Document-drafting assistance device and program

Abstract

To easily create high-quality patent-office submission documents by providing various assistance information suited to user's intentions.SOLUTION: A document-drafting assistance device 1 of the present invention includes: a document database in which cumulative patent and utility-model document information is stored in a state of being normalized in a standardized data format so as to be adapted to language-model learning for natural-language processing; and an assistance information creation unit 115 that creates assistance information for assisting the drafting of patent-office submission documents by using, according to the content of a prompt, a language model that has been trained and adjusted by combining, based on the document database, one or more types of natural-language processing so as to specialize in drafting patent-office submission documents for patents and utility-models.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a document creation support device and a program. [Background technology]

[0002] Regarding a technology for supporting the preparation of documents to be submitted to the Patent Office, such as patent and utility model applications, Patent Document 1 discloses a technology for updating the related information by associating a specific word before amendment and the amended word when the document creator later amends a word in a first claim that has already been created and the word is amended, and storing words having a higher or lower concept relative to the word before amendment in a memory unit as related information, and by associating a specific word before amendment and the amended word when the document creator later amends a word in a second claim that has already been created and the word is amended, and storing the associated information in a memory unit, and updating the related information, and outputting related information for words entered when creating a third claim based on the updated related information.

[0003] According to the technology of Patent Document 1, when preparing application documents for a patent or utility model, related information such as words with higher or lower concepts relative to the word before amendment is output as support information, thereby assisting the document writer in preparing application documents using appropriate expressions by referring to the support information. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2021-086425 Summary of the Invention [Problem to be solved by the invention]

[0005] However, since the technology of Patent Document 1 uses information generated based on related information that associates words before and after correction as support information, the support information is limited to a range based on the relationship before and after correction. As a result, application documents are created with reference to the limited support information, so there is room for further improvement in terms of easily creating high-quality application documents.

[0006] The present invention has been made in consideration of the above circumstances, and its purpose is to enable a user to easily prepare high-quality documents to be submitted to the Patent Office by providing various support information that meets the user's wishes. [Means for solving the problem]

[0007] As a result of intensive research into solving the above problems, the inventors have found that the above object can be achieved by generating support information for supporting the preparation of documents to be submitted to the Patent Office by utilizing a language model that has been trained and tuned specifically for the preparation of documents to be submitted to the Patent Office for patents and utility models, depending on the content of the prompt.The inventors have then completed the present invention.Specifically, the present invention provides the following.

[0008] The present invention relates to a document database in which document information on patents and utility models is stored in a standardized data format so that the document information can be applied to learning a language model for natural language processing; a support information generating unit that generates support information for supporting the preparation of documents to be submitted to the Patent Office by combining one or more of the natural language processing methods based on the literature database and utilizing a language model that has been trained and adjusted to be specialized for the preparation of documents to be submitted to the Patent Office for patents and utility models in accordance with the content of the prompt; The document creation support device is characterized by having the following features.

[0009] According to a feature of the present invention, a language model for natural language processing specialized for creating documents to be submitted to the Patent Office for patents and utility models is used to generate support information according to the content of the prompt, thereby providing a variety of support information that matches the intentions of the user who entered the content of the prompt, making it easy to create high-quality documents to be submitted to the Patent Office. Effect of the Invention

[0010] According to the present invention, by providing various support information that meets the user's wishes, high-quality documents to be submitted to the Patent Office can be easily prepared. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is an explanatory diagram showing the flow of information in the document creation support device of this embodiment. [Diagram 2] FIG. 2 is a block diagram showing an example of a hardware configuration and a software configuration of the document creation support device of this embodiment. [Diagram 3] FIG. 3 is an explanatory diagram of a display screen showing a user interface. [Figure 4] FIG. 4 is an explanatory diagram of a display screen showing a user interface. [Diagram 5] FIG. 5 is an explanatory diagram of a display screen showing a user interface. [Figure 6] FIG. 6 is an explanatory diagram of a display screen showing a user interface. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, an example of an embodiment of the present invention will be described in detail with reference to the drawings. (Document Creation Support Device 1) As shown in FIG. 1, the document creation support device 1 is configured to generate support information for supporting the creation of documents to be submitted to the Patent Office by utilizing a language model for natural language processing specialized for the creation of documents to be submitted to the Patent Office for patents and utility models.

[0013] As a specific example, the document creation support device 1 has a literature database in which accumulated document information on patents and utility models is stored in a normalized state in a unified data format so that it can be adapted to the learning of a language model for natural language processing, and a support information generation unit 115 that generates support information to support the creation of documents to be submitted to the Patent Office by combining one or more types of natural language processing based on the literature database and utilizing a language model that has been trained and adjusted to be specialized for the creation of documents to be submitted to the Patent Office for patents and utility models, depending on the content of the prompt.

[0014] Here, "patent and utility model document accumulation information" includes domestic documents such as published patent gazettes, published utility model gazettes, and registered gazettes (patent publication gazettes (patent gazettes), registered utility model gazettes), foreign documents such as U.S. patent specifications and international publications, and non-patent documents such as domestic technical magazines and proceedings. Furthermore, "document accumulation information" also includes documents such as opinions, amendments, various decision documents (ex parte trials, inter partes trials), opposition decision documents, and judgment publications. This document accumulation information is information collected from various search sites such as J-PlatPat (registered trademark), a patent information search site, Espacenet (registered trademark), a patent information search site provided by the European Patent Office, and WIPO PatentScope, an international patent information search site, the Intellectual Property High Court's case precedent search site, and data within each patent office.

[0015] "Natural language processing" is a method for enabling a computer to understand text and voice data written in natural language and execute processing according to the purpose. Specifically, examples include morphological analysis, which breaks down natural language into "morphemes," the smallest units that make up the language, and assigns information such as parts of speech; syntactic analysis, which analyzes the grammatical structure of natural language to clarify the structure and meaning of a sentence; semantic analysis, which understands the meaning of words and sentences by analyzing the meaning of natural language, and performs logical judgment and inference; contextual analysis, which understands natural language while considering the context before and after a sentence; and intent analysis, which extracts the intention of a speaker or writer from a conversation or text using natural language. As a result, "natural language processing" processes natural language by combining processes such as morphological analysis, syntactic analysis, semantic analysis, contextual analysis, and intent analysis, and enables the generation of support information that supports the preparation of documents to be submitted to the Patent Office in this embodiment, as well as machine translation, automatic summarization, a question-answering system, and voice recognition.

[0016] A "language model" is a type of probabilistic model used in natural language processing, which is a model for probabilistically predicting how likely a given word or sentence is to occur in natural language. Specifically, a language model calculates the occurrence probability of a given word sequence or sentence, or compares the occurrence probabilities of multiple word sequences or sentences, making it possible to automatically generate the most likely word or sentence based on the context when predicting the next word or sentence.

[0017] "Normalized to a unified data format" means that when dealing with huge amounts of data such as patent documents, information stored in different formats for each document is converted into a common format and organized in a unified manner. For example, patent documents contain various information such as the names of applicants and inventors, application numbers and publication numbers, technical fields, document summaries, and claims, but this information is often stored in different formats for each country, document, or database. This can make it difficult to collect necessary information from multiple databases or handle information in different formats to create a language model for natural language processing, but normalizing to a unified data format makes it easier to search and analyze data. Furthermore, when machine learning is performed on document accumulation information, the efficiency and accuracy of processing can be improved by using normalized data as input. "Normalization" is a processing method for organizing and structuring data in a database table according to certain rules, eliminating data redundancy and maintaining data consistency and consistency.

[0018] In the "literature database," document accumulation information of patents and utility models is stored in a state normalized into a unified data format so that it can be adapted to the learning of a language model for natural language processing. To give a specific example, the specification database 121 storing specification information of patents and utility models, and the intermediate document database 122 storing intermediate document information such as opinion information and amendment information of patents and utility models correspond to the literature database. As a result, even if specifications with different description styles, such as those in Japan and the United States, are collected as document accumulation information, the specification data divided into normalized states such as "problems to be solved" and "embodiments" are stored in each table of the specification database 121, thereby reducing data duplication and improving data consistency. In addition, the tables in the specification database 121 are linked to each other, making it possible to efficiently obtain necessary information.

[0019] "Patent and utility model documents submitted to the Patent Office" are documents submitted to the Patent Office, and examples of such documents include patent and utility model specifications, amendments, opinions, requests for appeal, and patent oppositions. "Language model" refers to a mathematical model in the field of natural language processing that learns language patterns and grammatical rules, and generates and understands natural language. For example, a language model used in creating documents submitted to the Patent Office is one that has been trained specifically for creating documents submitted to the Patent Office, and is used to generate specifications and opinions for patent applications, which are a type of documents submitted to the Patent Office, according to the content of the prompt, and to generate support information for creating specifications and opinions.

[0020] The "learning" in "language model training and tuning" includes supervised learning (e.g., the task of predicting the next word) and unsupervised learning (e.g., the task of learning vector representations of words), etc. Also, "tuning" means evaluating the trained language model and adjusting the parameters of the model, such as weights, as necessary, or appropriately adjusting the values ​​of hyperparameters, such as the number of hidden layers and units of the neural network, the learning rate, and the strength of regularization, to improve the model's performance.

[0021] A "prompt" is information that displays to the user 4 the content to be entered and the operation method, etc., and gives instructions for the user 4 to perform the operation. Examples of "support information to support the preparation of documents to be submitted to the Patent Office" include suggestions for appropriate terminology and expressions when entering the necessary information for documents, suggestions for revisions regarding grammar and expressions, provision of information useful for preparing documents by referring to similar patent documents, etc., and information and suggestions regarding the form and format of documents. Such prompts and support information will be explained in detail in the user interface section below.

[0022] According to the above configuration, a language model for natural language processing specialized for creating documents to be submitted to the Patent Office for patents and utility models is used to generate support information according to the content of the prompt, thereby providing various support information that matches the intentions of user 4 who inputs the content of the prompt, thereby making it easy to create high-quality documents to be submitted to the Patent Office.

[0023] 2, the document creation support device 1 has, in addition to the support information generation unit 115, an activation unit 111, a data collection unit 112, a model learning unit 113, an input processing unit 114, a terminal control unit 116, and a communication unit 13. A part or all of the support information generation unit 115, the activation unit 111, the data collection unit 112, the model learning unit 113, the input processing unit 114, and the terminal control unit 116 may be configured as either hardware or software, and are included in the control unit 11, which is a computer.

[0024] The communication unit 13 is connected to the user terminal 2 operated by the user 4 via the Internet 5 so as to be able to perform data communication. The data communication between the communication unit 13 and the user terminal 2 is not limited to the Internet 5, and may use an information communication network such as a dedicated line or a LAN (Local Area Network), or may use Bluetooth (registered trademark), which is a wireless communication standard for short-distance communication. The data communication between the communication unit 13 and the user terminal 2 may be a dedicated line in order to prevent leakage of highly confidential documents submitted to the Patent Office. Furthermore, when performing data communication via the Internet 5, the communication unit 13 and the user terminal 2 preferably have a VPN (Virtual Private Network) function. When the communication unit 13 and the user terminal 2 are equipped with a VPN function, data communication from the user terminal 2 passes through a VPN connection, so that the data communication is protected from external unauthorized access and secure communication is ensured. The user terminal 2 is an information processing device such as a general personal computer, laptop computer, smartphone, tablet terminal, etc.

[0025] The activation unit 111 has a function of enabling data communication only with authenticated user terminals 2. Specifically, the activation unit 111 has a function of verifying whether an activation signal transmitted from a specific user terminal 2 matches pre-set authentication information. Examples of authentication methods include authentication modes that combine one or more authentication elements, such as password authentication, biometric authentication, one-time password authentication, and smart card authentication using a card with an embedded IC chip. This allows the document creation support device 1 to communicate data only with authenticated user terminals 2, making it difficult to leak highly confidential documents submitted to the Patent Office.

[0026] The data collection unit 112 has a function of collecting document accumulation information on patents and utility models from the patent information search site 6 and the like, normalizing the collected information into a unified data format, and storing it in a document database. As a result, the data collection unit 112 collects and organizes data required for learning and adjusting the language model, and stores it in the document database, thereby enabling the support information generation unit 115 to efficiently and accurately support the creation of documents to be submitted to the Patent Office. The collection of document accumulation information may be performed by the administrator of the document creation support device 1 operating the administrator terminal 7 to access the patent information search site 6 and the like.

[0027] The model learning unit 113 has a function of learning and adjusting a language model for natural language processing based on a document database of patents and utility models. As a result, the model learning unit 113 learns and adjusts the language model to become specialized for creating documents to be submitted to the Patent Office, thereby performing more advanced natural language processing and enabling the support information generation unit 115 to generate high-quality support information to support the creation of documents to be submitted to the Patent Office.

[0028] The input processing unit 114 has a function of converting prompt information indicating the contents of the prompt transmitted from the user terminal 2 into information that is easy to handle for a language model of natural language processing. The terminal control unit 116 has a function of setting the display screen of the user terminal 2 to a screen suitable for creating documents to be submitted to the Patent Office, based on data in the UI database 124 (user interface database 124). Details will be described later.

[0029] Furthermore, the document creation support device 1 has an input device 15 connected to the input reception unit 118 and a display device 14 connected to the display control unit 117. Examples of the input device 15 include a keyboard, a mouse, a touch panel, and a voice input device. Examples of the display device 14 include a liquid crystal display device. This allows the document creation support device 1 to be configured with an information processing device such as a general personal computer, a laptop computer, a smartphone, or a tablet terminal. Note that the document creation support device 1 may lack at least one of the input device 15 and the display device 14. In this case, since the input device 15 and the display device 14 are provided in an external terminal (not shown), the document creation support device 1 can be used as a document creation support server. Furthermore, the document creation support device 1 may be used as a user terminal 2, and the document to be submitted to the Patent Office may be created in the document creation support device 1 while the user 4 receives support information.

[0030] In this embodiment, the case where the functions of the document creation support device 1 are installed in an information processing device is described, but the present invention is not limited to this, and the functions of the document creation support device 1 may be installed in cloud computing. In this case, a large amount of document data can be processed by adding computer resources as needed through cloud computing, enabling faster and more efficient processing, and even if the number of users 4 increases significantly, the processing capacity can be easily expanded to accommodate the increase.

[0031] (Storage unit 12, etc.) As shown in FIG. 1, a specification database 121, an intermediate document database 122 in which documents associated with assessments such as opinions and amendments are stored, and a UI database 124 are stored in the storage unit 12. The storage unit 12 is connected to the document preparation support device 1 so as to be capable of data communication. The storage unit 12 may be configured as a hard disk, or may be configured as a combination of a hard disk and a memory. In the case of a combination of a hard disk and a memory, a part of data and indexes used by the database is cached in the memory as necessary, thereby making it possible to speed up access to the database. In addition, the storage unit 12 also stores a user database 123 in which various information including identification information for identifying the user 4 and authentication information for authenticating the user 4 is stored. The activation unit 111 is configured to execute processing such as authentication processing based on the data in the user database 123.

[0032] The storage unit 12 may be a data server connected to an information communication network such as the Internet 5, separate from the document creation support device 1. The storage unit 12 may be composed of a plurality of data servers provided for each database.

[0033] (User Interface) As shown in FIG. 3, the terminal control unit 116 has a function of setting the display screen of the user terminal 2 to a screen suitable for creating documents to be submitted to the Patent Office based on the UI database 124. To explain a specific example, the terminal control unit 116 has a function of controlling the display screen 21 of the user terminal 2 to display a prompt unit 212 that receives the contents of a prompt, a support information unit 213 that displays the support information generated by the support information generation unit 115, and a document creation unit 211 that is a creation area for documents to be submitted to the Patent Office. This allows the user 4 using the user terminal 2 to simultaneously check the contents of the prompt unit 212 and the support information of the support information unit 213 while creating documents to be submitted to the Patent Office, so that the user 4 can easily proceed with the creation of documents to be submitted to the Patent Office. Note that the user terminal 2 may display entry items in a format conforming to the rules on the document creation unit 211 at the start of creating documents to be submitted to the Patent Office, such as a specification.

[0034] Furthermore, as shown in FIG. 4, the terminal control unit 116 has a function of enabling the user to specify a standard phrase indicating a predetermined instruction content such as a similar word, an antonym, or a role, and controlling the display of a prompt operation unit 214 on the display screen 21 of the user terminal 2, which combines the specified standard phrase with a word specified in the document creation unit 211 to form the content input to the prompt unit 212.

[0035] For example, when the "predetermined instruction content" includes multiple instruction elements such as a synonym, a superordinate concept, an antonym, and a role, a standard phrase including these instruction elements is made into a button, and a first instruction button 2141 for a standard phrase having a synonym as an instruction content, a second instruction button 2142 for a standard phrase having a superordinate concept as an instruction content, a third instruction button 2143 for a standard phrase having an antonym as an instruction content, and a fourth instruction button 2144 for a standard phrase having a role as an instruction content are displayed on the prompt operation unit 214. For example, when the phrase "A spring is provided between the top board and the base" is written on the document creation unit 211, if the user 4 drags the word "spring" to the first instruction button 2141 while designating the word "spring" or clicks the first instruction button 2141 after designating the word "spring", the word "spring" is stored in the memory of the user terminal 2 and is combined with the prompt data of the standard phrase associated with the first instruction button 2141 that was previously stored in the memory. The synthesized data is then displayed in the prompt section 212 of the user terminal 2 .

[0036] As a result, the prompt section 212 displays information combining a phrase and a fixed phrase, such as "Please give examples of similar words to rubber," as the content of the prompt. The content of this prompt is transmitted to the document creation support device 1, and the support information generation section 115 generates support information such as "(examples of similar words) spring, coil, damper." This support information is transmitted to the user terminal 2 and displayed in the support information section 213, so that the user 4 can proceed with writing the specification as examples of similar words to springs while visually checking or copying and pasting the support information in the support information section 213. As a result, the user 4 using the user terminal 2 can easily proceed with the creation of documents to be submitted to the Patent Office, since the information combining the specified instruction content and the specified phrase becomes the content input to the prompt section 212 while creating documents to be submitted to the Patent Office.

[0037] Furthermore, as shown in Figures 5 and 6, the terminal control unit 116 has a function of allowing the user to specify a standard phrase indicating a predetermined instruction content, and controlling the display of a prompt operation unit 214 on the display screen 21 in which information combining the specified standard phrase with a phrase including a word specified in the document creation unit 211 is treated as the content input to the prompt unit 212.

[0038] As a specific example, when the phrase "A spring is provided between the top board and the base" is written in the document creation unit 211, if the user 4 designates the word "spring" and drags it to the fourth instruction button 2144, or if the user 4 designates the word "spring" and clicks the fourth instruction button 2144, the phrase including the word "spring" is stored in the memory of the user terminal 2 and is synthesized with the standard phrase prompt data associated with the fourth instruction button 2144 that has been stored in advance in the memory. The synthesized data is then displayed in the prompt unit 212 of the user terminal 2.

[0039] As a result, the prompt section 212 displays the phrase "A spring is provided between the top plate and the base" and the phrase "Please give an example of a similar word to "rubber" in the text." as the contents of the prompt. The contents of this prompt are transmitted to the document creation support device 1, and the support information generation section 115 generates the support information "In the context of "A spring is provided between the top plate and the base," the role of the spring is to generate tension between the top plate and the base and support the top plate. The spring can be deformed by compression or extension, and its elastic force causes the top plate to..." as the contents of the prompt. This support information is transmitted to the user terminal 2 and displayed in the support information section 213, so that the user 4 can proceed with writing the specification as the role of the spring while visually checking or copying and pasting the support information in the support information section 213. As a result, during the creation of documents to be submitted to the Patent Office, information combining a predetermined instruction content and a phrase including a specified word is input to the prompt section 212, and since an appropriate answer can be obtained from the context of the phrase, the creation of documents to be submitted to the Patent Office can be further facilitated.

[0040] Furthermore, the terminal control unit 116 may have a function of making the user interface of the user terminal 2 into the following configurations 1 to 6. (Configuration 1) While writing a sentence in the document creation unit 211, the timing at which a phrase, a phrase, or a paragraph is finished may be automatically detected, and text information of the phrase, phrase, or paragraph may be transferred to the prompt unit 212 at these timings, and the text following the text information may be inferred in the document creation support device 1 and displayed as support information in the support information unit 213. At this time, a portion of the document creation unit 211 corresponding to the text information transferred to the prompt unit 212 may be highlighted. In this case, the user 4 can easily determine which phrase, phrase, or paragraph the support information corresponds to. Instead of automatically detecting the timing at which a phrase, phrase, or paragraph is finished, a fifth instruction button may be provided, and support information in which the text following the phrase, phrase, or paragraph is inferred may be displayed when the fifth instruction button is clicked.

[0041] (Configuration 2) The document creation section 211 may be provided with a sixth instruction button for requesting advice on the preparation of a patent or utility model specification based on the invention information such as the input outline of the invention and the documents of the invention. For example, when documents for a meeting are input and the sixth instruction button is clicked, the document creation support device 1 extracts and summarizes important points in the documents and displays them as support information in the support information section 213. Also, when the sixth instruction button is clicked, for example, "Please read the following document 1 and tell us what you think is not known to a person skilled in the art. (Line break x 2) (Document 1 body)" is displayed in the prompt section 212, and support information in which important points that may be novel are listed in bullet points spaced every two lines is displayed in the support information section 213. Next, when the sixth instruction button is clicked, "Please read the following document 1 and tell us what you think is well known to a person skilled in the art. (Line break x 2) (Document 1 body)" is displayed in the prompt section 212, and support information in which important points that may be inventive are listed in bullet points spaced every two lines is displayed in the support information section 213.

[0042] Furthermore, when the user 4 considers and inputs the points of the invention with reference to the support information (important points) and then clicks the sixth instruction button, the document creation support device 1 extracts prior art documents from the specification database 121, identifies elements that may be novel and have an inventive step and elements that are suspected to be well-known art, and displays each element as support information. In addition, in the configuration 2, in order to improve the operability of the user 4, a user interface is provided in which the novelty extraction process, the inventive step extraction process, and the element evaluation process are performed successively by successively clicking the sixth instruction button, but this is not limited to this, and an instruction button may be provided for each evaluation process. In addition, each time the sixth instruction button is clicked, multiple types of prompt contents indicating the novelty extraction process, the inventive step extraction process, and the element evaluation process may be displayed in the prompt section 212 so as to be selectable.

[0043] (Configuration 3) The document creation section 211 may be provided with a seventh instruction button for creating a proposed claim. For example, when the invention points are input and the seventh instruction button is clicked, the document creation support device 1 generates a proposed claim based on the specification database 121 and displays it as support information. Furthermore, when the proposed claim is input and the seventh instruction button is clicked, a proposed overall configuration of the specification may be displayed as support information. Specifically, when the proposed claim is input and the seventh instruction button is clicked, "Please show us the proposed overall configuration of the specification corresponding to the following claims. (Line break x 2) (Claims)" is displayed in the prompt section 212, and support information showing the proposed overall configuration of the specification is displayed in the support information section 213. Furthermore, when the seventh instruction button is clicked, "Please show us an example of the description of the following components in the embodiment. If there are any parts where the materials should be referred to, please also tell us. (Line break x 2) (Components shown in the proposed overall configuration)" is displayed in the prompt section 212, and the description example of the embodiment and the reference parts of the materials are displayed in the support information section 213.

[0044] Furthermore, when the seventh instruction button is clicked after the user terminal 2 creates a proposed claim, the prompt section 212 may display "Please check whether the claims below are in a format including symbols. (2 line breaks) (claims)," and the check result may be displayed in the support information section 213, or the prompt section 212 may display "Please provide a candidate for a superordinate term for each term in the claims below. (2 line breaks) (claims)," and the candidate for a superordinate term may be displayed in the support information section 213. Note that, instead of the seventh instruction button, separate instruction buttons may be provided according to the contents of each prompt. Furthermore, when the seventh button is clicked, the contents of multiple types of prompts may be displayed so as to be selectable.

[0045] (Configuration 4) The document creation unit 211 may be provided with an eighth instruction button for checking the format, grammar, etc. of the specification and for checking inconsistencies in terminology, symbols, etc. For example, when the eighth instruction button is clicked during or after the specification is created, the document creation support device 1 checks the format, grammar, etc. of the specification and for checking inconsistencies in terminology, symbols, etc., and displays the results as support information. Furthermore, suggested modifications to various check targets may be displayed as support information.

[0046] (Configuration 5) The document preparation section 211 may be provided with a ninth instruction button for checking whether the proposed amendments and draft opinion can resolve the reasons for refusal (whether opinions are written for all the reasons for refusal, etc.). Specifically, when the ninth instruction button is clicked, "Please summarize and memorize the following notice of reasons for refusal. (Line break x 2) (Notice of reasons for refusal)" and "Please check whether the following draft opinion can resolve the reasons for refusal notified in the notice of reasons for refusal that you have just memorized. Please also indicate the proposed amendments. (Line break x 2) (Draft opinion)" are displayed in the prompt section 212, and the check result and the proposed amendments are displayed in the support information section 213.

[0047] (Configuration 6) The document creation section 211 may be provided with a tenth instruction button for generating a draft drawing such as a flowchart or block diagram or a draft data table corresponding to the content of the input claim or a part of the content of the specification, or may be provided with a tenth instruction button for generating a draft claim or a draft specification corresponding to the content of the drawing such as a flowchart or block diagram or the data table.

[0048] (Document preparation support program) The activation unit 111, the data collection unit 112, the model learning unit 113, the input processing unit 114, the support information generation unit 115, the terminal control unit 116, the display control unit 117, and the input reception unit 118 may be configured as either hardware or software. Each of these units 111 to 118 constitutes at least a part of the control unit 11. When each of the units 111 to 118 is configured as software, the control unit 11 is made to execute a document creation support program that generates support information for supporting the creation of documents to be submitted to the Patent Office by utilizing a language model for natural language processing specialized for the creation of documents to be submitted to the Patent Office for patents and utility models.

[0049] As a specific example, the document preparation support program is a program for executing a display processing step (S1) in which a computer of a user terminal 2, which is a terminal device accessible to a document preparation support device 1 having a document database in which document accumulation information of patents and utility models is stored in a state normalized in a unified data format so as to be adapted to the learning of a language model for natural language processing, and a support information generating unit 115 that generates support information for supporting the creation of documents to be submitted to the Patent Office by utilizing a language model that has been learned and adjusted to be specialized for the creation of documents to be submitted to the Patent Office for patents and utility models based on the document database and that combines one or more types of natural language processing based on the document database, according to the content of a prompt, to display on the user terminal 2 a prompt unit 212 that receives the content of the prompt, a support information unit 213 that displays the support information generated by the support information generating unit 115, a document preparation unit 211 that is an area for creating documents to be submitted to the Patent Office, and a prompt operation unit 214 that allows a user 4 to specify a fixed phrase indicating a predetermined instruction content. According to the above program, the content of the prompt unit and various support information in the support unit can be simultaneously confirmed while creating documents to be submitted to the Patent Office.

[0050] The document creation support program may also have a configuration for causing the computer of the user terminal 2 to execute a prompt operation step (S2) for, when a phrase is specified in the document creation unit 211 and a fixed phrase is specified in the prompt operation unit 214, setting information combining the specified fixed phrase and the phrase specified in the document creation unit 211 as the content input to the prompt unit 212. According to the above program, during the creation of documents to be submitted to the Patent Office, information combining a predetermined instruction content and the specified phrase is set as the content input to the prompt unit 212, so that it is possible to easily proceed with the creation of high-quality documents to be submitted to the Patent Office.

[0051] Furthermore, the document creation support program may have a configuration for causing the computer of the user terminal 2 to execute processing steps that realize various functions of the terminal control unit 116.

[0052] According to the document preparation support program configured as described above, the user 4 can be supported in various forms of highly accurate preparation of documents to be submitted to the Patent Office, so that documents to be submitted to the Patent Office can be prepared quickly and with high quality. Furthermore, by simply installing the program in an information processing device such as a personal computer or a tablet terminal, the information processing device can function as the document preparation support device 1. The program may be distributed in a state recorded on a recording medium such as a CD-ROM or a USB memory, or may be distributed via a two-way communication network or communication line such as the Internet or a one-way communication network such as a television broadcast.

[0053] (Document preparation support method) A part or all of the steps in the document creation support program may be configured by hardware. That is, the user terminal 2 accessible to the document creation support device 1 may be configured to execute the document creation support method. Specifically, the document creation support method is executed in the user terminal 2 accessible to the document creation support device 1 having a document database in which document accumulation information of patents and utility models is stored in a state normalized to a unified data format so as to be adapted to learning of a language model for natural language processing, and a support information generating unit 115 that generates support information for supporting the creation of documents to be submitted to the Patent Office by combining one or more types of natural language processing based on the document database and using a language model that has been learned and adjusted to be specialized for the creation of documents to be submitted to the Patent Office for patents and utility models according to the contents of a prompt, and has a display processing step (S1). Furthermore, the document creation support method may have a prompt operation step (S2) or a processing step for realizing various functions of the terminal control unit 116.

[0054] In the above description, the document creation support device 1 that generates support information by utilizing a language model for natural language processing specialized for creating documents to be submitted to the Patent Office for patents and utility models has been described, but the present invention is not limited to this. That is, the terminal control unit 116 that sets the user interface may be provided in a document creation support device that generates support information using a language model for general-purpose natural language processing such as chat GPT, and a document creation support program or document creation support method may be applied to a user terminal 2 that can access such a document creation support device.

[0055] Specifically, a document creation support device that is capable of data communication with information sources such as websites and databases via the Internet 5 and generates support information by utilizing a language model for general-purpose natural language processing in accordance with the contents of a prompt may be provided with a terminal control unit 116 that sets a user interface for a user terminal 2. The document creation support program may be a program that causes a computer of the user terminal 2 that is capable of data communication with the document creation support device that generates support information using a language model for general-purpose natural language processing to execute various processing steps of this embodiment. The document creation support method may be a method executed in a user terminal 2 that is capable of data communication with the document creation support device that generates support information using a language model for general-purpose natural language processing.

[0056] It should be noted that within the scope of the concept of the present invention, a person skilled in the art may come up with various modifications and alterations. It is understood that such modifications and alterations fall within the scope of the present invention. For example, even if a person skilled in the art appropriately adds, deletes, or modifies the design of the above-described embodiment, or adds, omits, or modifies the conditions of a process, these modifications and alterations are included in the scope of the present invention as long as they include the gist of the present invention. [Explanation of symbols]

[0057] 1 Document creation support device 11 Control section 111 Activation Department 112 Data Collection Unit 113 Model Learning Department 114 Input Processing Unit 115 Support information generation section 116 Terminal control unit 117 Display control section 118 Input reception section 12 Storage section 121 Specification Database 122 Interim Document Database 123 User Database 124 UI Database 13. Communications Department 14 Display device 15 Input Devices 2. User terminal 21 Display screen 211 Document Preparation Department 212 Prompt section 213 Support Information Department 214 Prompt Operation Unit 4 User 5. Internet 6 Patent information search site 7 Administrator terminal

Claims

1. A literature database in which accumulated patent and utility model literature information is stored in a normalized state in a unified data format so that it can be adapted for training language models for natural language processing, A support information generation unit generates support information to assist in the preparation of patent and utility model submission documents to the Japan Patent Office by utilizing a language model according to the content of the prompt, A terminal control unit controls the display of a prompt unit that receives the content of the prompt, a support information unit that displays the support information generated in the support information generation unit, and a document creation unit that is the area for creating the documents to be submitted to the Japan Patent Office, on the user terminal. It has, The aforementioned document database includes a specification database storing patent and utility model specification information, and an intermediate document database storing intermediate document information including opinion information or amendment information. The language model is specialized for preparing patent office submissions by combining one or more of the morphological analysis, syntactic analysis, semantic analysis, contextual analysis, and intent analysis processes in natural language processing based on the document storage information in the specification database and the intermediate document database, probabilistically predicting how likely a word or sentence given by a prompt is to occur in natural language, and by being trained and adjusted to generate support information in response to the prompt to assist in the preparation of the patent office submission documents. The support information generation unit generates support information including, in accordance with the content of the prompt input to the prompt unit, a draft claim based on the points of invention, a draft overall structure of the specification corresponding to the draft claim, examples of descriptions and references to materials in embodiments of the components shown in the draft overall structure, the result of checking whether the draft claim is in a format that includes reference numerals, or candidate words that represent higher-level concepts for each term in the draft claim, and displays this information on the support information unit. Document creation support device.

2. The terminal control unit is configured to display instruction buttons on the document creation unit, The content of the prompt entered into the prompt unit is entered in response to the operation of the instruction button. The document creation support device according to claim 1.

3. The terminal control unit displays a selection of multiple types of content on the prompt unit in response to the operation of the instruction button. The document creation support device according to claim 2.

4. A literature database in which accumulated patent and utility model literature information is stored in a normalized state in a unified data format so that it can be adapted for training language models for natural language processing, A support information generation unit generates support information to assist in the preparation of patent and utility model submission documents to the Japan Patent Office by utilizing a language model according to the content of the prompt, It has, The aforementioned document database includes a specification database storing patent and utility model specification information, and an intermediate document database storing intermediate document information including opinion information or amendment information. The language model, based on the document storage information in the specification database and the intermediate document database, combines one or more of the morphological analysis, syntactic analysis, semantic analysis, contextual analysis, and intent analysis processes in natural language processing to probabilistically predict how likely a word or sentence given in a prompt is to occur in natural language, and is learned and adjusted to generate support information in response to the prompt to assist in the creation of the patent office submission documents, thereby providing a computer on a user terminal that has access to a document creation support device specifically designed for creating patent office submission documents. A display processing step that causes the user terminal to display a prompt unit that receives the content of the prompt, a support information unit that displays the support information generated in the support information generation unit, and a document creation unit that is the area for creating the documents to be submitted to the Japan Patent Office. The steps include generating support information in the support information unit, which includes, in accordance with the content of the prompt entered in the prompt unit, a draft claim based on the points of invention, a draft overall structure of the specification corresponding to the draft claim, examples of descriptions and references to materials in embodiments of the components shown in the draft overall structure, the result of checking whether the draft claim is in a format that includes reference numerals, or candidate words that represent higher-level concepts for each term in the draft claim, and displaying this information in the support information unit; A program to execute.

Images