JP3712966B2 - Presentation material generating apparatus, presentation material generating method, and presentation material generating program - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
  The present inventionPresentation material generating apparatus, presentation material generating method, and presentation material generating programFor example, it relates to a device that automatically generates presentation materials from materials that are the basis of presentations such as papers and reports.
[0002]
[Prior art]
The importance of presentation is increasing in various fields such as industry, academics, and education.
In the presentation, the performer explains a predetermined subject to the audience using presentation materials including diagrams and simple sentences.
The materials used for these presentations are printed on paper and distributed to the audience, or projected onto a screen using a projector, for example.
[0003]
Currently, various software (hereinafter referred to as presentation software) that supports the creation of such presentation materials is sold in the market.
The user can install these presentation software on a personal computer or the like and use them for creating presentation materials.
[0004]
In these presentation software, for example, a desired number of display units called slides can be generated, and the user can create presentation materials by pasting charts or writing text on these slides. Go.
[0005]
The created slide is printed on paper and distributed to the audience, or printed on film and projected by a projector, or data is directly transmitted from a personal computer to the projector, and the projector projects the slide. Is presented to the audience.
[0006]
In the case of giving a presentation, there are usually papers, reports, planning documents, etc. that are the basis of the presentation. The performer creates presentation materials by excerpting diagrams from these materials, or by extracting words that represent important points.
[0007]
As described above, there is “slide generation from GDA tag” published in the “Language Resource Sharing and Utilization” Symposium (1999) as an invention that supports the creation of presentation materials.
This is to generate presentation materials (which are described as “slide materials” in the paper) from a manually created GDA (Global Document Annotation) corpus.
[0008]
[Problems to be solved by the invention]
However, making this GDA corpus (tagging) requires more cost (time and labor) than creating presentation materials, and is not suitable for the purpose of generating presentation materials from documents.
Moreover, the presently sold presentation software does not include a function for automatically creating and generating presentation materials. Therefore, the user spends a lot of time and effort in creating the presentation material.
[0009]
  Therefore, an object of the present invention is to automatically generate presentation materials by using data (for example, a paper or a plan) as a source of presentation materials.Presentation material generating apparatus, presentation material generating method, and presentation material generating programIs to provide.
[0010]
[Means for Solving the Problems]
  In order to achieve the above object, the present invention provides a method according to claim 1,Receiving means for receiving the number of divisions for dividing the document, the maximum number of sentences to be extracted, the sentence end expression, and the layout;A document acquisition means for acquiring a document;Analyzing the document structure of the acquired document, determining means for determining the area of the solid written sentence, morphological analysis and syntactic analysis of the determined solid written sentence, the result of the analysis and a predetermined clue word Using the authorizing means for authorizing an important sentence from the solid written sentence, the dividing means for dividing the document into the accepted number of divisions based on the analysis result by the determining means, and the divided parts, Extracting means for extracting the recognized important sentence in accordance with the importance within the accepted maximum number of sentences, and simplifying the extracted important sentence, and the simplified sentence ending expression is the accepted sentence ending A concise sentence generating means for generating a concise sentence to be expressed; and an output means for outputting the generated concise sentence in the accepted layout, wherein the output means In the case of, only the generated concise sentence is output, in the case of a mixture of sentences and charts, the concise sentence and a chart that matches the concise sentence are output, and in the case of only the chart, only the chart that matches the concise sentence is output. Presentation material generating device characterized by outputI will provide a.
  In the invention according to claim 2,Simplified / detail receiving means for receiving selection of whether to generate simple presentation material or detailed presentation material is provided, and the extracting means is based on the selection received by the simplified / detail receiving means. The presentation material generating apparatus according to claim 1, wherein the number of important sentences to be extracted is increased or decreased within the range of the maximum number of sentences.
  In invention of Claim 3,In a computer including a receiving unit, a document acquiring unit, a determining unit, an authorizing unit, a dividing unit, an extracting unit, a concise sentence generating unit, and an output unit, the receiving unit divides the document. The accepting step for accepting the setting of the number of divisions, the maximum number of sentences to be extracted, the sentence end expression, and the layout, the document obtaining step for obtaining the document by the document obtaining means, and the document structure of the obtained document by the judging means Analyzing and determining the area of the solid written sentence, and using the certifying means, morphological analysis and syntactic analysis of the determined solid written sentence, using the result of the analysis and a predetermined clue word, A recognition step for recognizing an important sentence from the solid written sentence, and a dividing step for dividing the document into the accepted number of divisions based on the analysis result by the determining means by the dividing means. An extraction step of extracting the recognized important sentence according to importance within the accepted maximum number of sentences from the divided parts by the extracting means; and the extracted important sentence by the concise sentence generating means Concise sentence generation step for generating a concise sentence in which the sentence end expression of the simplified concise sentence becomes the accepted sentence ending expression, and the output means converts the generated concise sentence into the accepted layout. An output step for outputting, and in the output step, if the accepted layout is a sentence only, the generated concise sentence is output. A presentation material generation method characterized by outputting a chart that matches a concise sentence and outputting only a chart that matches the concise sentence if only the chart is output. Subjected to.
  In the invention according to claim 4,Accepts the number of divisions to divide a document, the maximum number of sentences to be extracted, sentence ending expression, and layout settings, the document acquisition function to acquire a document, the document structure of the acquired document, A determination function for determining an area, and a certifying function for performing morphological analysis and syntactic analysis on the determined solid written sentence, and certifying an important sentence from the solid written sentence using a result of the analysis and a predetermined clue word And a division function that divides the document into the accepted number of divisions based on the analysis result by the analysis function, and the recognition according to the degree of importance within the maximum number of sentences received from each of the divided parts. An extraction function for extracting the important sentence, and a concise sentence generation function for simplifying the extracted important sentence and generating a concise sentence in which the sentence ending expression of the simplified concise sentence becomes the accepted sentence ending expression, An output function to output a brief statement that the serial generated by the accepted layout, the presentation documentation generation program to be implemented by a computer, the output function, the accepted layout, of the sentence Only the generated concise sentence is output, and if the sentence and the chart are mixed, the concise sentence and the chart that matches the concise sentence are output, and if only the chart, only the chart that matches the concise sentence is output. Is provided. A presentation material generation program is provided.
[0011]
DETAILED DESCRIPTION OF THE INVENTION
When creating presentation materials, there are many cases where the original document exists. In the present embodiment, presentation material is automatically generated by extracting important parts from the original document and converting them into a concise expression.
Hereinafter, an example of a preferred embodiment of the present invention will be described in detail with reference to FIGS.
[0012]
FIG. 1 is a diagram conceptually showing the configuration of the presentation material generating apparatus 1 according to the present embodiment.
The presentation material generation apparatus 1 includes a document analysis unit 2, a morpheme analysis unit 4, an important sentence determination unit 6, a syntax analysis unit 8, a concise expression generation unit 10, a document structure generation unit 12, and the like.
[0013]
The presentation material generation apparatus 1 is a kind of information processing apparatus, and receives an input document 14 and input parameters 16 and generates a presentation material 18 using them.
The input document 14 is, for example, a document file such as an academic paper, a business report, or a plan, and is a document file from which the presentation material 18 is generated.
[0014]
The input document 14 is a document file created by a word processor or a text editor, for example, and may include chart data.
Further, the input document 14 may be a paragraph unit or a single document. Alternatively, the input document 14 may be a so-called solid document that does not have a document structure such as a title, chapter heading, or itemized list with line breaks. Here, the solid document is a document written over the entire display surface.
[0015]
The document structure analysis unit 2 analyzes the document structure of the input document 14 and extracts chapters, sections, bullets, charts, and the like from the input document 14. In addition, the document structure analysis unit 2 extracts chapters, sections, bullets, charts, and parts that are not determined as titles as solid written sentences.
The input document 14 is, for example, a paper, a report, a plan, etc., and usually has a title, the contents are assembled from fine units such as chapters and sections, and a table or list such as a photograph, a figure, or a graph. May be incorporated.
Thus, the input document 14 has various document structures.
[0016]
The document structure analysis unit 2 acquires the input document 14 and determines a document structure such as a chapter, a section, an itemized list, a chart, a title, and a solid area. In the text sentence, referring to the number of chapters and sections at the beginning of the line, the amount of indentation, etc., the word processor document also determines the document structure in addition to the judgment material such as serial number symbols and format (bold letters and underline).
[0017]
The morpheme analysis unit 4 performs a morpheme analysis on the written text extracted by the document structure analysis unit 2 using a morpheme analysis dictionary (not shown).
The morpheme analysis performed by the morpheme analysis unit 4 is to decompose the input document 14 into a sequence of morphemes and determine the attributes (part of speech, utilization, number, gender, personality, case, etc.) of each morpheme. It is what has been broken. The morpheme analysis unit 4 outputs the analysis result to the syntax analysis unit 8 as a morpheme string.
A morpheme is the smallest meaningful language unit.
[0018]
The syntax analysis unit 8 receives the morpheme string output from the morpheme analysis unit 4 as an input, and recognizes a clue word indicating dependency analysis or relationship between important sentences and sentences. Thereby, the syntax analysis unit 8 can collect the material for determining the extracted sentence that is the material of the sentence used in the presentation material.
Examples of the key words for the important sentence include “In short” and “That”, and these are stored in a syntax analysis dictionary (not shown).
[0019]
The syntax analysis unit 8 further performs dependency analysis or estimation of a erasable region (connective, adverb, conjunction modifier, etc.) on the extracted sentence extracted later by the important sentence determination unit 6, and the concise expression generation unit 10. Provide information to generate simple expressions.
[0020]
The important sentence determination unit 6 tree-structures the input document 14 based on the selection criteria specified by the input parameter 16 (for example, the number of sentences to be extracted) and the parsing result, and extracts the specified number of sentences. It is a component.
When the document structure analysis unit 2 determines the document structure, the important sentence determination unit 6 divides the input document 14 into a designated number of areas based on the document structure information (however, the maximum number of divisions is Number of sentences).
[0021]
The important sentence determination unit 6 selects and selects the sentence to be finally extracted based on the importance of the sentence recognized by the syntax analysis unit 8 and the appearance position of the sentence for each of the divided areas. Extract sentences.
In the present embodiment, it is assumed that the maximum number of sentences extracted in one area is defined by the input parameter 16 given by the user. The maximum number of sentences can be configured so that a default value is set in advance, and the user can change it as necessary or fix it to a predetermined value.
[0022]
The input parameter 16 is acquired from a user by an input parameter acquisition unit (not shown) and passed to the important sentence determination unit 6.
The input parameters 16 are composed of the maximum number of sentences, chart priority or document priority, selected template type, sentence ending expression type (mass key, key, title display, etc.), etc., each specified by the user can do. This is information for specifying the layout (arrangement) of a sentence or a diagram for outputting a template. In other words, the sentence and chart layout to be output are specified as input parameters.
When the chart priority is selected by the input parameter 16, the chart is extracted with priority, and when the document center is selected, the document is extracted with priority. In this way, when it is desired to extract a sentence and a chart by mixing them, it can be specified which one is preferentially extracted.
[0023]
In addition, when the input document includes a chart, the important sentence determination unit 6 extracts a chart instead of the sentence to be extracted by designating the parameter “preferred chart” with the input parameter 16. You can also
[0024]
The area to which the extracted chart is assigned is, for example, an expression such as “FIG. 1 is a diagram representing the configuration of the device” described in the input document 14 and the extracted chart. This is done by matching captions such as “FIG. If matching fails, an area is added and a chart is assigned to that area for the time being.
[0025]
The concise expression generation unit 10 converts an important sentence selected based on a parameter (specifying a sentence end expression or the like) input in advance as the input parameter 16 into a concise expression. The concise expression generation unit 10 deletes the erasable area estimated by the syntax analysis unit 8 and converts it to a sentence end expression specified in advance (mass key, key, title key). When "title style" is specified, conversion is performed by stopping the body or categorizing the main nouns.
Here, examples of body deterrence and synonymization of main nouns are shown below.
Example sentence: Yamamoto has extended his consecutive hit record to 20
Suppression: Yamamoto, 20 consecutive hit records
Combining the main nouns: Yamamoto with 20 consecutive hits
[0026]
The document structure generation unit 12 flows the output data (the concise expression generated by the concise expression generation unit 10, the chart extracted by the important sentence determination unit, etc.) into the template specified by the user. The document structure is created by pouring into a template designated by the user in advance.
[0027]
As the template, “sentence only”, “mixture of sentences and charts”, “tables and charts”, and the like can be selected.
When “sentence only” is selected, the presentation material is generated from the concise expression generated from the input document 14. In this case, even when a chart is extracted from the input document 14, the chart is not used for the presentation material.
[0028]
When “mixture of sentence and chart” is selected, a presentation material is generated using the concise expression generated from the input document 14 and the chart extracted from the input document 14. The position of the chart is determined by comparing the description such as “FIG. 1 is” in the input document 14 with the caption of the chart.
[0029]
When “only chart” is selected, the presentation material is generated using the chart extracted from the input document 14.
A template can be prepared in advance for each input document 14 to be input.
In addition, when the “sentence only” template is selected, an option “itemized” is prepared, and the concise expression generated by the concise expression generating unit 10 is, for example, 1, 2, 3,. , Etc. may be added to generate bullets.
[0030]
In addition, when the item “detailed / simplified” is provided in the input parameter 16 and the user selects “detailed”, a detailed presentation material 18 is generated by increasing the number of important sentences to be extracted. When “” is selected, the simplified presentation material 18 may be generated by reducing the number of important sentences to be extracted.
[0031]
As a result, when the presentation time is long, “details” is selected, and when the presentation time is short, “simple” is selected to generate an appropriate presentation material 18.
By configuring in this way, the presentation material 18 corresponding to the presentation time can be generated.
[0032]
FIG. 2A is a configuration diagram when the presentation material generating apparatus 1 is configured using a PC.
The presentation material generating apparatus 1 is configured by connecting an input device 34, an output device 38, a communication control device 42, a storage device 48, a storage medium drive device 46, an input / output interface 44, and the like to the control unit 26 via a bus line 43. Has been.
[0033]
The control unit 26 generates the presentation material 18 from the input document 14 according to the presentation material generation program 50 or the like, or controls the entire presentation material generation apparatus 1.
The control unit 26 includes a CPU 28, a ROM (Read Only Memory) 30, a RAM (Random Access Memory) 32, and the like.
[0034]
The ROM 30 is a read-only memory (read-only memory) that stores various programs, data, parameters, and the like for the CPU 28 to perform various calculations and controls. The CPU 28 can read programs, data, parameters, and the like from the ROM 30, but cannot rewrite or delete them.
[0035]
The RAM 32 is a random access memory used as a working memory for the CPU 28. The CPU 28 can write and erase programs and data in the RAM 32. In the present embodiment, the RAM 32 can secure an area for the CPU 28 to store the input document 14, document structure analysis, morphological analysis, important sentence determination, syntax analysis, concise expression generation, document structure generation, and the like. It has become.
[0036]
The input device 34 includes an input device such as a keyboard and a mouse.
The keyboard is a device for inputting information such as letters and numbers to the presentation material generating device 1.
The keyboard includes keys for inputting kana and English characters, numeric keys for inputting numbers, various function keys, cursor keys, and other keys.
[0037]
For example, the keyboard inputs a login ID and a password for the user to log in to the presentation material generation apparatus 1, or data necessary for various input fields on the screen displayed on the display device according to the presentation material generation program 50 (for example, input) Used to input parameter 18).
[0038]
In addition, when the presentation material generation apparatus 1 is equipped with a text editor, word processor software, or the like, the input document 14 can be directly input to the presentation material generation apparatus 1 from the keyboard using these software.
[0039]
A mouse is a pointing device. When the presentation material generation apparatus 1 is operated using a GUI (Graphical User Interface) or the like, predetermined information can be input by clicking a button or icon displayed on the display device with a mouse.
[0040]
The output device 38 includes an output device such as a display device or a printing device.
The display device is a device for presenting information formed on, for example, a CRT (Cathode Ray Tube) display, a liquid crystal display, a plasma display, or the like on a screen.
The display device can display the input result of the keyboard and mouse, the input document 14, the generated presentation material 18, and the like.
[0041]
The printing apparatus is an apparatus that prints the generated presentation material 18, the input document 14, and the like on a print medium such as paper in the form of text. The printing apparatus includes various printer apparatuses such as an ink jet printer, a laser printer, a thermal transfer printer, and a dot printer.
[0042]
The communication control device 42 is a device for connecting the presentation material generating device 1 to a server device or the like via a line (not shown), and is constituted by a modem, a terminal adapter, and other devices.
[0043]
The communication control device 42 is connected to, for example, the Internet or a LAN (Local Area Network), and acquires the input document 14 by communication from other terminal devices or server devices connected to these networks, or these devices. For example, the presentation material 18 can be transmitted.
[0044]
The communication control device 42 is controlled by the CPU 28 and performs transmission and reception of signals and data with these terminal devices and server devices according to a predetermined protocol such as TCP / IP.
[0045]
The storage device 48 includes a readable / writable storage medium and a drive device for reading / writing programs and data from / to the storage medium. A hard disk is mainly used as the storage medium, but it can also be configured by other readable / writable storage media such as a magneto-optical disk, a magnetic disk, and a semiconductor memory.
[0046]
The storage device 48 stores a presentation material generation program 50, other programs 52, an analysis dictionary 54, other data 60, and the like.
The presentation material generation program 50 is a program for causing the CPU 28 to exhibit the presentation material generation function, and is composed of modules described later.
[0047]
The other programs 52 are, for example, communication programs that control the communication control device 42 and maintain communication with the terminal device or server device connected to the presentation material generating device 1 via a network, and presentations such as memory management and input / output management. An OS (Operating System) that is basic software for operating the material generation apparatus 1 is configured.
[0048]
The analysis dictionary 54 stores a morpheme analysis dictionary, a syntax analysis dictionary, and the like that are used when the CPU 28 performs morphological analysis, syntax analysis, and the like. In addition, a key word dictionary storing key words used when the key sentence determination unit 6 determines key sentences is also stored.
[0049]
The CPU 28 can read / write programs and data from / to the storage device 48 by driving the drive device of the storage device 48.
Alternatively, the input document 14 may be stored in the other data 60, and the storage device 48 may be driven so that the CPU 28 reads and acquires the input document 14. Thus, the storage device 48 can be used as a means for acquiring the input document 14.
[0050]
The storage medium driving device 46 is a driving device for reading and writing data by driving a removable storage medium. Examples of the removable storage medium include a magneto-optical disk, a magnetic disk, a magnetic tape, a semiconductor memory, a paper tape punched with data, and a CD-ROM. Note that the CD-ROM can only be read.
[0051]
The presentation material generation apparatus 1 acquires the input document 14 from the storage medium in which the input document 14 is recorded by driving the storage medium by the storage medium driving device 46 or the generated presentation material 18 as the storage medium driving device. Can be output. Thus, the storage medium driving device 46 can be used as an input document acquisition unit.
[0052]
The input / output interface 44 is constituted by, for example, a serial interface or another standard interface. By connecting an external device corresponding to the interface to the input / output interface 44, the function of the presentation material generating apparatus 1 can be expanded. Examples of such external devices include a storage device such as a hard disk, a speaker, and a microphone.
[0053]
FIG. 2B is a diagram showing modules constituting the presentation material generation program 50.
The presentation material generation program 50 includes programs such as a document structure analysis module 62, a morphological analysis module 64, an important sentence determination module 66, a syntax analysis module 68, a concise expression generation module 70, and a document structure generation module 72.
When the CPU 28 loads and executes each module of the presentation material generation program 50, the PC can exhibit a function as a presentation material generation device.
[0054]
When the CPU 28 executes the document structure analysis module 62, the document structure analysis unit 2 (FIG. 1) is realized.
Similarly, the CPU 28 loads and executes the morpheme analysis module 64, the important sentence determination module 66, the syntax analysis module 68, the concise expression generation module 70, and the document structure generation module 72. The sentence determination unit 6, the syntax analysis unit 8, the concise expression generation unit 10, and the document structure generation unit 12 can be configured.
[0055]
That is, the presentation material generation apparatus 1 of FIG. 1 is realized by software by the presentation material generation program 50 being executed by the CPU 28.
[0056]
The presentation material generation program 50 includes an input parameter acquisition module (not shown).
The CPU 28 displays a parameter input screen on the display device by the input parameter acquisition module. The user can input the maximum number of sentences, the presence / absence of chart priority, the type of template, the type of sentence ending expression, and the like from a parameter input screen using a keyboard or a mouse.
[0057]
An editing module for editing the generated presentation material 18 may be added to the presentation material generation program 50 so that the user can edit the generated presentation material 18. As this editing function, for example, the following functions can be considered.
[0058]
As a function of the editing module, the size of the chart can be adjusted. In this case, the CPU 28 displays the generated presentation material 18 on the display device. Using the mouse, the user moves the pointer to the end of the chart on the displayed presentation material 18 to hold down the mouse button and drags it. Then, the CPU 28 enlarges / reduces the chart in accordance with the movement of the pointer. When the user releases the mouse button when the chart becomes an appropriate size, the CPU 28 fixes the chart to the size at this time.
[0059]
As a function of the editing module, the position of a chart or character string can be moved. In this case, the user operates the mouse to place a pointer around the center of the chart or character string and drags it. Then, the CPU 28 moves the position of the chart or character string together with the movement of the pointer. When the user releases the mouse button at an appropriate position, the CPU 28 fixes the chart or character string at that position.
[0060]
As a function of the editing module, the font, size, and color of characters can be changed. The user can specify a specific character or character string on the presentation material 18 using a mouse or a keyboard, and can specify the font, size, color, and the like of the specified character or character string. Then, the CPU 28 changes the designated character or character string to the font, size, and color designated by the user.
Furthermore, the predetermined character or character string can be emphasized by making the character or character string italicized or underlining the predetermined character or character string.
[0061]
Charts and character strings can be added as functions of the editing module. When adding a chart, a bitmap or other chart is prepared in advance on a storage medium that can be driven by the storage device 48 or the storage medium driving device 46. The user designates a specific position of the presentation material 18 displayed on the display device, and designates a chart to be added to the position. Then, the CPU 28 pastes the chart at a position designated by the user.
[0062]
When adding a character string, the user can designate a specific location on the presentation material 18 displayed on the display device, and can input a desired character string from the keyboard at that position. Then, the CPU 28 inserts the character string input by the user at the designated location.
In addition, characters and diagrams on the presentation material 18 can be deleted by a predetermined operation. In this case, the CPU 28 deletes the character or chart designated by the user from the slide.
[0063]
As described above, in the present embodiment, the presentation material generation apparatus 1 is realized by using a PC as an example. However, the present invention is not limited to this. For example, a word processor can be provided with a presentation material generation function.
It is also possible to provide a presentation material generation service to a user via a network by mounting a presentation material generation program on the server device.
In this case, the input document 14 is acquired from the terminal device, the presentation material 18 is generated by the server device, and then returned to the terminal device.
[0064]
It is possible to distribute a storage medium such as a CD-ROM in which the presentation material generation program 50 is stored, and the user can install the presentation material generation program 50 in his / her own PC, or the presentation material generation program 50 in the word processor program. It is also possible to incorporate and distribute this.
[0065]
FIG. 3 is a flowchart for explaining the operation of the presentation material generating apparatus 1.
First, the CPU 28 acquires the input document 14 (step 10). The input document 14 is stored in advance in the storage device 48, stored in the storage medium, read from the storage medium driving device 46, or acquired via the network via the communication control device 42.
The input document 14 is data such as a dissertation or a plan book from which presentation materials are generated, and may include a chart in addition to text.
[0066]
Next, the CPU 28 acquires the input parameter 16 (step 15). The CPU 28 can acquire the input parameter from the value input by the user from the parameter input screen displayed on the display device. This input parameter acquisition function is realized by an input parameter acquisition module.
[0067]
Next, the CPU 28 analyzes the document structure of the input document 14 (step 17). By this analysis, document structures such as chapters, sections, bullets, charts, titles, etc. are determined, and so-called solid texts to be subjected to morphological analysis are extracted. This document structure analysis function is realized by the document structure analysis module 62.
[0068]
Next, the CPU 28 performs a morphological analysis on the written text extracted from the input document 14 (step 20). The CPU 28 generates a morpheme string as a result of the morpheme analysis. This morpheme analysis function is realized by the morpheme analysis module 64.
Next, the CPU 28 parses the solid written sentence of the input document 14 using the morpheme string (step 25). In this parsing, a material for determining a sentence for extracting an important sentence is examined. For example, an important word (such as “In short”) that is a clue to an important sentence is recognized by the syntax analysis. This parsing function is realized by the parsing module 68.
[0069]
Next, the CPU 28 estimates an important sentence to be extracted based on the clue obtained by the syntax analysis (step 30). This estimation function is realized by the parsing module 68.
Next, the CPU 28 determines from the input parameter 16 whether what is extracted from the input document 14 is a sentence, a sentence and a chart, or a chart (step 35). This determination function is realized by the important sentence determination module 66.
[0070]
If what is to be extracted is a sentence (step 35; extract sentence), the CPU 28 extracts the sentence estimated as the important sentence in step 30 from the input document 14 (step 40).
If what is to be extracted is a sentence and a chart (step 35; extract sentence and chart), the CPU 28 extracts the sentence and chart estimated as an important sentence in step 30 from the input document 14 (step 45).
[0071]
When what is to be extracted is a chart (step 35; extract chart), the CPU 28 extracts a chart from the input document 14 (step 50).
The extraction functions of steps 40, 45, and 50 are realized by the important sentence determination module 66.
[0072]
Next, the CPU 28 parses the important sentence extracted in Step 40 or Step 45, and performs dependency analysis and estimation of a erasable area (connective, adverb, union modification clause, etc.) (Step 55). This parsing function is realized by the parsing module 68.
[0073]
Next, the CPU 28 deletes the estimated erasable area from the important sentence whose syntax analysis is completed in step 55, converts the sentence end of the important sentence to the sentence end expression specified by the input parameter 16, etc. Thus, a simple sentence is generated (step 60). This concise sentence generation function is realized by the concise expression generation module 60.
[0074]
Next, the CPU 28 generates the presentation material 18 by putting the generated simple sentence and chart into the template set by the input parameter 16 (step 65). This presentation material generation function is realized by the document structure generation module 72.
[0075]
The presentation material 18 is output as a file in a predetermined format and stored in, for example, a storage medium attached to the storage device 48 or the storage medium driving device 46.
[0076]
In the above embodiment, the following effects can be obtained.
By specifying the input parameter 16, various presentation materials can be easily created.
[0077]
For example, it is possible to set a presentation material in which sentences and diagrams are mixed, and a specific style such as a key / tone / title key.
This makes it possible to create diagram-centric presentation materials and document-centric presentation materials. can do.
[0078]
In addition, according to the present embodiment, it is possible to automatically generate a concise expression from a solid-written (no document structure) document.
Furthermore, since it can be applied to a short document that is easy to be written in solid, it is possible to generate a presentation material from a plurality of documents. For this reason, presentation materials can be created based on daily business reports, etc., or market analysis materials can be generated based on Web information.
[0079]
By inputting the presentation material as the input document 14 and generating the presentation material 18, it is possible to unify sentence ending expressions and to provide proofreading support.
[0080]
【The invention's effect】
According to the present invention, it is possible to automatically generate a presentation material by using data as a source of the presentation material as an input.
[Brief description of the drawings]
FIG. 1 is a diagram conceptually showing the configuration of a presentation material generating apparatus according to the present embodiment.
FIG. 2A is a configuration diagram when a presentation material generating apparatus is configured using a PC, and FIG. 2B is a diagram showing modules that constitute a presentation material generating program.
FIG. 3 is a flowchart for explaining the operation of the presentation material generating apparatus.
[Explanation of symbols]
1 Presentation material generator
2 Document structure analysis department
4 Morphological analyzer
6 important sentence judgment part
8 Parsing section
10 Concise expression generator
12 Document structure generator
14 Input documents
16 Input parameters
18 Presentation materials
26 Control unit
28 CPU
30 ROM
32 RAM
34 Input device
38 Output device
40 Printing device
42 Communication control device
43 Bus line
44 I / O interface
46 Storage Medium Drive Device
48 storage devices
50 Presentation material generation program
52 Other programs
54 Analysis Dictionary
60 Other data
62 Document structure analysis module
64 Morphological analysis module
66 Important sentence determination module
68 Parsing module
70 Concise Expression Generation Module
72 Document structure generation module

Claims (4)

Receiving means for receiving the number of divisions for dividing the document, the maximum number of sentences to be extracted, the sentence end expression, and the layout;
A document acquisition means for acquiring a document;
A determination means for analyzing the document structure of the acquired document and determining an area of a solid written sentence;
A morphological analysis and syntactic analysis of the determined solid writing, and using the result of the analysis and a predetermined clue word, an certifying means for certifying an important sentence from the solid writing,
A dividing unit that divides the document into the accepted number of divisions based on an analysis result by the determining unit;
Extraction means for extracting the recognized important sentence according to the importance within the accepted maximum number of sentences from each of the divided parts;
Concise sentence generating means for simplifying the extracted important sentence and generating a concise sentence in which the sentence ending expression of the simplified concise sentence becomes the accepted sentence ending expression;
Output means for outputting the generated concise sentence in the accepted layout,
The output means outputs only the generated concise sentence when the accepted layout is a sentence only, and outputs a chart matching the concise sentence and the concise sentence when the sentence and the chart are mixed. In the case of only the presentation material generating apparatus, only the chart matching the concise sentence is output. Simple and detailed reception means for receiving selection of whether to generate simple presentation materials or to generate detailed presentation materials,
  2. The presentation according to claim 1, wherein the extracting unit increases or decreases the number of important sentences to be extracted within the range of the maximum number of sentences based on the selection received by the simplified / detail receiving unit. Material generator. In a computer comprising a receiving means, a document obtaining means, a judging means, an authorizing means, a dividing means, an extracting means, a concise sentence generating means, and an output means,
  A reception step of receiving the number of divisions for dividing the document, the maximum number of sentences to be extracted, the sentence end expression, and the layout in the reception unit;
  A document acquisition step of acquiring a document by the document acquisition means;
  A determination step of analyzing a document structure of the acquired document and determining an area of a solid written sentence by the determination unit;
  The certifying means performs morphological analysis and syntactic analysis on the determined solid sentence, and uses the analysis result and a predetermined clue word to certify an important sentence from the solid sentence,
  A dividing step of dividing the document into the accepted number of divisions based on the analysis result by the determination unit;
  An extraction step of extracting the recognized important sentence according to the importance within the accepted maximum number of sentences from the divided parts by the extracting means;
  A concise sentence generation step of simplifying the extracted important sentence and generating a concise sentence in which the sentence ending expression of the simplified concise sentence becomes the accepted sentence ending expression in the concise sentence generating means;
  An output step for outputting the generated concise sentence in the accepted layout by the output means; and
  In the output step, when the accepted layout is a sentence only, only the generated concise sentence is output, and in the case of a mixture of a sentence and a chart, the concise sentence and a chart matching the concise sentence are output, In the case of only the presentation material, the presentation material generating method is characterized in that only the chart matching the concise sentence is output. A reception function that accepts the number of divisions to divide a document, the maximum number of sentences to be extracted, sentence end expressions, and layout settings;
  A document acquisition function for acquiring a document;
  A determination function for analyzing the document structure of the acquired document and determining an area of a solid written sentence;
  The determined solid sentence is subjected to morphological analysis and syntactic analysis, and the result of the analysis and a predetermined Using a clue word, an authorization function that authorizes important sentences from the written text,
  A division function for dividing the document into the accepted number of divisions based on the analysis result by the analysis function;
  From each of the divided parts, an extraction function that extracts the recognized important sentence according to the importance within the maximum number of accepted sentences;
  A concise sentence generation function for simplifying the extracted important sentence and generating a concise sentence in which the ending sentence expression of the simplified concise sentence becomes the accepted sentence ending expression;
  An output function for outputting the generated concise sentence in the accepted layout, and a presentation material generation program that realizes on a computer,
  The output function outputs only the generated concise sentence when the accepted layout is a sentence only, and outputs a chart matching the concise sentence and the concise sentence when the sentence and the chart are mixed. In the case of only, a presentation material generating program characterized in that only a chart matching the concise sentence is output.

Images