the original two or more terms. Two or more patent-related information related to each patent information may be output in association with each other.

As a result, the term constructed by acquiring the child population, which is a set of one or more patent information including the related words of the accepted term, from the parent population, which is a set of two or more patent information stored. An accurate map can be created from the offspring using a dictionary.

The map creation device 2 may not create a map but only search for patents. Such a map creating device 2 may be referred to as a "search device". Hereinafter, the search device 2a for performing a patent search will be described using the term dictionary constructed by the dictionary construction device 1.

(Modification example)

FIG. 23 is a block diagram of the search device 2a, which is a modification of the map creation device 2. The search device 2a includes a search storage unit 21a, a search reception unit 22a, a search processing unit 23a, and an output unit 24a. The search storage unit 21a includes a term dictionary storage unit 211 and a patent information storage unit 212.

Similar to the map storage unit 21 of the map creation device 2, the search storage unit 21a can store various types of information such as a term dictionary and patent information. The term dictionary storage unit 211 stores the term dictionary constructed by the dictionary construction device 1, and the patent information storage unit 212 stores one or more patent information, as in the case of the map creation device 2. The same is true.

The operations of the search reception unit 22a, the search processing unit 23a, and the search output unit 24a are the map reception unit 22, the map processing unit 23, and the map output unit 24 when the patent search function is selected in the map creation device 2. It is the same as the operation of.

FIG. 24 is a flowchart illustrating the operation of the search device 2a.

(Step S2401) The search processing unit 23a determines whether or not the search reception unit 22a has accepted the term. If it is determined that the search reception unit 22a has accepted the term, the process proceeds to step S2402, and if it is determined that the term has not been accepted, the process returns to step S2401.

(Step S2402) The search processing unit 23a acquires one or more related words related to the terms received in step S2401 from the term dictionary stored in the term dictionary storage unit 211.

(Step S2403) The search processing unit 23a sets the initial value “1” in the variable i. The variable i here is a variable for sequentially selecting unselected words from one or more related words acquired in step S2402.

(Step S2404) The search processing unit 23a determines whether or not there is an i-th related word. If it is determined that there is an i-th related word, the process proceeds to step S2405, and if it is determined that there is no i-th related word, the process proceeds to step S2408.

(Step S2405) The search processing unit 23a searches for two or more patent information stored in the patent information storage unit 212 using the i-th related word as a key.

(Step S2406) The search processing unit 23a acquires the IDs and the like of one or more patent information including the i-th related word.

(Step S2407) The search processing unit 23a increments the variable i. Then, the process returns to step S2404.

(Step S2408) The search processing unit 23a acquires a search result including a set of IDs and the like acquired in step S2406.

(Step S2409) The search output unit 24a outputs the search result acquired in step S2408. Then, the process returns to step S2401.

In the flowchart of FIG. 24, the process starts when the power of the search device 2a is turned on or the program is started, and the process ends when the power is turned off or an interrupt for the end of the process occurs. However, the trigger for the start or end of processing does not matter.

According to this modification, the term dictionary constructed by the dictionary construction device 1 can be used to perform an accurate patent search with few omissions.

The software that realizes the search device 2a in this modification is, for example, the following program. That is, this program accepts terms from a computer that can access the term dictionary storage unit 211 in which the term dictionary configured by the dictionary construction device 1 is stored and the patent information storage unit 212 in which two or more patent information is stored. The search reception unit 22a and one or more related words related to the terms accepted by the search reception unit 22a are acquired from the term dictionary, and each of the acquired one or more related words is used as a key in the patent information storage unit 212. It is a program for functioning as a search processing unit 23a for searching two or more stored patent information and acquiring a search result, and a search output unit 24a for outputting the search result.

FIG. 25 is an external view of a computer system 900 that executes a program in each embodiment to realize a dictionary construction device 1, a map creation device 2, and the like. This embodiment can be realized by computer hardware and a computer program executed on the computer hardware. In FIG. 25, the computer system 900 includes a computer 901 including a disk drive 905, a keyboard 902, a mouse 903, and a display 904. The entire system including the keyboard 902, the mouse 903, and the display 904 may be called a computer.

FIG. 26 is a diagram showing an example of the internal configuration of the computer system 900. In FIG. 26, the computer 901 is connected to the MPU 911, the ROM 912 for storing a program such as a bootup program, and the MPU 911 in addition to the disk drive 905, and temporarily stores the instructions of the application program and temporarily. It provides a RAM 913 that provides a storage space, a storage 914 that stores application programs, system programs, and data, a bus 915 that interconnects the MPU 911, ROM 912, and the like, and a connection to a network such as an external network or an internal network. It includes a network card 916. The storage 914 is, for example, a hard disk, an SSD, a flash memory, or the like.

A program that causes the computer system 900 to execute functions such as the dictionary construction device 1 and the map creation device 2 is stored in, for example, a disk 921 such as a DVD or a CD-ROM, inserted into a disk drive 905, and transferred to a storage 914. May be done. Alternatively, the program may be transmitted over the network to computer 901 and stored in storage 914. The program is loaded into RAM 913 at run time. The program may be loaded directly from disk 921 or the network. Further, the program may be read into the computer system 900 via another removable recording medium (for example, a DVD, a memory card, etc.) instead of the disc 921.

The program does not necessarily include an operating system (OS) that executes functions such as the dictionary construction device 1, the map creation device 2, or a third-party program in 901 that shows the details of the computer. The program may contain only parts of instructions that call the appropriate functions or modules in a controlled manner to achieve the desired result. It is well known how the computer system 900 works, and detailed description thereof will be omitted.

The computer system 900 described above is a server or a stationary PC, but a terminal device (not shown) may be realized by a mobile terminal such as a smartphone, a tablet terminal, or a notebook PC. In this case, for example, the keyboard 902 and the mouse 903 may be replaced with a touch panel, the disk drive 905 may be replaced with a memory card slot, and the disk 921 may be replaced with a memory card. However, the above is an example, and the hardware configuration of the computer that realizes the dictionary construction device 1, the map creation device 2, and the like does not matter.

In the above program, in the transmission step of transmitting information and the receiving step of receiving information, processing performed by hardware, for example, processing performed by a modem or interface card in the transmission step (only performed by hardware). Processing that is not done) is not included.

Further, the number of computers that execute the above program may be singular or plural. That is, centralized processing may be performed, or distributed processing may be performed.

Further, in each of the above embodiments, the two or more communication means existing in one device (for example, the reception function of the reception unit 12 and the transmission function of the output unit 14) are physically realized by one medium. Needless to say, it's okay.

Further, in each of the above-described embodiments, each process (each function) may be realized by centralized processing by a single device (system), or by distributed processing by a plurality of devices. May be done.

It goes without saying that the present invention is not limited to the above embodiments, and various modifications can be made, and these are also included in the scope of the present invention.

As described above, the dictionary construction device according to the present invention has the effect of easily constructing a term dictionary containing more related words of terms without including terms that do not belong to a predetermined class, and constructs a dictionary. It is useful as a device or the like. In addition, the map creation device according to the present invention uses a term dictionary constructed by the dictionary construction device to create an accurate map from two or more patent information with less noise and more related words. It has the effect of being able to be used, and is useful as a map creation device or the like. Further, the search device according to the present invention has an effect of performing an accurate patent search with few omissions by using the constructed term dictionary, and is useful as a patent search device.

1 Dictionary construction device 2 Map creation device 2a Search device 11 Storage unit 12 Reception unit 13 Processing unit 14 Output unit 21 Map storage unit 21a Search storage unit 22 Map reception unit 22a Search reception unit 23 Map processing unit 23a Search processing unit 24 Map output Part 24a Search output unit 111 Initial terminology storage unit 111 Initial terminology storage unit 112 Top-level terminology storage unit 131 Term classification unit 132 Reduction processing unit 133 Document search unit 134 Extended processing unit 135 Control unit 211 Term dictionary storage unit 212 Patent information Storage part 231 Term acquisition part 232 Term summary upper part 233 Related word correspondence part 234 Map composition part

Claims (19)

An initial glossary storage unit that stores an initial glossary that is a set of two or more terms,
A term classification unit that determines whether each of the above two or more terms belongs to a predetermined class or does not belong to a predetermined class.
Using the classification results in the term classification unit, a reduction processing unit that performs reduction processing, which is a processing for removing terms that do not belong to the predetermined class from the two or more terms, and a reduction processing unit.
A document search unit that searches a group of documents using at least one or more remaining terms as a result of the reduction processing as a key, and acquires a document corresponding to each of the one or more terms.
Information in a document acquired by the document search unit, one or more related words related to the term are acquired from the information of a predetermined location, and the one or more related words correspond to the corresponding terms. A dictionary construction device comprising an extension processing unit that acquires a term dictionary having a plurality of sets of a term and one or more related words associated with the term, and performs an expansion process for accumulating the term. The expansion processing unit
From the information of the first predetermined place in the document acquired by the document search unit, one or more synonyms related to the term are acquired, and the one or more synonyms are associated with the corresponding terms. The dictionary construction device according to claim 1, wherein a term dictionary having a plurality of sets of a term and one or more synonyms associated with the term is acquired and accumulated, and the first expansion process is performed. The expansion processing unit
From the information of a predetermined second place in the document acquired by the document search unit, one or more hypernyms related to the term are acquired, and the one or more hypernyms are associated with the corresponding terms. The dictionary construction device according to claim 1 or 2, wherein a term dictionary having a plurality of sets of a term and one or more hypernyms associated with the term is acquired and accumulated in the second expansion process. The document search unit
The extension processing unit searches the document group using the hypernym acquired by the second extension process as a key, and acquires the document corresponding to each of one or more hypernyms.
The expansion processing unit
Information in a document corresponding to the hypernym acquired by the document search unit, and one or more hypernyms related to the hypernym are acquired from the information in the second location.
The dictionary construction apparatus according to claim 3, further comprising a control unit that controls the processing of the document retrieval unit and the second expansion processing of the expansion processing unit once or twice or more. It further includes a top-level terminology storage unit that stores the top-level terminology, which is a set of top-level terms that are one or more terms of the top-level concept.
The control unit
The processing of the document retrieval unit and the second expansion of the expansion processing unit until the term acquired by the second expansion processing of the expansion processing unit becomes any of the top-level terms included in the top-level glossary. The dictionary construction device according to claim 4, wherein the process is controlled to be repeated. The dictionary construction device according to any one of claims 1 to 5, wherein the predetermined class is a class of technical terms. The dictionary construction device according to any one of claims 1 to 5, wherein the predetermined class is a class of a company name. The dictionary construction device according to any one of claims 1 to 5, wherein the predetermined class is the class of the inventor. A term dictionary storage unit for storing a term dictionary configured by the dictionary construction device according to any one of claims 1 to 8.
A patent information storage unit that stores two or more patent information,
A term acquisition unit that acquires terms from each of the above two or more patent information,
A term summary upper part that performs a summary process for acquiring related words common to each of the two or more terms acquired by the term acquisition unit from the term dictionary, and
Correspondence between the original two or more patent information from which each of the two or more terms acquired by the term acquisition unit corresponding to the related word acquired by the term summary upper part is associated with the related word acquired by the term summary upper part. With word correspondence and
A map creating device including a map output unit that outputs the related words in association with two or more patent-related information related to each of the two or more original patent information. The term acquisition unit
Obtain two or more different classes of terms from each of the two or more patent information,
The upper part of the terminology is
For each of the two or more different classes, the above-mentioned summarization process is performed.
The related word correspondence part is
For each of the two or more different classes, the original two or more patent information from which each of the two or more terms acquired by the term acquisition unit corresponding to the related word acquired by the term summary upper part and the terminology upper part are obtained. Corresponds to the related words acquired by
Each of the two or more different classes further includes a map component that constitutes a map in which the related word and two or more patent-related information related to each of the original two or more patent information are associated with each other.
The map output unit
The map creation device according to claim 9, which outputs a map configured by the map configuration unit. The map reception section that accepts terms and
One or more related words related to the terms accepted by the map reception unit are acquired from the term dictionary, and two or more patents stored in the patent information storage unit using each of the acquired one or more related words as a key. It also has a map processing unit that searches for information and acquires search results.
The map output unit
The map creation device according to claim 9 or 10, which outputs the search result. The search result is an identification information group which is a set of identification information for identifying one or more patent information including the related word.
The map output unit
The identification information group is handed over to the term acquisition unit,
The term acquisition unit
The map creation device according to claim 11, wherein a term is acquired from each one or more patent information corresponding to the identification information group. A term dictionary storage unit for storing a term dictionary configured by the dictionary construction device according to any one of claims 1 to 8.
A patent information storage unit that stores two or more patent information,
The reception desk that accepts terms and
One or more related words related to the terms accepted by the reception unit are acquired from the term dictionary, and two or more patent information stored in the patent information storage unit using each of the acquired one or more related words as a key. A processing unit that searches for and obtains search results,
A search device including an output unit that outputs the search result. A dictionary construction method realized by an initial terminology storage unit, a term classification unit, a reduction processing unit, a document retrieval unit, and an extension processing unit that store an initial terminology that is a set of two or more terms.
A term classification step in which the term classification unit determines, for each of the two or more terms, whether the term belongs to a predetermined class or does not belong to a predetermined class.
A reduction processing step in which the reduction processing unit performs a reduction processing, which is a process of removing terms that do not belong to the predetermined class from the two or more terms, using the classification result in the term classification unit.
A document search step in which the document search unit searches a document group using at least one or more terms remaining as a result of the reduction processing as a key, and acquires a document corresponding to the one or more terms.
The extended processing unit is information in a document acquired by the document search unit, and one or more related words related to the term are acquired from the information of a predetermined location, and the one or more related words are acquired. A dictionary construction method including an extension processing step of acquiring a term dictionary having a plurality of pairs of a term and one or more related words associated with the term and accumulating the term in association with the corresponding term. .. A term dictionary storage unit for storing a term dictionary configured by the dictionary construction device according to any one of claims 1 to 8, a patent information storage unit for storing two or more patent information, a term acquisition unit, and terms. It is a map creation method realized by the upper part of the summary, the related word correspondence part, and the map output part.
A term acquisition step in which the term acquisition unit acquires a term from each of the two or more patent information,
The upper part of the term summarization is a term summarization step of performing a summarization process for acquiring related words common to each of the two or more terms acquired by the term acquisition unit from the term dictionary.
The related word correspondence part is the original two or more patent information from which each of the two or more terms acquired by the term acquisition unit corresponding to the related word acquired by the term summary upper part, and the terminology upper part A step with related word correspondence that associates with the acquired related word,
A map creation method including a map output step in which the map output unit outputs the related words in association with two or more patent-related information related to each of the two or more original patent information. A term dictionary storage unit for storing a term dictionary configured by the dictionary construction device according to any one of claims 1 to 8, a patent information storage unit, a reception unit, and a processing unit for storing two or more patent information. , And a search method realized by the output unit,
The reception step where the reception department accepts terms and
The processing unit acquires one or more related words related to the terms accepted by the receiving unit from the term dictionary, and stores the acquired one or more related words as a key in the patent information storage unit. A processing step to search for two or more patent information and obtain search results,
A search method including an output step in which the output unit outputs the search result. A computer that can access the initial glossary storage, which stores the initial glossary, which is a set of two or more terms.
A term classification unit that determines whether each of the above two or more terms belongs to a predetermined class or does not belong to a predetermined class.
Using the classification results in the term classification unit, a reduction processing unit that performs reduction processing, which is a processing for removing terms that do not belong to the predetermined class from the two or more terms, and a reduction processing unit.
A document search unit that searches a group of documents using at least one or more remaining terms as a result of the reduction processing as a key, and acquires a document corresponding to each of the one or more terms.
Information in a document acquired by the document search unit, one or more related words related to the term are acquired from the information of a predetermined location, and the one or more related words correspond to the corresponding terms. A program for acquiring a term dictionary having a plurality of pairs of a term and one or more related words associated with the term, and functioning as an extended processing unit for performing the accumulated extended processing. A computer that can access a term dictionary storage unit that stores a term dictionary configured by the dictionary construction device according to any one of claims 1 to 8 and a patent information storage unit that stores two or more patent information. ,
A term acquisition unit that acquires terms from each of the above two or more patent information,
A term summary upper part that performs a summary process for acquiring related words common to each of the two or more terms acquired by the term acquisition unit from the term dictionary, and
Correspondence between the original two or more patent information from which each of the two or more terms acquired by the term acquisition unit corresponding to the related word acquired by the term summary upper part is associated with the related word acquired by the term summary upper part. With word correspondence and
A program for functioning as a map output unit that outputs the related words in association with two or more patent-related information related to each of the two or more original patent information. A computer that can access a term dictionary storage unit that stores a term dictionary configured by the dictionary construction device according to any one of claims 1 to 8 and a patent information storage unit that stores two or more patent information. ,
The reception desk that accepts terms and
One or more related words related to the terms accepted by the reception unit are acquired from the term dictionary, and two or more patent information stored in the patent information storage unit using each of the acquired one or more related words as a key. A processing unit that searches for and obtains search results,
A program for functioning as an output unit that outputs the search results.

Images