Information processing device, reading support method and program

Abstract

This information processing device is provided with: an analyzing unit which analyzes text data indicating the scope of the patent claims contained in patent document data, and identifies the constituent elements of the invention for each claim included in the scope of the patent claims; and a display control unit which divides the text indicating each claim in the scope of the patent claims into the constituent elements, and causes a display device to display the same.

Description

[Technical Field]

[0001] The present invention relates to an information processing device, a reading support method, and a program. [Background technology]

[0002] Technologies to assist in the reading comprehension of patent documents have been developed. In particular, the claims contained in patent documents are often more difficult to understand than general documents. Therefore, technologies to assist in the reading comprehension of patent documents, especially the claims, have been researched.

[0003] For example, Patent Document 1 discloses a device that outputs a diagram showing the relationship between an element indicated by a specified character string in a claim description and its subordinate elements. Patent Document 2 also discloses a device that divides a claim description into phrases and generates structured information on the relationships between the divided multiple description fragments. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2014-219833 [Patent Document 2] Japanese Patent Application Laid-Open No. 2012-003517 Summary of the Invention [Problem to be solved by the invention]

[0005] The task of reading and interpreting patent documents is carried out for the purpose of various tasks such as research and studies. In such tasks, it is often necessary to read and interpret a large number of patent documents, and it is important to be able to read and interpret the claims quickly and accurately.

[0006] However, when reading and understanding a large number of patent documents, the technology disclosed in Patent Document 1 or Patent Document 2 does not allow the reader to grasp the claims at a glance, and therefore lacks the speed of reading and understanding.

[0007] The invention disclosed in Patent Document 1 supports reading comprehension by dividing the description of the scope of a patent claim into multiple elements according to set rules, extracting the relationships between the divided elements to perform a structural analysis of the description of the scope of a patent claim, accepting the specification of a character string included in the description of the scope of a patent claim, extracting structural information corresponding to the specified character string from the structural information of the document obtained by the structural analysis, and outputting the extracted structural information in a diagram.

[0008] The invention disclosed in Patent Document 2 is a claim structure information generation device that generates description fragments into which patent claim text is divided and claim structure information that indicates the structure of the description fragments, and includes a storage unit that stores patent claim information, which is the text of the patent claim, a morphological analysis unit that performs morphological analysis on the patent claim information, a phrase identification unit that identifies the position of the phrases in the patent claim information, a surface division information storage unit that stores two or more pieces of surface division information having surface clue information that separates the description fragments and indicates the relationship between the description fragments and tokens corresponding to the surface clue information, a token assignment unit that assigns tokens corresponding to the surface clue information to positions in the patent claim information that correspond to the surface clue information, and a description fragment identification unit. The system is equipped with a phrase type correspondence information storage unit that stores two or more pieces of phrase type correspondence information having part-of-speech clue information of phrases that separate fragments and separator phrase types that correspond to the part-of-speech clue information, a separator phrase type assignment unit that assigns separator phrase types that correspond to the part-of-speech clue information to phrases in patent claim information that correspond to the part-of-speech clue information, a generation unit that uses the tokens and separator phrase types assigned to the patent claim information to generate claim structure information that indicates the structure of description fragments of patent claim information in accordance with predefined rules that indicate the structure of patent claim information, and an output unit that outputs the claim structure information generated by the generation unit, thereby performing structural analysis on patent claims with deeper structures.

[0009] As such, while the technology disclosed in Patent Document 1 or Patent Document 2 is suitable for the purpose of deeply reading and understanding the disclosure contents of a single patent document, it is not specialized for the purpose of improving the readability of the claims, and therefore is not suitable for the purpose of sufficiently reading and understanding the claims quickly and accurately when it is necessary to read and understand a large number of patent documents.

[0010] The present invention has been made in view of the above circumstances to solve the problem, and aims to support the quick and accurate reading and understanding of the claims. [Means for solving the problem]

[0011] The present invention has the following configuration. [1] An analysis unit that analyzes text data indicating the scope of patent claims included in patent document data and identifies constituent features of the invention for each claim included in the scope of patent claims; a display control unit that divides text indicating each claim of the claims into constituent features and displays the divided text on a display device, Information processing device. [2] The analysis unit further identifies key terms indicating important terms from the text data indicating the scope of the claims, the display control unit highlights text indicating the keyword in text indicating each claim of the scope of claims and displays it on the display device; [1] The information processing device according to [1]. [3] The analysis unit further analyzes text data indicating the specification included in the patent document data, and further identifies new terms that are used in the description of the invention in the specification and that are not previously described in the claims; the display control unit causes the display device to highlight text indicating the new word in text indicating each claim of the scope of claims, [1] or [2]. [4] an operation reception unit that receives an input of a user's evaluation result regarding the patent document data; an evaluation registration unit that associates the evaluation result with the patent document data and registers it; the display control unit causes the display device to display the evaluation result. An information processing device according to any one of [1] to [3]. [5] The display control unit displays the patent document data analyzed by the analysis unit and the evaluation results registered in the evaluation registration unit on a device used by multiple users. [4] The information processing device according to [4]. [6] The display control unit displays the divided components in a diagrammatic form as a structural diagram. An information processing device according to any one of [1] to [5]. [7] Analyzing the text data indicating the scope of patent claims contained in the patent document data, and identifying the constituent elements of the invention for each claim contained in the scope of patent claims; The text indicating each claim in the scope of claims is displayed by dividing it into constituent features. Reading support methods. [8] To the computer, a step of analyzing text data indicating the scope of claims included in the patent document data, and identifying constituent features of the invention for each claim included in the scope of claims; a step of dividing the text indicating each claim of the scope of claims into parts for each of the constituent features and displaying the part on a display device; A program to execute. [9] An analysis unit that analyzes text data indicating the scope of patent claims included in the patent document data and identifies the subject matter of the invention for each claim included in the scope of patent claims; a display control unit that causes a display device to display the text indicating the subject matter and the claim number in association with each other, Information processing device.

[10] The analysis unit further identifies the constituent features of the invention for each claim included in the scope of the claims, the display control unit divides the text indicating each claim of the claims into constituent features and further displays the divided text on the display device; [9] The information processing device according to [9].

[11] The display control unit switches between a display including the text indicating each claim of the claims and a display not including the text in response to a user operation, and causes the display device to display the same. [9] or

[10] .

[12] An operation reception unit that receives an input of a user's evaluation result for the patent document data; an evaluation registration unit that associates the evaluation result with the patent document data and registers it; the display control unit causes the display device to display the evaluation result. [9] to

[11] .

[13] The display control unit displays the patent document data analyzed by the analysis unit and the evaluation results registered in the evaluation registration unit on a device used by multiple users.

[12] The information processing device according to

[12] .

[14] The analysis unit selects the text indicating the subject matter from the text data indicating the claim. [9] to

[13] .

[15] The analysis unit selects a phrase from the text data indicating the scope of the claims that uniquely represents the invention and is long enough for a user to easily identify the invention, and sets the selected phrase as the text indicating the subject matter. [9] to

[13] .

[16] Analyzing text data indicating the scope of patent claims contained in patent document data, and identifying the subject matter of the invention for each claim contained in the scope of patent claims; displaying the text indicating the subject matter in association with the claim number; Reading support methods.

[17] To the computer, a step of analyzing text data indicating the scope of claims included in the patent document data and identifying the subject matter of the invention for each claim included in the scope of claims; a step of displaying the text indicating the subject matter and the claim number in association with each other on a display device; A program to execute.

[18] An analysis unit that analyzes text data indicating the scope of patent claims included in the patent document data and identifies the dependency relationships of claims included in the scope of patent claims; a display control unit that causes a display device to display text indicating an independent claim included in the scope of claims based on the identified dependency relationship, Information processing device.

[19] The analysis unit further identifies the subject matter of the invention for each claim included in the scope of claims, the display control unit further causes a display device to display the text indicating the subject matter and the claim number in association with each other;

[18] The information processing device according to

[18] .

[20] The analysis unit further identifies the constituent features of the invention for each claim included in the scope of the claims, the display control unit divides the text indicating each claim of the claims into constituent features and further displays the divided text on the display device;

[18] or

[19] .

[21] The analysis unit further identifies the constituent features of the invention for each claim included in the scope of the claims, The display control unit, based on the identified dependency relationship, For independent claims, the text indicating each claim in the scope of claims is displayed divided by the constituent features; For dependent claims, the text indicating the subject matter is displayed in association with the claim number, and the display device is prompted to select either a divided display format in which the text indicating each claim divided by the constituent features is displayed, or a divided display format in which the text indicating each claim is not displayed, and the display device is prompted to display the dependent claims in the selected display format.

[19] The information processing device according to

[19] .

[22] An operation reception unit that receives an input of a user's evaluation result for the patent document data; an evaluation registration unit that associates the evaluation result with the patent document data and registers it; the display control unit causes the display device to display the evaluation result.

[18] to

[21] . [twenty three] The display control unit displays the patent document data analyzed by the analysis unit and the evaluation results registered in the evaluation registration unit on a device used by multiple users.

[22] The information processing device according to

[22] . [twenty four] the analysis unit classifies claims whose dependency relationships are unclear into independent claims in the process of identifying dependency relationships; An information processing device according to any one of

[18] to

[23] .

[25] Analyzing text data indicating the scope of patent claims contained in patent document data, and identifying the dependency relationships of claims contained in said scope of patent claims; displaying text indicating independent claims included within said claims based on said identified dependencies; Reading support methods.

[26] To the computer, A step of analyzing text data indicating the scope of claims included in the patent document data and identifying dependency relationships of the claims included in the scope of claims; displaying, on a display device, text indicating independent claims included in said claims based on said identified dependencies; A program to execute. [Effects of the Invention]

[0012] It can assist in the quick and accurate reading of claims. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a diagram illustrating an example of a system configuration of a reading support system according to an embodiment. [Figure 2] FIG. 1 is a diagram illustrating an example of a hardware configuration of an information processing apparatus according to an embodiment. [Figure 3] FIG. 2 is a diagram illustrating an example of functions of an information processing device according to an embodiment. [Figure 4] 10 is a flowchart illustrating an example of a reading support process of the information processing device according to an embodiment. [Figure 5] FIG. 10 is a diagram illustrating an example of an analysis result screen according to an embodiment. [Figure 6] FIG. 10 is a diagram illustrating another example of an analysis result screen according to an embodiment. [Figure 7] FIG. 10 is a diagram illustrating yet another example of an analysis result screen according to an embodiment. [Figure 8] FIG. 10 is a diagram illustrating yet another example of an analysis result screen according to an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0014] Hereinafter, an embodiment of a reading support system according to the present invention will be described with reference to the drawings.

[0015] FIG. 1 is a diagram illustrating an example of a system configuration of a reading support system according to an embodiment.

[0016] The reading support system 1 is a system that supports the reading comprehension of patent documents. Specifically, the reading support 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 connected to each other via a network 40 so as to be able to communicate with each other.

[0017] The information processing device 10 analyzes data indicating patent documents (hereinafter referred to as patent document data) and generates screen data to be displayed on a screen based on the analysis results. The generated screen data is data that shows a screen that makes it easy to read and understand the description of the scope of patent claims included in the patent document data.

[0018] The patent document extraction device 20 receives search conditions specified by a user's operation via the terminal device 30, and extracts patent document data from a database of patent publications, unexamined publications, etc. based on the search conditions. Then, the patent document extraction device 20 transmits the extracted patent document data to the information processing device 10 in response to a user's operation via the terminal device 30.

[0019] The terminal device 30 is a device that receives user operations, instructs the information processing device 10 or the patent document extraction device 20 to execute various functions, receives screen data from the information processing device 10 or the patent document extraction device 20, and displays the received screen data.

[0020] Next, the hardware configuration of the information processing device 10 will be described.

[0021] FIG. 2 is a diagram illustrating an example of a hardware configuration of an information processing device according to an embodiment.

[0022] The information processing device 10 includes a CPU (Central Processing Unit) 101, a main memory device 102, an auxiliary memory device 103, an input device 104, a display device 105, a communication interface device 106, and a drive device 107. These devices are connected via a bus.

[0023] The CPU 101 is a main control unit that controls the operation of the information processing device 10, and realizes various functions described below by reading and executing programs stored in the main storage device 102.

[0024] The main storage device 102 reads and stores programs from the auxiliary storage device 103 when the information processing device 10 is started up. The auxiliary storage device 103 stores installed programs, as well as files, data, etc. required for various functions described below.

[0025] The input device 104 is a device for inputting various types of information and is realized by, for example, a keyboard, a pointing device, etc. The display device 105 is for displaying various types of information and is realized by, for example, a display, etc. The communication interface device 106 includes a LAN card, etc., and is used for connecting to a network.

[0026] The program according to this embodiment is at least a part of various programs that control the information processing device 10. The program is provided, for example, by distributing a storage medium 108 or by downloading it from a network. The storage medium 108 on which the program is recorded can be of various types, including storage media that record information optically, electrically, or magnetically, such as a CD-ROM, a flexible disk, or a magneto-optical disk, and semiconductor memories that record information electrically, such as a ROM or a flash memory.

[0027] When storage medium 108 storing the program is set in drive device 107, the program is installed from storage medium 108 into auxiliary storage device 103 via drive device 107. A program downloaded from a network is installed into auxiliary storage device 103 via communication interface device 106.

[0028] Next, the functions of the information processing device 10 will be described.

[0029] FIG. 3 is a diagram illustrating an example of functions of the information processing device according to an embodiment.

[0030] 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 reception unit 16.

[0031] The storage unit 11 stores various data, programs, etc. Specifically, the storage unit 11 stores a trained model 17.

[0032] The trained model 17 is a model constructed by machine learning for the analysis of patent documents. The trained model 17 may be, for example, a neural network, a decision tree, a support vector machine, or the like, or may be a model constructed by deep learning. Specifically, the trained model 17 is preferably specialized for language analysis, and may be, for example, "IBM WATSON (registered trademark)." The "IBM WATSON (registered trademark)" used as the trained model 17 may be customized for the analysis of patent documents.

[0033] Machine learning is a technology in which a computer autonomously generates an algorithm from training data to efficiently execute a specific task, relying on patterns and inference. The trained model 17 according to this embodiment is a model representing an algorithm generated in this way.

[0034] The patent document acquisition unit 12 acquires patent document data. Specifically, the patent document acquisition unit 12 receives patent document data extracted by the patent document extraction device 20. The transmitted data is data indicating a set of one or more patent documents (hereinafter referred to as set data). The set data may be, for example, a file in CSV (Comma-Separated Values) format. The set data is an example of patent document data.

[0035] The analysis unit 13 analyzes the collective data. Specifically, the analysis unit 13 applies an algorithm indicated in the trained model 17 to analyze each patent document included in the collective data.

[0036] The analysis unit 13 identifies the constituent elements of the invention based on the description of the claims included in each patent document, and then breaks down the description of each claim into constituent elements.

[0037] Here, constituent elements are elements that specify an invention and are necessary for the subject matter to be included in the scope of the invention. Specifically, in the case of an invention of a product, the constituent elements may be elements such as parts that the product has, but are not limited to this. For example, the analysis unit 13 may break down the same part included in the product into multiple constituent elements.

[0038] Generally, in order to grasp the scope of an invention for each claim, the description of each claim is broken down into constituent elements and examined. It is known that if the description of each constituent element thus broken down is too long or too short, it becomes difficult to grasp the scope of the invention.

[0039] Therefore, it is desirable that the trained model 17 is constructed in advance by machine learning as an algorithm that breaks down each claim into constituent elements of an easily readable length. Then, the analysis unit 13 receives text data indicating each claim as input and outputs text data in which the description of each claim is broken down into constituent elements of an easily readable length, in accordance with the algorithm defined in the trained model 17 thus constructed.

[0040] Furthermore, the analysis unit 13 determines text indicating the subject matter of the invention for each claim. Specifically, the trained model 17 is constructed in advance by machine learning as an algorithm for extracting the subject matter of the invention from the text data for each claim. Then, according to the algorithm defined in the trained model 17 thus constructed, the analysis unit 13 receives the text data indicating each claim as input and outputs text data indicating the subject matter of the invention for each claim.

[0041] Furthermore, the analysis unit 13 classifies each claim into an independent claim and a dependent claim. An independent claim (hereinafter referred to as an independent claim) is a claim that is written independently of other claims, and a dependent claim (hereinafter referred to as a dependent claim) is a claim that is written by citing other claims. Specifically, the trained model 17 is constructed in advance through machine learning as an algorithm that identifies the dependency relationship of claims included in the scope of claims based on text data indicating the scope of claims. Then, in accordance with the algorithm defined in the trained model 17 thus constructed, the analysis unit 13 inputs the text data indicating the scope of claims and outputs data in which each claim is classified as an independent claim or a dependent claim. Note that the output data also includes data indicating the claim numbers to which the dependent claims cite. When it is unclear how to classify each claim, it can also be classified as an independent claim.

[0042] The classification of an independent claim or a dependent claim may be determined using the certainty (also referred to as confidence, reliability, or probability) that each claim is an independent claim and the certainty that each claim is a dependent claim. In this case, the algorithm defined in the trained model 17 outputs these certainties. The analysis unit 13 classifies a claim as an independent claim if the certainty that the claim is an independent claim is equal to or greater than a predetermined value. The analysis unit 13 also classifies a claim as a dependent claim if the certainty that the claim is a dependent claim is equal to or greater than a predetermined value. The analysis unit 13 also classifies a claim that is neither an independent claim nor a dependent claim (i.e., a claim whose certainty as an independent claim is less than a predetermined value and whose certainty as a dependent claim is less than a predetermined value) as an independent claim.

[0043] For each claim, if it is unclear or the output accuracy is low, it can be classified as an independent claim from a fail-safe perspective, thereby preventing the user from skipping over the independent claim.

[0044] In addition, 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 indicated in the trained model 17 to the collective data.

[0045] For example, the analysis unit 13 may extract text from the claims included in each patent document that serves as an index for dividing the document into claims. Specifically, the analysis unit 13 may extract text indicating each claim number, text immediately before a period, or text such as "characterized by."

[0046] Depending on the format of the patent document, the description of the scope of claims may not include the word "claim." However, since the description of the scope of claims is likely to include at least text indicating each claim number, it is desirable that the analysis unit 13 extracts text that serves as an index for dividing the document into claims based on the regularity of the text before and after each claim number.

[0047] Furthermore, in order to increase the accuracy of identifying the constituent features, the analysis unit 13 may extract text such as "the above" or "the" as text indicating an antecedent from the description of the claims included in each patent document. In this case, the word following the extracted character string becomes a candidate for text indicating the constituent feature.

[0048] The analysis unit 13 may extract text such as "comprises," "includes," or "consists of" as text indicating a structure, and may further extract text such as "procedure comprising," "procedure for...," etc. as text indicating a procedural structure.

[0049] The analysis unit 13 may extract text such as "here," "thereby," or "regarding that," as text indicating a cause-and-effect relationship or the like.

[0050] Furthermore, the analysis unit 13 may extract text such as "but" or "in" as text for identifying the preamble from among the constituent elements.

[0051] The analysis unit 13 may extract text such as "greater than or equal to," "less than or equal to," "less than," or "from to" as text that specifies that the content is a numerical range.

[0052] In addition, the analysis unit 13 may extract text such as "furthermore," "described in...," etc., used in dependent claims in order to improve the accuracy of classifying each claim into an independent claim or a dependent claim.

[0053] Furthermore, the analysis unit 13 may perform morphological analysis as preprocessing. For example, the analysis unit 13 divides the description of each claim into morphemes, selects text candidates indicating constituent features from the divided morphemes, and counts the number of such candidates contained in each claim or the description of the claims.

[0054] The analysis unit 13 inputs the results of these preprocessing steps into the trained model 17 together with the text for each patent document included in the collective data, and obtains analysis results output from the trained model 17.

[0055] Preferably, the analysis unit 13 may perform these preprocessing operations in such a way that the content of the preprocessing operation differs for each language used in the description of each patent document. Furthermore, the analysis unit 13 may perform analysis using a trained model 17 with different content for each language used in the description of each patent document. More preferably, the analysis unit 13 may perform preprocessing operations or analysis using a trained model 17 with different content for each subject of the application (specific country or international application). This allows the analysis unit 13 to perform analysis according to the characteristics of the language or the characteristics of the subject of the application.

[0056] Specifically, the analysis unit 13 determines the language used from the description of each patent document, and then extracts text for each language corresponding to the above-mentioned cases, as shown in Table 1.

[0057] [Table 1]

[0058] For example, when the analysis unit 13 determines that the patent document is in English or Chinese, it may extract the English or Chinese text shown in Table 1.

[0059] The aggregate data may also include text indicating the subject of the application for each patent document. For example, the text indicating each patent document may include text such as "US" indicating the United States, "EP" indicating Europe, and "PCT" indicating an international application. Therefore, the analysis unit 13 may extract text indicating the subject of the application from the text indicating each patent document and perform analysis using different preprocessing or trained models 17 with different content for each subject of the application.

[0060] The trained model 17 may also include multiple models that differ depending on the content of the analysis. For example, the analysis unit 13 may use separate models to identify constituent features, determine text that indicates the subject matter of the invention, and classify each claim into an independent claim or a dependent claim.

[0061] The display control unit 14 causes the display device 105 or the terminal device 30 to display various screens, which will be described later, based on the analysis results of the analysis unit 13, in order to assist in reading and understanding the patent documents.

[0062] The evaluation registration unit 15 registers the results of evaluating the patent document in response to a user operation received by the operation reception 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.

[0063] The operation reception unit 16 receives user operations from the input device 104 or the terminal device 30. Specifically, the operation reception unit 16 receives inputs to various input devices such as a keyboard, a mouse, and a touch panel provided in the input device 104 or the terminal device 30.

[0064] Next, the operation of the information processing device 10 will be described.

[0065] FIG. 4 is a flowchart illustrating an example of a reading support process of an information processing device according to an embodiment.

[0066] In response to a user operation, the patent document extraction device 20 transmits a signal requesting the start of reading support processing to the information processing device 10. The information processing device 10 starts the reading support processing in response to the request signal transmitted from the patent document extraction device 20. The patent document acquisition unit 12 acquires aggregate data of patent documents (step S11).

[0067] Specifically, the patent document extraction device 20 receives the specified search conditions and searches for patent documents from a patent document database. Then, the patent document extraction device 20 transmits the retrieved one or more patent documents as a set of data to the information processing device 10. The transmitted set of data is, for example, data in CSV format.

[0068] Next, the analysis unit 13 analyzes the received and acquired collective data (step S12). Specifically, the analysis unit 13 analyzes the collective data of patent documents according to an algorithm defined in the trained model 17, and outputs an analysis result for each patent document.

[0069] The output analysis results include text data that breaks down the description of each claim into constituent elements of an easy-to-read length, text data that indicates the subject matter of the invention of each claim, and data that classifies each claim into an independent claim or a dependent claim.

[0070] Next, the display control unit 14 displays an analysis result screen on the display device 105 or the terminal device 30 in response to the user's operation received by the operation receiving unit 16 (step S13). The analysis result screen to be displayed is a screen that assists in reading and understanding the patent document. Specific display contents will be described later.

[0071] Next, the evaluation registration unit 15 registers the evaluation result input by the user (step S14). Specifically, the operation reception unit 16 receives the user's operation and acquires information indicating the evaluation result input into the evaluation input field included in the analysis result screen. The evaluation registration unit 15 stores the information indicating the evaluation result acquired by the operation reception unit 16 in the storage unit 11.

[0072] The stored information indicating the evaluation results is associated with the patent document. When displaying the patent document, the display control unit 14 displays an analysis result screen including the evaluation results associated with the patent document. The information processing device 10 may also transmit information indicating the registered evaluation results to the patent document extraction device 20.

[0073] Next, a screen that the display control unit 14 causes the display device 105 or the terminal device 30 to display will be described.

[0074] The display control unit 14 of the information processing device 10 displays a collection list screen on the display device 105 or the terminal device 30 in response to a user operation received by the operation receiving unit 16. The collection list screen includes a list of collection data of patent documents acquired by the patent document acquisition unit 12 in step S11 of the above-described reading support process.

[0075] The display column for each set of data includes, for example, a panel header, a panel list, and a memo column.

[0076] The panel header displays, for example, the name of the analysis project for which the aggregate data is the subject.

[0077] The panel list displays attribute information of the set data in list form, such as the title of the set data, the number of publications included in the set data, the creation date or most recent revision date, the creator or most recent revision person, etc.

[0078] The memo field also includes, for example, a GUI (Graphical User Interface) button for popping up a memo editing screen that accepts input of memo text to be added to the collection data, and a display field that displays the input memo text.

[0079] The display control unit 14 of the information processing device 10 causes the display device 105 or the terminal device 30 to display a publication list screen in response to a user operation received by the operation receiving unit 16.

[0080] The publication list screen includes, for example, a list of publications included in the set data selected on the set list screen, and also includes a publication selection area and an analysis button.

[0081] The list of publications includes, as items, for example, a section number, a flag, a publication number, a name, an applicant, an evaluation, a status, and an invention subject matter.

[0082] The value of the item "item number" is the publication number in the aggregate data.

[0083] The value of the item "flag" displays a flag set on the analysis result screen described later. The flag is used, for example, to record that the publication is one that the user should pay attention to.

[0084] The value of the item "publication number" is the number of the publication in which each patent document, such as a patent publication or a publication without publication, is published.

[0085] The value of the item "Name" is the name of the invention of each patent document.

[0086] The value of the item "applicant" is the name of the applicant of each patent document.

[0087] The value of the item "Evaluation" is the evaluation result registered on the analysis result screen described later.

[0088] The value of the item "status" is the examination status of each patent document.

[0089] The value of the item "Subject of the Invention" is text indicating the subject of the invention determined by the analysis unit 13 by analyzing each patent document.

[0090] The publication selection area is a checkbox for selecting a publication. When a user selects a patent document in the publication selection area and presses the analysis button, the display control unit 14 causes the display device 105 or the terminal device 30 to display an analysis result screen showing the analysis result of the selected patent document, in response to the user's operation received by the operation reception unit 16.

[0091] The display of the collection list screen and the display of the list of publications may also be displayed on multiple display devices 105 or terminal devices 30 used by other users who are permitted to share information. This allows a team of specific users to share and manage the evaluation results entered in the evaluation registration unit 15. Furthermore, by managing a collection of patent documents among a team, the work of reading and understanding the patent documents can be shared among the team, reducing the burden on each user.

[0092] FIG. 5 is a diagram showing an example of an analysis result screen according to an embodiment.

[0093] The analysis result screen includes a header 1021 , a navigation display field 1022 , a claim display field 1023 , an evaluation registration field 1024 , a main text display field 1025 , and a drawing display field 1026 .

[0094] The header 1021 includes the name of the aggregate data, a link to the publication list screen, etc. The header 1021 also includes, for the selected patent document, the applicant, the name of the invention, a status display 1031, an icon center 1032, etc. The icon center 1032 includes, for example, an icon display or buttons for accepting operations such as a family presence / absence display button, a detailed display button, a flag button, a full text display button, a PDF (Portable Document Format) button, a CSV output button, and a print output button.

[0095] The status indicator 1031 indicates by color whether the patent right of the selected patent document is still in force. For example, if the patent right is still in force, the status indicator 1031 is green, indicating that the patent right is still in force, and if the patent right has expired, the status indicator 1031 is yellow, indicating that the patent right is no longer in force.

[0096] Specifically, the display control unit 14 determines whether or not the patent right is still valid based on the filing date of the patent document, and determines the color of the status display 1031 based on the result of the determination.

[0097] In the family presence / absence display, the presence or absence of a so-called patent family in the selected patent document may be indicated by color.

[0098] For example, if a patent family exists in a patent document, the family presence / absence indicator will be red, indicating that a patent family exists; if a patent family does not exist, the family presence / absence indicator will be gray, indicating that a patent family does not exist.

[0099] Specifically, data indicating the presence or absence of a patent family is included in each patent document of the collective data acquired by the patent document extraction device 20, and the display control unit 14 determines the color of the family presence / absence display based on the data indicating the presence or absence of a patent family included in the collective data.

[0100] The detail display button is a GUI for popping up a screen displaying details of the patent family, for example. Data showing the details of the patent family is also included for each patent document in the aggregate data acquired by the patent document extraction device 20.

[0101] The flag button is a GUI for receiving an operation to set a flag for a selected patent document, for example. When the flag is set, the set flag is displayed on the publication list screen described above and in the navigation display field described later.

[0102] The full text display button is a GUI for displaying a pop-up screen containing the description, claims, drawings, abstract, and other information contained in the selected patent document.

[0103] The PDF button is a GUI for generating and downloading a PDF file containing the description, claims, drawings, abstract, and other information contained in the selected patent document.

[0104] The CSV output button is a GUI for outputting the text displayed in the claim display field 1023 as a CSV file in accordance with the display format. If the description of each claim broken down by constituent element is obtained as a CSV file, the CSV file can be used for detailed analysis, such as claim chart analysis.

[0105] The print output button is a GUI for printing the claim display field 1023 currently being displayed.

[0106] The navigation display field 1022 contains a list of publications selected on the publication list screen, and is a display field for receiving operations to select patent documents to display in the header 1021, claim display field 1023, main text display field 1025, drawing display field 1026, etc.

[0107] The claim display field 1023 is a display field for reading and understanding the claims based on the analysis results of the analysis unit 13 for the selected patent document.

[0108] The claim display field 1023 includes an all claims button 1033 , an independent claims button 1034 , a split display format switching button 1038 , a folding symbol 1039 , a claim number display field 1040 , and a constituent element display field 1041 .

[0109] The All Claims button 1033 and the Independent Claims button 1034 display the number of all claims and the number of independent claims, respectively, and are GUIs for selecting the display object currently being displayed from two display objects, "All Claims" and "Independent Claims." When the display object is set to "All Claims," ​​all claims, including independent claims and dependent claims, are displayed, and when the display object is set to "Independent Claims," ​​only independent claims are displayed.

[0110] The split display format switching button 1038 is a GUI for switching the format of splitting the claims into multiple constituent elements from three split display formats, "expand all claims," ​​"hide all claims," ​​and "independent claims only," each time it is pressed. The selected split display format is displayed next to the split display format switching button 1038.

[0111] When the split display format is "Expand all claims," ​​the constituent features of all claims selected for display are displayed. When the split display format is "Hide all claims," ​​the constituent features of all claims selected for display are not displayed. When the split display format is "Independent claims only," the constituent features of only the independent claims selected for display are displayed.

[0112] Fig. 5 is an example of a screen where "all claims" is selected as the display object and "expand all claims" is selected as the split display format, and Fig. 6, which will be described later, is another example. Fig. 7, which will be described later, 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, and Fig. 8 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.

[0113] The folding symbol 1039 is a symbol indicating whether or not the constituent features of each claim are displayed. As shown in Figure 5, when the division display format is "expand all claims," ​​the constituent features of all claims selected for display are displayed, so the folding symbol 1039 becomes a downward arrow indicating that the constituent features are displayed.

[0114] The claim number display field 1040 includes the number of each claim, text indicating the subject matter of each claim, and, in the case of dependent claims, the number of the claim to which it refers.

[0115] The text indicating the subject matter of each claim, the claim numbers to which dependent claims cite, etc. are included in the analysis results of the analysis unit 13. Then, the display control unit 14 associates the text indicating the subject matter with the claim numbers based on the analysis results, and displays them on the display device 105 or the terminal device 30.

[0116] In the claim number display field 1040, for example, the background color for independent claims is different from the background color for dependent claims, so that independent claims and dependent claims can be distinguished at a glance.

[0117] In the constituent element display column 1041, text showing each claim is displayed in a separate display column for each constituent element. The text showing each constituent element is text that has been broken down by the analysis unit 13 into easy-to-read lengths according to the algorithm defined in the trained model 17.

[0118] By displaying the claim display field 1023 when the display target is "all claims" and the divided display format is "all claims expanded," the user can comprehensively check the description of all claims included in the scope of the claims and quickly and accurately read and understand the description of each claim.

[0119] The display control unit 14 divides the text showing each claim of the claims into constituent elements and displays it on the display device 105 or the terminal device 30. By reading the text divided into constituent elements, the user can reduce the time it takes to find the boundaries of the constituent elements, improving the speed of reading comprehension. In addition, the user will make fewer mistakes in identifying the boundaries of the constituent elements, improving the accuracy of reading comprehension.

[0120] The evaluation registration field 1024 displays options for the evaluation results. It is possible for each user to set an option to be preferentially displayed from preset options. When a "Display evaluation input" link included in the evaluation registration field 1024 is selected, the display control unit 14 causes the display device 105 or the terminal device 30 to display an evaluation input screen. The evaluation input screen will be described later.

[0121] If the results of user evaluations have already been registered for the selected patent document, the evaluation registration field 1024 displays the registered evaluation results.

[0122] A "Display Text" link is displayed in the text display field 1025. When the "Display Text" link is selected, the display control unit 14 causes the display device 105 or the terminal device 30 to display the text described in the specification of the selected patent document.

[0123] The representative drawing and each drawing of the selected patent document are displayed in the drawing display field 1026. In addition to the figures of the drawing documents, the drawing display field 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" in the specification.

[0124] FIG. 6 is a diagram showing another example of the analysis result screen according to an embodiment.

[0125] In claim display field 1023, text indicating each claim may be further divided into multiple layers and displayed, as shown in Fig. 6. Specifically, in claim display field 1023, text obtained by dividing the text indicating each claim is displayed as constituent element display field (upper layer) 1042, and text obtained by further dividing the text displayed in constituent element display field (upper layer) 1042 is displayed as constituent element display field (lower layer) 1043.

[0126] The constituent requirement display field (upper layer) 1042 and the constituent requirement display field (lower layer) 1043 are displayed in association with each other. The constituent requirement display field (lower layer) 1043 is located below the constituent requirement display field (upper layer) 1042, which is the higher layer.

[0127] Although FIG. 6 shows an example of a hierarchical display with two or fewer levels, a hierarchical display with three or more levels may also be included.

[0128] Furthermore, by reading only the non-hierarchical constituent element display column 1041 and the constituent element display column (lower layer) 1043, which is the lowest layer, it is possible to read all of the text representing each claim without duplication, so the constituent element display column (upper layer) 1042, which is a layer other than the lowest layer, is displayed less prominently than the non-hierarchical constituent element display column 1041 and the constituent element display column (lower layer) 1043, which is the lowest layer.

[0129] By displaying the text showing each claim in multiple layers, the sentence structure becomes easier to understand, even when the text showing each claim includes a complex compound sentence structure or a description of constituent elements with long sentences, leading to quick and accurate reading comprehension.

[0130] The claim display field 1023 is displayed in a diagrammatic form as a structural diagram. For example, the claim number display field 1040 is linked by lines to the constituent feature display field 1041, the constituent feature display field (upper hierarchy) 1042, or the constituent feature display field (lower hierarchy) 1043. In other words, the claim display field 1023 displays the relationships between the constituent features in a diagrammatic form as a structural diagram.

[0131] The constituent requirement display column 1041 constitutes a part of the structure diagram by showing constituent requirements as a group enclosed in a frame.

[0132] Furthermore, the diagrammatic representation of the claim structure makes the complex sentence structure of the text representing each claim visible. By visualizing the claim structure as a diagram, it is possible to quickly recognize, for example, that in the case of a single level, multiple constituent features are on the same level, and in the case of multiple levels or more, that the text representing the claim has a complex hierarchical relationship.

[0133] FIG. 7 is a diagram showing yet another example of the analysis result screen according to an embodiment.

[0134] Figure 7 is an example of the analysis result screen shown in Figure 5, where the All Claims button 1033 is pressed to select "All Claims" as the display target, and the Split Display Format Switch button 1038 is pressed to select "Independent Claims Only" as the split display format.

[0135] In this divided display format, for an independent claim, a claim number display field 1040 and a constituent feature display field 1041 are displayed. For a dependent claim, only the claim number display field 1040 is displayed, and the constituent feature display field 1041 is not displayed.

[0136] The fold symbol 1039 displayed next to the claim number display field 1040 of an independent claim is a downward arrow indicating that the claim displays constituent features. The fold symbol 1039 displayed next to the claim number display field 1040 of a dependent claim is a right arrow indicating that the claim does not display constituent features.

[0137] When the split display format is set to "independent claims only," only the independent claims that are directly related to the scope of the patent right of the selected patent document are displayed expanded into constituent elements, and the contents of the dependent claims that are not directly related to the scope of the patent right are not displayed. Therefore, since only the most necessary information is displayed on the screen, the user can read and understand the patent right efficiently, thereby quickly and accurately grasping the scope of the patent right.

[0138] FIG. 8 is a diagram showing yet another example of the analysis result screen according to an embodiment.

[0139] Figure 8 is an example of a screen on the analysis result screen shown in Figure 5 when the All Claims button 1033 is pressed to select "All Claims" as the display target, and the Split Display Format Switch button 1038 is pressed to select "Hide All Claims" as the split display format.

[0140] In this divided display format, only the claim number display field 1040 is displayed for all claims, and the constituent feature display field 1041 is not displayed.

[0141] The folding symbol 1039 displayed next to the claim number display field 1040 of each claim is a right-pointing arrow indicating that the constituent features are not displayed.

[0142] When the split display format is set to "hide all claims," ​​the content of each claim is not displayed, and more text indicating the subject matter of each claim is displayed on the screen, allowing users to distinguish between independent and dependent claims at a glance. This allows users to grasp the overall structure of the claims at a glance. Also, because only the text indicating the subject matter of each claim is displayed, users can quickly skip over patent documents that do not require reading.

[0143] In addition, by looking at the text that describes the subject matter of the invention, one can quickly determine whether a claim requires detailed reading before reading the claim description, thereby improving the overall speed of reading patent documents.

[0144] Although not shown, when the Independent Claim button 1034 on the analysis result screen shown in Figure 5 is pressed to select "Independent Claim" as the display target, and when the Split Display Format Switch button 1038 is pressed to select "Hide All Claims" display as the split display format, in the selected patent document, for independent claims, only the claim number display column 1040 is displayed and the constituent feature display column 1041 is not displayed, and for dependent claims, neither the claim number display column 1040 nor the constituent feature display column 1041 is displayed.

[0145] The evaluation input screen can be displayed as a pop-up when the "Display evaluation input" link in the evaluation registration field 1024 of the analysis result screen of FIG. 5, FIG. 6, FIG. 7 or FIG. 8 is selected.

[0146] The rating input screen can include a rating selection button, a category selection pull-down, a text input field, and a registration button.

[0147] The evaluation selection button is, for example, a GUI for selecting an option that has been set to be displayed preferentially for each user from among preset options.

[0148] In addition to the rating selection button, the rating input screen may also be provided with a rating selection pull-down menu. The rating selection pull-down menu is a GUI for selecting a rating result from among preset options other than the options set as priority display for each user.

[0149] The category selection pull-down is a GUI for selecting an evaluation category from options set in the patent document extraction device 20, for example.

[0150] The text entry field is an entry field for entering text such as notes and comments.

[0151] The registration button is, for example, a GUI for registering the selected and input information. When the registration button is pressed, the evaluation registration unit 15 associates the selected and input information with the selected patent document, stores it in the storage unit 11, and transmits it to the patent document extraction device 20.

[0152] This allows users to read and understand patent documents, record the results of their evaluation, and use the results of their evaluation themselves, as well as make the results of their evaluation known to other users so that they can use them.

[0153] Although an example in which the evaluation results are associated with patent documents has been shown, the evaluation registration unit 15 may be configured to register the evaluation results evaluated for each claim or each constituent element.

[0154] According to the reading support system 1 of this embodiment, the information necessary for reading comprehension is arranged on the analysis result screen, so that the contents of the patent document can be read quickly and accurately.

[0155] In the past, when reading and interpreting the claims included in the scope of a patent, the person in charge had to break down the claims into constituent elements and examine each element separately.

[0156] However, as shown in Figure 5, Figure 6 or Figure 7, the analysis unit 13 performs analysis using the trained model 17, and the display control unit 14 displays the claim description for each decomposed constituent element, thereby reducing the burden of the work of decomposing into constituent elements and avoiding the risk of misunderstandings due to inappropriate decomposition into constituent elements.

[0157] Furthermore, as shown in Figure 7, by displaying only the independent claims expanded into constituent elements, if the user wants to read and understand the patent by focusing on the scope of rights, for example, only the most necessary information is displayed on the screen, allowing the user to read and understand efficiently while avoiding the risk of skipping over information.

[0158] Furthermore, as shown in FIG. 8, the text indicating the subject matter of each claim is displayed in a list, allowing the user to grasp the overall structure of the claims at a glance.

[0159] According to the reading support system 1 of this embodiment, the accuracy of the user's reading of patent documents is improved, thereby reducing the number of search processes that the patent document extraction device 20 receives requests for from the user, and suppressing the processing load on the patent document extraction device 20.

[0160] In addition, improving the accuracy of patent document searches will promote the use of patented inventions in product development and other areas, reducing the risk of patent infringement.

[0161] The invention is not limited to the specifically disclosed embodiments, but various modifications and variations are possible without departing from the scope of the appended claims.

[0162] In this embodiment, an example has been shown in which the data indicating patent documents included in the collective data is data described in publications such as patent gazettes and unexamined patent publications. However, the data indicating patent documents is not limited to data described in publications. The data indicating patent documents does not have to include data indicating specifications, drawings, abstracts, etc., such as so-called draft claims, as long as it includes text data describing each claim.

[0163] In this embodiment, the text indicating the subject matter of the invention refers to text indicating the object of the invention. More specifically, a phrase that unambiguously represents the invention and is long enough for a user to easily identify the invention is selected from the text of each claim. The text indicating the subject matter of the invention may be the same as the title of the invention, or, in the case of Japanese, may be the same phrase as the wording at the end of each claim, or may be a different phrase from these descriptions. For example, instead of just the wording at the end of each claim, such as "current collector for an electricity storage device," it may also include wording that indicates a specific feature of the invention that can differentiate it from other inventions in the technical field, such as "current collector for an electricity storage device having a coating layer formed thereon."

[0164] If a user can roughly understand the content of an invention just by looking at the text indicating the subject matter of such an invention, he or she can quickly determine whether a claim requires detailed reading before reading the claim description.

[0165] The display control unit 14 may perform control so that key words, new words, etc. in the claims are displayed in an emphasized manner in the constituent element display field 1041 shown in FIG. 5, FIG. 6, or FIG.

[0166] A key term is a term that is used in a claim as an important term related to the essential part of the invention, and for which a detailed explanation is provided below. For example, a key term may be extracted based on the fact that it is repeatedly stated in the claim.

[0167] A new term is a term that is not mentioned in the claims and is used in the description of the invention. New terms may overlap with key terms, and may be limited to terms other than technical terms, general terms, or specialized terms.

[0168] In this case, the analysis unit 13 may extract new words, key words, etc. in the claims based on the description of the specification and the claims, and the display control unit 14 may perform control based on the analysis results to display new words in blue and key words in red, etc., in the constituent element display field 1041 in a color different from the other text colors. By displaying new words, key words, etc. in such an emphasized manner, points to focus on within the claims can be immediately found.

[0169] The information processing device 10 may output the claims broken down into their constituent features in a spreadsheet format such as spreadsheet software. The user can use the output data as is as the source data for research materials, etc.

[0170] Although the information processing device 10, patent document extraction device 20, and terminal device 30 according to this embodiment are shown as separate devices, some or all of these may be realized by the same device.

[0171] The display device 105 and the terminal device 30 are each an example of a display device that displays a screen under the control of the display control unit 14. The display device is not limited to this, and may be a projector, a monitor, or the like as long as it can display a screen.

[0172] In this embodiment, the patent documents and various display screens are in Japanese, but they may be in other languages. For example, in the case of English patent documents, if a trained model 17 specialized for English patent documents is constructed, the reading comprehension support system 1 can be realized in the same manner as in the case of Japanese patent documents.

[0173] This international application also claims priority based on Japanese Patent Application Nos. 2019-230888, 2019-230889, and 2019-230890, filed on December 20, 2019, the entire contents of which are incorporated herein by reference. [Explanation of symbols]

[0174] 1. Reading Comprehension Support System 10. Information processing equipment 11 Storage section 12 Patent Document Acquisition Department 13 Analysis Department 14 Display control unit 15 Evaluation Registration Department 16 Operation reception section 17 Pre-trained models 20 Patent document extraction device 30 Terminal Equipment 40 Network 101 CPU 102 Main storage 103 Auxiliary storage device 104 Input Device 105 Display device 106 Communication interface device 107 Drive device 108 Storage medium 1021 Header 1022 Navigation display column 1023 Claim display field 1024 Evaluation registration column 1025 Text display field 1026 Drawing display column 1031 Status Display 1032 Icon Center 1033 All Claims Button 1034 Independent Claim Button 1038 Split display format switching button 1039 Folding symbol 1040 Claim number display field 1041 Configuration requirements display field 1042 Configuration requirement display field (upper layer) 1043 Configuration requirement display field (lower hierarchy)

Claims

1. an analysis unit that analyzes text data indicating the scope of claims included in the patent document data and identifies constituent features of the invention for each claim included in the scope of claims; a display control unit that divides text indicating each claim of the scope of claims into constituent features and displays the divided text on a display device; the analysis unit, when receiving text data indicating claims, analyzes the text data indicating the claims included in the patent document data using a trained model that outputs a probability that each claim is an independent claim and a probability that each claim is a dependent claim, and identifies dependent relationships of the claims included in the claims; the display control unit causes the display device to display text indicating an independent claim included in the scope of claims based on the identified dependency relationship; Information processing device.

2. the analysis unit further analyzes text data indicating a description included in the patent document data, and further identifies new terms that are used in the description of the invention in the description and that are not described in advance in the claims; the display control unit causes the display device to highlight text indicating the new word in text indicating each claim of the scope of claims, The information processing device according to claim 1 .

3. an operation reception unit that receives an input of an evaluation result by a user regarding the patent document data; an evaluation registration unit that associates the evaluation result with the patent document data and registers it; the display control unit causes the display device to display the evaluation result.

3. The information processing device according to claim 1.

4. The display control unit displays the patent document data analyzed by the analysis unit and the evaluation results registered in the evaluation registration unit on a device used by multiple users. The information processing device according to claim 3 .

5. The display control unit displays the divided components in a diagrammatic form as a structural diagram. The information processing device according to claim 1 .

6. the analysis unit analyzes the text data indicating the claims included in the patent document data, and identifies the subject matter of the invention for each claim included in the claims; the display control unit causes the display device to display the text indicating the subject matter and the claim number in association with each other; The information processing device according to claim 1 .

7. the display control unit switches, in response to a user operation, between a display including the text indicating each claim of the scope of claims and a display not including the text, and causes the display device to display the same; The information processing device according to claim 6 .

8. the analysis unit selects the text indicating the main subject from the text data indicating the claim; 8. The information processing device according to claim 6 or 7.

9. the analysis unit selects a phrase from the text data indicating the claim that uniquely represents the invention and has a length that allows a user to easily identify the invention, and sets the selected phrase as the text indicating the subject matter; 8. The information processing device according to claim 6 or 7.

10. the analysis unit analyzes the text data indicating the claims included in the patent document data to identify dependency relationships of the claims included in the claims; The display control unit, based on the identified dependency relationship, For independent claims, the text indicating each claim in the scope of claims is displayed divided by the constituent features; For dependent claims, the text indicating the subject matter is displayed in association with the claim number, and the display device is prompted to select either a divided display format in which the text indicating each claim divided by the constituent features is displayed, or a divided display format in which the text indicating each claim is not displayed, and the display device is prompted to display the dependent claims in the selected display format. The information processing device according to claim 6 .

11. the analysis unit classifies claims whose dependency relationships are unclear into independent claims in the process of identifying dependency relationships; The information processing device according to claim 1 or 10.

12. The computer a step of analyzing text data indicating the scope of claims included in the patent document data, and identifying constituent features of the invention for each claim included in the scope of claims; a step of dividing the text indicating each claim of the scope of claims into parts for each of the constituent features and displaying the part on a display device; Run The step of identifying includes analyzing the text data indicating the claims included in the patent document data using a trained model that, when inputted, outputs a probability that each claim is an independent claim and a probability that each claim is a dependent claim, thereby identifying the dependency relationships of the claims included in the claims; The displaying step displays text indicating independent claims included in the claims on the display device based on the identified dependency relationships. Reading support methods.

13. The computer a step of analyzing the text data indicating the claims included in the patent document data, and identifying the subject matter of the invention for each claim included in the claims; a step of displaying the text indicating the subject matter and the claim number on the display device in association with each other; The reading support method according to claim 12, further comprising:

14. On the computer, a step of analyzing text data indicating the scope of claims included in the patent document data, and identifying constituent features of the invention for each claim included in the scope of claims; a step of dividing the text indicating each claim of the scope of claims into parts for each of the constituent features and displaying the part on a display device; Execute The step of identifying includes analyzing the text data indicating the claims included in the patent document data using a trained model that, when inputted, outputs a probability that each claim is an independent claim and a probability that each claim is a dependent claim, thereby identifying the dependency relationships of the claims included in the claims; The displaying step displays text indicating independent claims included in the claims on the display device based on the identified dependency relationships. program.

15. The computer, a step of analyzing the text data indicating the claims included in the patent document data, and identifying the subject matter of the invention for each claim included in the claims; a step of displaying the text indicating the subject matter and the claim number on the display device in association with each other; The program according to claim 14, further comprising:

Images