Information processing apparatus, reading comprehension assistance method, and program product

Abstract

An information processing apparatus includes an analysis section that analyzes text data representing a claim included in patent literature data to determine a constituent element of an invention for each claim included in the claim, and a display control section that divides text representing each claim of the claim into each of the constituent elements and displays on a display device.

Description

Technical Field

[0001] This invention relates to an information processing device, a reading comprehension aid method, and a program product. Background Technology

[0002] Traditionally, techniques have been developed to aid in the reading and understanding of patent documents. In particular, the claims contained in patent documents are often more difficult to understand than those in general documents. Therefore, techniques to aid in the reading and understanding of patent documents, especially the claims, are being researched.

[0003] For example, Patent Document 1 discloses an apparatus that outputs a diagram representing the relationship between an element represented by a string specified in the claims and its subordinate elements. Patent Document 2 discloses an apparatus that divides the claims into paragraphs and generates information structuring the relationships between the divided descriptive segments.

[0004] <Prior art documents>

[0005] <Patent Documents>

[0006] Patent Document 1: Japanese Patent Application Publication No. 2014-219833

[0007] Patent Document 2: Japanese Patent Application Publication No. 2012-003517 Summary of the Invention

[0008] <Problem to be solved by this invention>

[0009] This work involves reading and understanding patent documents for various purposes such as investigation and research. In such work, it is often urgent to read and understand a large number of patent documents, and it is crucial to quickly and accurately understand the claims.

[0010] However, when reading and understanding a large number of patent documents, the technology disclosed in Patent Document 1 or Patent Document 2 cannot be readily grasped in terms of the description of the claims, and lacks the speed of reading and understanding.

[0011] In the invention disclosed in Patent Document 1, the description of the claims is divided into multiple elements according to the set rules. The structural analysis of the description of the claims is performed by extracting the relationship between the divided elements. The specification of the strings contained in the claims is accepted. Information extraction is performed to extract the structural information corresponding to the specified strings from the structural information of the document obtained through structural analysis. The extracted structural information is visualized and output to assist in reading comprehension.

[0012] In the invention disclosed in Patent Document 2, a claim structure information generation device performs structural analysis on patent claims with a deeper structure. This device generates claim structure information representing descriptive segments into which the text of a patent claim is divided and the structure of these descriptive segments. The device includes: a storage unit for storing patent claim information as text; a lexical analysis unit for performing lexical analysis on the patent claim information; a paragraph determination unit for determining the division positions of paragraphs in the patent claim information; and a surface division information storage unit for storing two or more surface division information pieces, each surface division information having surface clue information representing the division of descriptive segments and indicating the relationship between the descriptive segments, and tokens corresponding to the surface clue information; and a command. The system comprises the following components: a token assignment unit, which assigns a token corresponding to the surface clue information in the patent claim information; a paragraph type correspondence information storage unit, which stores two or more paragraph type correspondence information, each having clue information about the word class of the paragraphs that divide the descriptive fragments and a corresponding paragraph division type; a paragraph division type assignment unit, which assigns a corresponding paragraph division type to the paragraphs of the clue information belonging to the word class in the patent claim information; a generation unit, which uses the tokens assigned to the patent claim information and the paragraph division type to generate claim structure information representing the structure of the descriptive fragments of the patent claim information, according to rules for representing the structure of a pre-defined patent claim; and an output unit, which outputs the claim structure information generated by the generation unit.

[0013] As stated above, while the technology disclosed in Patent Document 1 or Patent Document 2 is suitable for the purpose of in-depth reading and understanding of the disclosure of a patent document, it is not specifically designed to improve the readability of the claims. Therefore, it is not suitable for the purpose of reading and understanding the claims quickly and accurately when a large number of patent documents need to be read and understood.

[0014] In view of the above circumstances and in order to solve the above problems, the object of the present invention is to assist in the rapid and accurate reading and understanding of the claims.

[0015] <Methods for solving problems>

[0016] The present invention includes the following solutions.

[0017] [1] An information processing apparatus includes: an analysis unit that analyzes text data representing claims contained in patent document data to determine the constituent elements of an invention for each claim contained in the claims; and a display control unit that segments the text representing each claim of the claims into each of the constituent elements and displays it on a display device.

[0018] [2] According to the information processing apparatus described in [1], the analysis unit further determines important words representing important terms from the text data representing the claims, and the display control unit emphasizes the text representing the important words in the text representing each claim of the claims and displays it on the display device.

[0019] [3] According to the information processing apparatus described in [1] or [2], wherein the analysis unit further analyzes the text data representing the specification contained in the patent document data to further determine new words representing terms used to describe the invention in the specification that are not previously recorded in the claims, and the display control unit emphasizes the text representing the new words in the text representing each claim of the claims and displays it on the display device.

[0020] [4] The information processing apparatus according to any one of [1] to [3] further includes: an operation receiving unit for receiving user input of evaluation results for the patent document data; and an evaluation registration unit for registering the evaluation results in association with the patent document data, wherein the display control unit displays the evaluation results on the display device.

[0021] [5] According to the information processing apparatus described in [4], the display control unit displays the patent document data, which is the object of analysis by the analysis unit, and the evaluation results registered in the evaluation registration unit on a device used by multiple users.

[0022] [6] The information processing apparatus according to any one of [1] to [5], wherein the display control unit charts the segmented constituent elements into a structural diagram and displays it.

[0023] [7] A reading comprehension aid method analyzes the text data representing the claims contained in patent document data to determine the constituent elements of the invention for each claim contained in the claims, and segments and displays the text representing each claim of the claims into each constituent element.

[0024] [8] A program for causing a computer to perform the following steps: analyzing textual data representing claims contained in patent document data to determine the constituent elements of an invention for each claim contained in the claims; and segmenting the text representing each claim of the claims into each of the constituent elements and displaying them on a display device.

[0025] [9] An information processing apparatus includes: an analysis unit that analyzes text data representing claims contained in patent document data to determine the subject matter of an invention for each claim contained in the claims; and a display control unit that displays the text representing the subject matter in association with the number of the claim on a display device.

[0026]

[10] According to the information processing apparatus of [9], the analysis unit further determines the constituent elements of the invention for each claim included in the claims, and the display control unit further segments the text representing each claim of the claims into each of the constituent elements and displays it on the display device.

[0027]

[11] According to the information processing apparatus of [9] or

[10] , the display control unit switches between displaying the text containing the text representing each of the claims and displaying the text without the text according to the user's operation, and displays the text on the display device.

[0028]

[12] The information processing apparatus according to any one of [9] to

[11] further includes: an operation receiving unit for receiving user input of evaluation results for the patent document data; and an evaluation registration unit for registering the evaluation results in association with the patent document data, wherein the display control unit displays the evaluation results on the display device.

[0029]

[13] According to the information processing apparatus described in

[12] , the display control unit displays the patent document data, which is the object of analysis by the analysis unit, and the evaluation results registered in the evaluation registration unit on a device used by multiple users.

[0030]

[14] An information processing apparatus according to any one of [9] to

[13] , wherein the analysis unit selects the text representing the subject matter from the text data representing the claim.

[0031]

[15] The information processing apparatus according to any one of [9] to

[13] , wherein the analysis unit selects from the text data representing the claims a phrase that uniquely characterizes the invention and has a length that facilitates user identification of the invention, and uses it as the text representing the subject matter.

[0032]

[16] A reading comprehension aid method analyzes text data representing claims contained in patent document data to determine the subject matter of the invention for each claim contained in the claims, and displays the text representing the subject matter in association with the claim number on a display device.

[0033]

[17] A program for causing a computer to perform the following steps: analyzing textual data representing claims contained in patent document data to determine the subject matter of the invention for each claim contained in the claims; and displaying the text representing the subject matter in association with the number of the claim on a display device.

[0034]

[18] An information processing apparatus includes: an analysis unit that analyzes text data representing claims contained in patent document data to determine the dependency relationship of claims contained in the claims; and a display control unit that displays text representing independent claims contained in the claims on a display device based on the determined dependency relationship.

[0035]

[19] According to the information processing apparatus of

[18] , the analysis unit further determines the subject matter of the invention for each of the claims included in the claims, and the display control unit further displays text representing the subject matter on the display device in association with the number of the claim.

[0036]

[20] According to the information processing apparatus of

[18] or

[19] , wherein the analysis unit further determines the constituent elements of the invention for each claim contained in the claims, and the display control unit further segments the text representing each claim of the claims into each of the constituent elements and displays it on the display device.

[0037]

[21] According to the information processing apparatus described in

[19] , wherein the analysis unit further determines the constituent elements of the invention for each claim included in the claims, and the display control unit, based on the determined dependent relationship, segments the text representing each claim of the claims into each constituent element and displays it for independent claims, and displays the text representing the subject matter in association with the claim number for dependent claims, and selects either a segmented display form that displays the text representing each claim of the claims segmented into each constituent element, or a segmented display form that does not display the text representing each claim of the claims, and displays it on the display device in the selected display form.

[0038]

[22] The information processing apparatus according to any one of

[18] to

[21] further includes: an operation receiving unit for receiving user input of evaluation results for the patent document data; and an evaluation registration unit for registering the evaluation results in association with the patent document data, wherein the display control unit displays the evaluation results on the display device.

[0039]

[23] According to the information processing apparatus described in

[22] , the display control unit displays the patent document data, which is the object of analysis by the analysis unit, and the evaluation results registered in the evaluation registration unit on a device used by multiple users.

[0040]

[24] The information processing apparatus according to any one of

[18] to

[23] , wherein the analysis unit, in the process of determining the dependency relationship, classifies the claims with unclear dependency relationships as independent claims.

[0041]

[25] A reading comprehension aid method analyzes text data representing claims contained in patent document data to determine the subordinate relationship of claims contained in the claims, and displays text representing independent claims contained in the claims based on the determined subordinate relationship.

[0042]

[26] A program for causing a computer to perform the following steps: analyzing textual data representing claims contained in patent document data to determine the dependency relationship of claims contained in the claims; and displaying text representing independent claims contained in the claims on a display device based on the determined dependency relationship.

[0043] <The Effects of the Invention>

[0044] It can assist in the rapid and accurate reading and understanding of the claims. Attached Figure Description

[0045] Figure 1 This is a diagram illustrating an example of the system configuration of a reading comprehension assistance system according to one embodiment.

[0046] Figure 2 This is a diagram illustrating an example of the hardware configuration of an information processing apparatus according to one embodiment.

[0047] Figure 3 This is a diagram illustrating an example of the function of an information processing apparatus according to one embodiment.

[0048] Figure 4 This is a flowchart illustrating an example of reading comprehension assistance processing of an information processing apparatus according to one embodiment.

[0049] Figure 5 This is an example diagram showing an analysis result screen according to one implementation method.

[0050] Figure 6 This is another example of a screenshot showing the analysis results according to one implementation method.

[0051] Figure 7 This is another example of a screen showing the analysis results according to one implementation method.

[0052] Figure 8 This is another example of a screen showing the analysis results according to one implementation method. Detailed Implementation

[0053] Hereinafter, embodiments of the reading comprehension assistance system according to the present invention will be described with reference to the accompanying drawings.

[0054] Figure 1 This is a diagram illustrating an example of the system configuration of a reading comprehension assistance system according to one embodiment.

[0055] The reading comprehension assistance system 1 is a system that assists in reading and understanding patent documents. Specifically, the reading comprehension assistance system 1 includes an information processing device 10, a patent document extraction device 20, and a terminal device 30. The information processing device 10, the patent document extraction device 20, and the terminal device 30 are interconnected via a network 40 in a manner that enables communication.

[0056] The information processing device 10 analyzes data representing patent documents (hereinafter referred to as patent document data) to generate screen data for display on a screen based on the analysis results. The generated screen data represents a screen that facilitates reading and understanding of the claims contained in the patent document data.

[0057] The patent document extraction device 20 accepts the specified search criteria through user operation via the terminal device 30, and extracts patent document data from databases such as patent gazettes and publications based on the search criteria. Then, the patent document extraction device 20 sends the extracted patent document data to the information processing device 10 through user operation via the terminal device 30.

[0058] The terminal device 30 is a device that accepts user operations to instruct the information processing device 10 or the patent document extraction device 20 to perform various functions, or receives screen data from the information processing device 10 or the patent document extraction device 20 and displays the received screen data.

[0059] Next, the hardware configuration of the information processing device 10 will be described.

[0060] Figure 2 This is a diagram illustrating an example of the hardware configuration of an information processing apparatus according to one embodiment.

[0061] The information processing device 10 includes a CPU (Central Processing Unit) 101, a main storage device 102, an auxiliary storage device 103, an input device 104, a display device 105, a communication interface device 106, and a driver device 107. All of these devices are connected via a bus.

[0062] CPU 101 is the main control unit that controls the operation of the information processing device 10, and implements various functions described later by reading and executing programs stored in the main storage device 102.

[0063] When the information processing device 10 is started, the main storage device 102 reads the program from the auxiliary storage device 103 and stores it. The auxiliary storage device 103 stores the installed program and the files, data, etc. required for the various functions described later.

[0064] Input device 104 is a device for inputting various types of information, such as a keyboard or indicator. Display device 105 is a device for displaying various types of information, such as a monitor. Communication interface device 106 includes a LAN card or the like and is used for connecting to a network.

[0065] The program according to this embodiment is at least a part of various programs that control the information processing device 10. For example, the program is provided by distributing it through the storage medium 108 or downloading it from the network. The storage medium 108 on which the program is recorded can be various types of storage media, such as CD-ROM, floppy disk, magneto-optical disk and other storage media that record information optically, electrically or magnetically, and ROM, flash memory and other semiconductor memory that records information electrically.

[0066] Additionally, when the storage medium 108 containing the program is installed in the drive device 107, the program is installed from the storage medium 108 into the auxiliary storage device 103 via the drive device 107. Programs downloaded from the network are installed into the auxiliary storage device 103 via the communication interface device 106.

[0067] Next, the functions of the information processing device 10 will be explained.

[0068] Figure 3 This is a diagram illustrating an example of the function of an information processing apparatus according to one embodiment.

[0069] The information processing device 10 includes a storage unit 11, a patent document acquisition unit 12, an analysis unit 13, a display control unit 14, an evaluation registration unit 15, and an operation receiving unit 16.

[0070] The storage unit 11 stores various data, programs, etc. Specifically, the storage unit 11 stores the learned model 17.

[0071] The learning completion model 17 is a model constructed using machine learning for analyzing patent documents. The learning completion model 17 can be, for example, a neural network, decision tree, support vector machine, or a model constructed using deep learning. Specifically, the learning completion model 17 is preferably specifically designed for language analysis, and could be, for example, "IBM WATSON (registered trademark)". The "IBM WATSON (registered trademark)" used as the learning completion model 17 can be customized for the analysis of patent documents.

[0072] It should be noted that machine learning is a technique that enables computers to autonomously generate algorithms from learning data in order to efficiently perform specific tasks based on patterns and reasoning. The learning completion model 17 according to this embodiment is a model representing the algorithm thus generated.

[0073] The patent document acquisition unit 12 acquires patent document data. Specifically, the patent document acquisition unit 12 receives patent document data extracted from the patent document extraction device 20. The data sent is data representing a collection of one or more patent documents (hereinafter referred to as collection data). Collection data may be, for example, a file in CSV (Comma-Separated Values) format. It should be noted that collection data is an example of patent document data.

[0074] The analysis unit 13 analyzes the aggregated data. Specifically, the analysis unit 13 applies the algorithm shown in the learning completion model 17 to analyze each patent document contained in the aggregated data.

[0075] The analysis unit 13 determines the constituent elements of the present invention based on the claims contained in various patent documents. Then, the analysis unit 13 divides the description of each claim into each constituent element.

[0076] Here, a constituent element is an element that defines the invention and is necessary to include the object within the scope of the invention. Specifically, in the case of a product invention, a constituent element may be, but is not limited to, components included in the product. For example, the analysis unit 13 may decompose the same components included in the product into multiple constituent elements.

[0077] Typically, to grasp the scope of the invention in each claim, the description of each claim is broken down into its constituent elements for analysis. However, it is known that even with such breakdown, it is difficult to grasp the scope of the invention if the descriptions of the individual constituent elements are too long or too short.

[0078] Therefore, it is desirable to pre-construct the learning completion model 17 using machine learning as an algorithm for decomposing each claim into constituent elements of a length that is easy to read and understand. Then, the analysis unit 13, based on the algorithm specified in the learning completion model 17 thus constructed, takes the text data representing each claim as input and outputs text data that decomposes the description of each claim into constituent elements of a length that is easy to read and understand.

[0079] Furthermore, the analysis unit 13 determines the text representing the subject matter of the invention for each claim. Specifically, the learning completion model 17 is pre-constructed using machine learning as an algorithm to extract the subject matter of the invention from the text data of each claim. Then, the analysis unit 13, based on the algorithm specified in the learning completion model 17 constructed in this manner, takes the text data representing each claim as input and outputs text data representing the subject matter of the invention for each claim.

[0080] Furthermore, the analysis unit 13 classifies each claim into independent claims and dependent claims. Independent claims (hereinafter referred to as independent claims) are claims described independently of other claims, while dependent claims (hereinafter referred to as dependent claims) are claims described by referencing other claims. Specifically, the learning completion model 17 is pre-constructed using machine learning as an algorithm to determine the dependency relationships of claims contained in the claim statement based on textual data representing the claim statement. Then, based on the algorithm specified in the learning completion model 17 constructed in this manner, the analysis unit 13 takes the textual data representing the claim statement as input and outputs data classifying each claim into independent claims and dependent claims. It should be noted that the output data also includes data indicating the numbers of the claims referenced by the dependent claims. When classifying each claim, if the determination result is unclear, it can also be classified as an independent claim.

[0081] The classification of independent claims and dependent claims can be determined using the certainty (also known as confidence, reliability, or probability) of each claim as an independent claim and the certainty of each claim as a dependent claim. In this case, the algorithm specified in Model 17 outputs these certainty values. When the certainty of a claim as an independent claim is above a predetermined value, the analysis unit 13 classifies the claim as an independent claim. Furthermore, when the certainty of a claim as a dependent claim is above a predetermined value, the analysis unit 13 classifies the claim as a dependent claim. Additionally, the analysis unit 13 classifies claims that are neither independent claims nor dependent claims (i.e., claims whose certainty as independent claims is less than a predetermined value and whose certainty as dependent claims is less than a predetermined value) as independent claims.

[0082] In cases where the outcome of the determination of each claim is unclear or the certainty of the output is low, classifying them as independent claims from the perspective of failure protection can prevent users from overlooking independent claims.

[0083] It should be noted that, in order to improve the accuracy of the various analyses described above, the analysis unit 13 may perform rule-based preprocessing before applying the algorithm shown in the learned model 17 to the set data.

[0084] For example, the analysis unit 13 can extract text from the claims contained in various patent documents, which serves as indicators for segmenting each claim. Specifically, the analysis unit 13 can extract text indicating the claim number, text immediately preceding a period, or text such as "characterized in that".

[0085] It should be noted that, based on the format of patent documents, it can be assumed that the term "claim" does not exist in the description of the claims. However, since it is assumed that the description of the claims at least includes text indicating the number of each claim, the preferred analysis unit 13 extracts text as an indicator for segmenting each claim based on the regularity of the text before and after each claim number.

[0086] Furthermore, to improve the accuracy of determining the constituent elements, the analysis unit 13 can extract text such as "the" or "the" from the claims contained in various patent documents as text representing antecedents. In this case, the words following the extracted string are candidates for text representing the constituent elements.

[0087] The analysis unit 13 can extract text such as "possesses", "includes", or "composes of" as text representing the structure, and can further extract text such as "possesses the steps of" or "steps for performing..." as text representing the structure of the steps.

[0088] Analysis unit 13 can extract text such as "here", "therefore" or "to this" as text indicating the relationship between cause and effect.

[0089] In addition, the analysis unit 13 can extract text such as "characterized by" or "wherein" as text that specifically limits the premise among the constituent elements.

[0090] Analysis unit 13 can extract text such as "above", "below", "less than" or "from...to..." as text to limit the part of the recorded content that is a numerical range.

[0091] In addition, to improve the accuracy of classifying each claim as an independent claim or a dependent claim, the analysis unit 13 can extract text such as "further" and "according to..." used in the dependent claims.

[0092] Furthermore, the analysis unit 13 can perform morpheme analysis as preprocessing. For example, the analysis unit 13 segments the description of each claim into morphemes, selects candidate texts representing constituent elements from the segmented morphemes, and counts the number of morphemes contained in each claim or claim statement.

[0093] The analysis unit 13 inputs the results of these preprocessing steps, along with the text of each patent document contained in the set of data, into the learning completion model 17, and obtains the analysis results output from the learning completion model 17.

[0094] It should be noted that, preferably, the analysis unit 13 can perform preprocessing with different content for each language used in the various patent documents. Alternatively, the analysis unit 13 can perform analysis using a learning completion model 17 with different content for each language used in the various patent documents. More preferably, the analysis unit 13 can perform preprocessing with different content for each application (specific national or international application) or use an analysis using a learning completion model 17 with different content. Thus, the analysis unit 13 can perform analysis based on language characteristics or characteristics of the application.

[0095] Specifically, the analysis unit 13 determines the language used based on the descriptions in each patent document. Then, as shown in Table 1, the analysis unit 13 extracts the text for each language corresponding to the above examples.

[0096] [Table 1]

[0097]

[0098] For example, when a patent document is identified as being in English or Chinese, the analysis unit 13 can extract the English or Chinese text shown in Table 1.

[0099] Furthermore, the aggregated data can include text representing the application subject for each patent document. For example, the text representing each patent document may include "US" for the United States, "EP" for Europe, "PCT" for international applications, etc. Therefore, the analysis unit 13 can extract the text representing the application subject from the text representing each patent document and perform different preprocessing for each application subject or use learning completion model 17 with different content for each application subject.

[0100] Furthermore, the learning completion model 17 can include multiple models that differ depending on the content of the analysis. For example, the analysis unit 13 can use each model to determine the constituent elements, determine the text representing the subject matter of the invention, and classify each claim as an independent claim or a dependent claim.

[0101] In order to assist in reading and understanding patent documents, the display control unit 14 displays various screens, which will be described later, on the display device 105 or the terminal device 30 based on the analysis results of the analysis unit 13.

[0102] The evaluation registration unit 15 registers the evaluation results of the patent documents based on the user's operation received by the operation receiving unit 16. The registered evaluation content is displayed on the screen of the display device 105 or the terminal device 30 by the display control unit 14.

[0103] The operation receiving unit 16 receives user operations from the input device 104 or the terminal device 30. Specifically, the operation receiving unit 16 accepts input from various input devices such as keyboards, mice, and touch panels provided with the input device 104 or the terminal device 30.

[0104] Next, the operation of the information processing device 10 will be explained.

[0105] Figure 4 This is a flowchart illustrating an example of reading comprehension assistance processing of an information processing apparatus according to one embodiment.

[0106] In response to a user's operation, the patent document extraction device 20 sends a signal requesting the commencement of reading comprehension assistance processing to the information processing device 10. The information processing device 10, in response to the request signal sent from the patent document extraction device 20, commences reading comprehension assistance processing. The patent document acquisition unit 12 acquires the collection data of patent documents (step S11).

[0107] Specifically, the patent document extraction device 20 accepts the specified search criteria and retrieves patent documents from a patent document database. Then, the patent document extraction device 20 sends one or more retrieved patent documents as a set of data to the information processing device 10. The sent set of data is, for example, data in CSV format.

[0108] Next, the analysis unit 13 analyzes the collected data obtained through reception (step S12). Specifically, the analysis unit 13 analyzes the collected data of patent documents according to the algorithm specified in the learning completion model 17, and outputs the analysis results for each patent document.

[0109] The output analysis results include text data that breaks down the description of each claim into lengthy components that are easy to read and understand, text data that represents the subject matter of the invention in each claim, and data that classifies each claim into independent claims and dependent claims.

[0110] Next, the display control unit 14, based on the user's operation received by the operation receiving unit 16, causes the display device 105 or the terminal device 30 to display the analysis result screen (step S13). The displayed analysis result screen is a screen that assists in reading and understanding the patent document. The specific content displayed will be explained later.

[0111] Next, the evaluation registration unit 15 registers the evaluation results input by the user (step S14). Specifically, the operation receiving unit 16 accepts the user's operation and obtains information representing the evaluation results entered in the evaluation input field included in the analysis results screen. The evaluation registration unit 15 stores the information representing the evaluation results obtained by the operation receiving unit 16 in the storage unit 11.

[0112] It should be noted that the stored information representing the evaluation results is associated with the patent document. When the patent document is displayed, the display control unit 14 displays an analysis result screen that includes the evaluation results associated with the patent document. Additionally, the information processing device 10 can send information representing the registered evaluation results to the patent document retrieval device 20.

[0113] Next, the screen displayed on the display device 105 or the terminal device 30 by the display control unit 14 will be described.

[0114] In response to a user's operation received by the operation receiving unit 16, the display control unit 14 of the information processing device 10 causes the display device 105 or the terminal device 30 to display a collection overview screen. The collection overview screen includes a list of collection data of patent documents obtained by the patent document acquisition unit 12 in step S11 of the reading comprehension assistance processing described above.

[0115] The display bars for each collection of data include, for example, the panel title bar, the panel list, and the memo bar.

[0116] The panel title bar displays, for example, the name of the analysis project that uses collection data as its object.

[0117] The panel list displays, for example, the title of the collection data, the number of bulletins contained in the collection data, the creation date or the most recent modification date, the creator or the most recent modifier, and other attribute information of the collection data in a list format.

[0118] Additionally, the memo bar includes, for example, a GUI (Graphical User Interface) button for displaying a memo editing screen that pops up to accept input of memo text assigned to the collection data, and a display bar for displaying the input memo text.

[0119] The display control unit 14 of the information processing device 10 responds to the user's operation received by the operation receiving unit 16 and causes the display device 105 or the terminal device 30 to display a bulletin list screen.

[0120] The bulletin overview screen includes, for example, a list of bulletins contained in the selected collection data on the collection overview screen. Additionally, the bulletin overview screen includes a bulletin selection area and an analysis button.

[0121] A list of publications may include, for example, the project number, mark, publication number, name, applicant, evaluation, status, and the object of the invention as a project.

[0122] The value of "Project Number" is the bulletin number in the collection data.

[0123] The value of the "tag" for the project is displayed on the analysis results screen described later. This tag is used, for example, to record announcements that the user is interested in.

[0124] The value of the "Gazette Number" is the number of the gazette that publishes each patent document, such as the Patent Gazette or the Publication Gazette.

[0125] The "Name" value is the name of the invention in each patent document.

[0126] The value of the "Applicant" field is the name of the applicant in each patent document.

[0127] The "evaluation" value for the project is the evaluation result recorded on the analysis results screen described later.

[0128] The "status" value of the project represents the examination status of each patent document.

[0129] The value of the item "Object of Invention" is a text representing the subject of the invention determined by the analysis of various patent documents by the analysis department 13.

[0130] The publication selection area is a checkbox for selecting publications. When a user selects a patent document in the publication selection area and presses the analysis button, the display control unit 14 responds to the user's operation received by the operation receiving unit 16 and causes the display device 105 or the terminal device 30 to display an analysis result screen that shows the analysis results of the selected patent document.

[0131] The display of the summary table and the list of publications can also be displayed on multiple display devices 105 or terminal devices 30 used by other users who are licensed to share information. This allows for the sharing and management of evaluation results entered into the evaluation registration department 15 by a team of specific users. Furthermore, by managing the collection of patent documents by a team, the reading and understanding of patent documents can be done in a division of labor, reducing the burden on each user.

[0132] Figure 5 This is an example diagram showing an analysis result screen according to one implementation method.

[0133] The analysis results screen includes a title bar 1021, a navigation display bar 1022, a claims display bar 1023, an evaluation registration bar 1024, a text display bar 1025, and a figures display bar 1026.

[0134] The title bar 1021 includes the name of the collected data and links to the gazette overview screen. Additionally, the title bar 1021 includes the applicant, invention title, status display 1031, and icon center 1032 for the currently selected patent document. The icon center 1032 includes, for example, icons displaying whether there are patent families, a detailed display button, a markup button, a full-text display button, a PDF (Portable Document Format) button, a CSV output button, and a print output button, or buttons indicating whether these are for accepting operations.

[0135] Status display 1031 uses color to indicate whether the patent right of the currently selected patent document is valid. For example, if the patent right is valid, status display 1031 is green to indicate that it is still valid, and if the patent right has expired, status display 1031 is yellow to indicate that it is not valid.

[0136] Specifically, the display control unit 14 determines whether the patent right is valid based on the application date of the patent document, and determines the color of the status display 1031 according to the result of the determination.

[0137] In the display of whether or not there is a patent family, the presence of a so-called patent family can be indicated by color.

[0138] For example, when a patent family exists in the patent literature, the presence or absence of a patent family is displayed in red, indicating the existence of a patent family; when no patent family exists, the presence or absence of a patent family is displayed in gray, indicating the absence of a patent family.

[0139] Specifically, for each patent document in the set of data obtained by the patent document extraction device 20, data indicating whether a patent family exists is included, and the display control unit 14 determines the display color for whether there is a patent family based on the data indicating whether a patent family exists included in the set of data.

[0140] A detailed display button is, for example, a GUI that pops up a screen displaying detailed information about the patent family. Also, for each patent document in the set of data obtained by the patent document extraction device 20, data representing detailed information about the patent family is included.

[0141] The marking button is, for example, a GUI used to accept the operation of setting a mark in the currently selected patent document. When a mark is set, the set mark is displayed in the aforementioned gazette overview screen and the navigation display bar described later.

[0142] The "Full Text Display" button is used to display a pop-up GUI screen containing the description, claims, drawings, abstract, and other information contained in the currently selected patent document.

[0143] The PDF button is a GUI for generating and downloading PDF files containing the description, claims, drawings, abstract, and other information contained in the currently selected patent document.

[0144] The CSV output button is a GUI function used to output the text displayed in the claims display bar 1023 as a CSV format file according to the display format. When the description of each claim, broken down into each constituent element, is obtained as a CSV format file, it can be used as a basis for detailed analysis such as claims table analysis.

[0145] The print output button is a GUI tool used to print the currently displayed claims display bar 1023.

[0146] The navigation display bar 1022 includes a list of publications selected in the publication list screen, and is a display bar for accepting operations of selecting patent documents displayed in the title bar 1021, the claims display bar 1023, the text display bar 1025, the drawing display bar 1026, etc.

[0147] The claim display panel 1023 is a display panel used to read and understand the contents of the claim document based on the analysis results of the analysis unit 13 on the currently selected patent document.

[0148] The claims display bar 1023 includes a full claims button 1033, an independent claims button 1034, a split display format switching button 1038, a folding mark 1039, a claims number display bar 1040, and a constituent element display bar 1041.

[0149] Additionally, the "All Claims" button 1033 and the "Independent Claims" button 1034 are used to display the number of all claims and the number of independent claims, respectively, and to select the currently displayed GUI object from the two display objects: "All Claims" and "Independent Claims". When the display object is "All Claims", all claims, including independent and dependent claims, are displayed; when the display object is "Independent Claims", only independent claims are displayed.

[0150] The split display format switch button 1038 is a GUI that, upon each press, sequentially switches between three split display formats: "Expand All Claims," ​​"Hide All Claims," ​​and "Independent Claims Only," to display the description of the claims as multiple constituent elements. The selected split display format is displayed next to the split display format switch button 1038.

[0151] When the split display mode is set to "Expand All Claims," ​​the elements of all selected claims are displayed. When the split display mode is set to "Hide All Claims," ​​the elements of all selected claims are not displayed. Furthermore, when the split display mode is set to "Independent Claims Only," only the elements of the independent claims selected for display are displayed.

[0152] It should be noted that, Figure 5 This is an example of selecting "All Claims" as the display target and selecting "Expand All Claims" as the segmented display format, as described below. Figure 6 This is another example. Additionally, as discussed later... Figure 7 This is an example of a screen where "All Claims" is selected as the display object and "Independent Claims Only" is selected as the split display format. Figure 8 This is an example of a screen where "All Claims" is selected as the display object and "Hide All Claims" is selected as the split display format.

[0153] Folding symbol 1039 indicates whether the constituent elements of each claim are displayed. It should be noted that, as... Figure 5 As shown, when the split display format is "Expand All Claims", since the constituent elements are displayed for all claims selected as display targets, the fold mark 1039 is a downward arrow indicating the display of the constituent elements.

[0154] The claim number display field 1040 includes the number of each claim, the text indicating the subject matter of the invention in each claim, and the number of the claim referenced in the case of dependent claims.

[0155] The text indicating the subject matter of each claim, the claim numbers referenced by dependent claims, etc., are included in the analysis results of the analysis unit 13. Then, based on the analysis results, the display control unit 14 displays the text indicating the subject matter in association with the claim numbers on the display device 105 or the terminal device 30.

[0156] In the claim number display column 1040, for example, the background color is different in the case of independent claims and the background color is different in the case of dependent claims, so that independent claims and dependent claims can be distinguished at a glance.

[0157] In the constituent element display column 1041, text representing each claim is displayed in separate display columns for each constituent element. The text representing each constituent claim is decomposed into easily readable and comprehensible text by the analysis unit 13 according to the algorithm specified in the learning completion model 17.

[0158] By displaying the claim display bar 1023 when the display object is "all claims" and the split display form is "expand all claims", the user can comprehensively confirm the description of all claims contained in the claim book, and at the same time, can quickly and accurately read and understand the description of each claim.

[0159] The display control unit 14 divides the text representing each claim of the claim into individual constituent elements and displays them on the display device 105 or the terminal device 30. By reading the text divided into individual constituent elements, the user can shorten the time spent searching for the constituent elements and improve the speed of reading comprehension. In addition, since there are fewer cases of incorrect division of constituent elements, the accuracy of reading comprehension is improved.

[0160] The evaluation registration field 1024 displays the evaluation results. Each user can be assigned a preferred option from a pre-defined selection. When the "Evaluation Input Display" link in the evaluation registration field 1024 is selected, the display control unit 14 displays the evaluation input screen on the display device 105 or the terminal device 30. The evaluation input screen will be explained later.

[0161] If the results of user evaluations have already been registered for the currently selected patent document, the registered evaluation results will be displayed in the evaluation registration column 1024.

[0162] A "Text Display" link is displayed in the main text display area 1025. When the "Text Display" link is selected, the display control unit 14 displays the text described in the specification of the currently selected patent document on the display device 105 or the terminal device 30.

[0163] The drawing display panel 1026 displays representative figures and various figures of the currently selected patent document. In addition to the figures in the accompanying drawings, the drawing display panel 1026 may also display tables such as "Table 1", chemical formulas or calculation formulas such as "Formula 1", or chemical structure diagrams such as "Chemical 1".

[0164] Figure 6 This is another example of a screenshot showing the analysis results according to one implementation method.

[0165] like Figure 6As shown, in the claim display bar 1023, the text representing each claim can be further divided into multiple levels. Specifically, in the claim display bar 1023, the text obtained by dividing the text representing each claim is displayed as the constituent element display bar (superior level) 1042, and the text obtained by further dividing the text displayed in the constituent element display bar (superior level) 1042 is displayed as the constituent element display bar (inferior level) 1043.

[0166] The component element display bar (upper level) 1042 and the component element display bar (lower level) 1043 are displayed in relation to each other. The component element display bar (lower level) 1043 is located at the bottom of the screen compared to the component element display bar (upper level) 1042, which is its upper level.

[0167] It should be noted that, although in Figure 6 The example shown is a display of tiers with two or fewer tiers, but it can also include displays of tiers with three or more tiers.

[0168] Furthermore, since all the texts representing each claim can be read without repetition by only reading the un-hierarchical component display bar 1041 and the component display bar (lower level) 1043 which is the lowest level, the component display bar (upper level) 1042 which is the lowest level is less conspicuous compared to the un-hierarchical component display bar 1041 and the component display bar (lower level) 1043 which is the lowest level.

[0169] By displaying the text representing each claim in a multi-level manner, the text structure is easily understood even when the text representing each claim contains descriptions of complex compound sentence structures or long sentence components, thereby achieving fast and accurate reading comprehension.

[0170] It should be noted that the claim display area 1023 is displayed graphically as a structural diagram. For example, the claim number display area 1040 is interconnected with the constituent element display area 1041, the constituent element display area (higher level) 1042, or the constituent element display area (lower level) 1043 by lines. That is, in the claim display area 1023, the relationships between the constituent elements are displayed graphically as a structural diagram.

[0171] The component display panel 1041 represents the component elements as a whole by enclosing them in a frame, thus forming part of the structure diagram.

[0172] Furthermore, by visualizing the text as a structural diagram, the complex structure of the text representing each claim can be visualized. Moreover, by visualizing the text as a structural diagram, it is possible to quickly identify, for example, cases where multiple constituent elements are in the same column at a single level, and cases where the text representing the claims has complex hierarchical relationships at multiple levels or above.

[0173] Figure 7 This is another example of a screen showing the analysis results according to one implementation method.

[0174] Figure 7 Is it pressed? Figure 5 An example of a screen showing the analysis results where the All Claims button 1033 selects "All Claims" as the display object, and the split display format switch button 1038 selects "Independent Claims Only" as the split display format.

[0175] In this split display format, in the case of an independent claim, both the claim number display bar 1040 and the constituent element display bar 1041 are displayed. In the case of a dependent claim, only the claim number display bar 1040 is displayed, and the constituent element display bar 1041 is not displayed.

[0176] The fold mark 1039 displayed next to the claim number display column 1040 in the independent claim is a downward arrow indicating that the constituent elements are displayed. The fold mark 1039 displayed next to the claim number display column 1040 in the dependent claim is a right-pointing arrow indicating that the constituent elements are not displayed.

[0177] When the display format is set to "Independent Claims Only," only the independent claims directly related to the scope of the patent right in the currently selected patent document are displayed as constituent elements. Dependent claims not directly related to the scope of the patent right are not displayed. Therefore, because only essential information is shown on the screen, users can efficiently read and understand the information, enabling them to quickly and accurately grasp the scope of the patent right.

[0178] Figure 8 This is another example of a screen showing the analysis results according to one implementation method.

[0179] Figure 8 Is it pressed? Figure 5 The analysis results screen shown uses the All Claims button 1033 to select "All Claims" as the display object, and the split display format switch button 1038 to select "Hide All Claims" as the split display format. This is an example of a screen.

[0180] In this split display format, only the claim number display bar 1040 is displayed for all claims, and the constituent element display bar 1041 is not displayed.

[0181] The fold mark 1039 displayed next to the claim number display column 1040 of each claim is a right-pointing arrow indicating that no constituent elements are displayed.

[0182] When the split display mode is set to "Hide All Claims," ​​the content of each claim is not shown. Instead, more text describing the subject matter of the invention in each claim is displayed on the screen, making it easy to distinguish between independent and dependent claims. Therefore, users can grasp the entire structure of the claims at a glance. Furthermore, since only the text describing the subject matter of the claims is displayed, users can quickly skip over patent documents that do not require reading and comprehension.

[0183] Furthermore, by reviewing the text representing the subject matter of the invention, it is possible to quickly determine whether a claim requires detailed reading and understanding before reading the description of the claims, thereby improving the speed of reading and understanding the entire patent document.

[0184] Although not shown in the diagram, when pressed... Figure 5 When the independent claim button 1034 on the analysis results screen is used to select "independent claim" as the display target, and the split display format switch button 1038 is pressed to select "hide all claims" as the split display format, in the currently selected patent document, for independent claims, only the claim number display column 1040 is displayed, and the constituent element display column 1041 is not displayed. For dependent claims, neither the claim number display column 1040 nor the constituent element display column 1041 is displayed.

[0185] In selection Figure 5 , Figure 6 , Figure 7 or Figure 8 When you access the "Evaluation Input Display" link in the evaluation registration column 1024 of the analysis results screen, the evaluation input screen will pop up and be displayed.

[0186] The evaluation input screen may include an evaluation selection button, a category selection drop-down menu, a text input field, and a registration button.

[0187] Evaluation selection buttons are, for example, GUI options used to select from a pre-defined set of options that are set to be displayed first for each user.

[0188] In addition to setting a rating selection button, the rating selection drop-down menu can also be set in the rating input screen. The rating selection drop-down menu is a GUI for selecting rating results from options other than those preset options that are set to be displayed first for each user.

[0189] The category selection drop-down menu is, for example, a GUI for selecting an evaluation category from options set in the patent document extraction device 20.

[0190] Text input fields are, for example, input fields used to enter notes, comments, and other text.

[0191] The registration button is, for example, a GUI for registering selected and input information. When the registration button is pressed, the evaluation registration unit 15 stores the selected and input information in association with the currently selected patent document in the storage unit 11 and sends it to the patent document retrieval device 20.

[0192] As a result, users can record the results of reading and evaluating patent documents, use their evaluation results, and share their evaluation results with other users.

[0193] It should be noted that although an example of linking evaluation results with patent documents is shown, the evaluation registration unit 15 can also register evaluation results for each claim or for each constituent element.

[0194] With the reading comprehension assistance system 1 according to this embodiment, since the information required for reading comprehension is configured in the analysis result screen, the content of the patent document can be read and understood quickly and accurately.

[0195] Traditionally, when reading and understanding the claims contained in the claims document, the person in charge and others need to break down the claims into each constituent element and study each constituent element.

[0196] However, as Figure 5 , Figure 6 or Figure 7 As shown, the analysis unit 13 performs analysis by effectively utilizing the learning completion model 17, and the display control unit 14 displays each constituent element decomposed from the description of the claims, thereby reducing the workload of decomposing the claims into constituent elements and avoiding the risk of misunderstanding caused by improper decomposition into constituent elements.

[0197] In addition, such as Figure 7As shown, by expanding and displaying only the independent claims as constituent elements, for example when reading and understanding the scope of the claims is important, only the most essential information is displayed on the screen, thereby enabling users to efficiently read and understand the information while avoiding the risk of missing anything.

[0198] In addition, such as Figure 8 As shown, by displaying the text representing the subject matter of the invention in each claim in a summary table, users can gain a clear understanding of the entire claims structure at a glance.

[0199] By using the reading comprehension assistance system 1 according to this embodiment, the accuracy of the user's reading comprehension of patent documents is improved, thereby reducing the number of times the patent document extraction device 20 processes the retrieval requests received from the user and suppressing the processing load of the patent document extraction device 20.

[0200] Furthermore, by improving the accuracy of patent document retrieval, the effective utilization of patented inventions in product development and other fields has been promoted, thereby reducing the risk of patent infringement.

[0201] This invention is not limited to the specific disclosed embodiments, and various modifications and alterations can be made without departing from the claims.

[0202] In this embodiment, an example is shown where the data representing the patent documents included in the collection data is data recorded in publications such as patent gazettes and public notices. However, the data representing patent documents is not limited to data recorded in publications. The data representing patent documents may not include data representing descriptions, drawings, abstracts, etc., as long as it represents the claims and includes textual data for each claim.

[0203] In this embodiment, the text indicating the subject matter of the invention is the text indicating the object of the invention. More specifically, the text indicating the subject matter of the invention is a phrase of length selected from the text of each claim that uniquely characterizes the invention and is easily identifiable by the user. The text indicating the subject matter of the invention may be the same as the name of the invention, or, in the case of Japanese or other languages, the same phrase as the wording at the end of each claim, or a phrase different from those descriptions. For example, it may not only be the wording at the end of each claim, such as "current collector for energy storage device," but may also include wording that distinguishes it from other inventions in the same technical field, such as "current collector for energy storage device with a coating."

[0204] If a user can roughly understand the content of an invention simply by looking at the text describing the subject matter, then they can quickly determine whether a claim requires detailed reading and understanding before reading the claims themselves.

[0205] The display control unit 14 can be in Figure 5 , Figure 6 or Figure 7 The method of emphasizing important words and new words in the claims in the component display bar 1041 is controlled.

[0206] Key terms are those used in the claims as essential elements of the invention, and which are described in detail later. For example, key terms can be extracted from those that are repeatedly mentioned in the claims as one of the requirements.

[0207] Newly coined terms are terms that are not previously mentioned in the claims and are used to describe the invention in the specification. Newly coined terms may be repeated with important terms and may be limited to terms other than technical, general, or specialized terms.

[0208] In this case, the analysis unit 13 extracts new and important terms from the claims based on the description and claims, and the display control unit 14 controls the display of new terms in the constituent element display bar 1041 using a color different from other text colors, such as red, based on the analysis results. By emphasizing new and important terms in this way, the parts of interest can be found immediately within the claims.

[0209] The information processing device 10 can reflect the description of the claims, which are broken down into individual constituent elements, into tabular data in the form of spreadsheet software and output it. Users can use the output data as is for original data such as survey data.

[0210] Although examples have been shown of the information processing apparatus 10, the patent document extraction apparatus 20, and the terminal apparatus 30 according to this embodiment being separate devices, some or all of them may also be implemented by the same apparatus.

[0211] Display device 105 and terminal device 30 are examples of display devices controlled by display control unit 14 to display images. The display device is not limited to these; it can also be a projector, monitor, etc., as long as it can display images.

[0212] Although examples of patent documents and various displays in Japanese are shown in this embodiment, other languages ​​are also possible. For example, in the case of English patent documents, the reading comprehension assistance system 1 can also be implemented using the same mechanism as in the case of Japanese patent documents, as long as a learning completion model 17 specifically designed for English patent documents is constructed.

[0213] Furthermore, this international application takes priority based on Japanese Patent Application Nos. 2019-230888, 2019-230889 and 2019-230890, filed on December 20, 2019, and incorporates the entire contents of those Japanese patent applications in this international application.

[0214] Symbol Explanation

[0215] 1. Reading comprehension assistance system;

[0216] 10. Information processing device;

[0217] 11. Storage Department;

[0218] 12. Patent Document Acquisition Department;

[0219] 13. Analysis Department;

[0220] 14. Display and control unit;

[0221] 15. Evaluation and Registration Department;

[0222] 16. Operation receiving unit;

[0223] 17. Complete the learning process using the model;

[0224] 20. Patent document extraction device;

[0225] 30. Terminal devices;

[0226] 40. Network;

[0227] 101 CPUs;

[0228] 102 Main storage device;

[0229] 103. Auxiliary storage device;

[0230] 104 Input devices;

[0231] 105 Display device;

[0232] 106 Communication interface device;

[0233] 107. Drive unit;

[0234] 108 Storage media;

[0235] 1021 Title bar;

[0236] 1022 Navigation display bar;

[0237] 1023 Claims display bar;

[0238] 1024 Evaluation Registration Section;

[0239] 1025 Main text display area;

[0240] 1026 Attached Figure Display Column;

[0241] Status 1031 is displayed;

[0242] 1032 Icon Center;

[0243] 1033 All Rights Button;

[0244] 1034 Independent weighted button;

[0245] 1038. Split display mode switching button;

[0246] 1039 Folding mark;

[0247] 1040 Claim number display column;

[0248] 1041 Component Display Bar;

[0249] 1042 Component Display Bar (Higher Level);

[0250] 1043 Component Display Bar (Lower Level).

Claims

1. An information processing apparatus, comprising: The analysis department analyzes the textual data representing the claims contained in the patent document data to determine the constituent elements of the invention for each claim contained in the claims; and The display control unit divides the text representing each claim of the claim into each of the constituent elements and displays them on the display device. The analysis unit determines key words representing important terms from the text data representing the claims. The display control unit emphasizes the text representing the key words in the text representing each claim of the claim and displays it on the display device. The key words are extracted as elements that are repeatedly mentioned in the claims. The analysis unit further analyzes the textual data representing the specification contained in the patent document data to further identify new terms that represent expressions used in the specification to describe the invention and which are not previously mentioned in the claims. The display control unit emphasizes the text representing the newly introduced term in the text representing each claim of the claim and displays it on the display device.

2. The information processing apparatus according to claim 1, wherein, The analysis unit uses the learned model output to segment each claim into text data consisting of the constituent elements.

3. The information processing apparatus according to claim 1 or 2, further comprising: The operation receiving unit accepts user input of evaluation results for the patent document data; as well as The evaluation and registration department registers the evaluation results in association with the patent document data. The display control unit displays the evaluation results on the display device.

4. The information processing apparatus according to claim 3, wherein, The display control unit displays the patent document data, which is the object of analysis by the analysis unit, and the evaluation results registered in the evaluation registration unit on a device used by multiple users.

5. The information processing apparatus according to claim 1 or 2, wherein, The display control unit visualizes the segmented constituent elements into a structural diagram and displays it.

6. The information processing apparatus according to claim 1 or 2, wherein, The analysis unit analyzes the textual data representing the claims contained in the patent document data to determine the subject matter of the invention for each claim contained in the claims. The display control unit displays text representing the subject matter on the display device in association with the number of the claim.

7. The information processing apparatus according to claim 6, wherein, The display control unit switches between displaying the text containing each claim of the claim and displaying the text without the claim according to the user's operation, and displays the text on the display device.

8. The information processing apparatus according to claim 6, wherein, The analysis unit selects the text representing the subject matter from the text data representing the claim.

9. The information processing apparatus according to claim 6, wherein, The analysis unit selects a phrase from the text data representing the claims that uniquely characterizes the invention and has a length that facilitates user identification of the invention, and uses it as the text representing the subject matter.

10. The information processing apparatus according to claim 1 or 2, wherein, The analysis unit analyzes the textual data representing the claims contained in the patent document data to determine the dependency relationships of the claims contained in the claims document. Based on the determined subordinate relationship, the display control unit displays the text representing the independent claims included in the claims statement on the display device.

11. The information processing apparatus according to claim 6, wherein, The analysis unit analyzes the textual data representing the claims contained in the patent document data to determine the dependency relationship of the claims contained in the claims. The display control unit, based on the determined subordinate relationship, For each independent claim, the text representing each claim in the claim statement is segmented into each of the constituent elements and displayed. For dependent claims, the text representing the subject matter is displayed in association with the claim number, and either a split display format representing the text of each claim of the claim divided into each of the constituent elements is selected, or a split display format not representing the text of each claim of the claim is selected, and the selected display format is displayed on the display device.

12. The information processing apparatus according to claim 10, wherein, In determining the dependency relationship, the analysis unit classifies claims with unclear dependency relationships as independent claims.

13. A reading comprehension aid method, The textual data representing the claims contained in patent literature data is analyzed to determine the constituent elements of the invention for each claim contained in the claims. The text representing each claim of the claim statement is segmented into each of the constituent elements and displayed on the display device. From the text data representing the claims, key words indicating important terms are identified. In the text representing each claim of the claim, the text indicating the key words is emphasized and displayed on the display device. The key words are extracted as elements that are repeatedly mentioned in the claims. Further analysis of the textual data representing the specification contained in the patent document data is conducted to further identify new terms that represent expressions used in the specification to describe the invention and which are not previously mentioned in the claims. In the text representing each claim of the claim, the text representing the newly introduced term is emphasized and displayed on the display device.

14. The reading comprehension assistance method according to claim 13, wherein, The textual data representing the claims contained in the patent document data is analyzed to determine the subject matter of the invention for each claim contained in the claims. The text representing the subject matter is displayed in association with the number of the claim.

15. The reading comprehension assistance method according to claim 13 or 14, wherein, The textual data representing the claims contained in the patent document data is analyzed to determine the dependency relationship of the claims contained in the claims. Based on the established dependency relationship, the text representing the independent claims included in the claim statement is displayed.

16. A program product for causing a computer to perform the following steps: The step of analyzing the textual data representing the claims contained in the patent document data to determine the constituent elements of the invention for each claim contained in the claims; The step of segmenting the text representing each claim of the claim into each of the constituent elements and displaying it on the display device; The step of determining key words representing important terms from the text data representing the claims, wherein the key words are extracted as elements repeatedly mentioned in the claims; and The step of emphasizing the text representing the key words in the text of each claim of the claim and displaying it on the display device. Further analysis is performed on the textual data representing the specification contained in the patent document data, in order to further identify new terms that represent expressions used in the specification to describe the invention and which are not previously recorded in the claims. The step of emphasizing the text representing the newly introduced term in the text representing each claim of the claim and displaying it on the display device.

17. The program product according to claim 16, wherein, The program product is used to further enable the computer to perform the following steps: The step of analyzing the textual data representing the claims contained in the patent document data to determine the subject matter of the invention for each of the claims contained in the claims; as well as The step of displaying text representing the subject matter on the display device in association with the number of the claim.

18. The program product according to claim 16 or 17, wherein, The program product is used to further enable the computer to perform the following steps: The steps include analyzing the textual data representing the claims contained in the patent document data to determine the dependency relationships of the claims contained in the claims; and Based on the determined dependency relationship, the step of displaying the text representing the independent claims included in the claims document on the display device.

Images