JP2006277108A - Information providing method, document editing device and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide information relating to information in an original document as requested by a user. <P>SOLUTION: A document to be translated to which annotations are added is set on a scanner device, and the document is downloaded to acquire image data. The document structure is analyzed for the image data, and the annotations and script portions (character information) are separated from each other and extracted. Then, translating processing is given to the character information. The contents of the separated and extracted annotations are specified. Information specified by the user is specified from the specified contents of the annotations, and a relative information DB is searched to extract the information specified by the user. A text after translating processing is combined with the extracted information. Finally, the text is output in a predetermined method. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to a technique for editing and presenting information.

In today's information-oriented society, for the purpose of organizing and effectively utilizing information, so-called document digitization processing is performed in which a document printed on paper or the like is read with a scanner device or the like to obtain necessary information. ing. As an example of digitization processing, an original document is captured as digital image data, character recognition processing (so-called OCR processing) is performed to extract character information (text data), and a document structure is created using dictionary data or a predetermined algorithm. There is a so-called machine translation process in which a document in one language is translated into a document in another language by replacing the character (phrase) with another character (phrase) through analysis or the like (see, for example, Patent Document 1) ).
Japanese Patent Laid-Open No. 62-154845

  However, even if character information can be extracted from the original document without omission by OCR processing or the like, all of the information is not necessarily required for the user. For example, among the information obtained by extracting character information from a tourist brochure printed on paper (translation processing if necessary), the information that the user is interested in is a part of many information The case is normal. Further, as can be seen in the example of a tourist brochure, when a user who has read a translated document is interested in specific information, he often wants to acquire more detailed information about the information. In this regard, in the prior art, for example, the document cannot be edited according to the user's needs, and as a result, the digitized document cannot be effectively used.

  The present invention has been made in view of the above-described background, and an object thereof is to provide a method and apparatus for providing information related to information included in an original document in response to a user request.

  In order to solve the above problems, the present invention provides a document input step for inputting a document, an additional information extraction step for extracting character information and annotation from the document input in the document input step, and the additional information extraction step. A translation step for performing a translation process on the character information extracted in step 1, a specification step for specifying the content of the annotation extracted in the additional information extraction step and a document element to which the annotation is added, and the specification step A related information extracting step for extracting information corresponding to the annotation content and document element specified in step 1 from the database, information extracted in the related information extracting step, and a document subjected to translation processing in the translating step And an output step of performing an editing process by a predetermined method and outputting the information It provides a test method. According to the present invention, when a user adds a predetermined annotation to a desired document element, related information can be extracted and provided to the user based on the content of the addition process.

  According to another aspect of the information providing method of the present invention, a document input step for inputting a document, and an extraction for extracting form elements, which are elements forming the form of the document, from the document input in the document input step A step, an additional information specifying step for specifying information added to the form element extracted in the extracting step, and a relationship between the additional information specified in the additional information specifying step or extraction in the extracting step An instruction content specifying step for specifying the instruction content of the document by specifying at least one of the relations between the formed form elements, and information corresponding to the instruction content specified in the instruction content specifying step in the database An information extraction step for extracting the information extracted from the information extraction step and outputting the information extracted in the information extraction step by a predetermined method. Has a step, a. According to this aspect, information corresponding to information given to a document having a form structure can be provided to the user.

  In another aspect, the present invention provides a database, document input means for inputting a document, additional information extraction means for extracting character information and annotation from a document input by the document input means, and the additional information extraction A translation means for performing a translation process on the character information extracted by the means, a specification means for specifying the content of the annotation extracted by the additional information extraction means and a document element to which the annotation is added, and the specification Related information extracting means for extracting information corresponding to the annotation content and document element specified by the means from the database, information extracted by the related information extracting means, and translation processing being performed by the translating means There is provided a document editing apparatus having an output means for performing an editing process on a document and outputting it by a predetermined method.

  According to another aspect of the document editing apparatus of the present invention, a database, a document input unit that inputs a document, and a form element that is an element that forms a form of the document from the document input by the document input unit. An extracting means for extracting; an additional information specifying means for specifying information added to the form element extracted by the extracting means; and a relationship between the additional information specified by the additional information specifying means or the extracting means By specifying at least one of the relationships between the form elements extracted in step 1, the instruction content specifying means for specifying the instruction content of the document and the instruction content specified by the instruction content specifying means Information extraction means for extracting information from the database, and output means for outputting the information extracted by the information extraction means by a predetermined method.

  In another aspect, the present invention provides a document input step for inputting a document to a computer having a database, and an additional information extraction step for extracting character information and annotation from the document input in the document input step. A translation step for performing a translation process on the character information extracted in the additional information extraction step, and a specification for specifying the content of the annotation extracted in the additional information extraction step and a document element to which the annotation is added A related information extracting step for extracting information corresponding to the content of the annotation and the document element specified in the specifying step from the database, and the information extracted in the related information extracting step and the translating step. Edit the document that has undergone translation processing in a predetermined way An output step of outputting Te provides a computer readable program for executing.

  According to another aspect of the program of the present invention, a document input step for inputting a document to a computer having a database, and a form element that forms a form of the document from the document input in the document input step. An extraction step for extracting information, an additional information specification step for specifying information added to the form element extracted in the extraction step, and a relationship between the additional information specified in the additional information specification step or the extraction By specifying at least one of the relationships between the form elements extracted in the step, the instruction content specifying step for specifying the instruction content of the document and the instruction content specified in the instruction content specifying step Information extraction step of extracting the information obtained from the database, and the information extraction step An output step of outputting the issued information in a predetermined manner, characterized in that for the execution.

<Example>
(First embodiment)
Hereinafter, preferred embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a diagram showing a functional configuration of a document editing apparatus 1 according to an embodiment of the present invention. As shown in FIG. 1, the document editing apparatus 1 includes a control unit 10, a storage unit 11, an input unit 12, an operation unit 13, a display unit 14, and an output unit 15. The control unit 10 includes a control processor such as a CPU, and controls each unit of the document editing apparatus 1. The control unit 10 includes a document structure analysis unit 101, an annotation recognition unit 102, a character information recognition unit 103, a translation processing unit 104, and an editing processing unit 105. The document structure analysis unit 101 performs layout analysis or the like on a document as image data captured by the input unit 12 using a predetermined algorithm, and determines the layout structure of the document. Specifically, it is determined whether or not the document contains characters and non-character (additional information such as illustrations, ruled lines, notes, etc. (hereinafter referred to as annotations)). Separates the character area from the other areas.

  The annotation recognition unit 102 is a target to which an annotation type and an annotation are added by performing predetermined analysis processing on image data of a region other than the characters separated and extracted by the document structure analysis unit 101. Determine locations (document elements such as words and phrases). The extracted annotation types include, for example, sticky notes, surrounding lines, underlines, marker processing (highlight processing), leader lines, notes / annotations (characters inserted between lines of the original text), and the like. Information relating to the annotation and the document element (word / phrase) to be added is stored in the storage unit 11. The character information recognition unit 103 performs character recognition processing on the region separated and extracted by the document structure analysis unit 101 to extract character information (phrase), and stores it in the storage unit 11. The translation processing unit 104 performs a replacement process on the character information extracted by the character information recognition unit 103 using dictionary data stored in the storage unit 11 or a predetermined algorithm, thereby changing the language of the document. A translation process for translating into another language specified by the user is performed. The relationship between the translated document data and the phrases in the original sentence and the phrases in the translated sentence is stored in the storage unit 11. The document structure analyzing unit 101, the annotation recognizing unit 102, the character information recognizing unit 103, and the translation processing unit 104 perform a translation process on the annotation and the character portion from the image data of the annotated document. For this, a function for extracting information on the phrase in the original sentence to which the type and annotation are added and the translated phrase is realized. The edit processing unit 105 reads the annotation extracted from the original document and the document element to which the annotation is added from the storage unit 11 and stores the translation database stored in the storage unit 11 based on the annotation and the document element. (DB) It has a function of extracting necessary information from the 111 and performing an editing process for synthesizing it with post-translation character information obtained by the translation processing unit 104. Details of this function will be described later. Details of these processes performed by the control unit 10 will be described later. The functions of these units realized by the control unit 10 may be realized by independent processors, or may be realized by, for example, one processor executing a plurality of software.

  The storage unit 11 is a storage device such as a RAM, a ROM, and a hard disk, and stores a translation DB 111 and related information DB 112 that are necessary when the control unit 10 performs the above-described processing, and other necessary data. As shown in FIG. 1, the translation DB 111 stores various dictionary data (for example, English-Japanese dictionary data in which English words and Japanese words are registered in association with each other) that can be used in translation processing. The related information DB 112 is a database in which information and words included in the information are registered in association with each other, and when a plurality of words are specified and the database is searched, data related to the words is extracted. It has a structure. For example, when the DB is searched using “A station” and “train” as keys, operation information of trains passing through the A station is extracted.

  The input unit 12 is a scanner device or the like, and is a device that reads a document printed on paper or the like as digital image data and supplies the digital image data to the control unit 10 and the storage unit 11. The operation unit 13 is an input device such as a keyboard or a mouse. When the user of the document editing apparatus 1 specifies a document to be translated, specifies an annotation to be added (details will be described later), and inputs other necessary information. Is used. Instructions and information input via the operation unit 13 are supplied to the control unit 10. The display unit 14 includes a drawing processor (not shown) and a display device (not shown) such as a liquid crystal display. Under the instruction of the control unit 10, the display unit 14 receives the original document, the translated document, and the related information DB 112. The extracted related information and other messages to the user are displayed on the screen. The output unit 15 is a printer for printing an edited document on paper or the like, a communication interface for supplying document data obtained by performing additional information editing processing to a printing apparatus, or document data is stored in a flash memory, A storage device for storing in a storage medium such as a CD-ROM.

  Hereinafter, an example of the operation of the document editing apparatus 1 will be described with reference to FIGS. 2 and 3. In the present embodiment, information desired by the user is provided in English from a tourist pamphlet (hereinafter referred to as a processing target document) written in Japanese and printed on paper as shown in FIG. Will be described. As shown in FIG. 2, the user first writes a predetermined annotation using a writing instrument such as a pencil or a pen in a predetermined portion (word / phrase) of the processing target document according to desired information (step S10). . FIG. 3A shows an example of annotations that are written when the user who has read this pamphlet wants detailed information about the train transfer information to “Keiage Station”. As shown in the figure, in order to specify the annotation addition target, the user adds a box line to “Keiage Station”, and further inserts a leader line for specifying the relationship between the addition target and the annotation. Write the letter “Train” that specifies the train as a means. In addition, if the user wants an enlarged map around Keage Station, enter a square box for the Keage Station shown on the map printed at the bottom of the document to be processed. A leader line is inserted, and a character “Details” for specifying enlargement of a predetermined portion is written.

  Returning to FIG. 2, the user sets the document to be translated with the annotation added to the scanner device, and acquires the image data by capturing the document (step S <b> 11). Then, the control unit 10 first performs document structure analysis on the image data (step S12), and separates and extracts the annotation and the document portion (character information) (step S13). Subsequently, translation processing is performed on the character information (step S14). Then, the content of the annotation that is separated and extracted (in this case, the fact that the annotation “Train” is assigned to “Keiage Station”) is specified (step S15). Similarly, the annotation attached to the map image specifies that the image corresponding to the area surrounded by the rectangle is to be enlarged and displayed at a predetermined enlargement ratio. Subsequently, information related to the specified annotation is retrieved from the related information DB 112. Specifically, the related information DB 112 is searched using “Keiage Station” and “Train” as keys. Information related to the train and the train, that is, information such as route routes, fares and required time of the main train to the train is extracted (step S16). At that time, when the place where the device is installed is stored in the device, the route from the nearest station to the lift station can be selected and extracted. In the example of FIG. 3, a route or the like is selected on the assumption that a device is installed at or near Kyoto Station. Subsequently, the sentence after translation processing obtained in step S14 and the information extracted in step S16 are synthesized (step S17). FIGS. 3B and 3C show an example of a document that has been subjected to editing processing in this way ((b) and (c) are different pages). As shown in FIG. 6B, the translated sentence and the map of the sentence are arranged at positions corresponding to the sentence and the map image in the original document shown in FIG. And as shown in the figure (c), the extracted related information (in this case operation information) is arrange | positioned at the end of a translation text, The said designated enlarged view is added under it. Finally, when the user inputs a predetermined instruction, the sentence displayed on the display unit is output in a manner designated by the user (step S18).

  As described above, according to the document editing apparatus 1, when a predetermined annotation (document element) in an original document is specified by a user and a predetermined annotation is added, the information content of the portion and the content of the annotation are related. The information to be extracted is extracted from the related information DB 112 and synthesized with the translated document and provided to the user. Thereby, the related information according to the user's needs can be provided to the user who has read the document.

(Second Embodiment)
FIG. 4 is a diagram illustrating a functional configuration of the document editing apparatus 1A according to the second embodiment. As shown in the figure, the document editing apparatus 1A is different from the document editing apparatus 1 according to the first embodiment in that a form analysis unit is replaced with a document structure analysis unit 101, an annotation recognition unit 102, and a translation processing unit 104. 106 and a mark recognizing unit 107, and a form DB 113 is provided in the storage unit 11 in place of the translation DB 111. The form analysis unit 106 performs predetermined image analysis on image data obtained by scanning a document having a structure (hereinafter referred to as a form) composed of areas divided by ruled lines, check boxes, input boxes, and the like. Processing is performed to acquire information on the type and arrangement position of each form element (input box, check box, etc .; hereinafter referred to as form element) The mark recognition unit 107 is information corresponding to the form element and the form element. (For check boxes, circles, etc .; hereinafter simply referred to as marks) In addition, for an input box or the like, the character information recognition unit 103 performs character recognition processing on the image data in the area inside the input box. Character information (text data) is extracted, and the form DB 113 stores information such as form elements and attributes of the form elements. Information is stored, and the edit processing unit 105 specifies the relationship between the extracted form elements using the form DB 113. This process will be described later. Has a function of extracting form elements from the scanned document and specifying the contents of the document from the relationship between the form elements.

  Hereinafter, an operation example of the document editing apparatus 1A will be described with reference to FIGS. Hereinafter, consider a case where the user scans a document printed on paper having a form structure as shown in FIG. In this example, the user says, “Information on how to get from Kyoto Station to Nanzenji using a train as a means of transportation, an enlarged map around the nearest station of the destination, and a conversation in Japanese expected to be used. In this example, the case where the user asks for a way, the case where he / she gets lost, and the case where he / she asks for the location of the toilet is designated is shown. The form structure is analyzed using the form DB 113 (step S30), and the form elements and the mark and character information for each form element are extracted, that is, “From:”, input box, check box, Each form element, such as a check mark and “Train”, a mark, and character information are extracted. Subsequently, the relationship between the extracted form elements is specified, and the content of the information designated by the user is specified (step S32).

  Specifically, first, the connection relationship of each form element is determined from the arrangement relationship. For example, it is determined that “From:” and the character “Kyoto station” in the adjacent input box are combined. Further, based on the positional relationship between the mark and the form element, the relationship between each mark and the corresponding form element (for example, a check mark is given to the form element “□”) is determined. Further, the subordinate relation between the form elements is determined for the character information from the font size and arrangement position, and the grouping is performed. For example, “□ Train”, “□ Bus”, “□ Taxi”, and “□ Other” are parallel relationships based on the layout relationship, and from the layout relationship between these four form elements and “Transportation”, The four elements are determined to be subordinate to the element “Transportation”. Subsequently, the commonality between the form elements is determined, and the elements are grouped. Specifically, using dictionary data or the like stored in the storage unit 11, the form elements “From:”, “To:”, and “Transportation” are words related to traffic information based on their semantic contents. Therefore, it is determined that they belong to the same information group.

  When the relationship between the form elements described above is determined in this manner, the control unit 10 confirms that the user has designated the information with the content “going from Kyoto Station to Nanzenji using a train as a means of transportation”. Identify. Similarly, the map image around the destination at 200% magnification should be specified from “Map”, “Large”, “Detail”, the dotted line between both form elements and the check mark position on the dotted line. Is identified. In addition, from the “Example”, “□ Route”, “□ Astray”, “□ Rest room”, and check mark locations, you can ask for directions in various situations, get lost, and determine the location of the toilet. Specify that a Japanese example sentence to be used when asking is specified.

  Returning to FIG. 5 again, when the information designated by the user is specified, the editing processing unit 105 extracts information corresponding to the specified information from the related information DB 112 (step S34), and performs a predetermined editing process (step S34). S36), displayed on the screen of the display unit 14 or printed on paper (step S38). 6B and 6C are examples of the document after the editing process. The document (c) is a document on the next page of the document (b). As shown in FIG. 5B, the destination designated by the user “Nanzen-ji Temple” is displayed in the title section. Below that, route information from “Kyoto Station” designated as the departure point to the nearest station of Nanzenji is displayed. Below that, a map image is displayed at an enlargement ratio designated by the user. On the next page, the example sentences corresponding to the situation specified by the user as shown in FIG.

  As described above, according to the document editing apparatus 1A, the content can be specified from the document created by the user in a predetermined form, and information corresponding to the content can be extracted and provided to the user.

<Modification>
The present invention is not limited to the above embodiments, and various modifications can be made. FIG. 7 is a diagram showing a schematic diagram of an information providing system 200 which is a modified example of the present invention. The information providing system 200 includes a document editing apparatus 1B, an information providing server 2, and a communication network 3. The document editing apparatus 1B is different from the document editing apparatus 1A only in that it has a communication I / F 16 for communicating with the information providing server 2 via the communication network 3 and does not have a related information DB 112. Different. The information providing server 2 includes a control unit 20, a user management DB 21, a related information DB 112, and a communication unit 23. As can be seen from the figure, in the present modification, the user acquires related information from the information providing server 2. More specifically, when the document editing apparatus 1B specifies annotation information (annotation and target location), the control unit 10 generates a request including the user ID stored in the storage unit 11 and this information, and the communication network 3 Is transmitted to the information providing server 2 via. Upon receipt of this request, the information providing server 2 refers to the user management DB 21 and performs user authentication or predetermined accounting processing, and then extracts related information corresponding to the annotation information from the related information DB 112 to obtain a document editing device. Send to 1B.

  According to such an aspect, it is not necessary to provide a database in the document editing apparatus. It is also possible to perform additional processing such as user authentication for providing related information, billing based on it, or free / discount by adding advertisements. For example, advertisement information related to the content of the document (for example, an advertisement of a nearby souvenir shop if the original document relates to tourist information) or the like is added to a predetermined portion of the text after output to the user. It can also be provided. An example of a document in which advertisement information is displayed is shown in FIG.

  In the above-described embodiment, an example in which a scanner is used to read a document printed on paper or the like with annotations and check marks written by hand. However, the present invention is not limited to this. It is also possible to scan a document in which nothing is filled in the form, display the image on the display unit 14, and add an annotation or mark and write on the form using a mouse or a keyboard on this screen. Needless to say. In short, any configuration is possible as long as it can discriminate annotations and marks given by the user and acquire information corresponding to them.

It is a figure which shows the function structure of the document editing apparatus 1 which concerns on 1st Embodiment of this invention. It is a figure for demonstrating the flow of the process performed in the document editing apparatus 1 in the Example. (A) is an original document to be edited, and (b) and (c) are diagrams showing an example of a document after editing processing. It is a figure which shows the function structure of 1 A of document editing apparatuses which concern on 2nd Embodiment of this invention. It is a figure for demonstrating the flow of the process performed in 1 A of document edit apparatuses in the Example. (A) is an original document to be edited, and (b) and (c) are diagrams showing an example of a document after editing processing. It is a figure which shows the function structure of the information provision system 200 which concerns on the modification of this invention. It is a figure which shows the document produced | generated in the modification.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Document editing apparatus, 2 ... Information provision server, 3 ... Communication network, 10 ... Control part, 11 ... Memory | storage part, 12 ... Input part, 13 ... Operation part , 14 ... Display section, 15 ... Output section, 16 ... Communication I / F, 20 ... Control section, 21 ... User management DB, 23 ... Communication section, 101 ... Document structure analysis unit 102 ... Annotation recognition unit 103 ... Character information recognition unit 104 ... Translation processing unit 105 ... Edit processing unit 106 ... Form analysis unit 107 ... Mark recognition unit 111. Translation DB, 112 Related information DB 113 Form DB 200 Information providing system

Claims (6)

A document input step for entering a document;
An additional information extraction step of extracting character information and annotation from the document input in the document input step;
A translation step for performing a translation process on the character information extracted in the additional information extraction step;
A specification step for specifying the content of the annotation extracted in the additional information extraction step and the document element to which the annotation is added;
A related information extracting step of extracting information corresponding to the content of the annotation specified in the specifying step and the document element from a database;
An output step in which the information extracted in the related information extraction step and the document subjected to the translation process in the translation step are edited and output in a predetermined method;
A method for providing information. A document input step for entering a document;
An extraction step of extracting a form element that is an element forming a form of the document from the document input in the document input step;
An additional information specifying step for specifying information added to the form element extracted in the extracting step;
Instruction content specifying the instruction content of the document by specifying at least one of the relationship between the additional information specified in the additional information specifying step or the relationship between the form elements extracted in the extraction step Specific steps,
An information extracting step of extracting information corresponding to the instruction content specified in the instruction content specifying step from a database;
An output step of outputting the information extracted in the information extraction step by a predetermined method;
A method for providing information. A database,
A document input means for inputting a document;
Additional information extraction means for extracting character information and annotation from the document input by the document input means;
Translation means for performing a translation process on the character information extracted by the additional information extraction means;
Specifying means for specifying the content of the annotation extracted by the additional information extracting means and the document element to which the annotation is to be added;
Related information extracting means for extracting information corresponding to the content of the annotation specified by the specifying means and the document element from the database;
An output means for performing an editing process in a predetermined method and outputting the information extracted by the related information extracting means and the document subjected to the translation process by the translation means;
A document editing apparatus. A database,
A document input means for inputting a document;
Extraction means for extracting form elements, which are elements forming the form of the document, from the document input by the document input means;
Additional information specifying means for specifying information added to the form element extracted by the extracting means;
Instruction contents for specifying instruction contents of the document by specifying at least one of the relation between additional information specified by the additional information specifying means or the relation between form elements extracted by the extracting means Specific means,
Information extracting means for extracting information corresponding to the instruction content specified by the instruction content specifying means from the database;
Output means for outputting the information extracted by the information extraction means by a predetermined method;
A document editing apparatus. On the computer with the database
A document input step for entering a document;
An additional information extraction step of extracting character information and annotation from the document input in the document input step;
A translation step for performing a translation process on the character information extracted in the additional information extraction step;
A specification step for specifying the content of the annotation extracted in the additional information extraction step and the document element to which the annotation is added;
A related information extracting step of extracting information corresponding to the content of the annotation specified in the specifying step and the document element from the database;
An output step in which the information extracted in the related information extraction step and the document subjected to the translation process in the translation step are edited and output in a predetermined method;
A computer-readable program that executes On the computer with the database
A document input step for entering a document;
An extraction step of extracting a form element that is an element forming a form of the document from the document input in the document input step;
An additional information specifying step for specifying information added to the form element extracted in the extracting step;
Instruction content specifying the instruction content of the document by specifying at least one of the relationship between the additional information specified in the additional information specifying step or the relationship between the form elements extracted in the extraction step Specific steps,
An information extracting step of extracting information corresponding to the instruction content specified in the instruction content specifying step from the database;
An output step of outputting the information extracted in the information extraction step by a predetermined method;
A computer-readable program that executes

Images