JP2010198281A - Information processing apparatus, information processing method, and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To solve the problem of conventional information processing apparatuses being unable to easily obtain appropriate information through searches using the names of places. <P>SOLUTION: An information processing apparatus includes: an areal feature word storage unit 101 in which areal feature words, i.e., character strings highly related to an area, and region information, i.e., information indicating regions including areas highly related to the areal feature words, are stored in association; a position information acquisition unit 102 which acquires position information, i.e., information indicating positions; an areal feature word acquisition unit 103 which acquires from the areal feature word storage unit 101 areal feature words corresponding to the region information indicating regions containing positions indicated by the position information acquired by the position information acquisition unit 102; and an areal feature word output unit 104 which outputs the areal feature words acquired by the areal feature word acquisition unit 103. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to an information processing apparatus that can be used when searching for information related to a region.

  As a conventional information processing technology, for a user in an automobile, a place name existing in the vicinity of the user is acquired based on the position information, and a search is performed using the place name as a search query. It has been known that a high so-called blog content is extracted, made audible, and presented. (For example, refer nonpatent literature 1).

Hiroshi Gun, 2 others, "Proposal of an audible interface for regional blog information and extraction method of text content suitable for speech", DEWS2006

  However, as described above, the search target may be limited content such as Blog content. However, when searching from WEB or the like without limiting the search target to Blog content, the place name is searched. As a condition, it cannot be said that the search results can be sufficiently narrowed down. In addition, in a search using a place name, a WEB page of a prefectural office or government office that contains the place name in a normal search site etc. Therefore, in the search using the place name as a search condition as described above, there is a problem that a WEB page or the like related to a characteristic event about a region cannot always be obtained as a search result. Therefore, when it is desired to know information on various events that are characteristic for a region or the like, there is a problem that it is difficult to obtain appropriate information by a search using a place name as described above.

  In the information processing apparatus of the present invention, a regional feature word that is a character string that is highly relevant to a region is associated with region information that is information indicating a region including a region that is highly relevant to the regional feature word. The region feature word storage unit stored in the above, the location information acquisition unit for acquiring location information that is information indicating the location, and the region information indicating the region including the location indicated by the location information acquired by the location information acquisition unit An area feature word acquisition unit that acquires an area feature word corresponding to the area feature word from the area feature word storage unit, and an area feature word output unit that outputs the area feature word acquired by the area feature word acquisition unit Device.

  With this configuration, it is possible to provide information on a character string suitable for searching for information characteristic of the area. For this reason, for example, it is possible to simplify processing when the user searches for an event or the like characteristic to the area.

  In the information processing apparatus of the present invention, the information processing apparatus performs a search using a region information receiving unit that receives region information that is information indicating a region, and a search condition that includes the region information received by the region information receiving unit. A region-related information acquisition unit that acquires region-related information that is information related to the region indicated by the region information, and a region that extracts the region feature word from the region-related information acquired by the region-related information acquisition unit A feature word extraction unit; a region feature word storage unit that stores the region feature words extracted by the region feature word extraction unit in the region feature word storage unit in association with the region information including the region indicated by the region information; Is an information processing apparatus.

  With this configuration, it is possible to extract a regional feature word using regional information received from a user or the like, and associate it with the regional information and store it in the regional feature word storage unit. Thereby, regional feature words can be added. As a result, it is possible to construct a database or the like that is a dictionary of regional feature words, for example.

  In the information processing apparatus according to the present invention, in the information processing apparatus, the region information receiving unit receives a plurality of the region information, and the region related information acquiring unit receives the plurality of regions received by the region information receiving unit. A search is performed using a search condition that includes each region information, and each region related information indicated by each region information is acquired. The region feature word extracting unit is one region information acquired by the region related information acquiring unit. For the character string appearing in the region-related information of the region indicated by, the frequency of occurrence in the region-related information of the region indicated by the one region information and the region-related information of the plurality of regions indicated by the plurality of region information Using the appearance frequency of the region-related information including the character string that matches the character string, the region characteristic degree that is information indicating the strength of the relation of the character string to the region is calculated, and the region characteristic degree is The area feature word that is the character string that satisfies a certain condition is extracted, and the area feature word storage unit includes the area indicated by the one area information including the area feature word extracted by the area feature word extraction unit This is an information processing apparatus that accumulates in the region feature word storage unit in association with region information.

  With this configuration, it is possible to extract the region feature words from the region related information acquired using the region information received from the user or the like using the appearance frequency of the character string. As a result, for example, it is possible to selectively accumulate only character strings that are characteristic of a region as a regional feature.

  Further, in the information processing apparatus according to the present invention, in the information processing apparatus, the area information receiving unit further receives information related to positions of a plurality of area information, and the area feature word extracting unit extracts and extracts each of the plurality of area information. A clustering unit that clusters the similar regional information using the calculated one or more regional feature words and the regional feature degree thereof, and information on the distance between a plurality of regions acquired using information on the location of the regional information The regional feature word storage unit associates the one or more regional feature words with the regional information including the regions indicated by the regional information gathered into one cluster by the clustering. An information processing apparatus that accumulates in a storage unit.

  With this configuration, it is possible to store the region feature words in association with the region formed by collecting the regions having similar region feature words. Thereby, for example, it is possible to output a region feature word of a region similar to the region corresponding to the input position information, and present the region feature word of the region related to the input position information to the user. Is possible.

  In the information processing apparatus according to the present invention, in the information processing apparatus, the regional feature word is stored in association with a regional feature degree that is information indicating the strength of association with the region. The feature word acquisition unit is an information processing apparatus that acquires the regional feature words according to the regional feature degree.

  With this configuration, for example, it is possible to preferentially acquire and output a regional feature having a high degree of association with a region included in the region indicated by the region information.

  In the information processing apparatus of the present invention, in the information processing apparatus, the region-related information acquisition unit searches for a WEB page using a search condition including each of the plurality of region information received by the region information receiving unit. This is an information processing apparatus that obtains region-related information that is information on the WEB page of the region indicated by each region information.

  With this configuration, it is possible to extract regional feature words from a wide variety of information. For example, the accuracy of the regional feature words, that is, the extracted regional feature words are character strings that are characteristic of the region. The degree of showing can be improved.

  In the information processing apparatus of the present invention, in the information processing apparatus, a search condition generation unit that generates a search condition including the region feature word output by the region feature word output unit, and a search created by the search condition creation unit The information processing apparatus further includes a search unit that performs a search using a condition and acquires information indicating a search result, and a search result output unit that outputs information indicating the search result of the search unit.

  With such a configuration, it is possible to perform an appropriate search using a search condition generated using an area feature word corresponding to a position indicated by position information designated by a user or the like. This makes it possible to easily provide information characteristic of the area.

  Further, in the information processing apparatus according to the present invention, in the information processing apparatus, the regional feature word output unit displays a list of regional feature words acquired by the regional feature word acquisition unit, and among the regional feature words displayed in the list A designation receiving unit that receives designation of one or more regional feature words, wherein the search condition generation unit accepts designation from the regional feature words output by the regional feature word output unit. This is an information processing device that generates a search condition by using a local feature word.

  With such a configuration, a user or the like can assist in creating a search condition, suggest a keyword or the like used for the search, and the like.

  Further, in the information processing apparatus according to the present invention, in the information processing apparatus, the region information is information indicating a range of the region, and the position information acquisition unit is information indicating a position where the user exists. The region feature word acquisition unit detects region information indicating a range including the position indicated by the position information acquired by the position information acquisition unit, and the region feature word associated with the region information is It is an information processing apparatus acquired from a regional feature word storage unit.

  With this configuration, it is possible to easily acquire regional feature information about the position where the user exists.

  In the information processing apparatus of the present invention, in the information processing apparatus, the regional feature word is stored in the regional feature word storage unit in association with time information that is information indicating time, and the position information acquisition The unit further acquires time information, and the region feature word acquisition unit is a region feature word associated with time information including the time indicated by the time information, and the position information acquired by the position information acquisition unit It is the information processing apparatus which acquires the area feature word corresponding to the area information indicating the area including the position indicated by from the area feature word storage unit.

  With this configuration, it is possible to selectively acquire regional feature words according to time information. As a result, for example, it is possible to selectively acquire only regional feature words indicating available events only at the time indicated by the time information.

  In the information processing apparatus of the present invention, in the information processing apparatus, the regional feature word is stored in the regional feature word storage unit in association with field information that is information indicating a field, and the position information acquisition The unit further acquires field designation information that is information for designating a field, and the region feature word acquisition unit is a region feature word associated with field information including the field indicated by the field designation information, In the information processing apparatus, the local feature word corresponding to the region information indicating the region including the position indicated by the positional information acquired by the positional information acquisition unit is acquired from the regional feature word storage unit.

  With this configuration, it is possible to selectively acquire regional feature words corresponding to the field designation information. As a result, it is possible to selectively acquire regional feature words related to the field desired by the user.

  According to the information processing apparatus and the like according to the present invention, it is possible to provide appropriate information for searching for information characteristic for a region.

  In addition, it is possible to provide an information processing apparatus or the like that can perform an appropriate search using a search condition including such information.

Block diagram of an information processing apparatus in an embodiment of the present invention Flow chart for explaining the operation of the information processing apparatus Conceptual diagram of the information processing device The figure which shows the list of area information for demonstrating operation | movement of the information processing apparatus. The figure which shows an example of the area feature word extracted from the area relevant information for demonstrating operation | movement of the information processing apparatus The figure which shows an example of the area range information management table for demonstrating operation | movement of the information processing apparatus The figure which shows an example of the area characteristic word management table for demonstrating operation | movement of the information processing apparatus. The figure which shows the example of a display of the list | wrist of a regional feature word for demonstrating operation | movement of the information processing apparatus. The figure which shows the example of a display of a search result for demonstrating operation | movement of the information processing apparatus. The figure which shows the modification of the information processing apparatus The figure which shows the modification of the information processing apparatus Schematic diagram showing an example of the appearance of a computer system in an embodiment of the present invention The figure which shows an example of a structure of the computer system in embodiment of this invention

  Hereinafter, embodiments of an information processing apparatus and the like will be described with reference to the drawings. In addition, since the component which attached | subjected the same code | symbol in embodiment performs the same operation | movement, description may be abbreviate | omitted again.

(Embodiment)
FIG. 1 is a block diagram of an information processing apparatus 1 in the present embodiment.

  The information processing apparatus 1 includes an area feature word storage unit 101, a position information acquisition unit 102, an area feature word acquisition unit 103, an area feature word output unit 104, an area information reception unit 105, an area related information acquisition unit 106, and an area feature word extraction. Unit 107, clustering unit 108, region feature word storage unit 109, search condition generation unit 110, search unit 111, search result output unit 112, designation reception unit 113, and region range information storage unit 114.

  The regional feature word storage unit 101 associates regional feature words that are character strings that are highly relevant to a region with region information that is information indicating regions including regions that are highly relevant to the regional feature words. Can be stored. The character string described here is, for example, a word. However, compound words can also be considered words. The regional feature word is, for example, character string information regarding an event having a high degree of dependence on the region included in the region indicated by the corresponding region information. In addition, the regional feature word may be, for example, information on a character string such as a keyword representing an event or the like that appears depending on or related to only a part of the region. The regional feature word is, for example, character string information about an event that is highly relevant in the region. Specifically, the regional characteristic words are words unique to the region such as special products, regional foods and souvenirs, events such as festivals and traditional events, historic sites, sights, buildings, dialects, and the like. An area feature word is an event that appears in content related to a certain area and does not appear much in content related to another area. Specifically, regional feature words include the names of festivals unique to the region, such as “Nebuta Festival”, “Owara Kaze no Bon”, “Danjiri Festival”, “Daidai”, “Yodakii”, “ Dialects such as “Ookini”. The region described here is, for example, a region as an administrative unit such as a prefecture, city, ward, county, town, or village. Moreover, the area classified according to the cultural sphere etc. may be sufficient. Or the area which combined these, for example, Tohoku district, Kanto district, districts, such as a port district, a city, etc. may be sufficient. The regional feature words are preferably information that does not include information such as place names and addresses. The region described here is preferably, for example, a region composed of one or more regions in which corresponding region feature words are similar. For example, when two regions are included in one region, it is preferable that region feature words that are highly relevant to each of the two regions are similar. That is, it is preferable that regions having high similarity of region feature words constitute one region. Moreover, it is preferable that the distance between the areas which comprise one area | region is short. The one region described here is, for example, a region constituted by one or more regions divided into one cluster by the clustering unit 108 described later based on the similarity of region feature words. Note that one area may be composed of only one area. When there is one region that constitutes the region corresponding to the region feature word, it may be considered that only that region is a region where the region feature word is similar.

  The area information may be information that can identify the area. For example, identification information that can identify the region may be used. The area information may be information serving as an area index. The area information may be information indicating the area range. The information indicating the range of the region may be considered as information that can define the boundary line (contour) of the region. The area information is, for example, information that defines a boundary line (contour) of the area, for example, information that indicates the boundary line of the area with coordinate information or vector information in association with latitude and longitude. Further, the region information that is information indicating the range of the region may be information that specifies one or more regions constituting the region using, for example, region identification information such as a region name. Also, in this case, information that defines the boundary line of the area is stored in advance in a storage unit (not shown) or the like, and as a result, the boundary line of the area configured by the area Can be obtained. The area information may be information indicating an address, a place name, a station name, or the like included in the area as long as it is information that can specify the area range, that is, the range from where to where.

  The regional feature word may be stored in the regional feature word storage unit 101 together with the regional feature degree in association with the regional feature degree that is information indicating the strength of association with the region. Here, the strength of the relationship with the region may be considered as the strength of the relationship with the region indicated by the corresponding region information. As long as the regional feature is information that can indicate the strength of the relationship, the data format or the like such as a numerical value or a value such as “high” or “low” may be used. Further, the regional feature words may be stored in the regional feature word storage unit 101 in association with time information that is information indicating the time. The period described here is a season, a time zone, a period, or the like. The time information is, for example, information indicating the start and end date, time, and the like. Further, the regional feature word may be stored in the regional feature word storage unit 101 in association with the field information that is information indicating the field of the regional feature word. The field is a field to which the regional feature word belongs, and may be considered as an attribute of the regional feature word. The field may be a broader word that is a character string indicating a broader concept of regional feature words. For example, when the regional feature word is “Seki Saba”, the field may be “food”, “marine products”, or the like. The time information and the field information may be appropriately input by the user or the like through an input device or the like with reference to the regional feature words. In addition, time information, field information, etc. are prepared in advance, and when the region-related information acquisition unit 106 described later acquires the region-related information, the time information and the field information are added to the search condition to perform a search. The region feature words extracted from the region-related information obtained by this search may be associated with these time information and field information. The fact that the regional feature words are associated with the region information or the like means that, for example, the associated information is managed as one record such as a database. There is no limitation on the process or timing at which information such as regional feature words, regional information, regional features, field information, and time information is stored in the regional feature word storage unit 101. For example, these pieces of information input via the recording medium may be accumulated in the regional feature word storage unit 101. These pieces of information input via the input device may be accumulated in the regional feature word storage unit 101. In addition, the regional feature word, the regional information, and the regional feature degree may be accumulated by the regional feature word accumulation unit 109 described later. The regional feature word storage unit 101 is preferably a non-volatile recording medium, but can also be realized by a volatile recording medium.

  The position information acquisition unit 102 acquires position information that is information indicating a position. The position information may be information that can specify the position in any one of the areas indicated by the area information described above. The position information is coordinate information such as latitude and longitude. However, it may be regional identification information such as a regional name, or information such as an address or a station name. The position information acquisition unit 102 may acquire the position information in any way. For example, you may acquire the positional information input from the user via the input device etc. which are not shown in figure. Further, the position information acquisition unit 102 may acquire position information that is information indicating a position where the user exists. For example, coordinate data acquired using a GPS (global positioning system) (not shown) may be acquired as the position information. In addition to the position information, the position information acquisition unit 102 may further acquire time information that is information indicating time. The time information is preferably information on the current time when the position information is acquired. The time information may be information including date information. The time information may be acquired from, for example, a clock inside the information processing apparatus 1 or may be acquired from an NTP server or the like via a network using NTP (Network Time Protocol) or the like. Here, the description of the configuration of communication means for performing network connection is omitted. The position information acquisition unit 102 may further acquire field designation information that is information for designating a field in addition to the position information. For example, the position information acquisition unit 102 may acquire information specifying a field input by a user or the like via an input device (not shown). When receiving position information, etc., from a user or the like via an input means such as a numeric keypad, a keyboard, or a mouse, the position information acquisition unit 102 is realized by a device driver for the input means such as a numeric keypad or a keyboard, or control software for a menu screen. You may do it. Moreover, when acquiring position information etc. from GPS etc., the position information acquisition part 102 may be implement | achieved from MPU, memory, etc., for example. The processing procedure of the position information acquisition unit 102 is realized by software, and the software is recorded in a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit). Further, the position information acquisition unit 102 may or may not include a GPS or the like.

  The region feature word acquisition unit 103 acquires from the region feature word storage unit 101 a region feature word corresponding to region information indicating a region including a position indicated by the position information acquired by the position information acquisition unit 102. Specifically, the area feature word acquisition unit 103 detects area information indicating a range including the position indicated by the position information acquired by the position information acquisition unit 102, and determines the area feature word associated with the area information. Obtained from the local feature word storage unit 101. For example, when the area information includes information defining the latitude and longitude coordinates of the boundary line of the area, the latitude and longitude coordinates indicated by the position information are stored in the area feature word storage unit 101. It is determined whether or not it is included in the range indicated by any of the region information in the region information associated with the word. If it is included in the range indicated by any region information, the region feature word acquisition unit 103 reads out the region feature word corresponding to the region information from the region feature word storage unit 101. Further, for example, when the region information is composed of region names, the region feature word acquisition unit 103 reads the region feature word corresponding to the region information including the region name indicated by the position information from the region feature word storage unit 101. You may make it appear. Further, when the regional feature word is associated with the regional feature word, the regional feature word acquisition unit 103 may acquire the regional feature word according to the regional feature degree. For example, a predetermined number of regions specified in advance from the region feature words corresponding to the region information indicating the region including the position indicated by the position information acquired by the position information acquisition unit 102 in descending order of the corresponding region feature degree A feature word may be acquired. Further, only the values of the corresponding regional feature values that are equal to or greater than the average of the regional feature values corresponding to the regional feature words corresponding to the region information may be acquired.

  When the regional feature word is associated with the time information, the regional feature word acquisition unit 103 is the regional feature word associated with the time information including the time indicated by the time information acquired by the position information acquisition unit 102. Thus, the area feature word corresponding to the area information indicating the area including the position indicated by the position information acquired by the position information acquisition unit 102 may be acquired from the area feature word storage unit 101. For example, when the time information associated with a certain regional feature word is information indicating a period from March to May, and the time information acquired by the position information acquisition unit 102 is April 18, The regional feature word is determined to be a regional feature word associated with time information including the time indicated by the time information acquired by the position information acquisition unit 102.

  When the regional feature word is associated with the field information, the regional feature word acquisition unit 103 associates the regional feature word with the field information including the field indicated by the field designation information acquired by the position information acquisition unit 102. In this case, the area feature word corresponding to the area information indicating the area including the position indicated by the position information acquired by the position information acquisition unit 102 may be acquired from the area feature word storage unit 101. For example, when the field information associated with a certain regional feature word is “food” and the field designation information acquired by the position information acquisition unit 102 is “food”, the regional feature word is It is determined that the region feature word is associated with the field information including the field indicated by the field designation information acquired by the acquisition unit 102.

  The regional feature word acquisition unit 103 can be usually realized by an MPU, a memory, or the like. The processing procedure of the regional feature word acquisition unit 103 is usually realized by software, and the software is recorded in a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  The regional feature word output unit 104 outputs one or more regional feature words acquired by the regional feature word acquisition unit 103. Here, output means display on a display, projection using a projector, printing on a printer, sound output, transmission to an external device, accumulation or temporary storage in a recording medium, other processing device or other It is a concept that includes delivery of processing results to a program or the like. The regional feature word output unit 104 may construct a list using one or more regional feature words acquired by the regional feature word acquisition unit 103 and display the list of regional feature words. Further, when displaying the list, the region feature words may be arranged according to the region feature degree corresponding to the region feature word. For example, the regional feature words may be arranged in order from the highest regional feature, that is, from the top in the descending order of the relevance to the region, or from the bottom. In addition, the regional feature word output unit 104 temporarily stores one or more regional feature words acquired by the regional feature word acquisition unit 103 in a memory (not shown) or the like, and the user inputs characters into an input field (not shown), for example. Each time it is input, the region feature words that match the input character string in the forward direction may be read out in order of the region feature degree, and a so-called drop-down list or the like may be configured and displayed. The program described here is an instruction for a procedure of processing (calculation / operation / communication) performed by a computer. The regional feature word output unit 104 may be considered as including or not including an output device such as a display or a speaker. The regional feature word output unit 104 can be implemented by output device driver software, or output device driver software and an output device. Further, an MPU or the like for outputting, that is, accumulating regional characteristic words in a memory or the like may be provided.

  The area information receiving unit 105 receives one or more pieces of area information that is information indicating the area. The region described here is the same as the region described above. The area information is information that can identify an area such as an area name, for example. The regional information is, for example, information on a search keyword provided in a search WEB site (search site) or the like, or character string information that can be used as a part thereof. In addition, the area information receiving unit 105 may further receive information regarding the position of a plurality of area information. In other words, the information on the positions of the plurality of pieces of area information is information on the positions of the areas indicated by the pieces of area information. As a result, the information regarding the position of the plurality of area information may be information that can calculate the distance between the plurality of areas. For example, it may be information indicating the position of a region indicated by a plurality of region information, such as latitude and longitude coordinates, or may be information indicating a distance between regions indicated by a plurality of region information. The information indicating the position of the region may be any position in the region, for example, information on the position considered to be the center of the region, the position of the center of gravity, etc., or one position on the boundary of the region It may be information indicating. The position considered as the center of the area may be considered as the position where the administrative center of the area, for example, a prefectural office or a government office exists. The reception described here refers to reception of information input from an input device such as a keyboard, mouse, and touch panel by a user, reception of information transmitted via a wired or wireless communication line, an optical disk, a magnetic disk, and a semiconductor memory. It is a concept including reception of information read from a recording medium. The area information input means may be anything such as a numeric keypad, keyboard, mouse or menu screen. The area information receiving unit 105 can be realized by a device driver of input means such as a numeric keypad or a keyboard, control software for a menu screen, and the like.

  The region-related information acquisition unit 106 performs a search using the search condition including the region information received by the region information reception unit 105, and acquires one or more region-related information that is information related to the region indicated by the region information. . The region related information is, for example, information on a WEB page including information related to the region. The information on the WEB page may be information that can be browsed or downloaded by a so-called WEB browser or the like, for example, information in an HTML format or an XML format. Here, the region-related information is information including character string information. Note that here, information related to a region that can be downloaded from WEB or the like is also considered to be information on the WEB page. For example, the region-related information acquisition unit 106 searches for a WEB page using search conditions each including a plurality of region information received by the region information reception unit 105, and uses the information on the WEB page of the region indicated by each region information. Each area related information is acquired. Specifically, the region-related information acquisition unit 106 configures a search condition including the region information received by the region information reception unit 105, and searches the WEB page on a predetermined WEB specified in advance. To a search site or the like through a network such as the Internet. Then, the result of the search executed by the search site using the search condition is received via the network. The search site is a WEB site that provides a search program for searching a WEB page, for example. Normally, this search result is information indicating addresses such as URLs of a plurality of WEB pages that match the search conditions, and therefore the information of the WEB page indicated by the search results is acquired from the WEB site or the like via a network. This acquired information is region-related information. Usually, the search result of a search site or the like is often information of a plurality of addresses. Therefore, when acquiring region-related information, the degree of matching with the search condition in the address information obtained as a search result is It is preferred to use only a predetermined number of high pre-specified address information. The search condition is, for example, a character string configured using the area information received by the area information receiving unit 105, that is, a keyword string. In this case, the search condition may be composed only of regional information. The search condition may be a search query including area information, for example. For example, it may be an SQL sentence including the area information in the where clause. When the region information receiving unit 105 receives a plurality of pieces of area information, the region related information acquiring unit 106 performs a search using a search condition including each of the plurality of pieces of region information received by the region information receiving unit 105. Each area related information of the area indicated by is acquired. The acquired area-related information is accumulated in, for example, a storage medium (not shown). The region-related information acquisition unit 106 transmits and receives search conditions and search results using a transmission unit and a reception unit (not shown) connected to a network such as the Internet. Here, the transmission unit and the reception unit are used. The description of the configuration etc. is omitted. Further, the region-related information acquisition unit 106 does not necessarily need to search the WEB page and acquire the region-related information that is information on the WEB page of the region indicated by each region information. For example, when a region-related information database or the like is prepared in advance in a storage unit (not shown), the region-related information may be acquired from the database using a search condition including the region information. The region-related information acquisition unit 106 can usually be realized by an MPU, a memory, or the like. The processing procedure of the region-related information acquisition unit 106 is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  The region feature word extraction unit 107 extracts a region feature word from the region related information acquired by the region related information acquisition unit 106. Here, the regional feature word extraction unit 107 may obtain a character string having a high appearance frequency as a regional feature word from the regional related information obtained corresponding to one piece of regional information. It is conceivable that the regional feature word is not necessarily a character string characteristic of one region. For example, the region-related information acquired for other regions may be a character string having a high appearance frequency.

  For this reason, for example, the area information receiving unit 105 receives a plurality of pieces of area information, and the area related information acquisition unit 106 acquires one or more pieces of area related information for each area information. For the character string that appears in the region-related information of the region indicated by the one region information acquired by the region-related information acquisition unit 106, the extraction unit 107, the appearance frequency in the region-related information of the region indicated by the one region information, Indicates the strength of the relationship between the character string and the region using the frequency of appearance of the region related information including the character string that matches the character string in the region related information of the plurality of regions indicated by the plurality of region information. The regional feature degree which is information is calculated. Then, an area feature word that is a character string whose area feature degree satisfies a predetermined condition is extracted. The character string here is a character string that satisfies a predetermined condition among character strings that appear in the region-related information. For example, a character string with a specific part of speech. When the region-related information acquisition unit 106 acquires a plurality of pieces of region-related information for a region indicated by one piece of region information, the region feature word extraction unit 107 handles the plurality of pieces of region-related information as one piece of region-related information.

  Specifically, the region feature word extraction unit 107 extracts a character string (for example, a word) in the region related information from the region related information of the region indicated by the one region information acquired by the region related information acquisition unit 106 by morphological analysis. Part-of-speech is acquired, and only a character string of a specific part-of-speech, for example, a character string of nouns and adjectives is extracted from the character strings in the region-related information. As a morphological analysis system, for example, “Mecab (Japanese candy)” (http://mecab.sourceforge.net/), “ChaSen” (http://chasen.naist.jp), etc. are used. Is possible.

  Next, a character string characteristic in the region-related information of each region is extracted from the character strings of nouns and adjectives extracted by morphological analysis. Here, a so-called tf-idf technique is used for this extraction. Specifically, for each character string extracted from within the region-related information of one region, the region feature degree is calculated using the following formula. Since tf-idf is a known technique, detailed description thereof is omitted. For tf-idf, see, for example, http: // mikilab. doshisha. ac. jp / dia / research / report / 2008/1110/002 / report2000081110002. Please refer to “html” and the like.

  DLC is a regional feature (Degree of Local Characteristic), tf is an appearance frequency of a character string in the region-related information of one region, and df includes the same character string of the region-related information of other regions Represents the frequency of appearance of region-related information. The plurality of other regions are preferably all regions other than the one of the regions indicated by the region information received by the region information receiving unit 105, but may be some of the regions. Normally, the area information received by the area information receiving unit 105 is one area level among the area levels such as “prefecture, city”, “ward”, and “town”. Information. A region indicated by region information at one region level is usually a region that does not overlap. Of the character strings that frequently appear in the region-related information in one region (here, the WEB page), the characters that do not appear frequently or do not appear in the region-related information in other regions by using the above formula The value of the regional feature (DLC) becomes higher as the column is reached. Then, for each regional level, those having a high regional feature value are extracted as regional feature words of that one region. Here, for example, a region feature value having a value greater than or equal to a threshold value previously designated by the user or the like is designated and acquired as a region feature word. By doing in this way, it becomes possible to acquire a character string having a high appearance frequency in one region and not having a high appearance frequency in another region as a regional feature word. Similarly, the regional feature word extraction unit 107 may sequentially extract the regional feature words for each of a plurality of pieces of regional information.

  The tf-idf method is used to calculate the regional feature, but the extracted regional feature words and regional features differ depending on the level of the target region. Depending on what level the region level is set to, the calculation time of the region feature degree and the accuracy of the result have a great influence. Therefore, what level of regional information should be used may be appropriately selected according to its use and situation. The regional level may be considered as information indicating the regional hierarchy.

  In addition, as described above, the area information received by the area information receiving unit 105 is normally the area level such as “prefecture (city), city (city), word (ward), town (town)”, etc. Although it is information about one regional level, the regional information receiving unit 105 may receive regional information of a plurality of different levels for each regional level. When the regional information receiving unit 105 receives regional information according to different regional levels such as “prefecture, city (city), ward (town), town”, etc., the regional related information acquisition unit 106 Separately, region-related information is acquired, and the region feature word extraction unit 107 may calculate a region feature degree for each region level, and may acquire a region feature word or the like for each region level. In this case, the regional feature word storage unit 109 to be described later may be stored in the regional feature word storage unit 101 in association with level information that is information indicating the level to which the regional feature word corresponds, or clustering. The unit 108 may perform clustering or the like for each level area. Further, in this case, the position information acquisition unit 102 described above acquires level designation information for designating which level information is associated with the position information along with the position information. The word acquisition unit 103 may acquire the regional feature word from the regional feature words corresponding to the level information designated by the level designation information. Alternatively, the region feature word acquisition unit 103 may acquire the region feature words from the region feature words corresponding to all the level information regardless of the level. However, the regional feature word extraction unit 107 may extract regional feature words by a method other than the above. The regional feature word extraction unit 107 can usually be realized by an MPU, a memory, or the like. The processing procedure of the regional feature word extraction unit 107 is usually realized by software, and the software is recorded in a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  When the regional feature word extraction unit 107 extracts and calculates one or more regional feature words and their regional feature degrees for each of a plurality of pieces of regional information, the clustering unit 108 extracts and calculates each of the plurality of pieces of regional information. Similar regional information is clustered using the regional feature words and their regional feature degrees, and information on the distances between a plurality of regions acquired using information on the location of the regional information.

  For example, if the regional feature word extraction unit 107 or the like acquires regional related words for each region as described above, for example, when the level of the region is too subdivided, the adjacent region or distance There are cases where the region feature words extracted between regions close to are similar. In such a case, rather than considering each region with similar regional feature words as a single region and associating the regional feature words with each other, the region formed by merging these regions is a single region. Therefore, it is preferable to associate a region feature word with the area in order to reduce the amount of data. In addition, when acquiring regional feature words for one of the merged regions, the region feature words for other similar regions that were merged are also presented as a supplement. When performing a search or the like, there is an effect that it becomes easy for the user to grasp what kind of area the area is.

  For this reason, the clustering unit 108 creates a cluster of regions where the region feature words are similar. Here, for example, a clustering method called a centroid method can be used. For the centroid method, refer to “http://www.ie.reitaku-u.ac.jp/˜tak/datB/datB_clust.pdf”. Specifically, first, the characteristics of one region G are defined as vectors as shown below.

Here, / LC _G is assumed to be a vector of region G. Here, this vector is referred to as a regional feature word vector. lg represents the regional feature degree of a certain regional feature word in one region. lg _{1 to} lg _n correspond to regional feature words obtained by merging the regional feature words extracted by the regional feature word extraction unit 107 from a plurality of regions received by the regional information reception unit 105 by excluding duplicates. As the value of each element, for example, the value of the regional feature degree for the corresponding regional feature word is used. However, if one of the merged regional feature words is not included in the regional feature word extracted from the regional G, the value of the element corresponding to the regional feature word in the regional feature word vector of the regional G is, for example, 0. The regional feature words to be merged may not be all of the regional feature words extracted in each region. For example, regional feature words having a regional feature value (DLC) value from the top to a predetermined rank are used. There may be.

The clustering unit 108 uses the regional feature word vectors configured by using the regional feature degrees acquired by the regional feature word extraction unit 107 for the two regions G ₁ and G ₂ , and the regional information reception unit 105. The similarity between the two regions G ₁ and G ₂ is determined using the following formula using the distance between the two regions acquired using the information on the positions of the two regions G ₁ and G _{2 received} by To do. As described above, the n vector elements constituting the area feature word vector / LC _G2 are the same area features as the area feature words corresponding to the n vector elements constituting the area feature word vector / LC _G1. Suppose that it is the local feature degree about a word.

w ₁ and w ₂ (= 1−w ₁ ) (0 ≦ w ₁ , w ₂ ≦ 1) are weights, and distance (G ₁ , G ₂ ) is a distance between the regions G ₁ and G ₂ . In addition, if the information regarding the positions of the two regions G1 and G2 received by the region information receiving unit 105 is a value of the distance between the regions, the value is used as it is, and the information regarding the positions of the two regions G ₁ and G ₂ is used. If the information is information indicating the position of the area, the distance between the positions is calculated by calculation or the like. The values of w ₁ and w ₂ are set in advance by appropriately determining values considered appropriate by changing the values on a trial basis and calculating the similarity between regions. The greater the value of the above equation, the higher the similarity between the two regions. This method of comparing vectors to find the similarity between two regions is called a vector space method. However, here, it differs from the general vector space method in that the value of the distance between two regions is incorporated as an element. By adding such a distance element, even if the degree of similarity of the regional feature words in the two regions is high, the two regions are not clustered as the same region if the distance between the two regions is greatly separated. Can be. If there is no need to add a distance element, the distance element may be omitted.

  Such processing is sequentially performed on the combination of two regions extracted from the plurality of regions from which the region feature word extraction unit 107 has extracted the region feature words, and the similarity between the two regions is sequentially calculated, The regional feature vectors of similar regions will be collected sequentially. At the time of grouping, for example, a vector having a value obtained by averaging the values of the elements of the region feature word vectors to be grouped, that is, a barycentric vector is generated as a vector after grouping. By repeatedly performing this process, it is possible to divide a region having similar extracted region feature words into clusters. In addition, the clustering unit 108 generates, for example, a centroid vector as a result of clustering, and a character string corresponding to an element having a high value in the vector, that is, a character string having a high regional feature is used as a regional feature word of each cluster. get. Or, in each of one or more regional feature vectors combined into one cluster by clustering, local words corresponding to high value elements, that is, regional feature words corresponding to high regional feature values are deleted and merged. The regional feature word group obtained in this way may be acquired as the regional feature word of the one cluster. High regional feature means that the regional feature is a value exceeding a predetermined threshold, the value of the regional feature is a value from a higher rank to a predetermined rank, and the like. As for the regional feature, the clustering unit 108 temporarily stores information indicating regions divided into clusters, that is, information indicating similar regions, for example, in a storage unit (not shown). In addition, the regional feature words acquired corresponding to the clustered regional information are temporarily stored.

  The clustering unit 108 can be usually realized by an MPU, a memory, or the like. The processing procedure of the clustering unit 108 is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  The region feature word storage unit 109 stores the region feature words extracted by the region feature word extraction unit 107 in the region feature word storage unit 101 in association with region information including the region indicated by the region information. For example, the region feature word storage unit 109 associates the region feature word extracted by the region feature word extraction unit 107 for one region of the plurality of region information with the region information including the region indicated by the one region information. Are stored in the local feature word storage unit 101. For example, in the case where clustering as described above is not performed, the regional feature word storage unit 109 stores information indicating the boundary line of the region indicated by one region information in the region range information storage unit 114 and the like described later. The information is acquired from information that defines the boundary line of the area indicated by the area information and stored in association with the area information, and this information is stored in association with the area feature word as area information. Alternatively, regional information or the like may be accumulated as region information instead of information such as a boundary line. Further, as described above, when the clustering unit 108 performs clustering of the region, the region feature word storage unit 109 indicates one or more region feature words and the region information divided into one cluster by the clustering. The region feature word storage unit 101 stores the region information including the region in association with each other. For example, the area information stored in association with the area information in the area range information storage unit 114 or the like, which will be described later, is stored in the area range information storage unit 114, which will be described later, etc. Is obtained from information that defines the boundary of the region indicated by, and the information of the boundary line formed by merging this information is used as region information and associated with the region feature word used when judging the similarity between regions Accumulate. In addition, instead of obtaining information that defines the boundary line of the region from the region range information storage unit 114 or the like, a WEB page or the like that provides information that provides numerical information about the national land via a network such as the Internet The information indicating the boundary line and outline of the area may be acquired from the information. Further, the regional feature word accumulation unit 109 may accumulate, as one area information, area information or the like of one or more areas divided into one cluster instead of information such as a boundary line. Further, the area feature word storage unit 109 may store the area feature degree corresponding to the area feature word extracted by the area feature word extraction unit 107 described above in association with the area feature word. Further, time information or field information received from a user or the like via an input device such as a keyboard via a reception unit (not shown) or the like may be stored in association with the regional feature. The regional feature word storage unit 109 can be usually realized by an MPU, a memory, or the like. The processing procedure of the regional feature word storage unit 109 is usually realized by software, and the software is recorded in a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  The search condition generation unit 110 generates a search condition including the region feature word output by the region feature word output unit 104. The search condition is, for example, a keyword string including regional feature words. In this case, the local feature word may be a search condition. Further, the search condition may be, for example, a search query including an area feature word. The search condition is, for example, an SQL sentence including a region feature word in the where clause. In addition, the search condition generation unit 110 may generate a search condition using the regional feature words that the designation receiving unit 113 has received the designation out of the regional feature words output by the regional feature word output unit 104. . For example, the search condition may be generated using the regional feature words designated by the user via the designation receiving unit 113 to be described later among the regional feature words displayed as a list by the regional feature word output unit 104. The search condition generation unit 110 can usually be realized by an MPU, a memory, or the like. The processing procedure of the search condition generation unit 110 is usually realized by software, and the software is recorded in a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  The search unit 111 performs a search using the search condition created by the search condition creation unit 110 and acquires information indicating the search result. The search unit 111 searches for a WEB page using a search condition via a network such as the Internet. Note that description of a transmission unit, a reception unit, and the like for the search unit 111 to transmit search conditions and receive search results via the network is omitted here. The search performed by the search unit 111 is the same as the search performed by the region-related information acquisition unit 106 described above. Note that the information acquired as a search result by the search unit 111 is not limited to information including a character string, and may be location information such as a tourist attraction that matches the search condition, or an image that matches the search condition. It may be information. The information acquired as a search result by the search unit 111 may be WEB page information indicating a search result by a search site indicating a WEB page address or the like, or a WEB page comment. The search unit 111 can usually be realized by an MPU, a memory, or the like. The processing procedure of the search unit 111 is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  The search result output unit 112 outputs information indicating the search result of the search unit 111. The output described here refers to display on a display, projection using a projector, printing on a printer, sound output, transmission to an external device, storage on a recording medium, and output to other processing devices or other programs. It is a concept including delivery of processing results. The search result output unit 112 may be considered as including or not including an output device such as a display or a speaker. The search result output unit 112 can be implemented by output device driver software, or output device driver software and an output device.

  The designation accepting unit 113 accepts designation of one or more regional feature words among the regional feature words displayed in a list by the regional feature degree output unit 104. For example, when the user clicks on one of the regional feature words displayed in the list using a mouse or the like, the designation of the regional feature word is accepted by accepting an event in which the region feature word is clicked. The input means for designating the regional feature words may be anything such as a numeric keypad, a keyboard, a mouse, or a menu screen. The designation receiving unit 113 can be realized by a device driver for input means such as a numeric keypad or a keyboard, control software for a menu screen, and the like.

  The area range information storage unit 114 can store area information and information defining a boundary line (outline) of the area indicated by the area information in association with each other. Since the information defining the boundary line of the region information is the same as the information defining the boundary line of the region described above, the description thereof is omitted here. The area range information storage unit 114 is preferably a non-volatile recording medium, but can also be realized by a volatile recording medium.

  Next, the operation of the information processing apparatus 1 will be described using the flowchart of FIG. Here, a case where a region feature word is acquired using a plurality of pieces of region information will be described as an example.

  (Step S201) The area information receiving unit 105 determines whether a plurality of area information has been received. If accepted, the process proceeds to step S202. If not accepted, the process proceeds to step S208.

  (Step S202) The region-related information acquisition unit 106 searches the WEB page by using the region-related information corresponding to each region indicated by the plurality of region information received in step S201, for example, using each region information as a search keyword or the like. Acquired by performing etc. As the region-related information corresponding to each region, for example, a predetermined number of region-related information is acquired.

  (Step S203) The region feature word extraction unit 107 acquires a predetermined character string for each region by morphological analysis using the region-related information acquired for each region indicated by the plurality of region information received in step S201. This predetermined character string is, for example, a character string of a predetermined part of speech such as an adjective and a noun. In step S202, when a plurality of pieces of area-related information are acquired for one area, the plurality of pieces of area-related information about the one area are handled as one piece of area-related information, and morphological analysis is performed.

  (Step S204) The area feature word extraction unit 107 extracts area feature words for each area indicated by the plurality of area information received in step S201 using the tf-idf method. Specifically, the region feature word extraction unit 107 calculates the appearance frequency in the region-related information from which the character string is obtained for each character string acquired from the region-related information for each region in step S203, and Of the region-related information acquired for the remaining regions other than the column acquisition source, the appearance frequency of the region-related information including the same character string as the character string is calculated. However, when a plurality of pieces of area-related information are acquired for one area in step S202, the plurality of pieces of area-related information about the one area are handled as one piece of area-related information by, for example, merging. Then, by inputting these calculated appearance frequency values into the above-described equation (1), the regional feature degree of each character string is calculated. Then, a character string whose calculated regional feature degree is equal to or greater than a predetermined threshold specified in advance is extracted as a regional feature degree corresponding to each region. The calculated regional feature degree is temporarily stored in a storage medium such as a memory in association with the extracted range feature word, for example.

  (Step S205) The clustering unit 108 clusters similar regions by using the region feature word vector configured for each region using the region feature degree calculated in step S204. Specifically, for each of the plurality of regions indicated by the plurality of region information received in step S201, a region feature word vector as shown in Expression (2) is configured, and the region feature word vectors of the two regions are described above. By substituting into equation (3), the similarity between regions is calculated sequentially. Then, clustering is performed by putting together the calculated regions with high similarity. In addition, a region feature word vector for the clustered region is acquired.

  (Step S206) The region feature word storage unit 109 acquires region information for regions configured by similar regions divided by clustering in step S205. For example, one or more region range information corresponding to the region information of one or more regions constituting each region is acquired from the region range information storage unit 114, and the one or more region range information is combined to form a boundary line of the region Is configured.

  (Step S207) The area feature word storage unit 109 acquires the area information acquired in Step S206, the area feature words acquired in Step S204 for the area constituting the area indicated by the area information, and the information calculated in Step S204. The regional feature words corresponding to the regional feature words are stored in the regional feature word storage unit 101 in association with each other. It should be noted that the area feature words corresponding to the area feature words constituting the area feature word vector used when acquiring the area information by clustering may be stored in the area feature word storage unit 101 in association with the area information. The regional feature word storage unit 109 may store field information, time information, and the like received from a user or the like via a reception unit (not shown) or the like in association with the regional feature word. Then, the process returns to step S201.

  (Step S208) The position information acquisition unit 102 determines whether position information has been acquired. For example, it is determined whether or not the position information of the current position of the user has been acquired via a GPS (not shown) or the like. Alternatively, it may be determined whether there is position information input by a user or the like. If position information has been acquired, the process proceeds to step S209. If position information has not been acquired, the process returns to step S201.

  (Step S209) The position information acquisition unit 102 determines whether field designation information has been acquired. For example, it is determined whether or not field designation information input by a user or the like has been received. If there is no input of field designation information by the user or the like, the position information acquisition unit 102 may acquire the field designation information designated by default in advance, and may determine that the position information has been obtained. The field designation information designated by default in advance is, for example, field designation information for designating all field information, field designation information indicating no field designation, or the like. If the field information has been acquired, the process proceeds to step S210. If the field designation information has not been acquired, the process returns to step S209.

  (Step S210) The position information acquisition unit 102 acquires time information that is information of the current time. Note that this step may be omitted if the time information is not used when acquiring regional feature words.

  (Step S211) The area feature word acquisition unit 103 detects area information indicating an area including the position indicated by the position information acquired in step S208.

  (Step S212) The area feature word acquisition unit 103 is an area feature word associated with the area information detected in step S211 and is specified by the area specification information received in step S209, and in step S210. The area feature word associated with the time information indicating the period including the time indicated by the acquired time information is read from the area feature word storage unit 101. Moreover, you may make it read also the regional feature degree matched with the said regional feature word. Note that when acquiring the regional feature words, only the regional feature words associated with the regional feature degree larger than the predesignated value may be acquired.

  (Step S213) The regional feature word output unit 104 outputs the regional feature word acquired in step S212. For example, the regional feature word output unit 104 configures a list using the regional feature words acquired in step S212, and displays the list on a monitor or the like (not shown). Further, when creating this list, the regional feature words may be arranged in descending order of the associated regional feature degree.

  (Step S214) The designation receiving unit 113 determines whether or not the regional feature word output unit 104 has received designation for one or more regional feature words out of the regional feature words output by, for example, list display. If accepted, the process proceeds to step S215. If not accepted, the process returns to step S214.

  (Step S215) The search condition generation unit 110 creates a search condition including the area feature word that has been designated in step S214, specifically, a search query.

  (Step S216) The search unit 111 performs a search using the search condition created in step S215. For example, the search condition created in step S215 is transmitted to a search site on the WEB and the search result is acquired.

  (Step S217) The search result output unit 112 outputs the search result performed in step S216. For example, it is displayed on a monitor (not shown). Then, the process returns to step S201.

  In the flowchart of FIG. 2, the process is terminated by powering off or a process termination interrupt.

  Hereinafter, a specific operation of the information processing apparatus 1 in the present embodiment will be described.

  FIG. 3 is a conceptual diagram of the information processing apparatus 1 according to the present embodiment. In this example, the information processing apparatus 1 is assumed to be a portable information terminal that can be connected to a wireless or wired network. Examples of the portable information terminal include a mobile phone, a multi-function mobile phone, a small mobile computer, a PDA (Personal Digital Assistant), and a navigation terminal. The information processing apparatus 1 is connected to the WEB server 2 or the like via, for example, a wireless or wired network. Here, it is assumed that the information processing apparatus 1 has a GPS as a means for acquiring position information.

  When the user inputs a list of area names as a plurality of area information to the information processing apparatus 1, the area information receiving unit 105 receives the list of area names. The area name here is, for example, the name of a city (however, if there is a town or village that does not belong to the city, the name of the town or village).

  FIG. 4 is a diagram illustrating a list of area names that are area information received by the area information receiving unit 105.

  The region-related information acquisition unit 106 creates a search query using the received region names in order, and transmits the search query to a search site on a web designated in advance via a transmission unit (not shown). Then, the URL of the WEB page having a high degree of relevance with respect to the area name, which is transmitted as a search result from the search site, is received via a receiving unit (not shown). Then, a WEB page is acquired from this URL. Here, it is assumed that the region-related information acquisition unit 106 acquires a WEB page having the highest degree of relevance among the search results for each region name. That is, for each region, 10 WEB page data, specifically, 10 HTML files are acquired. This acquired WEB page is the region related information. The area-related information acquisition unit 106 combines the acquired 10 WEB pages into one document, that is, one HTML file. Thereby, one area related information can be obtained about one area.

  Next, the region feature word extraction unit 107 extracts a region feature word for each region name received by the region information reception unit 105 using the region related information acquired corresponding to the region name. The region feature word extraction unit 107 performs morphological analysis on the region-related information acquired corresponding to each region name shown in FIG. 4 using Mecab or the like, so that the part of speech included in the region-related information is a noun and an adjective. Extract a string that is For example, from the region-related information acquired for “Toyama City” shown in FIG. 4, “Toyama Castle”, “Thunderbird”, “Kan Buri”, “Toyama Regional Railway”, “Japan Sea”, “Business Hotel” , Suppose that a word such as “daiya” is detected.

  The region feature word extraction unit 107 first acquires “Toyama Castle”, which is the first character string, for the region whose region name is “Toyama City”, and “Toyama Castle” in the region related information of “Toyama City”. The appearance frequency of is calculated. In addition, the frequency of appearance of the region-related information including the character string “Toyama Castle” among the region-related information acquired for the region name other than “Toyama City” is calculated. Then, the region-related information acquired for the remaining region information of all the region-related information including the appearance frequency of “Toyama Castle” in tf of the above formula (2) and the character string “Toyama Castle” in df By substituting the appearance frequency for, the regional feature (DLC) is calculated. If the value of the regional feature value exceeds a predetermined threshold value, the character string “Toyama Castle” is extracted as a regional feature word. If the threshold is not exceeded, it is not extracted as a regional feature word. When the regional feature is a value that decreases as the feature increases, the fact that the regional feature is smaller than the threshold is interpreted as exceeding the threshold. Here, for example, if the threshold value is exceeded, the character string “Toyama Castle” is extracted as a regional feature word. Then, the regional feature word, the regional name, and the calculated regional feature degree are associated with each other and temporarily stored in a storage medium or the like (not shown).

  Similarly, for other character strings such as “Thunderbird” obtained from the regional feature word “Toyama City”, whether or not the character string is a regional feature word is sequentially determined. The character string determined as is associated with the area name and the calculated area characteristic, and is temporarily stored in a storage medium (not shown). Here, with respect to “Toyama City”, it is assumed that “Toyama Castle”, “Kan Buri”, “Toyama Regional Railway”, and “Dayai” are determined as regional feature words.

  Further, the same processing as described above is repeatedly performed for other regions.

  FIG. 5 is a diagram illustrating an example of the region feature words extracted from the region-related information acquired for each region name as a result of repeating the process of extracting the region feature words as described above. In the figure, “region name” indicates a region name, “region feature word” indicates a region feature word, and “region feature degree” indicates a region feature degree.

  Next, the clustering unit 108 performs clustering of the region indicated by the region name using the extracted region feature word and the calculated region feature. First, the clustering unit 108 creates, for each region name, a region feature vector having region feature values corresponding to all region feature words appearing in the region feature word extraction result shown in FIG. 5 as vector values. . For example, if the number of area feature words excluding overlapping area feature words from the merged area feature words obtained for each area name shown in FIG. 5 is m, the area feature vector is m It becomes an m-dimensional vector having an element. In the regional feature vector for a certain regional name, the value of the element corresponding to the regional characteristic word that does not exist for the regional name is set to “0”. The value of the element corresponding to the regional feature word is set to the value of the regional feature degree corresponding to the regional feature word.

  For example, in the regional feature vectors [lg1, lg2, lg3, lg4, lg5, lg6,..., Lgm] generated based on FIG. , Lg3 is the regional feature of “Toyama District Railway”, lg4 is the regional feature of “Daiyi”, lg5 is the regional feature of “Maimirou”, and lg6 is the regional feature of “Kurobe Watermelon” Become. The regional feature word vector of “Toyama City” is [60, 50, 40, 36, 0,..., 0], and the regional feature word vector of “Uozu City” is [0, 48, 30, 32, 80, 0. .., 0], “Kurobe City” area feature word vectors are [0, 40, 30, 28, 0, 75. Note that the values and the like in this specific example are for explanation, and are different from those based on actual search results and calculation results.

  The clustering unit 108 performs clustering using these regional feature word vectors. First, the similarity between two regions is sequentially calculated by substituting the respective region word feature vectors into Equation (3) for a combination of two regions of a plurality of regions. Then, two regions having the highest similarity with one region are collected, and the center vector of the region feature word vectors is set as the region feature word vector of the newly collected region group. By repeating the same process and collecting the regions, the regions can be divided into clusters. Note that the clustering may be terminated when there are no two regions (including a grouped region) that have a similarity that exceeds a predetermined threshold value, for example, or the regions included in one clustering. It is also possible to make a determination using the upper limit or the upper limit of the number of clusters formed by clustering.

  Then, the clustering unit 108 acquires the regional feature degree of each cluster when the clustering is completed. Specifically, the regional feature words constituting the centroid vector, which is the regional feature word vector of each cluster finally obtained by clustering, are the regional feature words from the top to the predetermined rank as regional feature words of each cluster. get. In addition, it can be appropriately changed according to the acquisition method of regional feature words of each cluster, the purpose, etc. For example, among the centroid vectors, those having a regional feature value exceeding a predetermined threshold are used as the regional feature values of each cluster. You may get it. Also, a predetermined number of regional feature words may be acquired in descending order of the regional feature degree from among the regional feature words corresponding to similar regions constituting each cluster.

  Here, as a result of clustering, for example, a set of Toyama City and Namerikawa City, and a set of Uozu City and Kurobe City are each divided into clusters. In addition, the status characteristic words of the group of Toyama City and Namerikawa City are “Toyama Castle”, “Kanburi”, [Toyama Regional Railway ”,“ Daiai ”, and the local characteristic words of the pair of Uozu City and Kurobe City. , “Mirage”, “Kurobe Watermelon”, “Kurobe Gorge”, “Toyama District Railway”.

  FIG. 6 is a regional range information management table for managing the regional range information stored in the regional range information storage unit 114. The area range information management table includes “area name” and “area range information”. The “region name” is region information, and here is the same region name as the region information received by the region information receiving unit 105. “Region range information” is region range information, and here is a plurality of coordinate information defining a boundary line of a region. This coordinate information indicates coordinates obtained by combining latitude and longitude.

  The region feature word storage unit 109 acquires region information indicating the boundary line of the region for regions formed by similar regions divided by clustering. For example, one or more region range information corresponding to the region names of one or more regions constituting each region divided into clusters is acquired from the region range information storage unit 114, and the one or more region range information is combined. The area information indicating the boundary line of the area of one cluster is configured. The regional feature word storage unit 109 may appropriately acquire regional range information by searching or the like from a server or the like that is provided on the network and can provide the same information as the regional range information storage unit 114. good.

  The region feature word storage unit 109 associates the region feature words corresponding to each cluster acquired by the clustering unit 108, the region feature degree corresponding to the region feature word, and the region information configured corresponding to each cluster. And accumulated in the local feature word storage unit 101. Note that a message or the like prompting the user to input time information or field information corresponding to the regional feature word is displayed immediately before storing the regional feature word in the regional feature word storage unit 101, and is input by the user or the like. The time information, the field information, and the like may be further stored in association with the regional feature words. In addition, as for the area feature words stored in the area feature word storage unit 101, the field information and time information input by the user at an arbitrary timing through an input reception unit (not shown) are stored in association with each other. May be.

  FIG. 7 is a regional feature word management table for managing regional feature words and the like accumulated in the regional feature word storage unit 101. The regional feature word management table has items of “region ID”, “region information”, “region feature word”, “region feature degree”, “time information”, and “field information”. The “area ID” is identification information given to manage the area. Further, items other than “area ID” correspond to the above-described area information, area feature words, area feature, time information, and field information, respectively. Information on each item constituting one record of the regional feature word management table is information associated with each other. For example, in FIG. 7, the region whose “region ID” is “001” is a region including a set of Toyama City and Namekawa City, and the region whose “region ID” is “002” is Uozu City. It is an area that includes a set with Kurobe City.

  Here, it is assumed that the user moves to Toyama City with the information processing apparatus 1 and displays a search screen for performing a search on a display unit or the like (not shown) in order to perform a search for Toyama City. With the display of the search screen or the like as a trigger, the GPS (not shown) that the information processing apparatus 1 has is coordinate information (N36.42.16.27, E137.12.53.19) as current position information. To get. The position information acquisition unit 102 acquires position information acquired by the GPS.

  The area feature word acquisition unit 103 searches for area information including the position indicated by the position information acquired by the position information acquisition unit 102 in the “area information” of the area feature word management table shown in FIG. Here, “area information” of the record whose “area ID” is “001” is detected as area information indicating an area including the position indicated by the position information. The position information acquisition unit 102 acquires the current time information from, for example, a processing unit (not shown) that measures the time in the information processing apparatus 1. For example, it is assumed that the time information acquired here is information “March 7th 10:00 am”. In addition, the position information acquisition unit 102 acquires information specifying a field that is specified in advance by a user or the like. Here, it is assumed that the field designation information “sightseeing” and “food” has been designated in advance. Before and after acquiring the position information, information requesting information specifying the field may be displayed to the user or the like, and the field information input from the user may be acquired according to the display. For this reason, the regional feature word acquisition unit 103 performs “regional feature words” “Toyama Castle”, “Kan Buri”, “Toyama District Railway”, “Daidai” of the record whose “region ID” is “001”. ”, Etc.,“ regional feature words associated with “time information” indicating a period including “10 am on March 7” and “field information” such as “tourism” or “food”. Read from the word storage unit 101. Since the time information corresponding to “Toyama Castle” is “9:00 am to 5:00 pm” without specifying a date, it is determined that the time information indicates a period including time information. Since the time information corresponding to “Toyama district railway” is “5 am to 22:00 pm” without specifying a date, it is determined that the time information indicates a period including time information. Also, since the time information corresponding to “cold bristle” is from November 1st to February 28th, it is determined as time information indicating a period including time information. By using the time information in this way, for example, it is possible to prevent the acquisition of regional feature words for events that the user cannot use during the current period. In addition, since the field information of “Toyama Castle” and “Toyama District Railway” is “Tourism” and the field information of “Kanburi” is “Food”, these field information are the fields specified by the field designation information. It is determined to be information. For this reason, “Toyama Castle”, “Toyama District Railway” and “Kanburi” are acquired as regional feature words. The regional feature words acquired in this way are temporarily stored in a storage medium (not shown) by the regional feature word output unit 104.

  Next, it is assumed that the user inputs the characters “to” in an input field or the like on a search screen or the like.

  The area feature word output unit 104 searches for area feature words starting with “to” among the area feature words read out by the area feature word acquisition unit 103 by a forward matching search or the like. Here, “Toyama Castle” and “Toyama District Railway” are searched. Then, a list including the searched regional feature words is constructed and displayed in the vicinity of the input field. At this time, the list display is performed so that the regional feature words having high regional features, in this case “Toyama Castle”, are displayed at positions closest to the input field.

  FIG. 8 is a diagram showing a display example of a list of regional feature words.

  If more characters are added, the regional feature words may be further searched using the added characters, and the region feature words as a search result may be displayed as a list.

  Next, when the user selects “Toyama Castle” from the list of regional feature words displayed by operating the touch panel or the like, the regional feature word output unit 104 inputs the selected regional feature word into an input field or the like. Display the selected screen.

  Then, when the user gives an instruction for performing a search to the information processing apparatus 1, the search condition generation unit 110 creates condition information including “Toyama Castle” that is the selected regional feature word, for example, a search query. The created condition information is, for example, “q = Toyama Castle” transmitted as a GET parameter to a predetermined search WEB site (where q is a variable used as a search condition in the search WEB site), etc. is there. Then, the search unit 111 transmits the condition information to a search web site designated in advance via a network or the like. And the information of the WEB page which shows the search result which a WEB site etc. transmits is received via a network. The search result output unit 112 displays a WEB page indicating the received search result on a monitor or the like (not shown). When the search is performed on an SQL server (not shown) or the like, if the field name (item name) in which the regional feature word is managed is “local feature word”, for example, the condition generated by the search condition generating unit 110 The information may be “SELECT field name FROM table name WHERE region feature word =“ Toyama Castle ”; However, “table name” is a table name in which regional feature words and information to be searched are managed, and “field name” is information to be searched, in other words, information that can be output as a search result is managed. Field name.

  FIG. 9 is a diagram illustrating a display example of search results by the search result output unit 112.

  In addition, although the case where position information is acquired by GPS has been described here, for example, as shown in FIG. 10, a map is displayed on a monitor or the like (not shown), and a touch panel or the like is input for the position on the map information. When the designation is received by operating the device, the position information of the actual area corresponding to the position where the designation is accepted may be accepted. The map information for displaying such a map may be stored in a map information storage unit or the like (not shown). Further, the display of the map information may be performed by a display unit (not shown) or the like, and the designation of the displayed position on the map may be received by a reception unit (not shown) or the like. In addition, the process in which the position information acquisition unit 102 or the like acquires the coordinate information of the actual area from the position on the map received by such a reception unit is known as a technique for displaying a map image on a WEB page or the like. Since there are, description is abbreviate | omitted here.

  In addition, when the regional feature word stored in the regional feature word storage unit 101 is associated with the regional level information that specifies the regional level, the location information is acquired using the map information as described above. In addition, scale information indicating the scale of the displayed map is received in order to receive the designation of the position, and the regional feature word acquisition unit 103 selects from the regional feature words corresponding to the regional level information corresponding to the scale information. You may make it acquire a local feature word.

  For example, when the scale is smaller than 1 / 755,000, the regional feature word extracted using the local information at the municipal level is used. When the scale is larger than 1 / 755,000, the prefecture The regional feature words extracted using the level regional information may be used. For example, when the scale is small, a plurality of prefectures are displayed on the map, so that the area can be specified only by the difference in the prefecture level. For this reason, it is only necessary to display a regional feature word that shows the difference at the prefecture level as a regional feature word. Conversely, even if a regional feature word at a finer level can be acquired, the selected location on the map Because different regional feature words are acquired with a subtle shift, there is a possibility of confusion for the user. For this reason, it is possible to present regional feature words at an appropriate level according to the scale of the map displayed from the map by selecting the regional feature words at a level corresponding to the scale. . Note that the correspondence between the scale information and the regional level information may be managed by storing information in which the scale information and the regional level information are associated with each other, for example, in a storage unit (not shown). Further, the same information may be used as the scale information and the regional level information.

  In the above specific example, the regional feature word output unit 104 displays the regional feature words including the characters input in the input field. However, as shown in FIG. A list including at least a part of the read regional feature words may be displayed, and the regional feature words may be selected from the list. Further, the field information corresponding to the area feature word is displayed in association with the area feature word, for example, displayed side by side, and when one of the field information is selected, the field designation information corresponding to the field information is acquired as the position information. The region feature word acquisition unit 103 may re-acquire only the regional feature words corresponding to the field designation information. By doing in this way, it is possible to narrow down by the field of regional feature words.

  As described above, according to the present embodiment, it is possible to acquire an area feature word that is information of a character string that is highly relevant to the position indicated by the position information and perform an information search using the area feature word. Is possible. Thereby, for example, it becomes possible to present to the user characteristic information highly relevant to the area where the user currently exists.

  Further, in the present embodiment, it is possible to extract regional feature words that are character string information highly relevant to the region designated by the user or the like and store them in the regional feature word storage unit 101.

  In addition, since the region feature words are accumulated by associating the similar regions with the clustered regions by clustering, the region feature words of the regions similar to the regions designated by the user or the like are supplementarily added. It is possible to output information, and it is also possible to present information on characteristic events in similar areas.

  In each of the above 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.

  Further, in each of the above embodiments, it goes without saying that two or more communication means (such as an information transmission unit) existing in one apparatus may be physically realized by one medium.

  In the above embodiment, information related to processing executed by each component, for example, information received, acquired, selected, generated, transmitted, and received by each component. In addition, information such as threshold values, mathematical formulas, addresses, etc. used by each component in processing is retained temporarily or over a long period of time on a recording medium (not shown) even when not explicitly stated in the above description. It may be. Further, the storage of information in the recording medium (not shown) may be performed by each component or a storage unit (not shown). Further, reading of information from the recording medium (not shown) may be performed by each component or a reading unit (not shown).

  Further, although cases have been described with the above embodiments where the information processing apparatus is a stand-alone, the information processing apparatus may be a stand-alone apparatus or a server apparatus in a server / client system. In the latter case, the output unit or the reception unit receives an input or outputs a screen via a communication line.

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

  The software that realizes the information processing apparatus in each of the above embodiments is a program as described below. In other words, this program associates a computer with a region feature word that is a character string highly related to a region and region information that is information indicating a region including a region that is highly related to the region feature word. Stored in the region feature word storage unit, a location information acquisition unit that acquires location information that is information indicating the location, a region feature word that is a character string highly related to the region, and the region feature word A region including the position indicated by the position information acquired by the position information acquisition unit from the region feature word storage unit in which the region information that is the information indicating the region including the region having high relevance is stored. This is a program for functioning as an area feature word acquisition unit that acquires an area feature word corresponding to the area information indicating, and an area feature word output unit that outputs the area feature word acquired by the area feature word acquisition unit.

  In the program, the functions realized by the program do not include functions that can be realized only by hardware. For example, a function that can be realized only by hardware such as a modem or an interface card in an acquisition unit that acquires information or an output unit that outputs information is not included in the function realized by the program.

  Further, the computer that executes this program may be singular or plural. That is, centralized processing may be performed, or distributed processing may be performed.

  FIG. 12 is a schematic diagram illustrating an example of an external appearance of a computer that executes the program and realizes the information processing apparatus according to the embodiment. The above-described embodiment can be realized by computer hardware and a computer program executed on the computer hardware.

  In FIG. 12, a computer system 900 includes a computer 901 including a CD-ROM (Compact Disk Read Only Memory) drive 905 and an FD (Floppy (registered trademark) Disk) drive 906, a keyboard 902, a mouse 903, a monitor 904, and the like. Is provided.

  FIG. 13 is a diagram showing an internal configuration of the computer system 900. In FIG. 13, in addition to the CD-ROM drive 905 and the FD drive 906, a computer 901 is connected to an MPU (Micro Processing Unit) 911, a ROM 912 for storing a program such as a bootup program, and the MPU 911. A RAM (Random Access Memory) 913 that temporarily stores program instructions and provides a temporary storage space, a hard disk 914 that stores application programs, system programs, and data, and an MPU 911 and a ROM 912 are interconnected. And a bus 915. The computer 901 may include a network card (not shown) that provides connection to the LAN.

  A program that causes the computer system 900 to execute the functions of the information processing apparatus according to the above-described embodiment is stored in the CD-ROM 921 or FD 922, inserted into the CD-ROM drive 905 or FD drive 906, and transferred to the hard disk 914. May be. Instead, the program may be transmitted to the computer 901 via a network (not shown) and stored in the hard disk 914. The program is loaded into the RAM 913 when executed. The program may be loaded directly from the CD-ROM 921, the FD 922, or the network.

  The program does not necessarily include an operating system (OS) or a third-party program that causes the computer 901 to execute the functions of the information processing apparatus according to the above-described embodiment. The program may include only a part of an instruction that calls an appropriate function (module) in a controlled manner and obtains a desired result. How the computer system 900 operates is well known and will not be described in detail.

  The present invention is not limited to the above-described embodiment, and various modifications are possible, and it goes without saying that these are also included in the scope of the present invention.

  As described above, the information processing apparatus and the like according to the present invention are suitable as an information processing apparatus and the like that assists in searching, and are particularly useful as an information processing apparatus and the like that assists in searching for information related to a region.

DESCRIPTION OF SYMBOLS 1 Information processing apparatus 101 Area feature word storage part 102 Location information acquisition part 103 Area feature word acquisition part 104 Area feature word output part 105 Area information reception part 106 Area related information acquisition part 107 Area feature word extraction part 108 Clustering part 109 Area feature Word accumulation unit 110 Search condition generation unit 111 Search unit 112 Search result output unit 113 Designation reception unit 114 Area range information storage unit

Claims (13)

A region feature word that is stored in association with a region feature word that is a character string that is highly relevant to a region and region information that is a region that includes a region that is highly relevant to the region feature word A storage unit;
A position information acquisition unit that acquires position information that is information indicating a position;
An area feature word acquisition unit that acquires an area feature word corresponding to the area information indicating an area including the position indicated by the position information acquired by the position information acquisition unit from the area feature word storage unit;
An information processing apparatus comprising: an area feature word output unit that outputs the area feature word acquired by the area feature word acquisition unit. An area information receiving unit for receiving area information, which is information indicating the area;
A region-related information acquisition unit that performs a search using a search condition including the region information received by the region information reception unit, and acquires region-related information that is information related to the region indicated by the region information;
A region feature word extraction unit that extracts the region feature word from the region related information acquired by the region related information acquisition unit;
The local feature word accumulation part which accumulates the regional feature word extracted by the regional feature word extraction part in the regional feature word storage part in association with the regional information including the area indicated by the regional information. The information processing apparatus according to claim 1 or 2. The regional information receiving unit receives a plurality of the regional information,
The region-related information acquisition unit performs a search using a search condition including each of the plurality of region information received by the region information reception unit, and acquires each region-related information indicated by each region information,
The region feature word extraction unit, for a character string that appears in the region related information of the region indicated by the one region information acquired by the region related information acquisition unit, appears in the region related information of the region indicated by the one region information In the region-related information of the plurality of regions indicated by the frequency and the plurality of region information,
Using the appearance frequency of the region related information including the character string that matches the character string, the region characteristic degree that is the information indicating the strength of the relation of the character string with the region is calculated, and the region characteristic degree is Extracting a local feature word that is the character string satisfying a predetermined condition;
The region feature word storage unit stores the region feature words extracted by the region feature word extraction unit in the region feature word storage unit in association with the region information including a region indicated by the one region information. 2. The information processing apparatus according to 2. The regional information receiving unit further receives information related to positions of a plurality of regional information,
One or more regional feature words extracted and calculated by the regional feature word extraction unit for a plurality of pieces of regional information, their regional feature degrees, and information on distances between the plurality of regions obtained using information on the location of the regional information And a clustering unit for clustering the similar regional information using
The regional feature word storage unit associates the one or more regional feature words with region information including a region indicated by the regional information grouped into one cluster by the clustering, and stores the region feature words in the regional feature word storage unit. The information processing apparatus according to claim 3. The regional feature word is stored in association with a regional feature degree, which is information indicating the strength of association with the region,
The information processing apparatus according to claim 1, wherein the regional feature word acquisition unit acquires the regional feature word according to the regional feature degree. The region-related information acquisition unit is information on a WEB page of a region indicated by each region information by performing a WEB page search using search conditions each including the plurality of region information received by the region information receiving unit. The information processing apparatus according to claim 2, wherein each area-related information is acquired. A search condition generation unit that generates a search condition including the region feature word output by the region feature word output unit;
A search unit that performs a search using the search condition created by the search condition creation unit and acquires information indicating a search result;
The information processing apparatus according to claim 1, further comprising: a search result output unit that outputs information indicating a search result of the search unit. The regional feature word output unit displays a list of regional feature words acquired by the regional feature word acquisition unit,
A designation receiving unit for accepting designation of one or more regional feature words of the list-displayed regional feature words;
The information processing according to claim 7, wherein the search condition generation unit generates a search condition by using a regional feature word that is designated by the designation receiving unit among the regional feature words output by the regional feature word output unit. apparatus. The region information is information indicating the range of the region,
The position information acquisition unit acquires the position information which is information indicating a position where the user exists,
The area feature word acquisition unit detects area information indicating a range including a position indicated by the position information acquired by the position information acquisition unit, and stores the area feature word associated with the area information. The information processing apparatus according to claim 1, wherein the information processing apparatus is acquired from a section. The regional feature word is stored in the regional feature word storage unit in association with time information which is information indicating time,
The position information acquisition unit further acquires time information,
The region feature word acquisition unit is a region feature word associated with time information including the time indicated by the time information, and indicates the region including the position indicated by the position information acquired by the position information acquisition unit The information processing apparatus according to claim 1, wherein a regional feature word corresponding to information is acquired from the regional feature word storage unit. The regional feature word is stored in the regional feature word storage unit in association with the field information that is information indicating the field,
The position information acquisition unit further acquires field designation information that is information for designating a field,
The region feature word acquisition unit is a region feature word associated with field information including a field indicated by the field specification information, and indicates a region including a position indicated by the position information acquired by the position information acquisition unit The information processing apparatus according to claim 1, wherein an area feature word corresponding to area information is acquired from the area feature word storage unit. A region feature word that is stored in association with a region feature word that is a character string that is highly relevant to a region and region information that is a region that includes a region that is highly relevant to the region feature word An information processing method performed using a storage unit, a location information acquisition unit, a regional feature word acquisition unit, and a regional feature word output unit,
The position information acquisition unit acquires position information that is information indicating a position; and
The area feature word acquisition unit acquires the area feature word corresponding to the area information indicating the area including the position indicated by the position information acquired in the position information acquisition step from the area feature word storage unit. Steps,
An information processing method comprising: an area feature word output step in which the area feature word output unit outputs the area feature word acquired in the area feature word acquisition step. Computer
A region feature word that is stored in association with a region feature word that is a character string that is highly relevant to a region and region information that is a region that includes a region that is highly relevant to the region feature word A storage unit;
A position information acquisition unit that acquires position information that is information indicating a position;
A regional feature word that is a character string that is highly relevant to the region, and a regional feature word acquisition unit that is highly relevant to the regional feature word;
A program for functioning as a regional feature word output unit that outputs a regional feature word acquired by the regional feature word acquisition unit.

Images