Information processing system and operation method of information processing system

Abstract

Provided are: an information processing system excellent in convenience and usefulness; and an operation method for the same. The information processing device has functions of: receiving a divisional examination instruction; acquiring patent family data corresponding to application information input by the divisional examination instruction; creating claim classification data in which claim data included in the patent family data is classified into one or more claim groups; and outputting, as a division candidate group, a claim group without an application in a divisional examination country in the claim classification data.

Description

Information processing system and operation method of information processing system

[0001] One aspect of the present invention relates to an information processing system and an information processing method.

[0002] Note that one embodiment of the present invention is not limited to the above technical field. The technical field of one embodiment of the invention disclosed in this specification relates to an object, a method, or a manufacturing method. Alternatively, one embodiment of the present invention relates to a process, a machine, a manufacture, or a composition of matter. Therefore, more specifically, examples of the technical field of one embodiment of the present invention disclosed in this specification include a data processing device, a semiconductor device, a memory device, a driving method thereof, or a manufacturing method thereof.

[0003] After a patent applicant files a patent application with the Japan Patent Office, if that patent application includes two or more inventions, they can file a part of that application as a new patent application, which is called a divisional application. Other countries also have a similar system, which is sometimes called a continuation application.

[0004] In addition, patent applications in other countries that claim priority from the "first patent application" (also called the basic application), as well as their divisional and continuation applications, are collectively referred to as a patent family. In the practice of patent management, it is important to understand the status of a patent family, and systems that assist in this are being considered (Patent Document 1).

[0005] In recent years, the development of language models using neural networks has been actively carried out, and large-scale language models (LLMs) in particular have attracted attention. A large-scale language model is a natural language processing model trained using a large amount of data. A large-scale language model can realize, for example, a dialogue model that responds to user instructions. Non-Patent Document 1 discloses GPT-4 (registered trademark) (Generative Pre-trained Transformer 4) as a large-scale language model and ChatGPT as a dialogue model. In addition to the above, other large-scale language models include LaMDA (Language Model for Dialogue Applications), PaLM (Pathways Language Model), Llama2, and Llama3.

[0006] JP 2002-207865

[0007] Summary of ChatGPT / GPT-4 Research and Perspective Towards the Future of Large Language Models, Yiheng Liu et al. (Submitted on 4 Apr 2023, [online], Internet <URL: https: / / arxiv.org / abs / 2304.01852>

[0008] When considering filing a divisional application in a certain country, the grant status and prosecution status of related patents in the same patent family may be taken into consideration.

[0009] For example, a divisional application may be filed with the same content as the family patent, if the patent has not already been filed in the country where the divisional application is filed (the country under consideration for division), by researching family patents that have already been granted in other countries. Conducting such a search when filing a divisional application requires a great deal of effort and time.

[0010] Therefore, an object of one embodiment of the present invention is to provide a system for proposing claims for a divisional application by referring to the grant status and prosecution status of related patents included in a patent family. Alternatively, an object of one embodiment of the present invention is to provide an information processing device that enables a user to perform intellectual property work with little effort.

[0011] Another object of one embodiment of the present invention is to provide a novel information processing system with excellent convenience, usefulness, or reliability, a novel information processing method with excellent convenience, usefulness, or reliability, or a novel information processing system, a novel information processing method, or a novel semiconductor device.

[0012] Note that the description of these problems does not preclude the existence of other problems. Note that one embodiment of the present invention does not necessarily solve all of these problems. Note that problems other than these will become apparent from the description of the specification, drawings, claims, etc., and it is possible to extract other problems from the description of the specification, drawings, claims, etc.

[0013] One aspect of the present invention is a method for operating an information processing system, comprising: a first step of receiving a division consideration instruction; a second step of acquiring patent family data corresponding to the application information input in the division consideration instruction; a third step of creating a prompt for creating divided claim data from the specification data and claim data contained in the patent family data, the divided claim data including technical features contained in the specification data but not contained in the claim data; a fourth step of creating the divided claim data in a language model based on the instructions of the prompt; and a fifth step of outputting the divided claim data.

[0014] Alternatively, one aspect of the present invention includes a first step of receiving a division consideration instruction, a second step of acquiring patent family data corresponding to the application information input in the division consideration instruction, a third step of creating a first prompt for creating permitted matter analysis data for each claim for which patent registration is permitted from the prosecution history data and claim data included in the patent family data, a fourth step of creating the permitted matter analysis data in a language model based on the instruction of the first prompt, and a second step of creating first divided claim data by deleting one technical feature from the claim data when the permitted matter analysis data does not include a permitted matter that is a technical feature that is a permitted element. a fifth step of creating a prompt in the language model based on the instructions of the second prompt; a sixth step of creating first divided claim data in the language model based on the instructions of the second prompt; a seventh step of creating a third prompt for creating second divided claim data from the specification data and claim data included in the patent family data if the first divided claim data cannot be created in the sixth step, the second divided claim data including technical features included in the specification data but not included in the claim data; an eighth step of creating the second divided claim data in the language model based on the instructions of the third prompt; and a ninth step of outputting the second divided claim data.

[0015] Alternatively, one aspect of the present invention is a method for operating an information processing system, comprising: a first step of receiving a division consideration instruction; a second step of acquiring patent family data corresponding to the application information input in the division consideration instruction; a third step of extracting a second technical feature corresponding to a subordinate concept of a first technical feature included in the claim data from the specification data and claim data included in the patent family data, and creating a prompt for creating divided claim data including the second technical feature; a fourth step of creating divided claim data in a language model based on the instructions of the prompt; and a fifth step of outputting the divided claim data.

[0016] Alternatively, one aspect of the present invention is a method for operating an information processing system, comprising: a first step of receiving a division consideration instruction; a second step of acquiring patent family data corresponding to the application information input in the division consideration instruction; a third step of extracting, from the specification data and claim data included in the patent family data, a second technical feature corresponding to a subordinate concept of a first technical feature included in the claim data, and creating a first prompt for creating first divided claim data including the second technical feature; a fourth step of creating the first divided claim data in a language model based on the instruction of the first prompt; a fifth step of outputting the divided claim data; a sixth step of receiving an instruction to modify the divided claim data in the form of text; a seventh step of modifying the first divided claim data based on the text and creating a second prompt for creating second divided claim data; an eighth step of creating second divided claim data in the language model based on the instruction of the second prompt; and a ninth step of outputting the second divided claim data.

[0017] Alternatively, one aspect of the present invention is an information processing system having a first component, a second component, and a third component, wherein the first component has a function of accepting a division consideration instruction, the second component has a function of obtaining patent family data corresponding to application information input in the division consideration instruction, a function of creating a first prompt including the patent family data, a function of sending the first prompt to the third component, a function of receiving divided claim data from the third component, and a function of sending the divided claim data to the first component, and the third component has a function of creating divided claim data from the specification data and claim data included in the patent family data based on the instructions of the first prompt, the divided claim data including technical features included in the specification data but not included in the claim data, and the divided claim data is output from the first component.

[0018] Alternatively, one aspect of the present invention is a system having a first component, a second component, and a third component, the first component having a function of receiving a division consideration instruction, the second component having a function of acquiring patent family data corresponding to application information input in the division consideration instruction, a function of creating a first prompt including the patent family data, a function of sending the first prompt to the third component, a function of receiving from the third component permitted matter analysis data created for each claim for which patent registration is permitted from the prosecution history data and claim data included in the patent family data, a function of creating a second prompt when the permitted matter analysis data does not include a permitted matter that is a technical feature that is an permitted element, a function of sending the second prompt to the third component, a function of receiving a processing result of the second prompt, and a function of transmitting the second prompt to the third component. an information processing system having a function of creating a third prompt when the first divided claim data is not included in the processing result of the prompt, a function of sending the third prompt to a third component, a function of receiving second divided claim data from the third component, and a function of sending the second divided claim data to the first component, wherein the third component has a function of creating permission analysis data based on the instructions of the first prompt, a function of creating first divided claim data by deleting one technical feature from the claim data based on the instructions of the second prompt, and a function of creating second divided claim data from the specification data and claim data included in the patent family data based on the instructions of the third prompt, the second divided claim data including a technical feature that is included in the specification data but not included in the claim data, and the second divided claim data is output from the first component.

[0019] Alternatively, one aspect of the present invention is an information processing system having a first component, a second component, and a third component, wherein the first component has a function of accepting a division consideration instruction, the second component has a function of obtaining patent family data corresponding to application information input in the division consideration instruction, a function of creating a first prompt including the patent family data, a function of sending the first prompt to the third component, a function of receiving divided claim data from the third component, and a function of sending the divided claim data to the first component, and the third component has a function of extracting a second technical feature corresponding to a subordinate concept of a first technical feature included in the claim data from the specification data and claim data included in the patent family data based on the instructions of the first prompt, and creating divided claim data including the second technical feature, and the divided claim data is output from the first component.

[0020] Alternatively, one aspect of the present invention is an information processing system having a first component, a second component, and a third component, wherein the first component has a function of accepting a division consideration instruction, the second component has a function of obtaining patent family data corresponding to application information input in the division consideration instruction, a function of creating a first prompt including the patent family data, a function of sending the first prompt to the third component, a function of receiving from the third component claim classification data that classifies claim data included in the patent family data by technical feature based on the instructions of the first prompt, and a function of sending the division candidate group to the first component if the claim classification data contains a division candidate group that does not have a patent application in a country under consideration for division, and the third component has a function of creating claim classification data and a function of sending the claim classification data to the second component, and the division candidate group is output from the first component.

[0021] In the above, the claim classification data can be created using the claim data of registered patents, the claim data for which a patent decision has been made, and the data for claims for which no reasons for rejection have been indicated, which are contained in the patent family data.

[0022] Alternatively, one aspect of the present invention is an information processing system having a first component, a second component, and a third component, wherein the first component has a function of accepting a division consideration instruction, the second component has a function of acquiring patent family data corresponding to application information input in the division consideration instruction, a function of creating a first prompt including the patent family data, and a function of sending the first prompt to the third component, a function of receiving from the third component permitted item analysis data that extracts permitted items, which are technical features that are permitted elements, for each claim for which patent registration has been granted from the prosecution history data and claim data included in the patent family data, and a function of sending, if there are multiple permitted items in the permitted item analysis data, divided claim data from which at least one of the multiple permitted items has been excluded to the first component, and the third component has a function of creating permitted item analysis data based on instructions from the first prompt and a function of sending claim classification data to the second component, and the divided claim data is output from the first component.

[0023] Alternatively, one aspect of the present invention is a system having a first component, a second component, and a third component, the first component having a function of receiving a division consideration instruction, the second component having a function of acquiring patent family data corresponding to application information input in the division consideration instruction, a function of creating a first prompt including the patent family data, a function of sending the first prompt to the third component, a function of receiving from the third component permitted matter analysis data created for each claim for which patent registration has been granted from the prosecution history data and claim data included in the patent family data, and a function of extracting permitted elements in the permitted matter analysis data. and a function for transmitting the second prompt to a third component when the claim data does not include a permission item that is a technical feature specified in the claim data, the third component having a function for generating permission item analysis data based on instructions from the first prompt, a function for transmitting claim classification data to the second component, and a function for generating divided claim data by deleting one technical feature from the claim data based on instructions from the second prompt, the divided claim data being output from the first component.

[0024] Alternatively, one aspect of the present invention has a first component, a second component, and a third component, the first component having a function of receiving a division consideration instruction, the second component having a function of acquiring patent family data corresponding to application information input in the division consideration instruction, a function of creating a first prompt including the patent family data, a function of sending the first prompt to the third component, a function of receiving from the third component, permitted matter analysis data created for each claim for which patent registration has been granted from the prosecution history data and claim data included in the patent family data, and a function of identifying technical patents that are permitted elements in the permitted matter analysis data. The information processing system has a function of creating a second prompt when the claim data contains only one permitted item that is a characteristic, a function of sending the second prompt to a third component, a function of receiving divided claim data from the third component, and a function of sending the divided claim data to the first component, wherein the third component has a function of creating permitted item analysis data based on instructions from the first prompt, a function of sending claim classification data to the second component, and a function of creating divided claim data by deleting one technical feature other than the permitted items from the claim data based on instructions from the second prompt, and the divided claim data is output from the first component.

[0025] According to one aspect of the present invention, it is possible to provide a system for proposing claims for a divisional application by referring to the grant status and prosecution status of related patents included in a patent family, or to provide an information processing device that enables a user to perform intellectual property work with little effort.

[0026] According to one embodiment of the present invention, a novel information processing system with excellent convenience, usefulness, or reliability can be provided. Alternatively, a novel information processing method with excellent convenience, usefulness, or reliability can be provided. Alternatively, a novel information processing system, a novel information processing method, or a novel semiconductor device can be provided.

[0027] Note that the description of these effects does not preclude the existence of other effects. Note that one embodiment of the present invention does not necessarily have all of these effects. Note that effects other than these will become apparent from the description in the specification, drawings, claims, etc., and it is possible to extract other effects from the description in the specification, drawings, claims, etc.

[0028] FIG. 1 is a diagram illustrating the configuration of an information processing system. FIG. 2 is a diagram illustrating an information processing method. FIG. 3A is a diagram illustrating an example of input to the information processing system, and FIG. 3B is a diagram illustrating an example of output from the information processing method. FIG. 4 is a diagram illustrating the information processing method. FIG. 5 is a diagram illustrating the information processing method. FIG. 6 is a diagram illustrating the configuration of an information processing system. FIG. 7 is a diagram illustrating the configuration of an information processing system. FIG. 8 is a diagram illustrating the configuration of an information processing device. FIG. 9 is a diagram illustrating the information processing method. FIG. 10 is a diagram illustrating the information processing method. FIG. 11 is a diagram illustrating the configuration of an information processing system. FIG. 12 is a diagram illustrating the information processing method. FIG. 13A is a diagram illustrating an example of input to the information processing system, and FIG. 13B is a diagram illustrating an example of output from the information processing method. FIGS. 14A and 14B are diagrams illustrating examples of output from the information processing method. FIG. 15 is a diagram illustrating an example of output from the information processing method. FIG. 16 is a diagram illustrating the information processing method. FIG. 17 is a diagram illustrating the information processing method. Fig. 18A is a diagram for explaining an example of input to the information processing system, Fig. 18B is a diagram for explaining an example of output from the information processing method, and Fig. 19 is a diagram for explaining the configuration of the information processing system.

[0029] The embodiments will be described in detail with reference to the drawings. However, the present invention is not limited to the following description, and it will be readily understood by those skilled in the art that various changes can be made in the form and details without departing from the spirit and scope of the present invention. Therefore, the present invention should not be interpreted as being limited to the description of the embodiments shown below.

[0030] In this specification, the words "first" and "second" may be used for the convenience of understanding the technical content or to identify each component. Therefore, the words "first" and "second" do not limit the number of each component. Furthermore, the words "first" and "second" do not limit the order of each component. Furthermore, the words "first" and "second" or identifying symbols used in this specification may not match the words or identifying symbols in the claims.

[0031] The embodiments will be described in detail with reference to the drawings. However, the present invention is not limited to the following description, and it will be readily understood by those skilled in the art that various changes in form and details can be made without departing from the spirit and scope of the present invention. Therefore, the present invention should not be interpreted as being limited to the description of the embodiments shown below. In the configuration of the invention described below, the same parts or parts having similar functions will be denoted by the same reference numerals in different drawings, and repeated explanations will be omitted.

[0032] In the drawings accompanying this specification, components are classified by function and shown as block diagrams that are independent of each other, but in reality, it is difficult to completely separate components by function, and one component may be involved in multiple functions.

[0033] Embodiment 1 In this embodiment, an information processing system and an information processing method (a method for operating the information processing system) according to one embodiment of the present invention will be described with reference to FIGS.

[0034] FIG. 1 is a diagram illustrating a configuration of an information processing system according to one embodiment of the present invention.

[0035] 1, the information processing system described in this embodiment includes an information processing device 10 and an information processing device 40. The information processing device 10 and the information processing device 40 are connected via a network 30, and can transmit and receive document data and the like.

[0036] The information processing system described in this embodiment may be configured so that a user can input documents and the like by directly operating the information processing device 10, or may be configured so that a user can input documents and the like using the information processing device 10 and an information terminal 20 connected via a network 30, as shown in Fig. 1. In this specification and the like, the information processing device 10, the information terminal 20, and the information processing device 40 may be referred to as components.

[0037] An example of an information processing method used in the information processing system described in this embodiment will be described with reference to FIGS.

[0038] [Information Processing Method 1] Figures 2, 4, 5, and 6 are flow diagrams illustrating an example of an information processing method according to one aspect of the present invention. Figure 3A is a diagram illustrating an example of an input to the information processing system, and Figure 3B is a diagram illustrating an example of an output from the information processing system.

[0039] The information processing method of one embodiment of the present invention is "started," and a divisional application consideration instruction is received in step S101 of Figure 2. The divisional application consideration instruction includes an indication that a divisional application is being considered and the application number of the target patent, and is input into the information processing system by a user operation. Note that instead of the application number of the patent, a reference number linked to the patent application number in the organization to which the user belongs may be input.

[0040] In step S101 of Figure 2, a division consideration instruction can be input as shown in input example 200 in Figure 3A, and the information processing system accepts this division consideration instruction. For example, as shown in input example 200 in Figure 3A, application information, typically the application number or serial number, is input in input box 211. Depending on the input content, a list of application countries for the patent family, countries to be divided, and other information may be displayed as in area 212. Also, as shown in input example 200, button 213 may be provided as a confirmation button (OK).

[0041] Next, in step S102 of FIG. 2 , patent family data corresponding to the application number or serial number received in step S101 is obtained. The patent family data includes claim data, prosecution history data, and grant status data for all patent applications belonging to the patent family. The patent family data may also include specification data and drawing data for each patent application. The prosecution history data includes information such as grants of patents, notices of reasons for refusal, and office actions sent by patent offices of various countries. The patent family data may be obtained from a database included in an information processing system, from a public database such as the Patent Information Platform, OnePortal Dossier, Patent Center, Espacenet, or KIPRIS, or from a database operated by a private patent information service company.

[0042] Next, in steps S103 to S106 of FIG. 2, the claims of granted patents, claims for which a patent decision has been issued, and claims for which no reasons for refusal have been issued, contained in the patent family data acquired in step S102, are grouped. Note that the claims of granted patents, claims for which a patent decision has been issued, and claims for which no reasons for refusal have been issued, contained in the patent family data, are sometimes collectively referred to as "granted claims" throughout this specification. The claim data contained in the patent family data includes data on granted claims (granted claim data) and data on claims other than granted claims. While these can be processed as a group of multiple claims, they can also be processed as individual data for each claim. The following explanation assumes that each claim is processed as individual data.

[0043] 2, a first prompt is created, which includes patent family data and an instruction for grouping all granted claim data included in the patent family data, such as "Please classify the following claims by technical features and divide them into groups." The granted claim data included in the patent family data includes claim data of granted patents, claim data for which a patent decision has been made, and claim data for which no reason for refusal has been indicated.

[0044] Next, in step S104 of Fig. 2, the first prompt is sent to the language model. The language model classifies the above-mentioned allowed claims based on the prompt (step S105). The data of the allowed claims classified by the language model in step S105 is called claim classification data. The claim classification data includes at least one claim group.

[0045] For example, if the technical features of claim 9 of Japanese Patent PA, which is included in a patent family, and claim 1 of U.S. Patent PB, which is also included in the same patent family, are identical, claim 9 of Japanese Patent PA and claim 1 of U.S. Patent PB belong to the same claim group. In the above example, the text data of claim 9 and the text data of claim 1 are independent claim data. In other words, a claim group includes at least one claim data. Furthermore, it is preferable that the claim data include, in addition to the claim text data, information associated with each claim, such as the application number, patent number (if registered), and filing country.

[0046] A prompt can be considered an input sentence that causes a language model to perform a desired operation. When a prompt is given to a language model, the language model generates a response content based on the prompt.

[0047] Next, in step S106 of Fig. 2, claim classification data is received from the language model. For the received claim classification data, the application countries of the claim data held by each claim group are investigated, and the countries in which the contents of each claim group have been applied for (registered) are sorted by application country (step S107).

[0048] If, as a result of the above process, a claim group that does not have a patent application in the filing country of the patent application to be divided (division consideration country) can be found, the claim group is called a division candidate group, and at the branch of step S108 in Figure 2, the process proceeds to step S109. Alternatively, if a group that does not have a patent application in the division consideration country cannot be found, the process proceeds to connector A.

[0049] In step S109 of Fig. 2, division candidate groups that have not yet been granted rights in the countries under consideration for division are output as the results of information processing. The contents of the division candidate groups may include correspondence information for each filing country, proposed divisional application claims (divisional claim data), etc., and at least a portion of these contents may be output as the results of information processing. Note that the divisional claim data is preferably document data expressed in the language of the country under consideration for division.

[0050] For example, step S109 in FIG. 2 can output the contents of the division candidate group as shown in the example output 201 in FIG. 3B. In the example output 201 in FIG. 3B, the processing results of step S107 are displayed in table format in area 221. Also, in the example output 201 in FIG. 3B, a dashed line 222 is used to display groups that have not been granted patents in the countries under consideration for division, overlapping with the table in area 221. In this manner, step S109 can output a division candidate group that includes proposed divisional application claims. A button 223 may also be provided to display details of the division candidate group. A button 224 may also be provided to display proposed divisional claims (divisional claim data). As shown in the example output 201, a button 225 may also be provided as a confirmation button (OK).

[0051] The display example of Figure 3B shows claim classification data for a patent family including Japanese, U.S., and Korean patents. The specific content of the display example of Figure 3B will now be described. All of the allowed claim data contained in the patent family data is classified into claim group GA, claim group GB, claim group GC, and claim group GD. Furthermore, claim group GA contains claim data for Japanese patents, U.S. patents, and Korean patents. Claim group GB contains claim data for U.S. patents and Korean patents. Claim group GC contains claim data for Japanese patents and Korean patents. Claim group GD contains claim data for Japanese patents. Therefore, claim group GB, which does not have a patent application in Japan, the target country for division, is a division candidate group and is highlighted by a dashed line 222. Here, for example, by pressing button 223, each claim data contained in the division candidate group can be displayed. Furthermore, the registration status and prosecution progress information for each claim data may also be displayed. Furthermore, for example, by pressing button 224, it is possible to display a divisional claim proposal in which each claim data included in the division candidate group is translated into the language of the country under consideration for division. Note that, as in the display example of Figure 3B, if the division candidate group contains claim data for multiple countries, multiple divisional claim proposals may be displayed.

[0052] As explained in Figures 2, 3A, and 3B, by using the information processing system of one embodiment of the present invention, it is possible to search for family patents that have already been granted rights in other countries, and to check whether applications for the technical features of those claims have already been filed in the country under consideration for division.If no applications have been filed, a proposal for divisional claims with content equivalent to the family patents can be received, allowing the user to file a divisional application with little effort.

[0053] Alternatively, by using an information processing system according to one embodiment of the present invention, it is possible to examine the claims of a family patent that has already been examined in another country and for which no grounds for refusal have been found, and to check whether the technical features of that claim have already been applied for in the country under consideration for division. If no application has been filed, a proposal for a divisional claim with content equivalent to that of the family patent can be received, allowing the user to file a divisional application with little effort.

[0054] [Branching Process A] Next, using Figure 4, we will explain Branching Process A, which occurs when, in the branching of step S108 in Figure 2, no unpatented claim group (division candidate group) can be found in the country under consideration for division and the process proceeds to Connector A. Branching Process A analyzes the prosecution history data and the allowed claims, extracts allowed matters, deletes at least one of the allowed matters from the original allowed claim, and creates a divisional claim whose scope of protection is expanded from the original allowed claim.

[0055] Connector A is connected to step S121 shown in Figure 4. In step S121, a second prompt is created, which includes the patent application prosecution history data and claim data contained in the patent family data, and an instruction for searching for permitted matters from the prosecution history data, such as "Based on the following prosecution history data and claim data, please extract and show all permitted matters for each claim of a granted patent, each claim for which a patent decision has been issued, and each claim for which no reasons for refusal have been indicated (allowed claims)." Note that, in processing each claim, dependent claims (also called dependent claims) should be processed together with the independent claims (also called independent claims) that they cite.

[0056] Claim data contains one or more technical features from the "Detailed Description of the Invention" of the corresponding specification. Among these, the technical features that are elements that are granted patent registration during the patent examination process are called "allowed features." However, there are cases in which allowed features are not indicated or cannot be read during patent examination.

[0057] Next, in step S122 of Fig. 4, the second prompt is sent to the language model. Based on the prompt, the language model analyzes the permitted matters for each permitted claim (step S123). Data representing the results of the analysis by the language model in step S123 is called permitted matter analysis data. Note that the permitted matter analysis data is created for each permitted claim, but it may be stored as a file for each permitted claim, or may be stored as a single file for all permitted claims.

[0058] Next, in step S124 of FIG. 4, permission analysis data is received from the language model.

[0059] In the analysis of the permitted claims, if permitted matters are read, the process branches from step S125 in Fig. 4 and proceeds to step S126. Alternatively, if permitted matters are not read, the process proceeds to connector B. In other words, in the branch from step S125 in Fig. 4, if permitted matters are included in the permitted matter analysis data for each permitted claim, the process proceeds to step S126, and if permitted matters are not included in the permitted matter analysis data, the process proceeds to step S125B.

[0060] Next, if multiple permission items are read in the analysis of the permitted claims, the process branches to step S126 in Fig. 4 and proceeds to step S127. Alternatively, if multiple permission items are not read, that is, if only one permission item is found, the process proceeds to connector C. That is, if multiple permission items are included in the permission item analysis data for each permitted claim in the branch of step S126 in Fig. 4, the process proceeds to step S127, and if only one permission item is included in the permission item analysis data, the process proceeds to step S126C.

[0061] In step S127 of Fig. 4, based on the multiple permission items read above, divided claim data (divided claim data DA) is created by removing at least one of the permission items from the permitted claim. Multiple divided claim data can be created. Note that a language model may be used to create the divided claim data. In this way, by removing at least one of the permission items, a divided claim with an expanded scope of protection can be created from the original permitted claim.

[0062] 4, the multiple divisional claim data DA created in step S127 are output as proposed claims to be used in a divisional application. If the creation of step S127 and the output of step S128 are performed on different devices or terminals, processing such as transmission and reception can be appropriately provided between steps S127 and S128.

[0063] In this way, by using the information processing system of one aspect of the present invention, analysis data on permitted matters can be created by extracting permitted matters, which are technical features that are elements that led to the approval of registration, from the examination progress data on registered claims or claims whose registration has been approved, and claims for which no reasons for refusal have been given.If there are multiple such permitted matters, a proposal can be received for divisional claims that exclude at least one of the permitted matters, allowing the user to file a divisional application with little effort.

[0064] [Branch Processing B] Next, using Fig. 5, we will explain branch processing B, which occurs when no permitted matter is read in the branch at step S125 in Fig. 4 and the process proceeds to connector B. In branch processing B, one of the technical features included in the permitted claim is deleted, and a divided claim with an expanded scope of protection is created from the original permitted claim.

[0065] Connector B is connected to step S141 shown in FIG. 5 . In step S141, a third prompt is created, which includes the allowed claim data and an instruction for creating a divided claim data DB with a new combination of technical features by deleting one technical feature from the allowed claim for which the permission item could not be read. The third prompt includes an instruction such as, "Please extract technical features from the following claim data. Then, if there are multiple technical features, please create and display divided claim data by deleting one of the technical features. If there are multiple variations in the divided claim data, please display all of them." This "new combination of technical features" refers, for example, to a allowed claim that has Technical Feature 1, Technical Feature 2, Technical Feature 3, and Technical Feature 4, but with Technical Feature 1 removed. In other words, a divided claim with a new combination of technical features can be considered to have an expanded scope of protection from the original allowed claim.

[0066] Next, in step S142 of Figure 5, the third prompt is sent to the language model, which creates a split claim data DB with a new combination of technical features based on the prompt (step S143).

[0067] Next, in step S144 of FIG. 5, the divided claim data DB is received from the language model.

[0068] Next, in step S145 of FIG. 5, the divisional claim data DB created in step S143 is output as a proposal for claims to be used in a divisional application.

[0069] In this way, by using the information processing system of one aspect of the present invention, even if a technical feature that constitutes the element for which registration was permitted cannot be found from the prosecution history data for registered claims or claims for which registration was permitted, a proposal for a divisional claim that differs from the claims that have been considered up to that point can be received, allowing the user to file a divisional application with little effort.

[0070] [Branch Processing C] Next, branch processing C when only one permitted matter is found in the permitted claim in the branching of step S126 in FIG. 4 and the process proceeds to connector C will be described with reference to FIG.

[0071] The connector C is connected to step S161 shown in FIG. 6 . In step S161, a fourth prompt is created, which includes the allowed claim data and an instruction for creating divided claim data DC from an allowed claim for which only one allowed feature was found, by retaining the allowed feature and deleting one technical feature. The fourth prompt includes an instruction such as, "Based on the claim data and the allowed feature analysis data below, please extract technical features from the claim data that include the allowed feature contained in the claim data and are not the allowed feature. If there are multiple technical features, then please create and display divided claim data from which one of the technical features is deleted. If there are multiple variations in the divided claim data, please display all of them." The fourth prompt also includes the allowed claim data and the allowed feature analysis data contained in the patent family data.

[0072] Next, in step S162 of Fig. 6, the fourth prompt is sent to the language model. Based on the prompt, the language model creates divided claim data DC by retaining the permitted items and deleting one technical feature (step S163). In this way, by deleting one technical feature other than the permitted items, it is possible to create a divided claim whose scope of protection is expanded from the original permitted claim.

[0073] Next, in step S164 of FIG. 6, divided claim data DC is received from the language model.

[0074] Next, in step S165 of FIG. 6, the divisional claim data DC created in step S163 is output as a proposed claim to be used in a divisional application.

[0075] In this way, by using the information processing system of one aspect of the present invention, permitted item analysis data is created by extracting permitted items, which are technical features that are elements that led to the registration being permitted, from the examination progress data related to registered claims or claims whose registration has been permitted.If one such permitted item exists, a proposal can be received for divisional claim data that retains the permitted item and deletes one technical feature, allowing the user to file a divisional application with little effort.

[0076] In the information processing method of one embodiment of the present invention described using Figures 2 to 6, which device or terminal, information processing device 10, information processing device 40, or information terminal 20, performs the processing of each step will be described using Figure 7.

[0077] 7 is a relationship diagram showing the processes performed by the information processing device 10, the information processing device 40, and the information terminal 20, using the symbols for each step used in FIGS. 2 to 6. Also, block arrows with network 30 attached indicate data transmission and reception between the information processing device 10 and the information processing device 40, and data transmission and reception between the information processing device 10 and the information terminal 20.

[0078] As shown in FIG. 7 , the information processing device 10 has a function to perform processing of step S102, a function to perform processing of step S103, a function to perform processing of step S104, a function to perform processing of step S106, a function to perform processing of step S107, a function to perform processing of step S108, a function to perform processing of step S121, a function to perform processing of step S122, a function to perform processing of step S124, a function to perform processing of step S125, a function to perform processing of step S126, a function to perform processing of step S127, a function to perform processing of step S141, a function to perform processing of step S142, a function to perform processing of step S144, a function to perform processing of step S161, a function to perform processing of step S162, and a function to perform processing of step S164.

[0079] Also, as shown in FIG. 7, the information processing device 40 has a function to perform processing of step S105, a function to perform processing of step S123, a function to perform processing of step S143, and a function to perform processing of step S163.

[0080] Also, as shown in FIG. 7, the information terminal 20 has a function to perform processing of step S101, a function to perform processing of step S109, a function to perform processing of step S128, a function to perform processing of step S145, and a function to perform processing of step S165.

[0081] An example of the configuration of the information processing device 10, the information processing device 40, the information terminal 20, and the network 30 will be described below.

[0082] <<Configuration Example of Information Processing Device 10>> A configuration example of the information processing device 10 included in the information processing system of one embodiment of the present invention will be described with reference to FIG.

[0083] As shown in FIG. 8, the information processing device 10 includes an input unit 110 , a storage unit 120 , a processing unit 130 , an output unit 140 , and a transmission path 150 .

[0084] [Input Unit 110] The input unit 110 can accept data from outside the information processing device 10. For example, the input unit 110 can accept data from the information terminal 20. The input unit 110 can also accept data from the information processing device 40.

[0085] The input unit 110 can supply the received data to one or both of the storage unit 120 and the processing unit 130 via the transmission path 150. Specifically, a device such as a wired communication port, a wireless communication port, or an optical communication port can be used.

[0086] [Storage Unit 120] The storage unit 120 has a function of storing a program executed by the processing unit 130. The storage unit 120 may also have a function of storing data generated by the processing unit 130 (e.g., calculation results, analysis results, inference results), data accepted by the input unit 110, and the like.

[0087] The storage unit 120 may have a database. Furthermore, the information processing device 10 may have a database separate from the storage unit 120. The information processing device 10 may have a function to retrieve data from a database that exists outside the storage unit 120, outside the information processing device 10, or outside the information processing system. Furthermore, the information processing device 10 may have a function to retrieve data from both its own database and an external database.

[0088] Either or both of a storage and a file server can be used as the memory unit 120. Also, a database that records paths of files stored in a file server can be used as the memory unit 120.

[0089] The storage unit 120 includes at least one of a volatile memory and a non-volatile memory. Examples of the volatile memory include a dynamic random access memory (DRAM) and a static random access memory (SRAM). Examples of the non-volatile memory include a resistive random access memory (ReRAM), a phase change random access memory (PRAM), a ferroelectric random access memory (FeRAM), a magnetoresistive random access memory (MRAM), and a flash memory. The storage unit 120 may also include at least one of NOSRAM (registered trademark) and DOSRAM (registered trademark). The storage unit 120 may also include a recording media drive. Examples of recording media drives include a hard disk drive (HDD) and a solid state drive (SSD).

[0090] NOSRAM is an abbreviation for "Nonvolatile Oxide Semiconductor Random Access Memory." NOSRAM refers to a memory in which memory cells are two-transistor (2T) or three-transistor (3T) gain cells, and the transistors are transistors (also called OS transistors) that use metal oxide in their channel formation regions. OS transistors have an extremely small leakage current, i.e., a current that flows between the source and drain in an off state. NOSRAM can be used as a nonvolatile memory by retaining a charge corresponding to data in the memory cell using its extremely small leakage current characteristic. In particular, NOSRAM can read stored data without destroying it (nondestructive read), making it suitable for arithmetic processing in which only data read operations are repeated a large number of times. NOSRAM can increase its data capacity by stacking layers, and therefore can be used as a large-scale cache memory, main memory, or storage memory to improve the performance of semiconductor devices.

[0091] DOSRAM is an abbreviation for "Dynamic Oxide Semiconductor RAM" and refers to a RAM having 1T (transistor) 1C (capacitor) type memory cells. DOSRAM is a DRAM formed using OS transistors, and is a memory that temporarily stores information sent from an external device. DOSRAM is a memory that takes advantage of the low off-state current of OS transistors.

[0092] In this specification and the like, a metal oxide refers to an oxide of a metal in a broad sense. Metal oxides are classified into oxide insulators, oxide conductors (including transparent oxide conductors), oxide semiconductors (also referred to as oxide semiconductors or simply as OSs), and the like. For example, when a metal oxide is used for a semiconductor layer of a transistor, the metal oxide may be referred to as an oxide semiconductor.

[0093] The metal oxide included in the channel formation region preferably contains indium (In). When the metal oxide included in the channel formation region contains indium, the carrier mobility (electron mobility) of the OS transistor is increased. Furthermore, the metal oxide included in the channel formation region is preferably an oxide semiconductor containing element M. The element M is preferably at least one of aluminum (Al), gallium (Ga), and tin (Sn). Other elements applicable to element M include boron (B), silicon (Si), titanium (Ti), iron (Fe), nickel (Ni), germanium (Ge), yttrium (Y), zirconium (Zr), molybdenum (Mo), lanthanum (La), cerium (Ce), neodymium (Nd), hafnium (Hf), tantalum (Ta), and tungsten (W). However, a combination of two or more of the above elements may be used as element M. The element M is, for example, an element having a high bond energy with oxygen. For example, it is an element having a higher bond energy with oxygen than indium. The metal oxide contained in the channel formation region is preferably a metal oxide containing zinc (Zn), since zinc-containing metal oxides may be easily crystallized.

[0094] The metal oxide contained in the channel formation region is not limited to a metal oxide containing indium, but may be, for example, a metal oxide containing zinc but not indium, such as zinc tin oxide or gallium tin oxide, a metal oxide containing gallium, or a metal oxide containing tin.

[0095] [Processing Unit 130] The processing unit 130 has a function of performing processes such as calculation, analysis, and inference using data supplied from one or both of the input unit 110 and the storage unit 120. The processing unit 130 can supply generated data (e.g., calculation results, analysis results, and inference results) to one or both of the storage unit 120 and the output unit 140.

[0096] The processing unit 130 has a function of acquiring data from the storage unit 120. The processing unit 130 may also have a function of recording or registering data in the storage unit 120.

[0097] The processing unit 130 may include, for example, an arithmetic circuit, a central processing unit (CPU), and a graphics processing unit (GPU).

[0098] The processing unit 130 may have a microprocessor such as a DSP (Digital Signal Processor). The microprocessor may be implemented by a PLD (Programmable Logic Device) such as an FPGA (Field Programmable Gate Array) or an FPAA (Field Programmable Analog Array). The processing unit 130 may also have a quantum processor. The processing unit 130 can perform various data processing and program control by interpreting and executing instructions from various programs using the processor. Programs that can be executed by the processor are stored in at least one of the memory area of ​​the processor and the storage unit 120.

[0099] The processing unit 130 may include a main memory. The main memory may include at least one of a volatile memory such as a random access memory (RAM) and a non-volatile memory such as a read-only memory (ROM). The main memory may also include at least one of the above-mentioned NOSRAM and DOSRAM.

[0100] The RAM may be, for example, a DRAM or an SRAM, and a virtual memory space is allocated and used as a working space for the processing unit 130. The operating system, application programs, program modules, program data, lookup tables, and the like stored in the storage unit 120 are loaded into the RAM for execution. The data, programs, and program modules loaded into the RAM are each directly accessed and operated by the processing unit 130.

[0101] The ROM can store a BIOS (Basic Input / Output System), firmware, etc., which do not require rewriting. Examples of ROM include mask ROM, OTPROM (One Time Programmable Read Only Memory), and EPROM (Erasable Programmable Read Only Memory). Examples of EPROMs include UV-EPROMs (Ultra-Violet Erasable Programmable Read Only Memories), which allow stored data to be erased by exposure to ultraviolet light, EEPROMs (Electrically Erasable Programmable Read Only Memories), and flash memories.

[0102] The processing section 130 can include one or both of an OS transistor and a transistor having silicon in a channel formation region (a Si transistor).

[0103] The processing unit 130 preferably includes an OS transistor. Because an OS transistor has an extremely small off-state current, using the OS transistor as a switch for retaining charge (data) flowing into a capacitor functioning as a memory element can ensure a long data retention period. By using this characteristic in at least one of the register and cache memory of the processing unit, the processing unit can be operated only when necessary, and can be turned off in other cases by saving information from the previous processing in the memory element. In other words, normally-off computing is possible, and the power consumption of the information processing system can be reduced.

[0104] It is preferable that the information processing device 10 uses AI for at least some of its processing.

[0105] In particular, it is preferable that the information processing device 10 uses an artificial neural network (ANN, hereinafter also simply referred to as a neural network). A neural network is realized by a circuit (hardware) or a program (software).

[0106] In this specification, a neural network refers to a general model that mimics the neural circuit network of a living organism, determines the connection strength between neurons through learning, and has problem-solving capabilities. A neural network has an input layer, an intermediate layer (hidden layer), and an output layer.

[0107] In this specification and the like, when discussing neural networks, determining the connection strengths (also called weighting coefficients) between neurons from existing information may be referred to as "learning."

[0108] In this specification and the like, the act of constructing a neural network using connection strengths obtained by learning and deriving a new conclusion from it may be referred to as "inference."

[0109] The information processing device 10 can perform processing using a natural language processing model that uses AI. For example, it can perform machine translation processing using a natural language processing model that uses AI. As a natural language processing model that performs machine translation processing, it is possible to execute processing using a natural language processing model that uses AI, such as Sequence-to-Sequence (seq2seq), Transformer, BERT (Bidirectional Encoder Representations from Transformers), or T5 (Text-to-Text Transformer).

[0110] [Output Unit 140] The output unit 140 can output at least one of the calculation results, analysis results, and inference results in the processing unit 130 to the outside of the information processing device 10. Specifically, a device such as a wired communication port, a wireless communication port, or an optical communication port can be used.

[0111] For example, the output unit 140 can transmit data to the information processing device 40. The output unit 140 can also transmit data to the information terminal 20.

[0112] [Transmission Path 150] The transmission path 150 has a function of transmitting data. Data can be transmitted and received between the input unit 110, the storage unit 120, the processing unit 130, and the output unit 140 via the transmission path 150. Specifically, a bus line on a motherboard, a wired communication cable, or an optical communication cable can be used.

[0113] <<Configuration Example of Information Processing Device 40>> The information processing device 40 can process received data and transmit the processing results. For example, the information processing device 40 can perform processing such as calculations using data received from the information processing device 10. Furthermore, the information processing device 40 can transmit the processing results to the information processing device 10. This can reduce the calculation load on the information processing device 10.

[0114] The information processing device 40 can perform processing using a natural language processing model, such as BERT or T5.

[0115] Furthermore, the information processing device 40 can perform processing using a model that utilizes a large-scale language model (such as a sentence generation model or a dialogue model).

[0116] In an information processing method according to one aspect of the present invention, the process of classifying claims by technical feature and creating claim classification data in step S105 described in FIG. 2 is preferably performed using a large-scale language model. The translation process described in the explanation of button 224 in FIG. 3B is preferably performed using a large-scale language model. In an information processing method according to one aspect of the present invention, the process of extracting permitted items based on the prosecution progress data and claim data in step S123 described in FIG. 4 is preferably performed using a large-scale language model. In an information processing method according to one aspect of the present invention, the process of creating divided claim data by excluding at least one permitted item in step S127 described in FIG. 4 is preferably performed using a large-scale language model. In an information processing method according to one aspect of the present invention, the process of creating divided claim data with a new combination of technical features in step S143 described in FIG. 5 is preferably performed using a large-scale language model. In an information processing method according to one aspect of the present invention, the process of creating divided claim data by retaining permitted items and deleting one technical feature in step S163 described in FIG. 6 is preferably performed using a large-scale language model. These processes can be performed using large-scale language models such as GPT-3, GPT-3.5, GPT-4 (registered trademark), LaMDA, PaLM, Llama2, and Llama3.

[0117] Furthermore, the information processing device 40 can execute processing using a general-purpose language processing model that can perform various natural language processing tasks.

[0118] The information processing device 40 is a large-scale computer such as a server computer or a supercomputer. Preferably, the information processing device 40 has a function as a parallel computer. By using the information processing device 40 as a parallel computer, it is possible to perform large-scale calculations required for AI learning and inference, for example.

[0119] The information processing device 40 is a computer with higher processing power than the information processing device 10. For example, if both the information processing device 10 and the information processing device 40 have functions as parallel computers, the information processing device 40 has higher processing power than the information processing device 10 and can perform large-scale calculations. Furthermore, for example, if both the information processing device 10 and the information processing device 40 can perform processing using a model that utilizes a large-scale language model, the information processing device 40 can execute processing using a larger-scale model than the information processing device 10.

[0120] It should be noted that the service provider does not necessarily have to own the information processing device 40. For example, the service provider can use part of the service provided by another business or the like using the information processing device 40.

[0121] <<Configuration Example of Information Terminal 20>> The information terminal 20 can accept data input by a user of the information processing system of one aspect of the present invention. The information terminal 20 can provide data output by the information processing system of one aspect of the present invention to the user by displaying the data on a display unit included in the information terminal 20. Alternatively, the information terminal 20 can provide data output by the information processing system of one aspect of the present invention to the user by printing the data on a printing unit included in the information terminal 20.

[0122] Furthermore, the information terminal 20 can transmit data received from the user to the information processing device 10. Furthermore, the information terminal 20 can provide data received from the information processing device 10 to the user.

[0123] Furthermore, the information terminal 20 can transmit data generated based on data received from the user to the information processing device 10. Furthermore, the information terminal 20 can provide data generated based on data received from the information processing device 10 to the user.

[0124] For example, dedicated application software or a web browser is installed on the information terminal 20. A user can access the information processing device 10 via either of these. This allows the user to enjoy services using the information processing system according to one aspect of the present invention, for example, using a computer with lower processing power than the information processing device 10.

[0125] The information terminal 20 may also be called a client computer, etc. Each of the information terminals 20 is an information terminal device used by a user of the information processing system according to one aspect of the present invention.

[0126] For example, a desktop computer 20a, a notebook computer 20b, a smartphone 20c, and a tablet computer 20d can be used as the information terminal 20. The tablet computer 20d can also be used as a notebook computer by connecting it to a housing 21 having a keyboard.

[0127] This allows a user of the information processing system to use a computer, such as an information terminal 20, which has lower processing power than the information processing device 10 or the information processing device 40, to control an information processing system according to one embodiment of the present invention, give instructions to the information processing device 40, and enjoy services.

[0128] <<Network 30>> The network 30 connects the information processing device 10 and the information processing device 40. The network 30 also connects a plurality of information terminals 20 and the information processing device 10. This allows input data and processed data to be transmitted and received between the two. Furthermore, the load related to information processing can be distributed.

[0129] In this embodiment, the network 30 can be, for example, a global network, such as the Internet, which is the foundation of the World Wide Web (WWW). The network 30 can also be a local network. The network 30 can also be an intranet or an extranet. The network 30 can also be a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), a global area network (GAN), or the like.

[0130] When a provider of a service using an information processing method according to an embodiment of the present invention and a user who receives the service belong to the same organization, such as a company, it is preferable that data be transmitted and received between the information terminal 20 and the information processing device 10 using, for example, a network established within the organization. This allows data to be transmitted and received between the information terminal 20 and the information processing device 40 more securely than when data is transmitted over the Internet. Furthermore, it is possible to prevent confidential information within the organization from leaking to the outside.

[0131] When wireless communication is performed, communication standards such as the fourth generation mobile communication system (4G), fifth generation mobile communication system (5G), and sixth generation mobile communication system (6G), or specifications standardized by the IEEE such as Wi-Fi (registered trademark) and Bluetooth (registered trademark), can be used as communication protocols or communication technologies.

[0132] The content of this embodiment can be freely combined with the content of other embodiment modes.

[0133] In this embodiment, an information processing system and an information processing method according to one embodiment of the present invention will be described with reference to FIGS. 9 to 15. Note that description of parts that are the same as those in Embodiment 1 may be omitted.

[0134] [Information Processing Method 2] Information Processing Method 1 described an example of an information processing method for creating divided claims by expanding the scope of protection from allowed claims included in patent family data. However, the information processing method of one embodiment of the present invention is not limited to this. For example, it is also possible to create divided claims by narrowing the scope of protection from allowed claims included in patent family data. An example of an information processing method including a case where the scope of protection of a divided claim is narrowed will be described using Figures 9 and 10. In Information Processing Method 2 described in this embodiment, the overall flow of the information processing method is similar to Information Processing Method 1 shown in the flow charts of Figures 2 and 4, but the content of Branching Process B described in Figure 5 differs from Information Processing Method 1.

[0135] The branching process B', which is different from that in FIG. 5, will be described with reference to FIG.

[0136] In the case where the permission items cannot be read at the branch of step S125 in FIG. 4 and the process proceeds to the connector B, the information processing method 2 can adopt a flow starting from the connector B' in FIG.

[0137] [Branch Processing B'] FIG. 9 is a flow diagram illustrating branch processing B' which replaces branch processing B described in FIG.

[0138] Here, the description of the processing of steps S241 to S244 in Fig. 9 will be omitted because it is similar to the processing of steps S141 to S144 in Fig. 5. Note that in the processing of step S243, a processing is performed in which the language model creates a divided claim data DB having a new combination of technical features based on the third prompt, and in step S244, the result of this processing is received.

[0139] Next, in step S251 of Fig. 9, it is determined whether a divided claim data DB having a new combination of technical features has been created. If a divided claim data DB having a new combination of technical features has been created, the process branches to step S252 in Fig. 9. Alternatively, if a divided claim data DB having a new combination of technical features has not been created, the process proceeds to connector D.

[0140] Examples of cases in which a divided claim data DB having a new combination of technical features cannot be created include when, when deleting one technical feature and creating a divided claim data DB having a new combination of technical features, the original permitted claim data contained in the patent family data describes only one technical feature, or when the divided claim data DB to be created by deleting one technical feature is already included in the patent family data. In other words, in step S251, a determination is made from the above perspective.

[0141] In step S252 of FIG. 9, similar to step S145 of FIG. 5, the divisional claim data DB created in step S243 is output as a proposal for claims to be used in a divisional application.

[0142] [Branching Process D] Branching Process D, which occurs when a divided claim data DB having a new combination of technical features cannot be created in step S243 of Fig. 9 and the process proceeds to connector D in the branch of step S251, will be described with reference to Fig. 10. In branching process D, new technical features that differ from the technical features of the allowed claim data contained in the patent family data are extracted from the specification, divided claim data DD is created as divided claim data including the existing technical features and the new technical features, and an output is performed proposing the divided claim data DD as a claim to be used in a divisional application.

[0143] As shown in Fig. 10, the process proceeds from the connector D to step S261. In step S261, new technical features that differ from the technical features of the allowed claim data included in the patent family data are extracted from the specification, and a prompt (fifth prompt) is created to create divided claim data DD that includes the existing technical features and the new technical features.

[0144] The fifth prompt includes, for example, an instruction such as "Based on the claim data and specification data below, please extract new technical features from the specification data other than the technical features included in the claim data. Then, please create and present divided claim data that combines the new technical features with existing technical features included in the claim data. If the divided claim data has multiple variations, please present all of them," as well as the permitted claim data and specification data included in the patent family data.

[0145] Next, in step S262 of Fig. 10, the fifth prompt is sent to the language model. Based on the prompt, the language model extracts new technical features from the specification that are different from the technical features included in the permitted claim data, and creates divided claim data DD that includes the existing technical features and the new technical features (step S263).

[0146] Next, in step S264 of FIG. 10, divided claim data DD is received from the language model.

[0147] Next, in step S265 of Fig. 10, it is determined whether divided claim data DD has been created. If divided claim data DD has been created, the process branches to step S266A in step S265 of Fig. 10. Alternatively, if divided claim data DD has not been created, the process proceeds to step S266B.

[0148] Next, if the divisional claim data DD has been created, in step S266A of FIG. 10, the divisional claim data DD created in step S263 is output as a proposed claim to be used in a divisional application.

[0149] Alternatively, if the divided claim data DD cannot be created, an output is made in step S266B of FIG. 10 indicating that there are no divided claims that can be proposed.

[0150] In this way, by using the information processing system of one aspect of the present invention, new technical features that differ from the technical features contained in existing permitted claim data can be extracted from the specification, and divisional claim data DD containing the new technical features can be proposed, allowing the user to file a divisional application with little effort.

[0151] 9 and 10, which device or terminal performs the processing of each step among the information processing device 10, the information processing device 40, and the information terminal 20 will be described with reference to Fig. 11. Note that the configuration example shown in Fig. 11 can be used in combination with the configuration example of the information processing method 1 described with reference to Fig. 7 and the like.

[0152] 11 is a relationship diagram showing the processes performed by the information processing device 10, the information processing device 40, and the information terminal 20 using the symbols for each step used in FIGS. 9 and 10. In addition, block arrows with network 30 attached indicate data transmission and reception between the information processing device 10 and the information processing device 40, and data transmission and reception between the information processing device 10 and the information terminal 20.

[0153] As shown in FIG. 11, the information processing device 10 has a function to perform processing of step S241, a function to perform processing of step S242, a function to perform processing of step S244, a function to perform processing of step S251, a function to perform processing of step S261, a function to perform processing of step S262, a function to perform processing of step S264, and a function to perform processing of step S265.

[0154] As shown in FIG. 11, the information processing device 40 has a function to perform the process of step S243 and a function to perform the process of step S263.

[0155] As shown in FIG. 11, the information terminal 20 has a function to perform the process of step S252, a function to perform the process of step S266A, and a function to perform the process of step S266B.

[0156] [Individual Processing] In the above-described information processing method 1 and information processing method 2, the branching processes of a plurality of processing flows (branching process A, branching process B, branching process C, and branching process D) have been described as a series of flows, but the information processing method of one embodiment of the present invention is not limited to this, and the processes shown in Figures 2, 4, 5, 6, 9, and 10 can be performed individually. In this case, for example, processing can be performed in accordance with individual processing instructions, as shown in the flow diagram of Figure 12.

[0157] In step S111 of FIG. 12, in addition to the division review instruction as shown in the input example 301 in FIG. 13A, an individual processing instruction can be input by selecting the division review process.

[0158] The information processing system accepts this division consideration instruction. For example, as shown in input example 301 in Figure 13A, application information, typically an application number or serial number, is entered in input box 311. Depending on the content of this input, a list of application countries for the patent family, information on countries to be divided, etc., may be displayed, as in area 312, or radio buttons may be provided for selecting countries to be divided.

[0159] 2, 4, 5, 6, 9, and 10 (all pattern examination), the process shown in Fig. 2 (group classification examination), the process shown in Fig. 4 (extension examination SA), the process shown in Fig. 5 (extension examination SB), the process shown in Fig. 6 (extension examination SC), or the process shown in Fig. 10 (reduction examination SD) can be provided as a selection of division examination processes, as in area 313, and instructions for the all pattern examination process or instructions for each individual process can be input. Also, a button 314 may be provided as a confirmation button (OK) as shown in input example 301.

[0160] Next, in step S112 of Fig. 12, the patent family data corresponding to the application number or serial number received in step S111 is acquired. The process of step S112 is the same as that of step S102 of Fig. 2, and therefore a description thereof will be omitted.

[0161] Next, in step S113 of FIG. 12, a determination is made as to whether an individual processing instruction exists, and branching processing is performed. The branching processing in step S113 is performed according to the input content in area 313 of FIG. 13A described in step S111. If "All Patterns Review" is selected, the process proceeds to "No," and processing from step S103 onward in FIG. 2 can be performed. Alternatively, if "Expansion Review SA" is selected, the process proceeds from step S113 to connector A. If "Expansion Review SB" is selected, the process proceeds from step S113 to connector B. If "Expansion Review SC" is selected, the process proceeds from step S113 to connector C. If "Reduction Review SD" is selected, the process proceeds from step S113 to connector D. In this way, the processing shown in FIGS. 2, 4, 5, 6, 9, and 10 can be performed individually.

[0162] Figures 13B to 15 are diagrams illustrating output examples of branching processes A to D. Figure 13B shows an example of the output when "Expansion Consideration SA" is selected, which is an example of step S128 in Figure 4. In output example 302 of Figure 13B, an example of the processing results of step S127 is displayed in table format in area 321. For example, proposal 2, indicated by a dashed line 322 in output example 302 of Figure 13B, shows a divided claim that combines permission items AA and AC. In this way, when divided claim data contains multiple divided claim candidates, it is preferable to clearly display the relationship between the permission items. Furthermore, as shown in output example 302, a button 323 for displaying details of the permission items may be provided. Furthermore, a button 324 for displaying a proposed divided claim (divided claim data) may be provided. As shown in output example 302, a button 325 may be provided as a confirmation button (OK).

[0163] FIG. 14A shows an example of the output when "Expansion Consideration SB" is selected, which is an example of step S145 in FIG. 5. In output example 303 of FIG. 14A, an example of the processing results of step S143 is displayed in table format in area 331. For example, proposal 2, indicated by a dashed line 332 in output example 303 of FIG. 14A, shows a divided claim combining technical features FA and FC. In this way, when divided claim data contains multiple divided claim candidates, it is preferable to clearly display the relationship between the technical features. Also, as shown in output example 303, a button 333 for displaying details of the technical features may be provided. A button 334 for displaying a proposed divided claim (divided claim data) may also be provided. As shown in output example 303, a button 335 may also be provided as a confirmation button (OK).

[0164] FIG. 14B shows an example of the output when "Extended Consideration SC" is selected, which is an example of step S165 in FIG. 6. In output example 304 in FIG. 14B, an example of the processing results of step S163 is displayed in table format in area 341. For example, Proposal 2, indicated by a dashed line 342 in output example 304 in FIG. 14B, shows a divided claim that combines permission items AA, technical features FA, and technical features FC. In this way, when divided claim data contains multiple divided claim candidates, it is preferable to clearly display the relationship between the permission items and technical features. As shown in output example 304, a button 343 for displaying details of the technical features may be provided. A button 344 for displaying a proposed divided claim (divided claim data) may also be provided. As shown in output example 304, a button 345 may also be provided as a confirmation button (OK).

[0165] FIG. 15 shows an example of the output when "Reduction Consideration SD" is selected, which is an example of step S266A in FIG. 10 . In output example 305 of FIG. 15 , area 351 displays the processing results of step S263 in a table format. For example, Proposal 1, indicated by a dashed line 352 in output example 305 of FIG. 15 , shows a divided claim that combines technical features FA, FB, FC, and a new technical feature. In this way, when divided claim data contains multiple divided claim candidates, it is preferable to clearly display the relationships between the technical features. As shown in output example 305, a button 353 for displaying details of the technical features may be provided. A button 354 for displaying a proposed divided claim (divided claim data) may also be provided. As shown in output example 305, a button 355 may also be provided as a confirmation button (OK).

[0166] As described above, by using an information processing system according to one embodiment of the present invention, a user can search for family patents that have previously been granted in other countries, and if there is a possibility that the scope of the claims can be expanded, they can receive suggestions for divisional claims with expanded scope, as shown in Figures 13B to 14B. Furthermore, by using an information processing system according to one embodiment of the present invention, a user can search for family patents that have previously been granted in other countries, and if there is a need to narrow the scope of the claims, they can receive suggestions for divisional claims with narrowed scope, as shown in Figure 15. In this way, users can file divisional applications with little effort in a variety of situations.

[0167] The content of this embodiment can be freely combined with the content of other embodiment modes.

[0168] In this embodiment, an information processing system and an information processing method according to one embodiment of the present invention will be described with reference to FIGS. 16 to 19. Note that description of parts that are the same as those in Embodiment 1 or 2 may be omitted.

[0169] [Information Processing Method 3] Information Processing Method 1 and Information Processing Method 2 have been described as unidirectional processing in which, after an initial user input, processing proceeds without any user intervention until final output is produced. However, one aspect of the present invention is not limited to this, and bidirectional processing can be performed in which user operations and inputs are accepted in the middle of a series of processes.

[0170] 16 and 17 are flow charts illustrating information processing method 3. Information processing method 3 has a function of examining previously granted family patents, extracting from their specifications technical features that can narrow the scope of the granted claims, and presenting a first divisional claim incorporating the results to the user. The user can also input comments about the presented first divisional claim and instruct the information processing system to revise the first divisional claim. The information processing system has a function of revising the first divisional claim based on the input user comments and creating a second divisional claim. The created second divisional claim is presented to the user, who can then accept the second divisional claim or enter further comments and instruct the information processing system to revise the second divisional claim. The user can repeatedly instruct the information processing system to revise the divisional claim.

[0171] In step S401 of Figure 16, a division consideration instruction can be input, as in step S101 of Figure 2, and the information processing system accepts this division consideration instruction. To input a division consideration instruction, for example, as shown in input example 450 of Figure 18A, application information, typically the application number or serial number, is entered in input box 451. Depending on the content of this input, a list of application countries for the patent family, information on countries to be divided, etc., may be displayed, as in area 452, and radio buttons may be provided for selecting countries to be divided.

[0172] As shown in area 453, the claims to be considered for division can be selected by listing the claims of the patent corresponding to the application number or docket number, or the allowed claims of that patent family, and selecting which allowed claims to consider for division. This selection can be made, for example, by providing radio buttons as shown in the figure.

[0173] Next, in step S402 of FIG. 16, similar to step S102 of FIG. 2, patent family data corresponding to the application number or serial number accepted in step S401 is obtained.

[0174] Next, in step S403 of FIG. 16, for the technical features of the allowed claims included in the patent family data, technical features that can narrow the scope of rights are extracted from the specification, and a prompt (sixth prompt) is created to create a first divisional claim incorporating the results.

[0175] The sixth prompt includes, for example, an instruction such as "Based on the claim data and specification data below, please extract from the specification data the technical feature (technical feature FE) that can narrow the scope of rights for the technical feature (technical feature FD) included in the claim data. Then, please create and present split claim data that combines the narrowing technical feature (technical feature FE) with the technical feature included in the claim data (technical feature FD).", as well as permitted claim data and specification data included in the patent family data.

[0176] Alternatively, the sixth prompt may include instructions such as, "Based on the following claim data and specification data, segment the claim and identify the segment containing a relatively broad technical feature (technical feature FF). Next, extract from the specification data another technical feature (technical feature FG) that can be substituted for the above technical feature (technical feature FF). Then, create and present split claim data that includes the technical feature (technical feature FG) of the more specific concept in place of the technical feature included in the claim data (technical feature FF)." The prompt also includes the allowed claim data and specification data included in the patent family data. For example, the technical feature FG may be a technical feature that corresponds to a more specific concept of technical feature FF. Note that the technical scope of a more specific concept in a patent claim is narrower and more specific than the technical scope of a more specific concept.

[0177] Next, in step S404 of Fig. 16, the sixth prompt is sent to the language model. Based on the prompt, the language model extracts from the specification technical features that can narrow the scope of protection, and creates a first divisional claim incorporating the results (step S405).

[0178] Next, in step S406 of FIG. 16, divided claim data is received from the language model.

[0179] Next, the created divisional claim data is output in step S407 of Fig. 16 as a proposed claim to be used in a divisional application. For example, the output of step S407 may display in area 461 of output example 460 of Fig. 18B the following message: "The third section of claim B (...omitted...) is a relatively broad expression. Another technical feature, 'having insulating material', has been found that can be substituted for the technical feature of the third section. Would you like to use divided claim B' (...omitted...) which includes 'having insulating material'?"

[0180] Furthermore, in response to the output of step S407 in Fig. 16, the user can input whether to "accept" the divided claim data as is or "enter a comment and instruct the information processing system to revise the divided claim (revise instruction)." As a specific example, in area 462 of output example 460 in Fig. 18B, the user can input a revision instruction in text such as "No. Please find in the specification a description of a specific example of a material name for 'insulating material.' Then, please create and submit divided claim data that includes the above material name. If no such description is found, please reply to that effect."

[0181] Next, in step S408 of FIG. 16, the above user input is accepted.

[0182] Next, in step S409 of Fig. 16, it is determined whether or not there is an instruction to correct the divided claim data. If there is an instruction to correct (Yes), the process proceeds to connector E at the branch of step S409 of Fig. 16. Alternatively, if there is no instruction to correct (No), the information processing system is terminated. At this time, it is preferable to save the divided claim data approved by the user in the previous step as a document file on a recording medium or the like.

[0183] The process when the user instructs to amend the divided claim and the process proceeds to connector E in the branch of step S409 in FIG. 16 will be described with reference to FIG.

[0184] As shown in Figure 17, the process proceeds from connector E to step S411. In step S411, another technical feature is extracted from the specification based on the user's comment received in step S408 of Figure 16, and a prompt (seventh prompt) is created to create a second divisional claim incorporating the extracted technical feature.

[0185] An example will be described in which a user gives an instruction in step S408 of FIG. 16 such as, "Search the specification for a specific example of the material name that is exemplified for 'having insulating material,' which is one of the technical features of the currently proposed divided claim, and include it in the divided claim."

[0186] In the above example, the seventh prompt may include an instruction such as, "Based on the claim data and specification data below, please search the specification for a specific example of the material name for the 'insulating material' included in the claim data. Then, please create and submit split claim data that includes the material name above." along with the granted claim data and specification data included in the patent family data.

[0187] Next, in step S412 of Figure 17, the seventh prompt is sent to the language model. Based on the prompt, the language model extracts specific examples of material names from the specification and creates second divided claim data incorporating the results (step S413).

[0188] Next, in step S414 of Fig. 17, the second divided claim data is received from the language model, and then the process proceeds to a connector F. The connector F is connected to step S407 of Fig. 16.

[0189] Next, in the second processing of step S407 in Figure 16, the second divisional claim data is output as a proposal for a claim to be used in a divisional application. Note that in step S407, all divisional claim data created up to this step (first divisional claim data and second divisional claim data) can also be output so that they can be compared and considered.

[0190] In the above output, the user is allowed to select whether to "accept" the divided claim data output in step S407 as is, or to "enter a comment and instruct the information processing system to revise the divided claims (revise instruction)." Next, in step S408 of Fig. 16, the above user selection is accepted.

[0191] Next, in step S409 of FIG. 16, it is determined whether or not there is an instruction to correct the divided claim data. If there is an instruction to correct the divided claim data (Yes), the process proceeds to connector E again at the branch of step S409 of FIG. 16, and the divided claim data is corrected again (re-correction). Alternatively, if there is no instruction to correct the divided claim data (No), the information processing system is terminated. At this time, it is preferable to save the divided claim data approved by the user in the previous step as a document file on a recording medium, etc. Note that the above-mentioned re-correction can be repeated multiple times.

[0192] As explained above, information processing method 3, which is one aspect of the present invention, allows for two-way processing in which user operations and inputs are accepted during a series of processes. This allows the user's know-how to be reflected in the content of the divided claims that are ultimately output, making it possible to create sophisticated divided claims.

[0193] In the information processing method 3 of one embodiment of the present invention described with reference to Figures 16 and 17, which device or terminal performs the processing of each step among the information processing device 10, the information processing device 40, and the information terminal 20 will be described with reference to Figure 19. Note that the configuration example shown in Figure 19 can be used in combination with the configuration example of the information processing method 1 described with reference to Figure 7 and the like and the configuration example of the information processing method 2 described with reference to Figure 11 and the like.

[0194] 19 is a relationship diagram showing the processes performed by the information processing device 10, the information processing device 40, and the information terminal 20 using the symbols for each step used in Fig. 16 and Fig. 17. In addition, block arrows with network 30 attached indicate data transmission and reception between the information processing device 10 and the information processing device 40, and data transmission and reception between the information processing device 10 and the information terminal 20.

[0195] As shown in FIG. 19, the information processing device 10 has a function to perform processing of step S402, a function to perform processing of step S403, a function to perform processing of step S404, a function to perform processing of step S406, a function to perform processing of step S409, a function to perform processing of step S411, a function to perform processing of step S12, and a function to perform processing of step S414.

[0196] As shown in FIG. 19, the information processing device 40 has a function to perform the process of step S405 and a function to perform the process of step S413.

[0197] As shown in FIG. 19, the information terminal 20 has a function to perform the process of step S401, a function to perform the process of step S407, and a function to perform the process of step S408.

[0198] The content of this embodiment can be freely combined with the content of other embodiment modes.

[0199] 10: information processing device, 20: information terminal, 20a: desktop computer, 20b: notebook computer, 20c: smartphone, 20d: tablet computer, 21: housing, 30: network, 40: information processing device, 110: input unit, 120: storage unit, 130: processing unit, 140: output unit, 150: transmission path,

Claims

a first component, a second component, and a third component; The first component comprises: It has the function of accepting division consideration instructions, The second component comprises: A function of acquiring patent family data corresponding to the application information input in the division consideration instruction; creating a first prompt including said patent family data; sending the first prompt to the third component; a function of receiving, from the third component, claim classification data in which the claim data included in the patent family data is classified by technical feature based on an instruction of the first prompt; a function of transmitting a division candidate group to the first component when the division candidate group does not have a patent application in a country under consideration for division in the claim classification data; The third component comprises: a function of creating the claim classification data; transmitting the claim classification data to the second component; The split candidate group is output from the first component. Information processing system. 　 In claim 1, The creation of the claim classification data is carried out using the claim data of registered patents, the claim data of claims for which a patent decision has been made, and the data of claims for which no reasons for refusal have been indicated, which are contained in the patent family data. Information processing system. 　 a first component, a second component, and a third component; The first component comprises: It has the function of accepting division consideration instructions, The second component comprises: A function of acquiring patent family data corresponding to the application information input in the division consideration instruction; creating a first prompt including said patent family data; sending the first prompt to the third component; a function of receiving from the third component analysis data of permitted matters, which extracts permitted matters, which are technical features that are elements of the permitted patent registration, for each claim for which patent registration has been granted from the examination history data and claim data included in the patent family data; and and a function of transmitting divided claim data excluding at least one of the plurality of permission items to the first component when the permission item analysis data includes a plurality of permission items, The third component comprises: a function of generating the permission analysis data based on an instruction of the first prompt; transmitting the claim classification data to the second component; the divided claim data is output from the first component; Information processing system. 　 a first component, a second component, and a third component; The first component comprises: It has the function of accepting division consideration instructions, The second component comprises: A function of acquiring patent family data corresponding to the application information input in the division consideration instruction; creating a first prompt including said patent family data; sending the first prompt to the third component; a function of receiving from the third component, approved matter analysis data created for each approved claim for patent registration from the examination history data and claim data included in the patent family data; a function of generating a second prompt when the permission analysis data does not include a permission that is a technical feature that is an element of the permission; sending the second prompt to the third component; receiving split claim data from the third component; a function of transmitting the divided claim data to the first component; The third component comprises: a function of generating the permission analysis data based on an instruction of the first prompt; transmitting the claim classification data to the second component; a function of creating the divided claim data by deleting one technical feature from the claim data based on an instruction of the second prompt, the divided claim data is output from the first component; Information processing system. 　 a first component, a second component, and a third component; The first component comprises: It has the function of accepting division consideration instructions, The second component comprises: A function of acquiring patent family data corresponding to the application information input in the division consideration instruction; creating a first prompt including said patent family data; sending the first prompt to the third component; a function of receiving from the third component, approved matter analysis data created for each approved claim for patent registration from the examination history data and claim data included in the patent family data; a function of generating a second prompt when the permission analysis data contains only one permission that is a technical feature that is the permitted element; sending the second prompt to the third component; a function of receiving divided claim data from the third component and a function of transmitting the divided claim data to the first component; The third component comprises: a function of generating the permission analysis data based on an instruction of the first prompt; transmitting the claim classification data to the second component; a function of creating the divided claim data by deleting one technical feature other than the permitted items from the claim data based on an instruction of the second prompt, the divided claim data is output from the first component; Information processing system. 　 a first component, a second component, and a third component; The first component comprises: It has the function of accepting division consideration instructions, The second component comprises: A function of acquiring patent family data corresponding to the application information input in the division consideration instruction; creating a first prompt including said patent family data; sending the first prompt to the third component; receiving split claim data from the third component; a function of transmitting the divided claim data to the first component; The third component comprises: a function of creating the divided claim data from the specification data and claim data included in the patent family data based on an instruction from the first prompt, the divided claim data including technical features that are included in the specification data but not included in the claim data; the divided claim data is output from the first component; Information processing system. 　 a first component, a second component, and a third component; The first component comprises: It has the function of accepting division consideration instructions, The second component comprises: A function of acquiring patent family data corresponding to the application information input in the division consideration instruction; creating a first prompt including said patent family data; sending the first prompt to the third component; a function of receiving from the third component, approved matter analysis data created for each approved claim for patent registration from the examination history data and claim data included in the patent family data; a function of generating a second prompt when the permission analysis data does not include a permission that is a technical feature that is an element of the permission; sending the second prompt to the third component; receiving a result of processing the second prompt; a function of creating a third prompt when the first divided claim data is not included in the processing result of the second prompt; sending the third prompt to the third component; receiving second division claim data from the third component; a function of transmitting the second divided claim data to the first component; and The third component comprises: a function of generating the permission analysis data based on an instruction of the first prompt; a function of creating the first divided claim data by deleting one technical feature from the claim data based on an instruction of the second prompt; a function of creating the second divided claim data from the specification data and claim data included in the patent family data based on an instruction of the third prompt, the second divided claim data including technical features that are included in the specification data and that are not included in the claim data; the second divided claim data is output from the first component; Information processing system. 　 a first component, a second component, and a third component; The first component comprises: It has the function of accepting division consideration instructions, The second component comprises: A function of acquiring patent family data corresponding to the application information input in the division consideration instruction; creating a first prompt including said patent family data; sending the first prompt to the third component; receiving split claim data from the third component; a function of transmitting the divided claim data to the first component; The third component comprises: a function of extracting a second technical feature corresponding to a subordinate concept of a first technical feature included in the claim data from the specification data and claim data included in the patent family data based on an instruction of the first prompt, and creating the divided claim data including the second technical feature; the divided claim data is output from the first component; Information processing system. 　 A first step of receiving a division consideration instruction; a second step of acquiring patent family data corresponding to the application information input in the divisional consideration instruction; a third step of generating a prompt for generating divided claim data from the specification data and claim data included in the patent family data, the divided claim data including technical features included in the specification data but not included in the claim data; a fourth step of generating the split claim data in a language model based on instructions from the prompt; a fifth step of outputting the divided claim data; A method for operating an information processing system having the above-mentioned components. 　 A first step of receiving a division consideration instruction; a second step of acquiring patent family data corresponding to the application information input in the divisional consideration instruction; a third step of creating a first prompt for creating permitted matter analysis data for each claim for which patent registration has been granted from the examination history data and claim data included in the patent family data; a fourth step of generating the permission analysis data in a language model based on the instructions of the first prompt; a fifth step of generating a second prompt for generating first divided claim data by deleting one technical feature from the claim data when the permitted item analysis data does not include a permitted item that is a technical feature that is the permitted element; a sixth step of creating the first divided claim data in a language model based on an instruction of the second prompt; a seventh step of generating a third prompt for generating second divided claim data from the specification data and the claim data contained in the patent family data, the second divided claim data including technical features that are contained in the specification data but not contained in the claim data, if the first divided claim data cannot be generated in the sixth step; an eighth step of generating the second divided claim data in a language model based on an instruction of the third prompt; a ninth step of outputting the second divided claim data; A method for operating an information processing system having the above-mentioned components. 　 A first step of receiving a division consideration instruction; a second step of acquiring patent family data corresponding to the application information input in the divisional consideration instruction; a third step of extracting a second technical feature corresponding to a subordinate concept of a first technical feature included in the claim data from the specification data and claim data included in the patent family data, and creating a prompt for creating divided claim data including the second technical feature; a fourth step of generating the split claim data in a language model based on instructions from the prompt; a fifth step of outputting the divided claim data; A method for operating an information processing system having the above-mentioned components. 　 A first step of receiving a division consideration instruction; a second step of acquiring patent family data corresponding to the application information input in the divisional consideration instruction; a third step of extracting a second technical feature corresponding to a subordinate concept of a first technical feature included in the claim data from the specification data and claim data included in the patent family data, and creating a first prompt for creating first divided claim data including the second technical feature; a fourth step of creating the first divided claim data in a language model based on an instruction of the first prompt; a fifth step of outputting the divided claim data; a sixth step of accepting a textual instruction to correct the divided claim data; a seventh step of modifying the first divided claim data based on the sentence and creating a second prompt for creating second divided claim data; an eighth step of generating the second divided claim data in a language model based on an instruction of the second prompt; a ninth step of outputting the second divided claim data; A method for operating an information processing system having the above-mentioned components.

Images