JP2021120790A - Sentence structure drawing device - Google Patents

Abstract

To provide an interface technology for making a comparatively difficult-to-read sentence such as a patent application document intelligible.SOLUTION: A sentence structure drawing device includes means for acquiring a sentence, means for performing syntax analysis for the acquired sentence, and means for displaying the result of the syntax analysis on a display in a tree structure form with a word, a phrase, or a clause as a node.SELECTED DRAWING: Figure 1

Description

The present invention relates to a sentence structure drawing apparatus.

A patent application basically consists of a specification, claims, a summary, and drawings, although there are some differences depending on the country. In general, the claims (also referred to as claims) of a patent application have been prepared by a patent attorney or by a person in the intellectual property department of a company.

In recent years, the term "artificial intelligence (AI)" has come to be often seen (see, for example, Non-Patent Document 1). In fact, AI has evolved significantly, and some, like the human brain, have a cognitive function that recognizes many images and sounds and finds specific patterns. For example, Google has succeeded in getting a computer to discriminate images of cats. As the performance of AI improves in this way, its application range is expanding.

http://www.nri.com/jp/journal/2016/10/161031_4/, Searched April 10, 2018

In general, patent application documents such as claims and specifications have a unique writing style, and therefore it takes time for a general person who is not an expert to read the patent application documents. The patent application documents generated by AI are the same as long as they are learned from past patent application documents.

The present invention has been made in view of these problems, and an object of the present invention is to provide a user interface technique for making relatively difficult-to-read sentences such as patent application documents easy to understand.

One aspect of the present invention relates to a sentence structure drawing apparatus. This sentence structure drawing device displays a means for acquiring a sentence, a means for parsing the acquired sentence, and the result of the parsing on a display in the form of a tree structure in which a word, phrase or clause is one node. It is provided with a means for causing it.

It should be noted that any combination of the above components and those in which the components and expressions of the present invention are mutually replaced between devices, methods, systems, computer programs, recording media storing computer programs, etc. are also the present invention. It is effective as an aspect of.

According to the present invention, it is possible to provide a user interface technique for making relatively difficult-to-read sentences such as patent application documents easy to understand.

It is a schematic diagram which shows the transition of the screen realized by the creation server which concerns on embodiment. It is a schematic diagram which shows the structure of the patent application document preparation support system which concerns on embodiment. It is a hardware configuration diagram of the creation server of FIG. It is a block diagram which shows the function and configuration of the creation server of FIG. It is a data structure diagram which shows an example of the patent information holding part of FIG. It is a flowchart which shows the flow of a series of processing in the creation server of FIG. It is a representative screen diagram of the syntax illustration screen displayed on the display of the user terminal. It is a representative screen diagram of the syntax illustration screen obtained by pressing the "1" button of the layer display level adjustment unit. It is a representative screen diagram of the syntax illustration screen obtained by pressing the "2" button of the layer display level adjustment unit. It is a representative screen view of the syntax illustration screen obtained by pressing the expansion button of a predetermined node in the state that the first layer of FIG. 8 is displayed. It is a representative screen diagram of the syntax illustration screen obtained by pushing down the anaphora relation display switching unit. It is a representative screen diagram of the syntax illustration screen obtained by selecting a different direction in the direction designation area. It is a representative screen diagram of the syntax illustration screen in the state where the syntax tree is modified in the syntax tree drawing area. It is a representative screen diagram of the syntax illustration screen including the syntax tree drawing area which displays the syntax tree modified by drag and drop in FIG. 13. It is a representative screen diagram of the syntax illustration screen in the state where the syntax tree is modified in the syntax tree drawing area. FIG. 5 is a representative screen view of a syntax illustration screen including a syntax tree drawing area for displaying a syntax tree modified by drag and drop in FIG. It is a representative screen diagram of the syntax illustration screen in the state where the edit button of the node to be edited is about to be pressed down. It is a representative screen diagram of the syntax illustration screen obtained by pressing the edit button. It is a representative screen diagram of the syntax illustration screen obtained by pressing the apply button. It is a representative screen diagram of the syntax illustration screen obtained by pressing the modified claim generation button.

Hereinafter, the same or equivalent components, members, and processes shown in the drawings shall be designated by the same reference numerals, and redundant description will be omitted as appropriate. In addition, some of the members that are not important for explanation are omitted in each drawing.

FIG. 1 is a schematic diagram showing screen transitions realized by the creation server according to the embodiment. As the user of the creation server, for example, a person in the intellectual property department of a company is assumed. The user uploads a technical document such as an invention proposal submitted by the research and development department to the creation server, and the creation server uses the uploaded technical document as the first edition of the claims and the specification, abstract, and drawings ( The first edition of (hereinafter referred to as the specification, etc.) is automatically generated.

First, the creation server causes the display 100 of the user's terminal to display the upload screen 102 that accepts the upload of the electronic file. The user can upload technical documents such as invention proposals, still images such as technical drawings and other photographs, and various electronic files such as moving images (hereinafter referred to as documents) through the upload screen 102. The user can upload the electronic file by dragging the desired electronic file and dropping it in the dotted line area of the upload screen 102. Alternatively, the user can refer to and upload a document or the like in the user's terminal by clicking the dotted line area in the upload screen 102.

When the user uploads a document or the like, the creation server acquires the input document or the like. The creation server implements a patent application document generation AI engine that is generated and updated by letting AI learn information on past patent applications. The creation server automatically generates the first edition of the claims and the first edition of the specification, etc. corresponding to the contents of the input documents, etc. by processing the input documents, etc. with this patent application document generation AI engine. do. The creation server causes the display 100 to display a generation result display screen 116 that displays the first edition of the generated claims. On the generation result display screen 116, the first edition of the generated claims is displayed in text, and the OK button 118 and the correction button 120 are displayed.

When the user is satisfied with the first edition of the generated claims, the user clicks the OK button 118. When the OK button 118 is clicked, the generation server causes the display 100 to display a screen (not shown) for presenting the first edition of the specification or the like to the user. The user clicks the modification button 120 if he / she wishes to modify the first edition of the generated claims. When the modification button 120 is clicked, the creation server causes the display 100 to display a syntax illustration screen 122 for accepting modification of the claims by the user.

On the syntax illustration screen 122, a syntax tree 104 drawn according to a predetermined description rule is displayed using the text of the claim included in the first edition of the claims as input information. The node 106 of the displayed syntax tree 104 is configured so that it can be added / edited / deleted on the graph. The user makes the desired modification to the displayed syntax tree 104. For example, if there is an unnecessary configuration requirement, the node 106 corresponding to the configuration requirement is specified and deleted. By returning the syntax tree 104 modified in this way to the text, the scope of claims (claims) is modified.

When the user clicks the reflect button 124 after making the desired modification to the syntax tree 104, the creation server causes the display 100 to display the modification result display screen 126 displaying the scope of claims reflecting the modification.

In this way, according to the patent application document creation support service provided by the creation server, since the patent application document generation AI engine is used, it is possible to reduce or eliminate the personal element when creating the patent application document, and the quality can be reduced. Uniformity can be achieved. In addition, the time required to prepare the patent application documents can be reduced. Further, since the graphical modification work using the drawn syntax tree becomes possible, the user convenience is improved.

FIG. 2 is a schematic diagram showing the configuration of the patent application document preparation support system 2 according to the embodiment. The patent application document creation support system 2 includes a creation server 4 and a user terminal 8. The creation server 4 and the user terminal 8 are communicably connected to each other via a network 6 such as the Internet. The creation server 4 includes a patent information holding unit 42 that holds information on past patent applications, and implements a patent application document generation AI engine as described above. The user terminal 8 is a terminal used by the user, and may be, for example, a desktop PC, a laptop PC, a mobile terminal, or the like.

In the present embodiment, the user inputs information to the user terminal 8, the user terminal 8 transmits the information to the creation server 4 via the network 6, the creation server 4 processes the information, and the processing result is networked. It is assumed that a so-called ASP (Application Service Provider) is returned to the user terminal 8 via 6 and the user terminal 8 displays the processing result. However, the technical idea of the present embodiment is to implement a patent application document generation AI engine on a stand-alone terminal, and when a user inputs information to the terminal and obtains a processing result, the system other than ASP can also be used. Applicable.

FIG. 3 is a hardware configuration diagram of the creation server 4 of FIG. The user terminal 8 may have a hardware configuration similar to the hardware configuration shown in FIG. The creation server 4 includes a memory 130, a processor 132, a communication interface 134, a display 136, and an input interface 138. Each of these elements is connected to bus 140 and communicates with each other via bus 140.

The memory 130 is a storage area for storing data and programs. The data or program may be permanently stored in the memory 130 or may be temporarily stored. In particular, the memory 130 has an area allocated as the patent information holding unit 42. The processor 132 realizes various functions in the creation server 4 by executing the program stored in the memory 130. The communication interface 134 is an interface for transmitting / receiving data to / from the outside of the creation server 4. For example, the communication interface 134 includes an interface for accessing the network 6. The display 136 is a device for displaying various information, such as a liquid crystal display or an organic EL (Electroluminescence) display. The input interface 138 is a device for receiving input from the user. The input interface 138 includes, for example, a mouse, a keyboard, or a touch panel provided on the display 138.

FIG. 4 is a block diagram showing the functions and configurations of the creation server 4 of FIG. Each block shown here can be realized by elements such as the CPU of a computer or a mechanical device in terms of hardware, and can be realized by a computer program or the like in terms of software, but here, it is realized by cooperation between them. It depicts a functional block to be done. Therefore, it will be understood by those skilled in the art who have referred to this specification that these functional blocks can be realized in various forms by combining hardware and software.

The creation server 4 includes a patent information holding unit 42, a learning unit 402, a document acquisition unit 404, a patent application document generation AI engine 406, a parsing unit 408, a display control unit 410, and a modification reception unit 403. , And a modified claim generation unit 405.

FIG. 5 is a data structure diagram showing an example of the patent information holding unit 42. The patent information holding unit 42 holds information on past patent applications. The patent information holding unit 42 is attached to the patent application, the patent ID that identifies the patent application, the application number of the patent application, the first IPC attached to the patent application, the patent strength value of the patent application, and the patent application. The examiner's free word, the free keyword attached to the patent application, the scope of the patent claim of the patent application, the subject of the patent application, the document cited at the time of examination of the patent application, and the said. A specification of a patent application (not shown), a drawing of the patent application (not shown), and a document or the like of the patent application (not shown) are held in association with each other. Documents of patent applications and the like may be registered only when they are available, such as documents related to invention proposals of the company's prior application.

The patent strength value is one of the indicators of the quality of a patent application. The patent strength value may be, for example, a TS (Technology Size) value provided by NRI Cyber Patent Co., Ltd. Alternatively, other indicators may be used.

The free keyword is a keyword set by a person reading the target patent application, and may be a keyword extracted by the person as a point of the target patent application. The free keyword may be, for example, a PATORIS keyword provided by NRI Cyber Patent Co., Ltd.

Returning to FIG. 4, the learning unit 402 generates a patent application document generation model by mechanically learning the information held in the patent information holding unit 42. At that time, the learning unit 402 may not refer to the information of the past patent application held in the patent information holding unit 42 but not the information of the past patent application that does not meet the predetermined quality-related criteria. The generation of the patent application document generation model in the learning unit 402 may be realized by using known techniques related to machine learning and artificial intelligence.

The learning unit 402 may specify a patent application whose patent strength value is equal to or higher than a threshold value among the patent applications held in the patent information holding unit 42. In other words, the learning unit 402 may exclude patent applications whose patent strength value is less than the threshold value from the learning target. In the present embodiment, the magnitude relationship with the threshold value is used as a predetermined criterion for quality, but the present invention is not limited to this, and for example, a range of patent strength values may be used instead of the threshold value.

The patent application document generation model is a model in which documents and the like are input and the claims and specifications and the like are output as a result of processing. The learning unit 402 sets the generated patent application document generation model in the patent application document generation AI engine 406.

The document acquisition unit 404 generates screen information for displaying the upload screen 102 and transmits it to the user terminal 8 via the network 6. The document acquisition unit 404 receives the document or the like uploaded by the user via the upload screen 102 displayed on the display 100 of the user terminal 8 from the user terminal 8 via the network 6. The document acquisition unit 404 may accept input of a keyword or text by the user in addition to or instead of uploading the document or the like.

The patent application document generation AI engine 406 applies a document or the like received from the user terminal 8 by the document or the like acquisition unit 404 to the patent application document generation model generated by the learning unit 402. The patent application document generation AI engine 406 acquires the claims, specifications, etc. output by the patent application document generation model.

The parsing unit 408 parses the claims of the claims acquired by the patent application document generation AI engine 406. The parsing in the parsing unit 408 may be realized by a known parsing technique.

The display control unit 410 displays the result of the parsing in the parsing unit 408 on the display 100 of the user terminal 8 in the form of a tree structure in which a word, a phrase, or a clause is one node. A node represents a word or phrase or clause, a meaningful chunk. "Word" includes artificial words and compound words. A "phrase" contains a noun phrase required to form a sentence with a verb. "Section" contains a larger knot, including verbs. When parsing involves morphological analysis, a word or phrase or clause contains a word. The display control unit 410 generates a syntactic illustration screen (described later) that displays the result of the syntactic analysis in a tree structure format, that is, a syntactic tree, and transmits the information of the syntactic illustration screen to the user terminal 8 via the network 6. The user terminal 8 causes the display 100 to display a syntax illustration screen based on the received information.

The correction receiving unit 403 receives the correction for the syntax tree displayed on the display 100 of the user terminal 8 from the user terminal 8 via the network 6. The user terminal 8 receives from the user a modification to the syntax tree displayed on the display 100. The user terminal 8 transmits the received modification contents to the creation server 4 via the network 6. The correction reception unit 403 receives the content of the correction so transmitted.

The modified claim generator 405 generates modified claims corresponding to the modified syntax tree. The modified claim generation unit 405 generates a claim corresponding to the modified syntax tree received by the modified receiving unit 403, and transmits the generated modified claim to the user terminal 8 via the network 6.

The operation of the creation server 4 with the above configuration will be described.
FIG. 6 is a flowchart showing a series of processing flows in the creation server 4 of FIG. The creation server 4 receives documents and the like from the user terminal 8 via the network 6 (S602). The creation server 4 generates the first edition of the patent application document by inputting the received document or the like into the patent application document generation model (S604). By communicating with the user terminal 8 via the network 6, the creation server 4 draws claims in the claims of the first edition of the patent application documents on the display 100 of the user terminal 8 with a syntax tree (S606). The creation server 4 receives a modification to the drawn syntax tree from the user by communicating with the user terminal 8 via the network 6 (S608). The creation server 4 modifies the claim based on the modified syntax tree (S610). The creation server 4 provides the modified claim to the user by communicating with the user terminal 8 via the network 6 (S612).

FIG. 7 is a representative screen view of the syntax illustration screen 122 displayed on the display 100 of the user terminal 8. The syntax illustration screen 122 has a claim original text input area 702, a button 704 to be a syntax tree, a direction designation area 706, a toolbar 708, a claim correction version display area 710, and a syntax tree drawing area 712.

Claims of the claims acquired by the patent application document generation AI engine 406 are input to the claim text input area 702. This input may be automatically performed by the patent application document generation AI engine 406, or may be performed by the user of the user terminal 8 in the form of inputting a desired claim into the claim original text input area 702 by copy and paste or the like. You may.

When the button 704 to make a syntax tree is pressed while the claim is input in the claim original text input area 702, the parsing unit 408 analyzes the input claim, and the display control unit 410 analyzes the result of this parsing. The syntax tree obtained as is drawn in the syntax tree drawing area 712. The syntax tree drawn in the syntax tree drawing area 712 represents a plurality of nodes 732 and the connection relationships between them. Each node 732 has a text box 730 that displays the word or phrase or clause corresponding to the node 732 in it, an expansion button 728 that is embedded and displayed in the upper left of the text box 730, and an upper left of the text box 730. It has an edit button 726 displayed away from the text box 730, a minus button, and a plus button.

The direction designation area 706 is an area for designating the direction of the syntax tree drawn in the syntax tree drawing area 712 in a pull-down format. The details of the direction designation area 706 will be described later.

The toolbar 708 includes an enlargement ratio adjustment unit 714, an undo unit 716, a layer display level adjustment unit 718, an anaphora display switching unit 720, a file output unit 722, and a correction claim generation button 724.

The enlargement ratio adjusting unit 714 makes it possible to adjust the enlargement / reduction ratio of the syntax tree drawn in the syntax tree drawing area 712. The undo section 716 makes it possible to undo the modifications made to the syntax tree drawn in the syntax tree drawing area 712. The layer display level adjusting unit 718 and the anaphora-related display switching unit 720 will be described later. The file output unit 722 is a button for outputting a JSON file for drawing a graph.

When the user modifies the syntax tree drawn in the syntax tree drawing area 712 and presses the modified claim generation button 724, the modified claim generator 405 claims the modified claim text corresponding to the modified syntax tree. It is displayed in the modified version display area 710.

FIG. 8 is a representative screen view of the syntax illustration screen 122 obtained by pressing the “1” button of the layer display level adjustment unit 718. FIG. 9 is a representative screen view of the syntax illustration screen 122 obtained by pressing the “2” button of the layer display level adjustment unit 718. The layer display level adjustment unit 718 makes it possible to control to what level the syntax tree drawing area 712 is displayed or emphasized by using the layer value information obtained from the result of the parsing in the parsing unit 408. .. The definition of the layer in this embodiment is as follows.
Starting value: 0
Layer: Follow the nodes in the opposite direction from the end of the sentence, and make one layer from the node before the verb phrase. The layer value is incremented from that verb phrase to the one before the next verb phrase as the upper layer.

FIG. 10 is a representative screen view of the syntax illustration screen 122 obtained by pressing the expansion button 736 of a predetermined node 734 while the first layer of FIG. 8 is displayed. When the expand button 736 of the node 734 is pressed down, all the nodes 738 that are directly or indirectly connected to the node 734 are released from the previously hidden state and put into the displayed state. This allows the user to easily see all the nodes 738 associated with the specified node 734.

FIG. 11 is a representative screen view of the syntactic illustration screen 122 obtained by pressing down the anaphora-related display switching unit 720. FIG. 11 corresponds to the function of the display control unit 410 that adds a display object corresponding to a predetermined word or phrase or clause to the tree structure displayed in the syntax tree drawing area 712. When the anaphora display switching unit 720 is pushed down, the display control unit 410 refers to a word indicating the relationship between the words in the claim, such as "the above", "the relevant", and "the said", and by such a word, the word indicates the relationship between the words. Identify the two associated nodes. The display control unit 410 displays a display object indicating a relationship, for example, an arrow, between the two specified nodes. The word indicating the relationship between the words in the claim may be registered in the creation server 4 in advance.

In the example of FIG. 11, when the noun node "○○" is present, the display control unit 410 searches for the appearance of "○○" before the appearance position of the node in the sentence, and the corresponding node is found. If there is, they are connected by the red dotted arrow 740.

FIG. 12 is a representative screen view of the syntax illustration screen 122 obtained by selecting different directions in the direction designation area 706. In response to a request from the user, the display control unit 410 creates a new tree structure displayed in the syntax tree drawing area 712 and a new tree structure in which the connection relationship between the nodes is the same but the connection order of the nodes is different. It has a function of displaying in the drawing area 712. FIG. 12 corresponds to this function, and in particular, in the state of FIG. 7, it is displayed when the selection of "Left-Right" (left to right) is stopped and "Right-Left" (right to left) is selected in the direction designation area 706. It is a screen to be displayed. When "Left-Right" (left to right) in FIG. 7 is selected, the syntax tree in the syntax tree drawing area 712 starts from the upper left and follows in order to the right, and if there is a branch, the same hierarchy. Corresponds to the reading order that moves to the upper left node of and follows to the right. When "Right-Left" (from right to left) in FIG. 12 is selected, the reading order of the syntax tree in the syntax tree drawing area 712 is the left and right of the reading order in FIG. 7 reversed.

For example, if English is written together with Japanese in the text box of the node, "Left-Right" (left to right) in Fig. 7 is the Japanese reading, and "Right-Left" (right to left) in Fig. 12 is read. ) Is suitable for reading English, so that the direction designation area 706 can switch between Japanese reading and English reading, which improves user convenience. Alternatively, when switching the connection order of the syntax tree in the direction specification area 706, the language before switching (for example, Japanese) may be switched to the language corresponding to the connection order of the switching destination (for example, English). good. In this sense, the direction designation area 706 may be an area for designating a language. That is, the language may be switched by switching the connection order, and conversely, the connection order may be switched by switching the language.

FIG. 13 is a representative screen view of the syntax illustration screen 122 in a state where the syntax tree is modified in the syntax tree drawing area 712. The user can move the node 742 to be modified by dragging and dropping. FIG. 14 is a representative screen view of the syntax illustration screen 122 including the syntax tree drawing area 712 that displays the syntax tree modified by drag and drop in FIG. 13. The syntax tree has been modified so that the node 742 to be modified relates to the node 744 to which it is dropped.

FIG. 15 is a representative screen view of the syntax illustration screen 122 in a state where the syntax tree is modified in the syntax tree drawing area 712. The user can move the node 746 to be modified by dragging and dropping. FIG. 16 is a representative screen view of the syntax illustration screen 122 including the syntax tree drawing area 712 that displays the syntax tree modified by drag and drop in FIG. The syntax tree has been modified so that the node 746 to be modified relates to the node 748 to which it is dropped.

FIG. 17 is a representative screen view of the syntax illustration screen 122 in a state where the edit button 752 of the node 750 to be edited is about to be pressed down. FIG. 18 is a representative screen view of the syntax illustration screen 122 obtained by pressing the edit button 752. When the edit button 752 is pressed down, the entire syntax illustration screen 122 becomes unselectable, and a dialog 754 for inputting the edited content is displayed at the same time. The dialog 754 is configured so that the name, type, and color of the node 750 to be edited can be edited. The user enters the desired name, type and color in dialog 754 and presses the apply button 756.

FIG. 19 is a representative screen view of the syntax illustration screen 122 obtained by pressing the apply button 756. The modification content input to the dialog 754 of FIG. 18 is reflected in the node 750 to be edited.

FIG. 20 is a representative screen view of the syntax illustration screen 122 obtained by pressing down the modified claim generation button 724. When the correction claim generation button 724 is pressed down in the state of FIG. 19, the correction reception unit 403 acquires the corrected syntax tree displayed in the syntax tree drawing area 712 at the time of pressing down. The modified claim generation unit 405 modifies the claim based on the acquired syntax tree, and displays the modified claim in the claim modified version display area 710.

In the above-described embodiment, examples of the holding unit are a hard disk and a semiconductor memory. Further, based on the description of this specification, each part is provided by a CPU (not shown), an installed application program module, a system program module, a semiconductor memory for temporarily storing the contents of data read from the hard disk, or the like. What can be achieved is understood by those skilled in the art who have referred to this specification.

According to the creation server 4 according to the present embodiment, the scope of claims, which is relatively difficult to read, is graphically presented as a syntax tree instead of the text as it is, thereby improving readability and making it easier for the user to understand. be able to.

Further, in the creation server 4 according to the present embodiment, the user can perform the correction work by an intuitive graphic operation such as drag and drop on the drawn syntax tree. This makes it possible to modify the claims more quickly and accurately.

Further, the creation server 4 according to the present embodiment outputs the corresponding modified claim text by reading the modified syntax tree. Therefore, the user can use the correction result as a sentence.

The configuration and operation of the patent application document preparation support system 2 according to the embodiment have been described above. This embodiment is an example, and it will be understood by those skilled in the art that various modifications are possible for each component and each combination of processes, and that such modifications are also within the scope of the present invention.

In the embodiment, the case where the first edition of the claims is obtained and the parsing is performed has been described. It may be expressed. For example, it is possible to visually grasp the syntax of such sentences by parsing the description of the detailed description of the invention in the specification and the sentences such as contracts, design documents, and articles and drawing them in a tree structure. can. As described above, in the present invention, by visualizing the difficult-to-understand sentence structure, the meaning can be understood even by a non-expert, and the syntax check time can be shortened.

In the embodiment, the case where the first edition of the claims generated by AI is obtained manually or automatically has been described, but the present invention is not limited to this. For example, in a patent information retrieval system such as an NRI cyber patent desk, the claims range of the patent document obtained as a result of the search may be automatically acquired, parsed, and drawn as a syntax tree.

2 Patent application document creation support system, 4 Creation server, 6 Network, 8 User terminal.

Claims (5)

Means to get sentences and
A means of parsing the retrieved text,
A sentence structure drawing device comprising a means for displaying the result of parsing on a display in the form of a tree structure in which a word or phrase or clause is one node. A means of accepting modifications to the displayed tree structure,
The sentence structure drawing apparatus according to claim 1, further comprising means for generating a modified sentence corresponding to the modified tree structure. The sentence structure drawing device according to claim 1 or 2, wherein the sentence includes claims within the scope of claims. The means for displaying the display is a claim for displaying on the display a tree structure displayed on the display and a tree structure having the same connection relationship between the nodes but different connection orders of the nodes, in response to a request from the user. The sentence structure drawing device according to any one of 1 to 3. The sentence structure drawing apparatus according to any one of claims 1 to 4, further comprising means for adding an object corresponding to a predetermined word or phrase or clause to the tree structure displayed on the display.

Images