JP2007109183A - Literature information analysis device and literature information analysis method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To generate a map wherein usability of a user is improved. <P>SOLUTION: Contour lines 101A, 101B or the like show distribution density of literature information included in the map 100. The map 100 is also displayed with a plurality of keywords 102. The keyword 102 is a main keyword characterizing each piece of the literature information of a literature information group configuring the map 100. The map 100 is also displayed with a target symbol 110 showing coordinates of target information described with an outline of invention contents, research contents or the like. One or more guide words 111 are respectively displayed around the target symbol 110 correspondingly to respective up-and-down and right-and-left coordinate axes of the map 100. The guide word 111 shows a revealed or potential keyword distributively present around the target information. The user can sets it as material for investigating directionality of patent application, or research and development. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to a document information analysis apparatus and a document information analysis method for analyzing document information such as patent documents and academic documents, for example.

  For example, by investigating patent documents as document information, it is possible to find out the direction of research and development or to make business plans. For this purpose, patent documents that match a predetermined purpose are extracted from a large group of patent documents, and the extracted patent documents are analyzed. A representation of this analysis result on a two-dimensional plane is known as a so-called patent map.

  However, it takes a lot of time and effort to select a patent document that meets a purpose from a huge group of patent documents and confirm the contents of each document to create a patent map.

Therefore, the present applicant has previously proposed an apparatus capable of automatically creating a patent map (Patent Document 1).
JP 2005-149346 A

  According to the technique described in the above document, it is possible to automatically extract a main keyword from a group of patent documents and easily create a patent map in which the distribution density of the patent document and the main keyword are arranged.

  By the way, when trying to make the created patent map useful for patent application strategy, research and development, or business planning, what is the position of the currently planned application contents and research contents on the patent map? Need to figure out. However, with the apparatus described in the above-mentioned document, it is not possible to automatically position the application contents and research contents that are currently planned, and there is room for improvement in usability.

  In addition, when the planned application contents and research contents are actually executed, the effect of the execution result on the patent map cannot be grasped, and there is room for improvement in terms of usability.

  Furthermore, it is not easy to look for future directions for application contents and research contents from the patent map. Therefore, there is room for improvement from the viewpoint of effective use of the automatically created patent map.

  Accordingly, an object of the present invention is to provide a literature information analysis apparatus and a literature information analysis method that can grasp the position of target information in generated map information. Another object of the present invention is to provide a literature information analysis apparatus and a literature information analysis method that can indicate the positioning of target information in map information and can support a user's decision making regarding the target information. . The further objective of this invention will become clear from description of embodiment mentioned later.

  In order to solve the above-described problem, a document information analyzing apparatus according to one aspect of the present invention includes a document information storage unit that stores a plurality of document information that has been digitized, and a predetermined document among the stored document information. A document coordinate calculation unit that calculates the coordinates of each document information of a predetermined document information group by performing principal component analysis based on a combination of a plurality of predetermined keywords extracted from the information group and the number of appearances; It is calculated by a keyword coordinate calculation unit that calculates the coordinates of each predetermined keyword and a document coordinate calculation unit by performing principal component analysis based on the total number of document information including each keyword and the number of occurrences of each predetermined keyword. The distribution density of each document information is calculated based on the coordinates of each document information, and the calculated distribution density and each predetermined keyword are visualized and mapped. A map generation unit that generates information, a target coordinate calculation unit that calculates coordinates of target information specified by a user by performing a predetermined principal component analysis, and the presence of target information is indicated at the calculated coordinates of target information A target coordinate display unit that displays display elements in association with each other on map information.

  Examples of the document information include patent documents (including open gazettes, registered gazettes) and academic papers. The document information is digitized and stored in the document information storage unit. Among a plurality of document information stored in the document information storage unit, a plurality of predetermined keywords are extracted from a predetermined document information group. The predetermined document information group can be defined as a group of document information that matches a search condition input by the user, for example. The predetermined plural keywords are, for example, main keywords that characterize each piece of document information in a predetermined document information group.

  The document coordinate calculation unit performs principal component analysis based on a combination of a plurality of predetermined keywords and the number of appearances of the plurality of predetermined keywords, and calculates the coordinates of each document information in a predetermined document information group. Principal component analysis is a method of multivariate analysis. To put it simply, each sample information that contains many variables is represented by several comprehensive indicators (principal components) that most directly represent the differences. This is an analysis method that reduces the number of dimensions.

  Similarly, the keyword coordinate calculation unit calculates the coordinates of each predetermined keyword by principal component analysis. The map generation unit calculates the distribution density of the document information based on the coordinates of each document information. For example, the map generation unit can detect the density of the document information for each block by dividing the entire area of the map into a plurality of blocks and calculating the number of document information located in each block. For example, the map generation unit arranges display elements (for example, contour lines) corresponding to the distribution density of the document information and display elements (for example, keyword characters themselves or symbols) indicating the presence of the keywords on the map area. As a result, map information is generated. This map information is expressed, for example, on a two-dimensional plane, but is not limited thereto, and can be expressed in a three-dimensional space.

  The user who visually recognizes the map information can specify the target information. Target information is information that the user wants to position in the map information, for example, information indicating the outline of the invention to be applied for in the future, or information indicating the outline of the research content to be studied from now on To do. For example, the user can input target information on the spot via a keyboard switch or the like, or can specify an already created document file as target information.

  When the target coordinate calculation unit calculates the coordinates of the target information, the target coordinate display unit displays a display element indicating the presence of the target coordinates superimposed on the map information. Thereby, the user can easily grasp the position of the target coordinates in the map information.

  In the embodiment of the present invention, the target coordinate calculation unit includes the target information in one of the predetermined document information groups, and performs the principal component analysis based on the combination and the number of occurrences of each predetermined keyword, The coordinates of the target information are calculated by performing a principal component analysis based on the first combination of keywords and the number of appearances without including the target information in the predetermined document information group and the first mode for calculating the coordinates of The coordinates of the target information can be determined in any one of the two modes: the second mode.

  When the first mode is selected, the target information is included in one of the predetermined document information groups. Therefore, if the coordinates of each document information and the coordinates of each keyword are calculated again, the map different from the original map information Information is generated. That is, the first mode is a mode in which target information is reflected in map information. On the other hand, when the second mode is selected, the target information is not included in the predetermined document information group, and therefore the map information is not affected even if the target information is input. In this way, multiple types of modes are prepared in advance, and if any one mode can be arbitrarily selected by the user, the difference between the case where target information is included in the basis of map information and the case where it is not included is confirmed. Can improve usability.

  In the embodiment of the present invention, on the map information, a guide word extracting unit that extracts a guide word for indicating the presence of a keyword located in a predetermined direction from the coordinates of the target information, and the extracted guide word are stored in a predetermined manner. A guidance word display unit that is displayed in association with the direction and superimposed on the map information.

  A guide word is information for indicating a keyword existing around target information. The keyword indicated as the guide word may be already displayed on the map information, or may not be displayed on the map information. Guidance words can point to either or both revealed keywords and potential keywords, respectively.

  The guide word extraction unit associates a guide word for indicating the presence of a keyword located in a predetermined direction from the coordinates of the target information with the calculated distance between the coordinates of the keyword and the coordinates of the target information. Can be extracted. Then, the guide word display unit can display the extracted guide words superimposed on the map information in association with a predetermined direction according to the calculated distance. For example, it can be displayed as a guide word in order from a keyword that is far from the target coordinate, or in order from a short distance from the target coordinate.

  The user adopts one or more of the displayed guide words, adds the adopted guide word to the target information, and re-inputs the coordinates of the target information corrected by the addition of the guide word. Is recalculated and displayed overlaid on the map information.

  In the embodiment of the present invention, when the user selects a guide word displayed on the guide word display unit, the target coordinate calculation unit includes the selected guide word in the target information and recalculates the coordinates of the target information. To do. As a result, the user can change the display position (coordinates) of the target information only by selecting one or more of the displayed guide words without recreating the target information.

  In the embodiment of the present invention, the guide word extraction unit extracts, as guide words, keywords that are not included in the target information among predetermined keywords.

  In the embodiment of the present invention, the guide word extraction unit calculates the distance between the coordinates of the keyword that is not included in the target information among the predetermined keywords and the coordinates of the target information, and the calculated distance is a keyword that is far away. Are preferentially extracted as guide words.

  In the embodiment of the present invention, the guide word extraction unit detects a boundary keyword located in the vicinity of the boundary of the map information among the predetermined keywords, and reads the document information including the detected boundary keyword from the document information storage unit. Thus, a guide word is extracted from words that are not extracted as predetermined keywords in the word group included in the read document information. Thereby, the hidden keyword which is not displayed on map information can be revealed as a guide word.

  In the embodiment of the present invention, the guide word extraction unit has an appearance frequency within a predetermined period specified in advance in a group of words included in the read document information higher than an appearance frequency in a period before the predetermined period. A guide word is extracted from words that are relatively large and are not extracted as predetermined keywords.

  The user can designate a predetermined period (for example, the past half year from the present, the past one year from the present, etc.) when designating the target coordinates. The guide word extraction unit calculates the appearance frequency in the designated predetermined period and the appearance frequency in the period before the designated predetermined period for each word in the word group. Note that the period before the predetermined period can be limited to a period specified by the user, such as one year or three years, or a period set as an initial value.

  Information indicating a recent trend is given to the user by extracting words that are relatively higher in appearance frequency than those in the past and not displayed on the map information as guide words. be able to.

  In the embodiment of the present invention, the guide word extraction unit includes a first extraction unit that extracts a keyword that is not included in the target information among the predetermined keywords as a guide word, and the vicinity of the boundary of the map information among the predetermined keywords. , The document information including the detected boundary keyword is read from the document information storage unit, and extracted as predetermined keywords from the word group included in the read document information. And a second extraction unit for extracting guide words from non-words.

  According to another aspect of the present invention, a program includes a computer, a document information storage unit that stores a plurality of document information that is digitized, and a predetermined document information group that is extracted from a predetermined group of document information. The document coordinate determination means for calculating the coordinates of each document information in a predetermined document information group by performing principal component analysis based on the combination and the number of occurrences of a plurality of keywords, and the document information including each predetermined keyword By performing principal component analysis based on the total number and the number of occurrences of each predetermined keyword, the keyword coordinate determining means for calculating the coordinates of each predetermined keyword, and the coordinates of each document information calculated by the document coordinate determining means Based on this, the distribution density of each document information is calculated, and the calculated distribution density and each predetermined keyword are visualized to map information. A map generating means for generating, a target coordinate determining means for calculating the coordinates of the target information designated by the user by performing a predetermined principal component analysis, and a display element indicating the presence of the target information at the calculated coordinates of the target information Are made to function as target coordinate display means for displaying and superimposing them on the map information. This program can realize a predetermined function by being executed on one or a plurality of computers.

  A document information analysis method according to still another aspect of the present invention includes a step of acquiring a search condition from a user, a step of searching for a plurality of document information that matches the search condition, and a predetermined information included in each searched document information Respectively extracting a plurality of keywords, calculating the coordinates of each retrieved document information by performing principal component analysis based on the combination and number of occurrences of each extracted keyword, Calculating the coordinates of each predetermined keyword by performing principal component analysis based on the total number of document information including each keyword and the number of occurrences of each predetermined keyword, and each calculated by the document coordinate determination means A step of calculating a distribution density of each document information based on the coordinates of the document information, and the calculated distribution density and each predetermined keyword Visualizing each predetermined graphic element in association with each other, generating map information, obtaining target information specified by the user, and performing predetermined principal component analysis on the coordinates of the acquired target information A step of calculating the information, a step of associating a graphic element indicating the presence of the target information with the calculated coordinates of the target information and displaying it superimposed on the map information, and moving the target information in a predetermined direction on the map information For extracting a guide word for the user, a step of displaying the extracted guide word in correspondence with a predetermined direction on the map information, and a guide word displayed on the guide word display unit are selected by the user In this case, the target information including the selected guide word is calculated again, and the coordinates of the target information are calculated again, and the recalculated coordinates are associated with the target information. Comprising a step of moving the graphic element to be, a.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. The document information analysis apparatus 1 according to the present embodiment can be configured as a computer apparatus including a map control unit 10, a guide word control unit 20, and an information storage unit 30. The document information analysis apparatus 1 is connected to the client terminal 2 so as to be capable of bidirectional communication via a communication network such as the Internet or a LAN (Local Area Network). The client terminal 2 can be configured as, for example, a personal computer or a portable information terminal (including a mobile phone).

  The map control unit 10 generates and outputs a technical map 100 based on a large number of document information stored in the information storage unit 30. The generated map 100 is transmitted to the client terminal 2 via the communication network. The map 100 may be stored in the client terminal 2 or may not be stored in the client terminal 2. Details of the map control unit 10 will be described later.

  The guide word control unit 20 extracts keywords based on a large number of document information stored in the information storage unit 30 and displays the keywords on the map 100 as guide words. Details of the guide word control unit 20 will be described later.

  The information storage unit 30 stores a large number of document information such as patent publications, registration bulletins, and scientific and technical papers.

  The configuration of the map 100 will be described. The map 100 is generated according to the purpose instructed by the user. For example, the user can select only a predetermined document information group from among a large number of document information groups stored in the information storage unit 30 by designating a technical field desired to be investigated, a specific search word, or the like. it can. The content of the document information group selected by the user is analyzed by the map control unit 10 and a map 100 is generated.

  The contour lines 101A, 101B, 101C and 101D are display elements indicating the distribution density of the document information included in the map 100. For example, the contour line 101A indicates that the number of document information existing therein is 1 or more and less than B1, and the contour line 101B indicates that the number of document information existing therein is B1 or more and less than B2 (B1, B1). B2 is a natural number). As described above, the number of document information included therein increases step by step from 101A to 101B, 101C, and 101D.

  A plurality of keywords 102 are also displayed on the map 100. These keywords 102 are main keywords that characterize each piece of document information of the document information group constituting the map 100, and may be referred to as the main keywords 102 in the following description.

  On the map 100, a target symbol 110 indicating the coordinates of the target information is displayed. The target information is information that the user desires to conduct a positioning survey on the map 100. Examples of the target information include an outline of the invention content and an outline of the research content.

Around the target symbol 110, one or a plurality of guide words 111 are displayed corresponding to the upper and lower and left and right coordinate axes of the map 100, respectively. The guide word 111 is information indicating a manifested or potential keyword that exists in a distributed manner around the target information. Thereby, the user can obtain hints for correcting the content of the target information, and can be used as a material for examining the direction of patent application and research and development.
Hereinafter, more detailed examples of the present embodiment will be described. It should be noted that the content disclosed in Japanese Patent Application Laid-Open No. 2005-149346 can be used within the scope necessary for carrying out the present invention.

FIG. 2 is a block diagram illustrating a functional configuration of the document information analysis apparatus 1. The map control unit 10 includes, for example, a map generation condition input reception unit 11, a document extraction unit 12, a document coordinate calculation unit 13, a keyword extraction unit 14, a keyword coordinate calculation unit 15, a map generation unit 16, and a map display. It can comprise including the part 17. FIG.
In addition, as an example of the information storage unit 30, a document database (in the figure, database is abbreviated as “DB”) 31, a word database 32, and an index database 33 can be provided.
The document database 31 stores a plurality of document information. The word database 32 is used as a dictionary. The index database 33 is for managing what keywords are included in each document.

  The map generation condition input receiving unit 11 is for receiving an input of a map generation condition designated by the user. Accepting means, for example, receiving information indicating map generation conditions designated by the user as electronic information via a communication interface and storing the information in a memory or the like.

  The document extraction unit 12 extracts document information within a range desired by the user by searching the document database 31 and the index database 33 based on conditions specified by the user. The document coordinate calculation unit 13 calculates coordinates on the map 100 by analyzing the extracted document information. For example, the document coordinate calculation unit 13 calculates the coordinates of each document on the two-dimensional plane by performing principal component analysis on the keyword combination and the number of appearances included in each extracted document information.

  The keyword extraction unit 14 extracts a plurality of keywords included therein by analyzing the extracted document information. The keyword coordinate calculation unit 15 calculates the coordinates of the extracted keywords. For example, the keyword coordinate calculation unit 15 calculates the coordinates of each keyword on the two-dimensional plane by performing principal component analysis on the total number and the total number of appearances of each piece of document information including the keyword. Principal component analysis is a technique for multivariate analysis, and is a known technique, so details are omitted.

  The map generation unit 16 generates the map 100 based on the calculated coordinates of each document information and the coordinates of each keyword. For example, the map generation unit 16 sets a large number of block areas by finely dividing a finite two-dimensional plane vertically and horizontally, and calculates the number of document information existing in each block area. Thereby, the map generation unit 16 obtains the distribution density of the document information, and sets the contour lines 101A and the like corresponding to the distribution density.

  The map display unit 17 generates a map 100 that can be visually recognized by the user by allocating predetermined display elements according to the configuration of the generated map 100, and provides the map 100 to the client terminal 2. Examples of the predetermined display element include an outline for indicating each contour line 101A and the like, characters for indicating each keyword, and the like. In addition, a menu display unit for performing operations on the map 100 is also added.

  The user reads the map 100 displayed on the terminal screen of the client terminal 2 to read how the document information group in the specified range is distributed and what keywords are used. Can do.

Then, the user inputs or designates target information 120 for which positioning confirmation on the map 100 is desired. As a method for inputting the target information 120, various methods can be adopted. For example, a form for inputting target information can be provided from the map control unit 10 to the client terminal 2, and the user can manually input the target information 120 on this form.
Alternatively, the user inputs the selected document file as the target information 120 by manually selecting the file name of the document file that has been created and stored in the auxiliary storage device 2005 or the like of the client terminal 2. You can also. More specifically, the user traces the directory hierarchy of the auxiliary storage device 2005, searches for a predetermined document file, and clicks this file name to select it. The data of the document file selected by the user is automatically read out, transmitted to the document analysis apparatus 1 via the communication network CN, and input as target information 120.
Furthermore, by providing a program for recognizing the user's voice and converting it into a text code, the user can input the target information 120 by dictation.

  The guide word control unit 20 includes, for example, a target information input reception unit 21, a target information coordinate calculation unit 22, a target information display unit 23, a guide word extraction unit 24, and a guide word display unit 25. Can do.

  The target information input receiving unit 21 electronically receives and stores the target information 120 input from the user by the method as described above. The target information coordinate calculation unit 22 calculates the coordinates of the input target information 120. The target information coordinate display unit 23 displays the target symbol 110 at the calculated coordinates.

  The guide word extraction unit 24 extracts one or more guide words associated with the target information 120 by referring to the document database 31 and the index database 33. The guide word display unit 25 displays the extracted guide word 111 on the map 100 in association with the direction according to the coordinates.

  FIG. 3 is a configuration explanatory diagram showing an outline of the hardware configuration of the document information analysis apparatus 1 and the client terminal 2. As described above, the document information analysis apparatus 1 can be configured as a server computer or the like.

  The document information analyzer 1 includes, for example, a communication interface (in the figure, the interface is abbreviated as “I / F”) 1001, a CPU (Central Processing Unit) 1002, a ROM (Read Only Memory) 1003, and a RAM (Random Access). Memory) 1004 and an auxiliary storage device 1005 can be provided.

  In the auxiliary storage device 1005, for example, in addition to the OS (Operating System), a document database 31, a word database 32, an index database 33, a guide word extraction program 1100, a display control program 1110, and a principal component analysis program 1120, a structural analysis program 1130, a search program 1140, and a web server program 1150 can be stored.

As described above, the document database 31 stores document information such as patent publications in advance. In the word database 32, for example, words, synonyms, synonyms, and the like inappropriate for keywords such as particles and conjunctions are stored in advance. The keywords included in each document information can be extracted by using the document database 31 and the word database 32, respectively. The index database 33 manages the location of keywords for each piece of document information extracted in this way. Therefore, by using the index database 33, necessary document information can be quickly retrieved from the document database 31 storing a large number of document information.
The guide word extraction program 1100 is a program for realizing the guide word extraction unit 24. The display control program 1110 is a program that performs drawing processing of the map 100 and the target symbol 110 and the like. The principal component analysis program 1120 is a program for performing principal component analysis. The structure analysis program 1130 is a program for analyzing the structure of text data based on a technique such as text mining. The search program 1140 is a program that searches the literature database 31 and the like based on the input search conditions. The web server program 1150 is a program that realizes a web server function.

  The configuration of the client terminal 2 will be described. The client terminal 2 is connected to the document information analysis apparatus 1 via a communication network CN such as the Internet. For example, the client terminal 2 can be configured to include a communication interface 2001, a CPU 2002, a ROM 2003, a RAM 2004, and an auxiliary storage device 2005. is there.

  In addition, the above structure is an illustration and this invention is not limited to this. For example, it may be possible to realize at least a part of each function by using a hardware circuit such as a programmable logic device instead of the program.

  A document information analysis method using the document information analysis apparatus 1 (hereinafter also referred to as the analysis apparatus 1) will be described. FIG. 4 is a flowchart showing an overview of map control processing for generating and outputting the map 100. The flowcharts described below are also the same, but each flowchart shows an outline of the process and is different from an actual program.

  First, the user inputs search conditions via the user interface of the client terminal 2 (S10). The search condition can be performed, for example, by specifying a keyword such as “photocatalyst” or by specifying a patent classification code, a publication date of a document, or the like.

  When acquiring the search condition from the client terminal 2 (S11), the analysis apparatus 1 searches the index database 33 and the document database 31 based on the search condition, and extracts all document information that matches the search condition (S12). More specifically, the index database 33 is used to extract document information having a keyword designated by the user. When document information having the specified keyword is specified, the document information is read from the document database 31. The extracted result is transmitted from the analyzer 1 to the client terminal 2 (S13) and displayed on the screen of the client terminal 2 (S14).

  The user confirms the total number of extracted documents, document names, and the like via the screen of the client terminal 2, and gives approval to the extraction result (S15). If the user is not satisfied with the extraction result, the search condition can be changed and the search can be instructed again.

  When the analysis device 1 confirms the user's approval, the analysis device 1 extracts a keyword from each extracted document information (S16). The keyword extraction result is transmitted from the analysis apparatus 1 to the client terminal 2 (S17) and displayed on the screen of the client terminal 2 (S18). The user confirms whether the desired keyword is included in the keyword extraction result, and gives approval (S19). If the user is not satisfied with the keyword extraction result, it is possible to request another keyword extraction.

  Upon confirming the approval of the user, the analysis device 1 calculates the coordinates of each extracted document information by performing principal component analysis (S20). Subsequently, the analyzer 1 calculates the distribution density of the document information based on the coordinates of each document information (S21).

  The analysis apparatus 1 calculates the coordinates of each extracted keyword by performing principal component analysis (S22). And the analyzer 1 produces | generates the map 100 and transmits to the client terminal 2 (S23). The user confirms the map 100 displayed on the screen of the client terminal 2 (S24).

  FIG. 5 is an explanatory diagram schematically showing how the map 100 is generated. The analysis apparatus 1 calculates the coordinates of each document information and stores them in the document coordinate management table T1. In the document coordinate management table T1, for example, the document number for specifying document information is associated with the X-axis coordinate and the Y-axis coordinate of the document information. Further, the analysis apparatus 1 calculates the coordinates of each extracted keyword (main keyword) and stores it in the keyword coordinate management table T2. For example, the keyword coordinate management table T2 stores a keyword, a document number including the keyword, and the X-axis coordinate and the Y-axis coordinate of the keyword. In the figure, only one document number including a keyword is shown, but all document numbers including the keyword can be included.

  As shown in the lower side of FIG. 5, for example, a large number of block regions 130 can be set on the map 100 by dividing each of the X-axis method and the Y-axis direction of the map 100 by a plurality. The analyzer 1 calculates the distribution density of the document information by calculating the number of document information located in each block region 130.

  FIG. 6 is an explanatory diagram showing a state in which the user manually inputs target information 120 to the displayed map 100. FIG. 6A shows the map 100 before the target information 120 is input. As shown in FIG. 6B, the user manually inputs target information 120 for this map 100. As a result, the coordinates of the target information 120 are calculated, and the target symbol 110 is displayed on the map 100.

  The target symbol 110 indicates the position of the target information 120 on the map 100. Based on the target symbol 110, the user can grasp the position of the target information 120 and make it useful for strategy and policy planning. For example, when the target information 120 is located in an area where the density of the literature information is high, the user can recognize that the research and development is a competition in an overcrowded field, and consider marketability in the overcrowded field. Thus, it is possible to determine whether or not to continue research and development. On the other hand, when the target information 120 is located in an area where there is little literature information, the user considers the reason for the delay in research and development in the field, marketability, etc. Can be judged.

  FIG. 7 is a flowchart showing a process for calculating the coordinates of the target information and displaying the target symbol 110 on the map 100.

  As described above, the user can input the target information 120 to the analysis device 1 by inputting a sentence via the keyboard switch of the client terminal 2 or by selecting a document file that has already been created. (S31). The analysis apparatus 1 stores the target information 120 input from the client terminal 2 in the RAM 1004 or the like (S32).

  The user can also input one or a plurality of set values related to the coordinate display of the target information 120 (S33). Examples of set values that can be input include a display calculation mode and a determination target period. The set value input by the user is stored in the RAM 1004 of the analyzer 1 (S34).

  Note that the user can also specify only the address of the file used as the target information 120. For example, when a document file such as an already created HTML (HyperText Markup Language) file exists on a computer device or storage device different from the client terminal 2, the user can specify a URL (Uniform Resource) indicating the location of the document file. Address information such as (Locator) is input to the analyzer 1. In this case, the analysis apparatus 1 accesses the document file based on the address information input from the user, downloads the document file, and stores it in the auxiliary storage device 1005 or the like. Such a configuration can be realized by providing the analysis apparatus 1 with a proxy server function or a function similar thereto.

  Now, the analysis apparatus 1 analyzes the syntax of the target information 120 input by the user by executing the structure analysis program 1130 (S35). Thereby, unnecessary words such as particles, conjunctions or fixed phrases included in the target information 120 are removed, and only keywords are extracted. The word database 32 is used to remove unnecessary words.

  Next, the analyzing apparatus 1 selects whether or not to reflect the target information 120 in the literature information group in the coordinates of the target information 120 (S36). That is, in the present embodiment, a plurality of types of coordinate calculation modes of the first mode and the second mode are prepared in advance, and the user can freely select any one mode in advance or after the fact.

  The first mode is a mode in which the target information 120 is included in one of the literature information groups included in the map 100 and the coordinates of the target information 120 are calculated (S38). In contrast, the second mode is a mode for calculating the coordinates of the target information 120 without including the target information 120 in the literature information group (S37).

  When the coordinates of the target information 120 are calculated based on one of the first and second modes, the analysis apparatus 1 associates the target symbol 110 with the calculated coordinate and displays the target symbol 110 on the map 100. It is displayed (S39). The user can confirm the positioning of the target information 120 via the screen of the client terminal 2 (S40).

  FIG. 8 is a flowchart showing an overview of the guidance word control process for arranging the guidance word 111 around the target symbol 110. Although details will be described later, the analysis apparatus 1 extracts guide words from keywords included in the map 100 (S41). Since this guide word is selected from the already extracted keyword group, it can be called a known guide word. Next, the analysis apparatus 1 extracts a word that is not displayed as a main keyword from the word group included in the document information group constituting the map 100 as a guide word (S42). Since this guide word does not appear on the map 100, it can be called an unknown guide word.

  Then, the analyzing apparatus 1 places the extracted guide words around the target symbols 110 along the coordinate axes of the map 100 (S43). Briefly, guide words existing in respective directions are arranged on the top, bottom, left, and right of the target symbol 110.

  FIG. 9 is a flowchart showing a process for extracting a known guide word. The analysis apparatus 1 extracts main keywords that are biased in the direction of each coordinate axis around the coordinates of the target information 120 (S52). That is, keywords that are distributed vertically and horizontally in the target information 120 are extracted. Next, the analyzer 1 determines whether or not the extracted keyword is included in the target information 120 (S53). If the keyword is already included in the target information 120 (S53: NO), the next keyword is determined because there is no meaning to extract as a guide word. On the other hand, when the keyword is not included in the target information 120 (S53: YES), the analysis apparatus 1 registers the keyword as a known guide word candidate (S54). The above steps S52 to S54 are executed one by one for the keywords displayed on the map 100 (S51).

  The analysis device 1 calculates the distance between the coordinates of the registered known guide word candidate (keyword) and the coordinates of the target information 120, and arranges the distance to the target information 120 in the order of increasing distance to each coordinate axis direction. Change (S55). Then, the analyzer 1 selects the top n1 known guide words (S56). That is, a keyword that is far from the target information 120 is preferentially selected.

  An example of a method for extracting a known guide word will be described with reference to FIGS. In the flowchart, it has been described that each keyword displayed on the map 100 is determined. However, instead of this, for example, a known guide word can be extracted as follows.

  FIG. 10 shows a state in which displayed keywords dispersed in the coordinate axes X and Y directions of the map 100 are extracted for each coordinate axis direction. The map 100 can be divided into, for example, a first area, a second area, a third area, and a fourth area. Here, when the coordinates of the target information 120 are the origin, the first area is on the positive Y axis, the second area is on the positive X axis, the third area is on the negative Y axis, and the fourth area is on the negative Y axis. Each corresponds to the X axis.

  The analysis apparatus 1 detects in which of the first region to the fourth region the coordinates of each keyword distributed on the map 100 and registers them in the keyword extraction table T3. In the keyword extraction table T3, the keywords included in the keywords and their coordinates are associated with each of the first to fourth regions.

  FIG. 11 shows a state in which a known guide word candidate is automatically selected. The analysis apparatus 1 compares only the keywords not included in the target information 120 with the known guide word candidate table T4 by comparing the known guide words registered in the keyword extraction table T3 with the words extracted from the target information 120. To register.

  FIG. 12 shows a state in which a predetermined number of guide words are automatically selected from registered known guide word candidates. In the known guide word candidate table T4, for example, for each of the first to fourth regions, a keyword included therein and a distance to the keyword and the target information 120 are stored in association with each other.

  The analysis apparatus 1 rearranges the keywords in descending order of distance, and selects the top n1 guide word candidates as known guide words. The selected known guide word is registered in the known guide word table T5 shown in FIG. The known guide word table T5 stores, for example, a keyword included in each of the first to fourth areas and a distance to the target information 120 in association with each other.

  FIG. 14 is a flowchart showing a process for extracting an unknown guide word. Steps S62 to S64 are executed for all the main keywords existing at the boundary of the map 100 (S61).

  The analysis apparatus 1 detects all document information including main keywords existing on the boundary of the map 100 (here, referred to as “boundary” including the vicinity of the boundary) among the document information group constituting the map 100. . And the analyzer 1 extracts the word used comparatively frequently recently from the words contained in each detected literature information (S62). That is, it finds a keyword of interest that has not been plotted on the map 100 as a main keyword, but has frequently appeared recently. This can also be referred to as alert analysis, and is obtained by calculating a rapid rise score described later. Details of this processing will be described later together with another flowchart.

  The analysis apparatus 1 determines whether or not a word extracted as a word that appears frequently recently is included in the target information 120 (S63). When the word is not included in the target information 120 (S63: NO), the analyzer 1 determines whether the word is already displayed on the map 100 as a main keyword (S64). When the word is not displayed on the map 100 as a main keyword (S64: NO), the analysis apparatus 1 registers the word as an unknown guide word candidate (S65). Next, the analysis apparatus 1 rearranges the unknown guide word candidates in descending order of the soaring score (S66), and selects only n2 words having a high soaring score as unknown guide words (S67).

  Next, FIG. 15 is a flowchart showing a soaring score calculation process for extracting a word requiring attention (word of interest) that frequently appears recently.

  The analysis apparatus 1 extracts each word used within the determination target period from the entire document information group included in the map 100 (S71). The determination target period means a period to be subjected to the determination process, and for example, a period selected by the user is set. When the user does not set a period, a preset initial value is used. For example, when the user sets “one year”, the period from the present to one year ago becomes the determination target period. The period before the determination target period is “outside the determination target period”. In the following description, the determination target period may be abbreviated as “target period”.

  The analysis apparatus 1 acquires the total number (e) of document information published or created in the target period from the document information group constituting the map 100 (S72). Each document information is associated with information such as a creation date and a publication date. Moreover, the analyzer 1 acquires the total number (f) of the literature information outside the target period (S73).

  Then, the steps S75 to S84 described below are repeated until all the words extracted in S71 are executed (S74).

  The analysis apparatus 1 acquires the number (a) of the words used in the target period for one word included in the word group extracted in S71 (S75). That is, the number of document information including the word is detected in the target period. If it is used in 100 documents, the value of (a) is 100. The number of uses in the same document does not matter.

  The analysis apparatus 1 acquires the number of cases (b) in which the word is not used in the target period (S76). The number of non-use cases (b) is a value obtained by subtracting the number of use cases (a) from the total number of documents (e) in the target period.

  Subsequently, the analysis apparatus 1 performs an inspection for a state before the target period. The analysis apparatus 1 acquires the total number (c) of document information in which the word is used outside the target period (S77), and calculates the number of non-use cases (d) of the word outside the target period (S78). . The number of non-use cases outside the target period (d) is a value obtained by subtracting the number of use cases outside the target period (c) from the total number of documents (f) outside the target period.

  Then, the analysis apparatus 1 uses the number of usages within the target period (a) and the number of non-uses (b), and the number of usages outside the target period (c) and the number of non-uses (d). Score Q is calculated (S79).

  The soaring score is an index indicating the degree of attention of the word, and can be calculated based on the following Equation 1, for example.

            Q = ± (ad-bc) ^ 2 / ((a + b) * (c + d) * (a + c) * (b + d)) (Formula 1)

  Here, the value of (ad-bc) is calculated first, and if (ad-bc) ≧ 0, a plus sign is given, and if (ad-bc) <0, a minus sign is given to Q .

  As shown in Equation 1, when the soaring score Q takes a positive value, it means that the usage rate of the word in the target period is larger than the usage rate outside the target period. That is, a large positive Q value indicates that the word is frequently used relatively recently.

  Next, the analyzer 1 calculates the significance level of the calculated soaring score Q (S80). The significance level is a level for eliminating chance. Then, the analysis apparatus 1 determines whether or not the calculated soaring score Q is a positive value (S81), and whether or not the calculated soaring score Q is less than a preset significance level threshold Th (S82). ) Respectively.

  Then, when the soaring score Q of the word is a positive value (S81: YES) and the significance level of the soaring score Q is less than the threshold Th (S82: YES), the analyzing apparatus 1 Is registered as a soaring word (S83). On the other hand, if the soaring score Q of the word is a negative value (S81: NO), or if the significance level of the soaring score Q is greater than or equal to the threshold Th (S82: NO), the analyzer 1 The word is discarded (S84). Here, “discarding” means not registering as a soaring word, and does not mean deleting the word from the document information including the word.

  An example of a method for extracting unknown guide words will be described with reference to FIGS. In the flowcharts shown in FIGS. 14 and 15 described above, the case where the extraction determination is performed for each keyword located at the boundary of the map 100 has been described. However, the extraction may be performed as follows.

  FIG. 16 is an explanatory diagram showing how boundary keywords of the map 100 are extracted. As shown in the upper side of FIG. 16, a keyword displayed on the boundary of the map 100, that is, the region from the contour line of the map 100 to the threshold line BL that is inward by a predetermined width is detected as a boundary keyword.

  The analysis apparatus 1 detects the boundary keyword for each of the first to fourth regions, and registers it in the boundary keyword extraction table T6. In the boundary keyword extraction table T6, for example, the boundary keywords included therein and the coordinates thereof are associated with each of the first to fourth areas.

  The analysis apparatus 1 extracts all document information including the boundary keyword registered in the boundary keyword extraction table T6 from the document information group constituting the map 100, respectively. The analysis apparatus 1 registers the document number in the boundary keyword-containing document management table T7 in association with the boundary keyword.

  FIG. 17 is a schematic diagram showing a state in which the soaring score of each word is calculated. For each word W1 to W3, the usage number (a) within the determination target period and the usage number (c) outside the determination target period are calculated. Then, the total number of documents (e) within the determination target period and the total number of documents outside the synchronization (f) are also calculated. Therefore, as described above, the number of non-uses within the determination target period (b) and the number of non-uses outside the determination target period (d) can also be calculated.

  FIG. 18 is an explanatory diagram illustrating a state in which a word registered as a soaring word is selected as a candidate for an unknown guide word.

  In the soaring word registration table T8, for example, for each of the first to fourth regions, a word existing there is associated with the calculated soaring score and significance level. The analyzer 1 determines whether or not the word registered in the soaring word registration table T8 is included in the target information 120 and whether or not it is registered in the keyword extraction table T3. If the word is not used in the target information 120 and is not displayed on the map 100, the analysis apparatus 1 causes the word to be registered in the unknown guide word candidate table T9.

  As shown in FIG. 19, in the unknown guide word candidate table T9, for each of the first to fourth areas, each candidate word and the rapid score are associated therewith. The analysis apparatus 1 rearranges the candidate words in descending order of the rapid rise score for each of the first to fourth regions, and selects the top n2 candidate words as unknown guide words. The selected unknown guide word is registered in the unknown guide word table T10 for each of the first to fourth areas.

  FIG. 20 is a flowchart showing guide word display processing. The analyzer 1 refers to the known guide word table T5 and acquires known guide words for each of the first to fourth areas (S91). Similarly, the analysis apparatus 1 refers to the unknown guide word table T10 and acquires unknown guide words for each of the first to fourth areas (S92). And the analyzer 1 displays an unknown guide word and a known guide word for every 1st-4th area | region, respectively.

  Here, the analyzer 1 can display the unknown guide word with priority over the known guide word. Although the known guide word is already displayed on the map 100 even though the distance from the target information 120 is far, the unknown guide word is a new word that is not displayed on the map 100. This is because it is thought that there is a great stimulus to the. However, the present invention is not limited to this, and the known guide word may be displayed with priority over the unknown guide word, or the display priority may be changed according to the user's request.

  FIG. 21 is a flowchart showing a process for changing the display position of the target symbol 110 by the user selecting the guide word 111. The analysis device 1 determines whether the user has selected the guide word 111 via the client terminal 2 (S100). The user can select any one or a plurality of desired guide words from among a plurality of guide words arranged around the target symbol 110.

  When the guide word is selected by the user (S100: YES), the analysis device 1 includes the selected guide word in the target information 120, recalculates the coordinates of the target information 120 (S101), and sets the target symbol 110. The display position is changed (S102).

  Since the present embodiment employs the above-described configuration, the following effects can be obtained. In this embodiment, the coordinates of the target information 120 are calculated, and the target symbol 110 is displayed on the map 100 in an overlapping manner. Therefore, the user can easily grasp the position of the invention content, research content, etc. in the map 100, and can make use of it for patent application, R & D strategy planning and the like.

  In other words, in the case of a conventional keyword layout type map, the number of documents and major keywords in a certain technical field can be confirmed. However, the user specifically describes what the intended application content and research content is in the technical field. It is difficult to read up to the position. Therefore, even if the map is created with cost and effort, it is only necessary to reconfirm the current state, and it is difficult to effectively use it for future planning and correction. On the other hand, in the present embodiment, by including the user's intention and target in the target information 120, the position on the map 100 can be easily grasped, and usability is improved.

  In the present embodiment, the target information 120 is included in one of the document information groups constituting the map 100, the first mode for calculating the coordinates of the target information 120, and the target information 120 is not included in the document information group. A second mode for calculating the coordinates of the information 120 is prepared in advance, and any one of the modes can be selected by the user. Accordingly, the influence of the target information 120 on the map 100 can be confirmed (first mode), the position of the target information 120 can be confirmed without affecting the map 100 (second mode), and user convenience Will improve.

  In the present embodiment, a manifested or potential guide word is displayed on the top, bottom, left, and right of the target information 120, respectively. Therefore, the user can obtain a clue (guide word) for moving the target information 120 as well as grasping the position of the invention content intended by the user in the map 100. Therefore, the user can use the information for correcting the policy of the contents of the invention and research, and the usability is improved.

  In the present embodiment, when the user selects the guide word 111, the selected guide word is included in the target information 120, and the coordinates of the target information 120 are recalculated. Therefore, the user can move the target information 120 on the map 100 simply by selecting a guide word, and usability is improved. Note that the user can also input new target information 120 including a desired guide word to the analyzer 1.

  In this embodiment, a keyword that is not included in the target information 120 among keywords displayed on the map 100 is extracted as a guide word. Therefore, the user can easily grasp the relationship between the displayed keyword and the target information 120.

  In the present embodiment, the distance between the keyword displayed on the map 100 and the target information 120 is calculated, and the keyword with the far calculated distance is preferentially displayed. Therefore, the user can grasp the distance between the target information 120 and the keyword on the map 100, and the usability is improved. In addition, since guide words are displayed in order of increasing distance, the user can easily select a guide word for increasing the moving distance of the target information 120, and the usability is improved in this respect as well.

  In this embodiment, a boundary keyword located in the vicinity of the boundary of the map 100 is detected, and a guide word is extracted from words not displayed on the map 100 and displayed from the word group included in the document information including the boundary keyword. It was set as the structure made to do. Therefore, a keyword that cannot be found from the map 100 can stimulate the user's willingness to create, and can be used to improve the contents of the invention and research.

  In the present embodiment, among the word groups included in the document information related to the boundary keyword, the appearance frequency within a predetermined determination target period specified in advance is a word that is relatively larger than the appearance frequency outside the determination target period. In addition, a guide word is extracted from words that are not used in the map 100. Therefore, it is possible to provide a user with new words that are frequently used since a relatively recent time as guide words.

  In this embodiment, both a known guide word extracted from the keyword displayed on the map 100 and an unknown guide word extracted from a new word extracted from the literature information group constituting the map 100 are used. The configuration is arranged around the target symbol 110. Therefore, the user's usability is improved and an intellectual stimulus can be given to the user.

  In this embodiment, an unknown guide word is displayed in preference to a known guide word. Therefore, the possibility that the user sees an unknown guide word increases, and the user can be surprised and stimulate the creative will.

  FIG. 22 shows a configuration example of a map 100 output from the literature information analysis apparatus 1 according to the second embodiment of the present invention. This embodiment corresponds to a modification of the first embodiment.

  In the upper side of FIG. 22, when a guide word is selected by the user, a state in which the coordinates of the target information 120 are recalculated and the planned destination of the target symbol 110 is displayed on the map 100 is shown.

  In the lower part of FIG. 22, when a guide word is selected by the user, the coordinates of the target information 120 are recalculated, the target symbol 110 is moved, and the position of the movement source is displayed on the map 100. It is shown.

  Thus, it is also possible to display the prediction or history of the coordinate change of the target information 120 on the map 100, and the user convenience is improved.

  The present invention is not limited to the above-described embodiment. A person skilled in the art can make various additions and changes within the scope of the present invention. For example, those skilled in the art can appropriately combine the above embodiments.

It is explanatory drawing which shows the whole literature information analyzer which concerns on embodiment of this invention. It is a functional block diagram of a literature information analysis device. It is explanatory drawing which shows the hardware and software structure outline | summary of a literature information analyzer. It is a flowchart which shows the process which produces | generates and displays a map. It is explanatory drawing which shows the relationship between a literature coordinate management table and a keyword coordinate management table, and a map. It is a screen block diagram which shows a state at the time of inputting target information into a map. It is a flowchart which shows the process which calculates the coordinate of target information and displays a symbol. It is a flowchart which shows the whole guidance word control process. It is a flowchart which shows the process for extracting a known guidance word. It is explanatory drawing which shows a mode that the keyword on a map is extracted according to the direction. It is explanatory drawing which shows a mode that the candidate of a known guidance word is extracted based on the content of a keyword extraction table, and the content of target information. It is explanatory drawing which shows a mode that a known guide word candidate is rearranged by the descending order of the distance from target information. It is explanatory drawing which shows a known guide word table. It is a flowchart which shows the process for extracting an unknown guidance word. It is a flowchart which shows the process which calculates a sudden rise score. It is a flowchart which shows a mode that the keyword located in the boundary of a map is extracted. It is explanatory drawing which shows a mode that the appearance frequency of each word is detected inside and outside a determination object period. It is explanatory drawing which shows a mode that the candidate of an unknown guidance word is extracted. It is explanatory drawing which shows an unknown guidance word candidate table. It is a flowchart which shows a guidance word display process. It is a flowchart which shows the process which moves target information. It is a screen block diagram which shows the map which the literature information analyzer which concerns on 2nd Example outputs.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Document information analysis apparatus, 2 ... Client terminal, 10 ... Map control part, 11 ... Map generation condition input reception part, 12 ... Document extraction part, 13 ... Document coordinate calculation part, 14 ... Keyword extraction part, 15 ... Keyword coordinate Calculation unit, 16 ... map generation unit, 17 ... map display unit, 20 ... guide word control unit, 21 ... target information input reception unit, 22 ... target information coordinate calculation unit, 23 ... target information coordinate display unit, 23 ... target information Display part 24 ... Guidance word extraction part 25 ... Guidance word display part 30 ... Information storage part 31 ... Document database 32 ... Word database 33 ... Index database 100 ... Map 101A, 101B, 101C, 101D ... Contour lines, 102 ... displayed keywords, 110 ... target symbols, 111 ... guide words, 120 ... target information

Claims (11)

A document information storage unit for storing a plurality of document information each digitized;
By performing principal component analysis based on a combination of a plurality of predetermined keywords extracted from a predetermined document information group and the number of appearances among the stored document information, each document information of the predetermined document information group A document coordinate calculation unit for calculating coordinates respectively;
A keyword coordinate calculation unit that calculates the coordinates of each of the predetermined keywords by performing principal component analysis based on the total number of document information including the predetermined keywords and the number of appearances of the predetermined keywords;
Based on the coordinates of each document information calculated by the document coordinate calculation unit, the distribution density of each document information is calculated, and the calculated distribution density and each predetermined keyword are visualized to generate map information. A map generator to
A target coordinate calculation unit for calculating coordinates of target information designated by a user by performing a predetermined principal component analysis;
A target coordinate display unit for displaying a display element indicating the presence of the target information in association with the calculated coordinates of the target information and displaying the display information on the map information;
A bibliographic information analyzer. The target coordinate calculation unit
A first mode for calculating coordinates of the target information by including the target information in one of the predetermined document information groups and performing principal component analysis based on the combination and number of occurrences of the predetermined keywords; ,
A second mode for calculating coordinates of the target information by performing principal component analysis based on the combination and number of occurrences of the predetermined keywords without including the target information in the predetermined document information group;
The literature information analysis apparatus according to claim 1, wherein the coordinates of the target information can be determined in any one of the two types of modes. On the map information, a guide word extraction unit that extracts a guide word for indicating the presence of a keyword located in a predetermined direction from the coordinates of the target information;
A guidance word display unit that displays the extracted guidance words in association with the predetermined direction and superimposed on the map information;
The literature information analyzer according to claim 1 or 2 provided with. When the user selects the guide word displayed on the guide word display unit,
The document information analysis apparatus according to claim 3, wherein the target coordinate calculation unit includes the selected guide word in the target information and recalculates the coordinates of the target information.   The literature information analysis device according to claim 3, wherein the guide word extraction unit extracts, as the guide words, keywords that are not included in the target information among the predetermined keywords.   The guide word extraction unit calculates a distance between a coordinate of a keyword that is not included in the target information among the predetermined keywords and a coordinate of the target information, and guides a keyword having a long distance calculated to the guide 6. The document information analysis apparatus according to claim 5, wherein the document information analysis apparatus extracts the words preferentially.   The guide word extraction unit detects a boundary keyword located in the vicinity of the boundary of the map information among the predetermined keywords, reads out document information including the detected boundary keyword from the document information storage unit, The document information analysis apparatus according to claim 3, wherein the guide word is extracted from words that are not extracted as the predetermined keywords among a group of words included in the read document information.   The guide word extraction unit has an appearance frequency within a predetermined period specified in advance in a group of words included in the read document information, which is relatively higher than an appearance frequency in a period before the predetermined period. The literature information analysis apparatus according to claim 7, wherein the guide word is extracted from words that are words and are not extracted as the predetermined keywords. The guide word extraction unit
A first extraction unit that extracts a keyword that is not included in the target information among the predetermined keywords as the guide word;
A boundary keyword located near the boundary of the map information is detected from the predetermined keywords, and document information including the detected boundary keyword is read from the document information storage unit, and the read document information is stored in the read document information. A second extraction unit that extracts the guide word from words that are not extracted as the predetermined keywords in the included word group;
The literature information analyzer of Claim 3 comprised by providing. Computer
Document information storage means for storing a plurality of document information each digitized,
By performing principal component analysis based on a combination of a plurality of predetermined keywords extracted from a predetermined document information group and the number of appearances among the stored document information, each document information of the predetermined document information group Literature coordinate determination means for calculating coordinates respectively;
Keyword coordinate determination means for calculating the coordinates of each predetermined keyword by performing principal component analysis based on the total number of document information including each predetermined keyword and the number of appearances of each predetermined keyword;
The distribution density of each document information is calculated based on the coordinates of each document information calculated by the document coordinate determination means, and the calculated distribution density and each predetermined keyword are visualized to generate map information. Map generating means for
Target coordinate determining means for calculating coordinates of target information designated by a user by performing a predetermined principal component analysis;
As target coordinate display means for displaying a display element indicating the presence of the target information in association with the calculated target information coordinates and displaying the map information in an overlapping manner.
Each program that functions. Obtaining a search condition from a user;
Searching for a plurality of document information that matches the search condition;
Extracting a plurality of predetermined keywords included in each searched document information;
Calculating the coordinates of each retrieved document information by performing principal component analysis based on the combination of the extracted predetermined keywords and the number of appearances;
Calculating the coordinates of each of the predetermined keywords by performing principal component analysis based on the total number of document information including the predetermined keywords and the number of appearances of the predetermined keywords;
Calculating the distribution density of each document information based on the coordinates of each document information calculated by the document coordinate determining means;
Visualizing the calculated distribution density and the predetermined keywords by associating predetermined graphic elements with each other, and generating map information;
Obtaining target information specified by a user;
Calculating the coordinates of the acquired target information by performing a predetermined principal component analysis;
Associating a graphic element indicating the presence of the target information with the coordinates of the calculated target information and displaying the map information superimposed on the map information;
Extracting a guide word for moving the target information in a predetermined direction on the map information;
Associating the extracted guide word with the predetermined direction and displaying it superimposed on the map information;
When the guide word displayed on the guide word display unit is selected by the user, the target information is included in the target information, and the coordinates of the target information are calculated again. Moving the graphic element associated with the target information to the coordinates,
Document information analysis method including

Images