JP4806249B2 - Document information analysis apparatus and document information analysis method - Google Patents

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 and to make business plans. By the way, in the case of a patent document such as a patent publication, a plurality of documents are closely connected, such as a so-called parent application and divisional application, a domestic priority claim application and an application on which the domestic priority claim is based. May be related.

By scrutinizing a plurality of patent documents having such a relationship, it is possible to determine whether or not the division or domestic priority claim is possible. Then, what makes the relevance of the cited literature and the literature which cites it express visually is proposed (patent document 1).
JP 2004-348771 A

  According to the technique described in the document, it is possible to know the relevance of each document, but it is impossible to know how each document is related. Here, some document creation software has a function of analyzing a difference between a plurality of documents and notifying the user. However, software provided with such a document comparison function simply analyzes the order of the text codes of both documents, and cannot detect a substantial difference between documents.

  For example, even if only the order of two paragraphs is changed, such software determines that all the paragraphs have been changed. Therefore, it is necessary for the user to analyze the matching part and the different part while checking the related documents one page at a time, and there is a problem that the workability is low and the time and cost required for the examination increase.

  Therefore, an object of the present invention is to compare the first document information and the second document information selected by the user with a block of a predetermined unit, and thereby compare the contents of the two more appropriately. It is to provide a literature information analysis method. Another object of the present invention is to connect and visualize related blocks with a display element indicating the relation, and the user can easily confirm the comparison result between the blocks only by selecting the display element indicating the relation. An object of the present invention is to provide a literature information analysis apparatus and a literature information analysis method that can be used. The further objective of this invention will become clear from description of embodiment mentioned later.

In order to solve the above-described problem, a literature information analyzing apparatus according to one aspect of the present invention includes a literature information storage unit that stores a plurality of digitized literature information, and a user's selection among each stored literature information. A first document information acquisition unit that acquires the first document information and the second document information obtained from the document information storage unit, and processes each of the first document information and the second document information as a block of a predetermined unit, and at least the first document In the coordinate system determined based on the word group included in the information and the second document information, a block coordinate calculation unit that calculates the coordinates of each block, and arranges each block based on the coordinates of each block, and Of each block, a predetermined first block derived from the first document information and a predetermined second block derived from the second document information are displayed to indicate the relationship between the two. In comprising a map generator for generating map information by connecting a map display unit for displaying the generated the map information.
The whole of the first document information and the whole of the second document information can be treated as a block of a predetermined unit each, or a plurality of information obtained by dividing the first document information and the first information A plurality of pieces of information obtained by dividing two pieces of document information can be handled as a predetermined unit block. When handling the entire document information as one block, for example, this block can be referred to as an “entire block”. When the document information is divided into a plurality of blocks and treated as one block, these These blocks can be called “partial blocks” or “sub-blocks”.

  Here, examples of the document information include technical document information, academic paper information, and patent document information. Examples of patent document information include document information relating to patent applications or utility model registration applications such as patent publications and utility model registration gazettes. As the predetermined unit, either a paragraph unit or a claim unit or both can be used.

  The user can select the first document information and the second document information, respectively, but can also provide support when selecting either one or both. For example, bibliographic items (applicant name, inventor name, special remarks, application number, basic application number, application date, publication date, etc.) included in each document information and prior art items (prior patent documents are specified) Bibliographic information related to each other can be automatically extracted based on a publication number or the like. By providing the related document extracting means for automatically extracting such related document information, the user only has to specify the first document information, and the operability is improved. The second document information related to (corresponding to) the first document information is automatically extracted by the related document extracting means.

  In this way, the user can select a plurality of document information directly or indirectly. Each selected document information is divided into predetermined units of blocks. Each document information may be divided into blocks only for the range designated by the user. For example, in the case of patent documents, only the claims can be divided in units of claims, or only the description of the embodiment can be divided in units of paragraphs.

  Then, the block coordinate calculation unit calculates the coordinates of each block in a predetermined coordinate system. The predetermined coordinate system can be determined, for example, by analyzing the appearance frequency of a word group included in each selected document information. Alternatively, when the entire document information is handled as one block, the coordinate system can be determined by performing principal component analysis on keyword combinations and appearance frequencies extracted from a plurality of document information. If two coordinate axes are set, a two-dimensional coordinate system can be obtained, and if three coordinate axes are set, a three-dimensional coordinate system can be obtained. For example, in the case where a block formed by dividing the first document information and the second document information is used, the block coordinate calculation unit obtains an average value of the coordinates of each word included in each block, and calculates the average value as the average value. Determined as block coordinates.

  Hereinafter, a case where the first document information and the second document information are each divided into a plurality of blocks will be mainly described as an example. A map generation part arrange | positions each block to each coordinate, and also produces | generates map information by connecting predetermined blocks with the display element which shows both relationship. Examples of display elements indicating the relationship between the two include various display elements such as lines, ellipses, rectangles, and triangles. When connecting related blocks with a line, the display area of map information can be used effectively. As a result, map information is generated in which each block is arranged at each position in a predetermined coordinate system, and the predetermined blocks are connected to each other by the display element to visualize the relationship. Here, it should be noted that the first block derived from the first document information and the second block derived from the second document information are connected. That is, the first blocks or the second blocks are not connected.

  In the embodiment of the present invention, when the first block and the second block are separated from each other by a predetermined distance or more, the map generation unit connects the first block and the second block with a display element indicating the relationship between the first block and the second block. . When the first block and the second block are not separated by a predetermined distance or more, that is, when both blocks are close to each other, it is possible to determine that the contents of both are almost the same. Therefore, in this case, the blocks are not connected, and only the blocks where a significant difference is seen are connected.

  In the embodiment of the present invention, when there are a plurality of at least one of the first block and the second block that are separated by a predetermined distance or more, the map generation unit is closest to the first block and the second block. Are connected with a display element indicating the relationship between the two. This is because it is considered highly relevant to the block closest to that block.

  In the embodiment of the present invention, when the display element indicating the relation is selected by the user, the contents of the first block and the contents of the second block connected by the display element indicating the selected relation are preset. In addition, a block comparison unit is provided that compares at a predetermined level and outputs the comparison result.

  Here, examples of the predetermined level include a word level, a phrase level, and a sentence level. The user can freely select which of these levels to use.

  The block comparison unit can output the difference between the content of the first block and the content of the second block connected by the display element indicating the relationship as a comparison result, or output the common part of both blocks as the comparison result It can also be made.

  A program according to another aspect of the present invention acquires a first document information and a second document information selected by a user from a plurality of document information stored electronically in a document information storage unit. In the coordinate system determined based on the word information included in the first document information and the second document information, the document information dividing means for dividing the first document information and the second document information into blocks of predetermined units, respectively, Block coordinate calculating means for calculating the coordinates of each block, each block is arranged based on the coordinates of each block, and the predetermined first block and second document information derived from the first document information among each block The predetermined second blocks that are derived are functioned as map generation means for generating map information by connecting them with display elements indicating the relationship between them.

  The document information analysis method according to still another aspect of the present invention includes a step of acquiring first document information and second document information selected by a user from among a plurality of document information stored in a document information storage unit, In the coordinate system determined based on a word group included in the first document information and the second document information, the step of dividing the first document information and the second document information into blocks of predetermined units, respectively, A step of calculating, a step of arranging each block on a map according to the coordinate system based on the coordinates of each block, and a predetermined first block derived from the first document information among the blocks arranged on the map Map information is generated by connecting a predetermined second block derived from the second document information with a display element indicating a relation between the two and the second document information. The step of displaying the generated map information and the display element showing the relation between the two when the user selects the contents of the first block connected by the display element showing the selected relation And comparing the contents of the second block with a predetermined level set in advance and outputting the comparison result.

  Before comparing a plurality of document information in units of blocks, the relationship between each document information to be compared is automatically detected in advance, and both document information is connected by a connection line indicating the relationship between the two. You can also. For example, the relationship between a plurality of document information selected by the user (pre-division and post-division applications, pre-change and post-change applications, pre-correction and post-correction applications, citations and citations, etc.) Judgment is automatically made based on the bibliographic items included, and the connection line of the line type (color, line type, line thickness, etc.) corresponding to the determined relationship is automatically selected, and each document information Can be connected and displayed. And when a user selects a connection line by manual operation, each literature information connected with this connection line may be compared in a block unit.

  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 comparison 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.

  When the connection line displayed on the map 100 is selected by the user, the comparison control unit 20 compares the contents of the blocks 111 and 112 connected by the connection line, and the result is displayed on the map 100. Display. Details of the contrast 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 at least two or more document information from among a large number of document information groups stored in the information storage unit 30 by designating a document number, a search word, or the like. For example, a user can submit a so-called parent application and divisional application, domestic priority claim application and basic application, change application and application before change, patent application based on utility model registration and utility model registration application, cited application and this application. A plurality of pieces of literature information related to each other can be selected as in the cited application.

  As will be described later, when any one of the mutually related document information is selected by the user, the other document information related to the selected document information may be automatically selected. In the following description, one document information selected by the user is referred to as first document information, and the other document information is referred to as second document information.

  A plurality of pieces of document information related to each other selected by the user are analyzed by the map control unit 10 and a map 100 is generated. The generated map 100 is provided to the client terminal 2.

  Next, the configuration of the map 100 will be described. The contour lines 101A and 101B are display elements indicating the distribution density of words included in the map 100. The map 100 displays a plurality of blocks 111 and 112. The first block 111 is generated by dividing the first document information by a predetermined unit. The second block 112 is generated by dividing the second document information by a predetermined unit. As the predetermined unit, for example, in the case of patent documents, a paragraph unit, a claim unit, an example unit, and the like can be used.

  Of the blocks 111 and 112, the blocks related to each other are connected by a connection line 113. With this connection line 113, the user can easily grasp that there is a relationship between the blocks. When the user selects the connection line 113 by clicking or the like, the comparison control unit 20 compares the contents of the blocks connected by the connection line 113 and displays the comparison result.

  In this way, in this embodiment, rather than comparing the entire plurality of document information as they are, each document information is divided into blocks 111 and 112, and only relevant blocks are connected by the connection line 113. Notify the user. The user can obtain a comparison result between specific blocks by individually selecting a desired connection line 113. Hereinafter, details of the present embodiment will be further described.

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 information division unit 12, a block coordinate calculation unit 13, an inter-block similarity determination unit 14, a map generation unit 15, and a map display unit 16. Can be configured.
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 information dividing unit 12 divides the first document information and the second document information selected by the user based on conditions specified by the user. For example, the user can specify a division unit such as a paragraph unit or a claim unit. Each document information is divided at the same level (unit).

  The block coordinate calculation unit 13 extracts a word included in each block by searching a literature database 31 (in the figure, the database is abbreviated as “DB”) 31 and a word database 32. For example, the block coordinate calculation unit 13 calculates the coordinates of the block by calculating the average value of the coordinates of each word in the block.

  The inter-block similarity determination unit 14 compares the coordinates of the blocks 111 and 112, and determines the similarity between them. As a result, blocks that can be determined to have substantially the same contents can be excluded from the connection targets, and only related blocks that are not substantially the same but can be extracted as connection targets.

  The map generation unit 15 generates the logical structure of the map 100 by arranging the blocks 111 and 112 at the respective coordinates and connecting the blocks related to each other by the connection line 113.

  The map display unit 16 generates a map 100 that can be visually recognized by the user by allocating predetermined display elements according to the structure of the generated map 100, and provides the map 100 to the client terminal 2. Examples of the predetermined display element include a graphic element for indicating each block, a contour display 101A, a menu display unit for performing an operation on the map 100, and the like.

  The user browses the map 100 displayed on the terminal screen of the client terminal 2 to determine how the description contents (blocks) of the selected document information are distributed and which description contents are related to each other. Can be easily read.

  The comparison control unit 20 can be configured to include, for example, a connection line designation information input reception unit 21, a block comparison unit 22, and a comparison result output unit 23.

  The connection line designation information input receiving unit 21 electronically receives and stores connection line designation information input from the user. For example, an operation on the map 100 by the user can be detected as an event by an event handler.

  The block comparison unit 22 compares the contents of the blocks 111 and 112 connected by the connection line 113 selected by the user using a technique such as text mining. This comparison result is displayed on the map 100 by the comparison result output unit 23.

  For example, the comparison result display unit 24 displays the comparison result in such a form that a matched portion and a mismatched portion between blocks to be compared can be clearly distinguished. For example, by appropriately changing the underline, strikethrough, font type, size, color, etc., it is possible to distinguish and display which part matches and which part does not match.

  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), the document database 31, the word database 32, the display control program 1110, the principal component analysis program 1120, the structure analysis program 1130, and the search program 1140. And the 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 index database 33 manages keywords included in each document. The display control program 1110 is a program that performs drawing processing of the map 100 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 the overall operation. The flowcharts described below are also the same, but each flowchart shows an outline of the process and is different from an actual program. In addition, as described later, the relationship between a plurality of document information selected directly or indirectly by the user is automatically determined, and both document information is connected by a connection line of a line type corresponding to the determined relationship. It can also be displayed.

  First, the user designates document information to be compared via the user interface of the client terminal 2 (S10). For example, the user can designate the respective document numbers of the first document information and the second document information. Alternatively, the user can specify only one of the document numbers.

  When the analyzer 1 acquires the specified condition from the client terminal 2 (S11), the analyzer 1 searches the document database 31 based on the specified condition, and extracts the document information that matches the specified condition (S12).

  The document number etc. of the extracted document information 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 instructs execution of analysis (contrast) via the screen of the client terminal 2 (S15).

  When giving this instruction, the user can also specify a comparison condition. Examples of the comparison condition include conditions such as which part of the first document information and the second document information is compared in which unit.

  When receiving an instruction from the user, the analysis apparatus 1 generates a map 100 based on the extracted first document information and second document information. Although details will be described later, the analysis apparatus 1 divides each of the first document information and the second document information into a plurality of blocks, arranges each block on the map, and connects the blocks related to each other through the connection line 113. Let The generated map 100 is transmitted to the client terminal 2 (S17).

  The user browses the map 100 via the screen of the client terminal 2 and confirms the arrangement state of the blocks, the setting state of the connection line 113, and the like. When the user desires a detailed comparison, the user designates the connection line 113 that connects the desired blocks (S19).

  When the analysis apparatus 1 detects the designation of the connection line by the user, the contents of the blocks are compared (S20), and the comparison result is transmitted to the client terminal 2 (S21). The user can confirm how much the contents of the desired blocks 111 and 112 are different (common) by browsing the display unit 24 displayed on the map 100.

FIG. 5 is a flowchart showing a process for generating the map 100 by dividing each document information into a plurality of blocks. This process corresponds to S16 in FIG. First, the analysis apparatus 1 determines two coordinate axes of words based on the appearance frequency of each word based on the word groups included in the first document information and the second document information (S31).
Note that the coordinate axis calculation processing in S31 uses principal component analysis, which is a common multivariate analysis technique. For example, as basic data used for coordinate calculation, a matrix of “1 (appearance)” and “0 (non-appearance)” indicates whether or not the target word appears for each document (or each block). An index called “principal component load amount” calculated as a result is used as an actual coordinate.

  Next, the analyzer 1 divides the first document information into predetermined units of blocks (S32). As described above, each document information can be divided, for example, in units of paragraphs or units of claims. Here, it should be noted that the predetermined unit is a unit on the semantic content and is not directly related to the data size of the block. The data size of each block differs depending on the amount of data included in each block.

  Next, the analyzer 1 executes the following S34 to S37 for each block of the first block group obtained by dividing the first document information (S33). The analysis apparatus 1 selects one first block 111, parses the contents of the first block 111 (S34), and extracts all the words included in the first block 111 (S35).

  The analysis device 1 obtains the coordinates of each word included in the block 111 and calculates the average value. Then, the analyzer 1 uses the calculated average value as the coordinates of the block 111 (S36). The analysis apparatus 1 places the block 111 in a predetermined display form at the calculated coordinate position (S37). The predetermined display form means, for example, the shape or color of a graphic showing the block 111. By repeating the above processing for all the blocks 111 in the first block group, the first document information is divided into blocks and displayed dispersed on the map 100.

  Next, the analyzer 1 divides the second document information into a plurality of blocks 112 in the same unit as the first block 111 (S38). The analysis apparatus 1 executes the following S40 to S47 for each block 112 of the second block group obtained by dividing the second document information (S39).

  The analysis apparatus 1 selects one second block 112, parses the contents of the second block 112 (S40), and extracts all the words contained therein (S41). The analysis apparatus 1 determines the coordinates of the second block 112 by calculating the average value of the coordinates of each word included in the block 112 (S42).

  The analysis apparatus 1 arranges the second block 112 in a predetermined display form at the calculated coordinate position (S43). By repeating the above processing for all the blocks 112 in the second block group, the second document information is divided into blocks and displayed dispersed on the map 100.

  Next, connection line setting processing is executed. The analyzer 1 determines whether or not the first block 111 exists within a predetermined range from the coordinates of the second block 112 (S44). When the first block 111 exists within the predetermined range from the second block 112 (S44: YES), it can be determined that the contents of the second block 112 and the first block 111 are substantially the same. Therefore, in this case, the process proceeds to the next second block 112 without setting the connection line 113.

  On the other hand, when the first block 111 does not exist within the predetermined range from the position of the second block 112 (S44: NO), the first block 111 having substantially the same content as the second block 112 is the second block 112. This is a case where it is not located near the block 112. That is, it is possible to determine that the first block 111 having a different content from the second block 112 exists around the second block 112 (S45).

  Therefore, the analysis apparatus 1 searches for the first block 111 closest to the second block 112 (S46), and connects the searched first block 111 and the second block 112 with the shortest distance through the connection line 113 ( S47).

  Here, the analyzer 1 can change the display form of the connection line 113 according to the distance between the blocks 111 and 112. For example, if the relationship between the distance between the blocks and the line type is registered in advance in the connection line display form management table T1, the analysis apparatus 1 sets the connection line 113 with the line type corresponding to the distance between the blocks. Can be displayed. Here, the “line type” is a concept including one or more of a line type (solid line, dotted line, alternate long and short dash line, etc.), line thickness, and line color.

  Next, FIG. 6 is a flowchart showing an inter-block comparison process for comparing contents between blocks. This process corresponds to S20 in FIG. The analysis apparatus 1 determines whether any of the connection lines 113 on the map 100 is designated by the user (S51).

  When the connection line 113 is designated by the user (S51: YES), the analysis apparatus 1 specifies the first block 111 and the second block 113 that are connected by the designated connection line 113 (S52). . The analyzer 1 acquires the contents of the first block 111 and the contents of the second block 112 (S53, S54).

  Then, the analysis apparatus 1 compares the contents of the first block 111 and the contents of the second block 112 (S55), and extracts and temporarily stores the matching part (common part) and the different part (difference). (S56). The analysis apparatus 1 displays the extracted matching part and different part on the map 100 (S57).

  FIG. 7 is an explanatory diagram illustrating a display example by the comparison result display unit 24. For example, the original text of each block 111, 112 can be displayed at the top, the matching part of both blocks 111, 112 can be displayed at the next level, and the difference between both blocks 111, 112 can be displayed at the last level. .

  However, the present invention is not limited to this, and for example, a configuration may be used in which a matching portion and a different portion are simultaneously displayed in the original text of each of the blocks 111 and 112 by using an underline or strikethrough.

  In addition, the user can freely set one or more of a word level, a phrase level, and a sentence level as levels to be compared.

  Next, FIG. 8 is an explanatory diagram showing an example of the map generation menu screen G1 displayed on the screen of the client terminal 2. For example, the menu screen G1 can include a document specifying part G2, a comparison range specifying part G3, a block unit specifying part G4, a related document search button B1, an execution instruction button B2, and a cancel button B3.

  The document designation part G2 allows the user to directly input the document numbers of the first document information and the second document information. Alternatively, after the user inputs only one of the document numbers, the user operates the related document search button B1 to cause the analyzer 1 to automatically search for a document number related to the input document number. It can also be set.

  The comparison range designating part G3 designates which part of each document information is to be compared. For example, the user can specify a desired range such as the whole literature, claims, detailed explanation of the invention, means for solving the problem, effects of the invention, summary, and the like. A plurality of comparison ranges can be specified.

  The block unit designation unit G4 designates a block generation unit. For example, the user can select any one or a plurality of desired units such as a claim unit, a paragraph unit, and a page unit.

  When the user operates the execution instruction button B2 after designating information (reference number) for identifying each piece of document information, a comparison range, and a block unit, the analysis apparatus 1 executes the above-described processing to execute the map 100. Is generated.

  Since the present embodiment employs the above-described configuration, the following effects can be obtained. In the present embodiment, the first document information and the second document information are each divided into predetermined units of blocks, and the first block 111 and the second block 112 that are related to each other are connected by the connection line 113 and displayed on the map 100. It was. Therefore, it is possible to grasp the structure of each piece of document information in block units and to intuitively understand which part of each piece of document information is related to how compared to the case of simply comparing the whole pieces of each piece of document information. It becomes possible to grasp it and to improve usability.

  In the present embodiment, when the first block 111 and the second block 112 are separated by a predetermined distance or more, the first block 111 and the second block 112 are connected by the connection line 113 and displayed. Therefore, only the blocks that are related to each other and that have different contents can be associated with each other by the connection line 113, and the usability is improved.

  In the present embodiment, when the first block 111 and the second block 112 are separated from each other by a predetermined distance or more, the closest first block 111 and the second block 112 are connected by the connection line 113 and displayed. did. Therefore, blocks that are highly likely to be related to each other can be connected and visualized, improving usability.

  In this embodiment, when the connection line 113 is selected by the user, the contents of the first block 111 and the contents 112 of the second block connected by the connection line 113 are compared at a predetermined level set in advance. The comparison result is output. Therefore, the user can easily grasp the degree of similarity between desired blocks simply by selecting the connection line 113, and usability is improved.

  In the present embodiment, either one or both of the matching part and the different part of each block can be displayed. Therefore, common parts and different parts of each document information can be individually examined in units of blocks, and usability is improved.

  A second embodiment of the present invention will be described with reference to FIGS. In the first embodiment, the case where the document information is divided into a plurality of blocks and compared in units of blocks has been described. However, in this embodiment, before comparing each document information in units of blocks, the document information to be compared is compared. Differentiate the relationship between them.

FIG. 9 is an explanatory diagram showing an overall outline of the present embodiment. In the present embodiment, as the preprocessing of the document information analyzing apparatus 1, the relationship between the document information selected by the user is visualized.
The relevance analysis apparatus 300 detects relevance of document information, and connects and displays the document information with connection lines corresponding to the relevance. The relevance analysis apparatus 300 can be provided in the same computer apparatus as the document information analysis apparatus 1, or can be provided in a computer apparatus different from the document information analysis apparatus 1.

The relevance analysis device 300 that can be expressed as “a preprocessing device of the document information analysis device 1” generates, for example, a document selection unit 310, a relationship detection unit 320, a connection line selection unit 330, and a display screen 350. A display output unit 340 and a selection operation detection unit 360 can be provided.
The relevance analysis apparatus 300 can use the document database 31, the word database 32, and the index database 33, similarly to the document information analysis apparatus 1. In other words, these databases 31 to 33 are shared between both analyzers 1 and 300.

  The document selection unit 310 extracts the document information desired by the user by searching the document database 31 (or the document database 31 and the index database 33) based on conditions specified by the user. For example, the user can extract a plurality of document information 111A, 112A, 113A by designating a document number such as a patent publication number or a patent application number.

  The relevance detection unit 320 determines the relationship between the extracted pieces of document information 111A, 112A, and 113A. For example, the relevance determination unit 320 can extract the second document information 112A related to the first document information 111A based on the bibliographic items included in each document information 111A, 112A, 113A.

Bibliographic items include, for example, patent classification, applicant name, inventor name, agent name, application number, publication number, registration number, application date, publication date, registration date, special application indication (priority claim, Display of divisional change, application of exception provision for loss of novelty, etc.), the number of claims, presence / absence of examination request, number of prior art documents, etc. Therefore, the relevance detection unit 320 can extract a plurality of document information 111A and 112A related to each other by analyzing bibliographic items.
The display screen 350 in FIG. 9 shows a state in which a plurality of second document information 112A is related to the first document information 111A with the first document information 111A as a reference. Note that the third document information 113A is a document that does not have a direct relationship (for example, a legal relationship) with the first document information 111A and has only a common keyword or the like.

  The connection line selection unit 330 refers to the connection line display form management table T1 based on the relevance detected by the relevance detection unit 320, thereby connecting the connection line 113A of the line type according to the relevance between the document information. Select.

  The display output unit 340 generates the display screen 350 by connecting the document information 111A and 112A using the selected connection line 113A. The generated display screen 350 is provided to the client terminal via the communication network.

  When the user selects the connection line 113A via the client terminal, the selection operation is detected by the selection operation detection unit 360. When the selection operation detection unit 360 detects a user's selection operation, the selection operation detection unit 360 instructs the literature information analysis apparatus 1 to start analysis. Thereby, the literature information analysis apparatus 1 divides each literature information 111A, 112A into a plurality of blocks as described above, connects corresponding blocks, and compares the contents.

FIG. 10 is an explanatory diagram showing an example of the connection line display form management table T1. The table T1 can include, for example, at least one of a plurality of tables T1A and T1B.
One table T1A is for selecting a line type according to the distance between the document information 111A and 112A. For example, in the coordinate system set based on a large number of document information groups extracted by the user, the coordinates of the first document information 111A and the second document information 112A are obtained, and the distance between the document information 111A and 112A is calculated. Table T1A can be used if possible. In this table T1A, for example, the line thickness and type are set to be different depending on the distance.

  The other table T1B is for selecting a line type according to the relevance of the document information 111A and 112A. As described above, as described above, a legal relationship such as a divisional application or a change application can be cited. In this table T1B, connection lines 113A of different colors are set according to the relationship between the two document information.

  For example, the connection line 113A may be blinked or displayed as an animation without being limited to the thickness and color of the line. In addition, the display form of the connection line 113A may be customizable by the user.

Next, FIG. 11 is a flowchart showing the overall operation of this embodiment.
First, the user inputs search conditions via the user interface of the client terminal 2 (S60). 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 (S61), the relevance analysis apparatus 300 searches the index database 33 and the document database 31 based on the search condition, and extracts all the document information that matches the search condition (S62). ). 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. Then, the extracted result is transmitted from the relevance analysis device 300 to the client terminal 2 (S63) and displayed on the screen of the client terminal 2 (S64).

The user confirms the total number of extracted documents, document names, and the like via the screen of the client terminal 2, and selects at least one document information (first document information 111A) (S65).
The relevance analyzing apparatus 300 extracts all the second document information 112A related to the first document information 111A selected by the user by analyzing the bibliographic items (S66).

  The relevance analysis apparatus 300 selects the connection line 113A according to the relevance between the extracted second document information 112A and the first document information 111A (S68), and connects the document information 111A and 112A to each other. (S69), it is displayed on the screen of the client terminal (S70).

  When the user selects one of the connection lines 113A by clicking or the like (S71), the relevance analysis apparatus 300 instructs the literature information analysis apparatus 1 to start analysis (S72). Thereby, the processing described in the first embodiment is started, and the map 100 is generated.

  Note that S60 to S64 can be omitted. That is, the user can explicitly specify the document numbers of the first document information 111A and the second document information 112A. Further, the user can shift to the processing described in the first embodiment by operating a menu displayed on the display screen 350 instead of the selection operation of the connection line 113A.

  In this embodiment configured as described above, it is possible to intuitively determine the relationship between the related document information 111A and 112A through vision. Then, after grasping the relationship between the two document information 111A and 112A, each document information 111A and 112A can be compared in block units, and the coincidence point or difference can be examined in detail, thereby improving the usability.

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, in the first embodiment, the case where the coordinate system is determined from the word group included in the first document information and the second document information is described. However, the present invention is not limited to this, and the word group included in a larger number of document information. A coordinate system may be determined based on this.
In the first embodiment, the case where the document information is divided into a plurality of blocks and compared is described. However, the present invention is not limited to this, and the entire document information may be treated as one block and the entire documents may be compared. it can.

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 whole operation | movement of a literature information analysis method. It is a flowchart which shows the process for dividing | segmenting literature information into a some block and producing | generating a map. It is a flowchart which shows the process for comparing the content between blocks. It is explanatory drawing which shows an example of the comparison result between blocks. It is explanatory drawing which shows an example of the menu screen for designating map generation conditions. It is explanatory drawing which shows the whole literature information analyzer provided with the relevance analyzer which concerns on 2nd Example of this invention. It is explanatory drawing which shows a connection line display form management table. It is a flowchart which shows whole operation | movement.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Literature information analyzer, 2 ... Client terminal, 10 ... Map control part, 11 ... Map generation condition input reception part, 12 ... Literature information division part, 13 ... Block coordinate calculation part, 14 ... Inter-block similarity determination part, DESCRIPTION OF SYMBOLS 15 ... Map production | generation part, 16 ... Map display part, 20 ... Comparison control part, 21 ... Connection line designation | designated information input reception part, 22 ... Block comparison part, 23 ... Comparison result output part, 24 ... Comparison result display part, 30 ... Information storage unit, 31 ... literature database, 32 ... word database, 100 ... map, 101A, 101B ... contour, 111, 112 ... block, 300 ... relevance analyzer, 310 ... literature selection unit, 320 ... relevance detection unit, 330 ... Connection line selection unit, 340 ... Display output unit, 350 ... Display screen, 360 ... Selection operation detection unit

Claims (9)

A document information storage unit that stores a plurality of document information, each of which is a patent document related to an electronic patent application or utility model registration application ,
The first document information and the second document information selected according to the map generation condition input from the user among the stored document information are respectively acquired from the document information storage unit, and the first document information and the second document information are acquired. A document information acquisition unit that divides and processes document information into blocks of a predetermined unit that is either a paragraph unit or a claim unit or both based on the map generation condition ,
Each of the blocks included in each block in a coordinate system determined by using principal component analysis based on the frequency of appearance of each word or each block of word information included in the first document information and the second document information and the block coordinate calculation unit configured to calculate an average value of coordinates in the coordinate system of the word as the coordinates of the blocks,
The respective blocks are arranged based on the coordinates of the respective blocks, and the second of the blocks is separated from a predetermined first block derived from the first document information by a predetermined distance in the coordinate system. a map generating unit for generating map information by a predetermined second block derived from literature data, connected by Viewing elements,
A map display unit for displaying the generated map information;
A bibliographic information analyzer. When there are a plurality of at least one of the first block and the second block that are separated by the predetermined distance or more, the map generation unit determines the closest first block and second block among them. Bibliography analyzer according to claim 1 which is connected in front Symbol Display element. If the previous SL Display element is selected by the user, the content and the second block of the content and the word level of the first block being connected by the selected table shown elements, phrase level, among the sentence level The literature information analysis apparatus according to claim 2 , further comprising: a block comparison unit that compares at least one level selected by the user and outputs a comparison result. Said block comparison unit, document information analyzer according to different part of the content of content and the second block of the connected first block in the previous Symbol Display element according to claim 3 for output as the comparison result. Said block comparison unit, document information analyzing apparatus according to the intersection of the content before Symbol Display element connected the first block with the content of the second block in claim 3 for output as the comparison result. Before SL document information obtaining section, among the first document information and the second document information is selected, the literature of claim 2 for dividing only the range selected by the user into blocks of the predetermined unit Information analysis device. Among the plurality of document information stored in the document information storage unit, the document information having a predetermined legal relationship is determined based on the bibliographic items of each document information, and the document information having the legal relationship is determined. A pre-processing unit for displaying by connecting with a connection line according to the legal relationship;
When the connection line is selected by a user, the document information acquisition unit converts each document information connected by the connection line from the document information storage unit as the first document information and the second document information, respectively. get,
The literature information analyzer according to any one of claims 1 to 6. Computer
The first document information and the second document information selected by the map generation condition input from the user from among a plurality of document information that is a patent document or a patent document relating to a utility model registration application electronically stored in the document information storage unit Document information division for acquiring document information and dividing the first document information and the second document information into blocks of a predetermined unit that is either a paragraph unit or a claim unit or both based on the map generation condition. Means,
Each word included in each block in the coordinate system determined by using principal component analysis based on the frequency of appearance of each word information or block for each word included in the first document information and the second document information and block coordinates calculating means for calculating respective average values of the coordinates as the coordinates of the respective blocks in the coordinate system of
The respective blocks are arranged based on the coordinates of the respective blocks, and the second of the blocks is separated from a predetermined first block derived from the first document information by a predetermined distance in the coordinate system. and a predetermined second block derived from literature data, a map generating means for generating map information by connecting with Viewing elements,
Each program that functions. The first document information and the second document selected by the computer based on the map generation condition input from the user from among a plurality of document information that is a patent application or a patent document related to the utility model registration application stored in the document information storage unit Obtaining each information step;
The computer dividing the first document information and the second document information into blocks of a predetermined unit which is either a paragraph unit or a claim unit or both based on the map generation condition ;
The computer, in the coordinate system is determined by using a principal component analysis based on the appearance frequency of each document information or each block of words contained in the first document information and the second document information, wherein in each block calculating respective average values of coordinates in the coordinate system of each word contained as the coordinates of the blocks,
The computer placing each block on a map according to the coordinate system based on the coordinates of each block;
The computer has a predetermined first block derived from the second document information that is separated from the predetermined first block derived from the first document information by a predetermined distance in the coordinate system among the blocks arranged on the map. and generating the map information by the two blocks, connected by Viewing elements,
The computer displaying the generated map information; and
Said computer, said if the selected pre-Symbol Display element by the user, the selected Viewing elements by the connected with the contents of the first block is the second block of the content and the word level, phrasal, compared with at least one of the level selected by the user out of the sentence level, document information analyzing method for performing the step of outputting the comparison result.

Images