Information processing system and method for operating the same

Abstract

Provided is an information processing device that is excellent in terms of convenience and usefulness. The information processing system can divide claims into respective technical features, compare the respective claims with prior art documents and thereby determine the technical features that are not disclosed in the prior art documents, and generate corrected claims on the basis of the results of the determination. The division, comparison, determination, and generation can be performed using a large-scale language model present in the information processing system. Further, the information processing system can have the function of assigning a recommended order to the generated corrected claims.

Description

Information processing system and its operating method

[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] When a patent applicant files a patent application with the Japan Patent Office, in order to obtain a patent right, the applicant must request examination by submitting a request for examination to the Japan Patent Office within three years from the date of filing the patent application.

[0004] When filing a patent application, prior art documents related to the invention for which a patent is sought are thoroughly researched and the content that is believed to be patentable is filed. However, it is not easy to conduct a thorough search of prior art documents, and new prior art documents may be cited after the patent application has been filed.

[0005] Prior art documents cited after a patent application include prior art documents discovered independently after the application is filed, prior art documents cited for the first time during an international search or international preliminary examination of an application based on the Patent Cooperation Treaty (PCT), prior art documents cited for the first time during the examination process of an application in another country (family application) that has the same basic application, and prior art documents that have the status of a prior application that are published after the patent application is filed.

[0006] When requesting examination, there are often prior art documents discovered after the patent application has been filed, as in the example above. Therefore, when requesting examination, claims may be amended by referring to prior art documents discovered after the patent application has been filed. Note that claims are a division of the matters deemed necessary to identify the invention for which a patent is sought, and a patent may contain one or more claims.

[0007] 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) 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.

[0008] 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>

[0009] When amending claims by referring to prior art documents discovered after the patent application has been filed, there are cases where the scope of the original claims is narrowed or expanded.

[0010] For example, if the technical features described in the original claim are all contained in one or more combinations of prior art documents discovered before the patent application and prior art documents discovered after the patent application, the content of the original claim may be considered for restriction.

[0011] Alternatively, if two or more of the technical features described in the original claim cannot be found even after referring to all prior art documents discovered before and after the patent application, the scope of the original claim may be considered to be expanded to include two or more potentially differentiating technical features. For example, the scope of the original claim may be considered to be expanded to include two or more potentially differentiating technical features individually.

[0012] As explained above, when requesting examination, claims can be amended by referring to not only prior art documents discovered before the patent application but also prior art documents discovered after the patent application. However, it takes a lot of time and effort to consider amendments to claims by referring to each prior art document regarding the content of the original claims.

[0013] Therefore, an object of one embodiment of the present invention is to provide an information processing system capable of amending claims by comparing claims with prior art documents. Another object of one embodiment of the present invention is to provide an information processing system that compares claims with prior art documents and presents a proposed amendment to the claims. Another object of one embodiment of the present invention is to provide an information processing method that compares claims with prior art documents and presents a proposed amendment to the claims. Another object of one embodiment of the present invention is to provide an information processing method that compares claims with prior art documents and presents a proposed amendment to the claims.

[0014] 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.

[0015] 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.

[0016] (1) One aspect of the present invention is a system including a first component, a second component, and a third component. The first component has a function of receiving specification data, claim data, and literature data, and a function of transmitting the specification data, claim data, and literature data to the second component. The second component has a function of creating a first prompt including the claim data, a function of transmitting the first prompt to the third component, a function of receiving from the third component claim decomposition data obtained by decomposing the claim data, a function of creating a second prompt including the claim decomposition data and literature data, a function of transmitting the second prompt to the third component, a function of receiving from the third component a result of determining whether technical features of the claim decomposition data are included in the literature data, and a function of determining whether the claim decomposition data is included in the literature data. a function of generating a third prompt including claim data and the two or more technical features when it is determined that at least two or more technical features among the above are not included in the document data; a function of sending the third prompt to a third component; and a function of receiving amended claim data from the third component, excluding at least one of the two or more technical features determined in the determination that the document does not include the technical feature; wherein the third component has a function of breaking down the claim data into technical features based on an instruction in the first prompt and generating claim decomposition data, a function of making a determination based on an instruction in the second prompt, and a function of generating amended claim data based on an instruction in the third prompt; and the claim decomposition data, the result of the determination, and the amended claim data are output to the first component.

[0017] (2) In the above (1), the second component preferably has a function of creating a fourth prompt including the claim data and the amended claim data, a function of sending the fourth prompt to the third component, and a function of receiving the claim data and the amended claim data with the recommended order from the third component, and the third component preferably has a function of assigning a recommended order to each of the claim data and the amended claim data based on the instructions of the fourth prompt. Note that the claim decomposition data, the determination result, the amended claim data, and the recommended order can be output to the first component.

[0018] (3) One aspect of the present invention includes a first component, a second component, and a third component, the first component having a function of receiving specification data, claim data, and literature data, and a function of transmitting the specification data, claim data, and literature data to the second component, the second component having a function of creating a first prompt including the claim data, a function of transmitting the first prompt to the third component, a function of receiving claim decomposition data from the third component, a function of creating a second prompt including the claim decomposition data and the literature data, a function of transmitting the second prompt to the third component, a function of receiving from the third component a result of determining whether the technical features of the claim decomposition data are included in the literature data, and a function of determining whether the claim decomposition data is valid. a function of generating a third prompt including description data, literature data, and claim data when it is determined that all technical features specified in a claim are included in the literature data; a function of transmitting the third prompt to a third component; and a function of receiving amended claim data from the third component including a first technical feature that is not included in the literature data and claim data but is included in the description data, wherein the third component has a function of breaking down the claim data into technical features based on an instruction in the first prompt and generating claim decomposition data, a function of making a judgment based on an instruction in the second prompt, and a function of generating amended claim data based on an instruction in the third prompt, and the claim decomposition data, the result of the judgment, the first technical feature, and the amended claim data are output to the first component.

[0019] (4) One aspect of the present invention is a technology comprising a first component, a second component, and a third component, wherein the first component has a function of receiving specification data, claim data, and literature data, and a function of transmitting the specification data, claim data, and literature data to the second component, and the second component has a function of creating a first prompt including the claim data, a function of transmitting the first prompt to the third component, a function of receiving claim decomposition data from the third component, a function of creating a second prompt including the claim decomposition data and the literature data, a function of transmitting the second prompt to the third component, a function of receiving from the third component a result of determining whether technical features of the claim decomposition data are included in the literature data, and, when it is determined in the determination that all technical features of the claim decomposition data are included in the literature data, a function of creating a third prompt including the specification data, the literature data, and claim data, and a function of transmitting the third prompt to the third component. a function of sending a prompt to a third component, a function of receiving from the third component a first technical feature that is not included in the literature data and the claim data but is included in the description data, a function of creating a fourth prompt including the claim data and the first technical feature, a function of sending the fourth prompt to the third component, and a function of receiving from the third component amended claim data including the first technical feature, wherein the third component has a function of breaking down the claim data into technical features based on an instruction in the first prompt and creating claim decomposition data, a function of making a determination based on an instruction in the second prompt, a function of obtaining the first technical feature that is not included in the literature data and the claim data but is included in the description data based on an instruction in the third prompt, and a function of creating amended claim data based on the fourth prompt, and the claim decomposition data, the result of the determination, the first technical feature, and the amended claim data are output to the first component.

[0020] (5) In (3) or (4) above, it is preferable that the first component has a function of creating a fifth prompt including the specification data and the first technical feature, a function of sending the fifth prompt to the third component, and a function of receiving from the third component the effect brought about by the first technical feature, and that the third component has a function of extracting the effect from the specification data based on instructions in the fifth prompt.

[0021] (6) In (5) above, it is preferable that the first component has a function of searching for literature data different from the literature data based on the first technical features and effects, and a function of adding the different literature data as literature data included in the second prompt if such data is found.

[0022] (7) One aspect of the present invention is a method for operating an information processing system, the method comprising: a first step of receiving specification data, claim data, and literature data; a second step of creating a first prompt including the claim data; a third step of breaking down the claim data into technical features and creating claim decomposition data based on an instruction in the first prompt; a fourth step of creating a second prompt including the claim decomposition data and the literature data; a fifth step of determining whether the technical features of the claim decomposition data are included in the literature data based on an instruction in the second prompt; a sixth step of creating a third prompt including the claim data and the first technical feature not included in the literature data when it is determined in the determination that all technical features possessed by the claim decomposition data are included in the literature data; a seventh step of creating amended claim data based on an instruction in the third prompt; and an eighth step of outputting the claim decomposition data, the result of the determination, and the amended claim data.

[0023] (8) One aspect of the present invention includes a first step of receiving specification data, claim data, and literature data; a second step of creating a first prompt including the claim data; a third step of breaking down the claim data into technical features and creating claim decomposition data based on an instruction in the first prompt; a fourth step of creating a second prompt including the claim decomposition data and the literature data; a fifth step of determining, based on an instruction in the second prompt, whether the technical features of the claim decomposition data are included in the literature data; and determining in the determination that all technical features possessed by the claim decomposition data are included in the literature data. a sixth step of creating a third prompt including specification data, literature data, and claim data when a technical feature is not included in the literature data and claim data, based on an instruction from the third prompt; a seventh step of acquiring a first technical feature that is included in the specification data and is not included in the literature data and claim data, based on an instruction from the third prompt; an eighth step of creating a fourth prompt including the claim data and the first technical feature; a ninth step of creating amended claim data including the first technical feature, based on an instruction from the fourth prompt; and a tenth step of outputting the claim decomposition data, the result of the determination, and the amended claim data.

[0024] (9) In the above (8), it is preferable to have an eleventh step in which the first technical feature is added to the claim decomposition data instead of the eighth step, and after processing the eleventh step, to return to the fourth step and sequentially perform processing of the fifth to tenth steps.

[0025] According to one aspect of the present invention, an information processing system can be provided that is capable of amending claims by comparing claims with prior art documents. Alternatively, according to one aspect of the present invention, an information processing system can be provided that compares claims with prior art documents and proposes amendments to claims. Alternatively, according to one aspect of the present invention, an information processing method can be provided that is capable of amending claims by comparing claims with prior art documents. Alternatively, according to one aspect of the present invention, an information processing method can be provided that compares claims with prior art documents and proposes amendments to claims.

[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. FIGS. 3A and 3B are diagrams illustrating the information processing method. FIG. 4 is a diagram illustrating the information processing method. FIG. 5 is a diagram illustrating the configuration of an information processing system. FIGS. 6A and 6B are diagrams illustrating an example of output from the information processing system. FIG. 7 is a diagram illustrating the configuration of an information processing device. FIG. 8 is a diagram illustrating the information processing method. FIG. 9 is a diagram illustrating the configuration of an information processing system. FIG. 10 is a diagram illustrating the information processing method. FIG. 11 is a diagram illustrating the information processing method. FIG. 12 is a diagram illustrating the configuration of an information processing system. FIGS. 13A and 13B are diagrams illustrating an example of output from the information processing system. FIG. 14 is a diagram illustrating the information processing method. FIG. 15 is a diagram illustrating the information processing method. FIG. 16 is a diagram illustrating the configuration of an information processing system. FIGS. 17A and 17B are diagrams illustrating the information processing method. FIG. 18 is a diagram illustrating the configuration of an 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 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] Furthermore, 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 . The information processing device 10, the information processing device 40, and the information terminal 20 can each be called a component. The information processing device 10 is a component that enables the above-described operation method, the information processing device 40 is a component that enables execution of a language model, and the information terminal 20 is a component that a user uses.

[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 to 4 are flow diagrams illustrating an example of an information processing method according to one aspect of the present invention. Figure 2 is a flow diagram illustrating the overall flow of the information processing method. Figure 3A is a flow diagram illustrating details of step S111 in Figure 2, and Figure 3B is a flow diagram illustrating details of step S121 in Figure 2. Figure 4 is a flow diagram illustrating details of step S141 in Figure 2.

[0039] The information processing method according to one aspect of the present invention is "started," and in step S101 of Fig. 2, specification data, claim data, and literature data are input to the information processing system. In other words, in step S101, the information processing system accepts the specification data, claim data, and literature data.

[0040] Here, specification data refers to the document data of the specification. Furthermore, claim data refers to the document data of one or more claims described in the claims filed together with the specification. The claim data contains one or more technical features among those described in the detailed description of the invention in the specification. Note that technical features are sometimes called components. Literature data refers to document data such as patent documents or non-patent documents.

[0041] In step S101, one or more claim data can be input. Also, one or more document data can be input. When multiple claim data are input, each of the multiple claim data can be processed one by one in order. In the case of a dependent claim (also called a dependent claim), it is preferable to input it together with the independent claim (also called an independent claim) that it cites.

[0042] Furthermore, when multiple document data are input, each of the multiple document data can be processed one by one in order, and the multiple claim data can be processed for each document data processing. In the following explanation, a method for processing claim data one by one in order will be described.

[0043] In step S111 of Fig. 2, the claim data (first claim data) input in step S101 is decomposed into technical features to generate decomposed claim data (first decomposed claim data). For example, if the claim data has only one technical feature, the decomposed claim data consists of one document data. For example, if the claim data has two technical features, the decomposed claim data consists of two document data. In other words, the decomposed claim data consists of the same number of document data as the number of technical features contained in the claim data.

[0044] Next, in step S121 of Fig. 2, each of the contents (technical features) of the first claim decomposition data created in step S111 is compared with the document data (first document data) input in step S101. As a result of the comparison, it is determined whether each of the technical features of the first claim decomposition data is included in the first document data.

[0045] Next, in step S131 of Fig. 2, if it is determined in step S121 that two or more technical features of the first claim decomposition data are not included in the first document data, the process proceeds to step S141. Note that technical features not included in the first document data are also referred to as first differentiable elements. In other words, the process proceeds to step S141 when there are two or more first differentiable elements.

[0046] Alternatively, in step S131 of FIG. 2, if it is determined as a result of the determination in step S121 that there is only one technical feature in the first claim decomposition data that is not included in the first document data (i.e., two or more technical features are not different), the process proceeds to step S151.

[0047] Next, in step S141 of Fig. 2, amended claim data (first amended claim data) is created. Here, an amended claim is an original claim amended to include at least one of two or more first differentiable elements and to remove at least one of the first differentiable elements. The same number of amended claims can be created as the number of first differentiable elements. In other words, the amended claim data includes document data for one or more amended claims.

[0048] One example of a situation in which the above-mentioned amended claim can be prepared is when the scope of the claim at the time of the patent application was set too narrowly. In such a case, an amended claim with a broader scope can be prepared by removing some of the first differentiable elements from the original claim (the claim at the time of the patent application). For example, if the original claim has a first differentiable element called technical feature A and a first differentiable element called technical feature B, an amended claim with technical feature A but not technical feature B can be prepared, as well as an amended claim with technical feature B but not technical feature A.

[0049] 2, it is checked whether there is any unprocessed claim data among the claim data input in step S101 that has not been processed in steps S111 to S141. If there is any unprocessed claim data in step S151, the process proceeds to step S111, where the unprocessed claim data is processed. Alternatively, if there is no unprocessed claim data in step S151, the process proceeds to step S152.

[0050] 2, it is checked whether there is any unprocessed document data that has not been processed in steps S111 to S151 among the document data input in step S101. If there is any unprocessed document data in step S152, the process proceeds to step S111, where the unprocessed document data is processed. Alternatively, if there is no unprocessed document data in step S152, the process proceeds to step S161.

[0051] Next, in step S161 of FIG. 2, the results of the processes in steps S101 to S152 are output, and the flow of the information processing method shown in FIG. 2 ends.

[0052] The above is the overall flow of an example of an information processing method according to one embodiment of the present invention. Next, step S111 in FIG. 2 will be described in detail with reference to FIG. 3A. Step S121 in FIG. 2 will be described in detail with reference to FIG. 3B. Step S141 in FIG. 2 will be described in detail with reference to FIG. 4.

[0053] [Step S111: Breaking down the claims into technical features] The flow diagram shown in FIG. 3A is a diagram for explaining an example of the process of step S111 in FIG.

[0054] Steps S112 to S115 shown in Fig. 3A are included in the processing of step S111. As the first processing of step S111, in step S112, a prompt (first prompt) for breaking down claim data into technical features is created.

[0055] A prompt for decomposing claim data into technical features includes, for example, first claim data and an instruction such as, "Please decompose the following claims into technical features and create claim decomposition data. Please refer to the following for the format of the claim decomposition data." A prompt can be considered an input sentence that causes a language model to perform a desired operation. When a prompt is given, the language model generates a response content based on the prompt.

[0056] By transmitting the first prompt created in step S112 to the large-scale language model in step S113, the large-scale language model can perform a process of decomposing the first claim data into technical features and creating first decomposed claim data in step S114. Thereafter, in step S115, the first decomposed claim data output from the large-scale language model is received, and the process can proceed to step S121 in FIG. 2.

[0057] [Step S121: Comparison with Literature and Determination for Each Technical Feature] The flow diagram shown in FIG. 3B is a diagram illustrating an example of the processing of step S121 in FIG.

[0058] Steps S122 to S125 shown in Fig. 3B are included in the process of step S121. As the first process of step S121, in step S122, a prompt (second prompt) is created for comparing each technical feature of the claim decomposition data with the literature data to determine whether the technical feature is included in the literature data.

[0059] The prompt for comparing the claim decomposition data with the literature data and determining whether the technical features of the claim decomposition data are included in the literature data includes, for example, first claim decomposition data, the first literature data, and an instruction such as "Compare the technical features of the following claim decomposition data with the literature data item by item, and determine whether the technical features of the compared claim decomposition data are included in the literature data." If the prompt exceeds the text length limit in the determination process, for example, a processing method may be used in which the above-mentioned first literature data is divided and each of the divided first literature data is compared with the first claim decomposition data.

[0060] By sending the second prompt created in step S122 to the large-scale language model in step S123, the large-scale language model can perform a process of comparing each technical feature of the claim decomposition data with the literature data and determining whether the technical feature is included in the literature data in step S124. Thereafter, in step S125, the determination result output from the large-scale language model is received, and the process can proceed to step S131 in Figure 2.

[0061] [Step S141: Creating Corrected Claim Data 1] The flow diagram shown in FIG. 4 is a diagram for explaining an example of the process of step S141 in FIG.

[0062] Steps S142 to S145 shown in Fig. 4 are included in the processing of step S141. As the first processing of step S141, in step S142, a prompt (third prompt) for creating corrected claim data is created.

[0063] The prompt for creating amended claim data includes, for example, the first claim data, the first differentiable element contained in the first claim decomposition data, and an instruction such as, "Please create an amended claim based on the following claim and the first differentiable element so that it includes one first differentiable element each."

[0064] By sending the third prompt created in step S142 to the large-scale language model in step S143, the large-scale language model can be made to perform the process of creating an amended claim in step S144. Thereafter, in step S145, the amended claim data output from the large-scale language model is received, and the process can proceed to step S151 in FIG. 2.

[0065] In the information processing method of one embodiment of the present invention described using Figures 2 to 4, 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 5.

[0066] 5 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 4. 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.

[0067] As shown in FIG. 5, the information processing device 10 has a function to perform processing of step S112, a function to perform processing of step S113, a function to perform processing of step S115, a function to perform processing of step S122, a function to perform processing of step S123, a function to perform processing of step S125, a function to perform processing of step S131, a function to perform processing of step S142, a function to perform processing of step S143, a function to perform processing of step S145, a function to perform processing of step S151, and a function to perform processing of step S152.

[0068] As shown in FIG. 5, the information processing device 40 has a function to perform the process of step S114, a function to perform the process of step S124, and a function to perform the process of step S144.

[0069] As shown in FIG. 5, the information terminal 20 has a function to perform the process of step S101 and a function to perform the process of step S161.

[0070] 6A and 6B show examples of the output of step S161. As shown in Figures 6A and 6B, the output of step S161 can be displayed on the display unit of the information terminal 20. The display unit of the information terminal 20 can be, for example, a liquid crystal display device, a light-emitting device (for example, a light-emitting device having a light-emitting element such as an organic EL element in each pixel), an electrophoretic display device, a DMD (Digital Micromirror Device), a PDP (Plasma Display Panel), an FED (Field Emission Display), or other display device.

[0071] FIG. 6A is a diagram illustrating an example of a screen 200 displayed on the display unit of the information terminal 20, and FIG. 6B is a diagram illustrating details of an area 220 in FIG. 6A.

[0072] 6A, the screen 200 preferably has, for example, an area 211 for displaying an overall image (tree view) of the claim data and an area 212 for displaying an overall image of the amended claim data. It also preferably has an area 220 for displaying the technical features of the claim data and the amended claim data. It may also have a button (OK button) 230 for inputting to the information terminal 20 that the output result of step S161 has been confirmed.

[0073] As shown in the example of FIG. 6B, the area 220 preferably includes an area 222 indicating the technical features of the claim data and an area 224 indicating the technical features of the amended claim data.

[0074] It is preferable that the area 222 showing the technical features of the claim data has a table 223 showing the correspondence with the document data. In the table 223 shown in Fig. 6B, a check mark indicates that the technical feature is described in the document data, and a blank box indicates that the technical feature is not described in the document data.

[0075] In addition, it is preferable that the area 224 showing the technical features of the amended claim data has a table 225 (table 225a and table 225b) showing the correspondence with the literature data for each of the multiple amended claim data created by the information processing system.

[0076] In the example of table 223 shown in Figure 6B, regarding technical feature A, technical feature B, technical feature C, and technical feature D possessed by claim data (independent claim 2), the table shows that technical feature A is described in document 1 (Ref1), technical feature B is described in document 2 (Ref2), technical feature C is not described in either document 1 or document 2, and technical feature D is not described in either document 1 or document 2.

[0077] In addition, the example of Table 225a is a table showing the technical features A, B, and C possessed by one of the plurality of amended claim data (independent claim 2a). Similarly, the example of Table 225b is a table showing the technical features A, B, and D possessed by one of the plurality of amended claim data (independent claim 2b).

[0078] In addition, area 224 may be provided with radio buttons (buttons 226a and 226b) for selecting whether to adopt (YES) or not adopt (NO) each of a plurality of corrected claim data.

[0079] The claim data and amended claim data described above may be displayed in area 220 for all claims at once, but this may make area 220 difficult to view, so it is preferable to use a method of displaying each claim individually, as shown in tabs 221a and 221b in Figure 6B.

[0080] 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.

[0081] <<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.

[0082] As shown in FIG. 7, 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 .

[0083] [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. As the input unit 110, for example, a communication port may be used, or a device such as a personal computer equipped with a communication function may be used.

[0084] 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 .

[0085] [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.

[0086] 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.

[0087] 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.

[0088] 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).

[0089] NOSRAM is an abbreviation for "Nonvolatile Oxide Semiconductor Random Access Memory (RAM)." NOSRAM refers to a memory in which memory cells are two-transistor (2T) or three-transistor (3T) gain cells and 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 readout), 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.

[0090] 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.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] [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.

[0095] 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.

[0096] The processing unit 130 may include, for example, an arithmetic circuit, a central processing unit (CPU), and a graphics processing unit (GPU).

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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).

[0102] 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.

[0103] It is preferable that the information processing device 10 uses AI for at least some of its processing.

[0104] 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).

[0105] 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.

[0106] 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."

[0107] 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."

[0108] The information processing device 10 can perform processing using a natural language processing model that uses AI. As the natural language processing model, it is possible to execute processing using a natural language processing model that uses AI, such as BERT (Bidirectional Encoder Representations from Transformers) or T5 (Text-to-Text Transformer).

[0109] [Output Unit 140] The output unit 140 can output at least one of the calculation results, analysis results, and inference results of the processing unit 130 to the outside of the information processing device 10. As the output unit 140, for example, a communication port or an input device such as a personal computer with a communication function may be used. Furthermore, if the input unit 110 is a device with a communication function, it may be configured to also have the function of the output unit 140.

[0110] 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.

[0111] [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. As the transmission path 150, for example, a LAN (Local Area Network) or the Internet, which is the foundation of the World Wide Web (WWW), may be used.

[0112] <<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.

[0113] The information processing device 40 can perform processing using a natural language processing model using AI. For example, it can execute processing using a natural language processing model using AI, such as BERT or T5.

[0114] 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).

[0115] In the information processing method according to one aspect of the present invention, the process of decomposing claim data into technical features and creating decomposed claim data in step S114 described in FIG. 3A is preferably performed using a large-scale language model. The process of comparing the decomposed claim data with literature data and determining whether the decomposed claim data is included in the literature data in step S124 described in FIG. 3B is preferably performed using a large-scale language model. The process of creating amended claim data in step S144 described in FIG. 4 is preferably performed using a large-scale language model. These processes can be performed using large-scale language models such as GPT-3 (registered trademark), GPT-3.5, LaMDA, PaLM, Llama2, and Llama3.

[0116] Furthermore, the information processing device 40 can execute processing using a general-purpose language processing model that can perform various natural language processing tasks.

[0117] 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.

[0118] 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. Also, 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 large-scale AI model compared to the information processing device 10.

[0119] 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.

[0120] <<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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] <<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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] [Consideration of the recommended order of claims] As explained above, by using the information processing device of one aspect of the present invention, it is possible to compare claims with prior art documents and amend the claims. In this case, by performing processing using the information processing method explained in Figures 2 to 4, newly created amended claims may be added, and the number of claims may increase.

[0132] The number of claims varies depending on the country in which the application is filed. For example, there may be a limit on the number of independent claims, the examination costs may increase depending on the number of independent claims, or the examination costs may increase depending on the total number of claims. Therefore, as an example of an information processing method according to one aspect of the present invention, it is preferable to have a function for providing a recommended order for claims, as this makes it easier to comply with the regulations of each country. Details of this will be explained using Figures 8 and 9.

[0133] The recommendation order of claims is preferably examined after the processing of step S152 in the flow of FIG. 2, for example.

[0134] As shown in FIG. 8, if there is no unprocessed document data in step S152, the process proceeds to step S153.

[0135] In step S153, a prompt (fourth prompt) is created to assign a recommendation order to each of the claim data input in step S101 and the amended claim data created in step S141.

[0136] The prompt for assigning the recommended order includes, for example, claim data, amended claim data, and instructions such as "Please arrange the following claims and amended claims in order of broader scope of rights at the top," or "Please arrange the following claims and amended claims in order of including differentiating elements and having fewer technical features other than the differentiating elements at the top."

[0137] The fourth prompt created in step S153 is sent to the large-scale language model in step S154, which allows the large-scale language model to assign a recommendation order to each of the claim data and amended claim data in step S155. Thereafter, the claim data and amended claim data with the assigned recommendation order are received in step S156, and the process can proceed to step S161.

[0138] In the information processing method of one embodiment of the present invention described with reference to FIG. 8 , which device or terminal among the information processing device 10, the information processing device 40, and the information terminal 20 performs the processing of each step will be described with reference to FIG. 9 .

[0139] As shown in FIG. 9, the information processing device 10 has a function to perform the processing of step S152, a function to perform the processing of step S153, a function to perform the processing of step S154, and a function to perform the processing of step S156.

[0140] As shown in FIG. 9, the information processing device 40 also has a function of performing the process of step S155.

[0141] As shown in FIG. 9, the information terminal 20 has a function of performing the process of step S161.

[0142] A plurality of configuration examples shown in this embodiment mode can be combined as appropriate.

[0143] 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 Fig. 10 to Fig. 17. Note that the same reference numerals are used for the same parts as those in this embodiment 1, and description thereof will be omitted in some cases.

[0144] [Information Processing Method 2] Figures 10 and 11 are flow diagrams illustrating an example of an information processing method according to one aspect of the present invention. Figure 10 is a flow diagram illustrating the overall flow of the information processing method. Figure 11 is a flow diagram illustrating the details of the processing that follows from connector a in Figure 10.

[0145] Here, the explanation of the processing of steps S101 to S121 in Fig. 10 will be omitted because it is the same as the processing of steps S101 to S121 in Fig. 2. Note that the processing of step S121 determines whether or not first claim decomposition data obtained by decomposing the first claim is included in the first document data.

[0146] Next, in step S130 of FIG. 10, if it is determined as a result of the determination in step S121 that all of the technical features possessed by the first claim decomposition data are included in the first document data, the process proceeds to connector a in FIG. 11.

[0147] Alternatively, in step S130 of FIG. 10, if it is determined as a result of the determination in step S121 that there is at least one technical feature of the first claim decomposition data that is not included in the first document data (not all technical features are included), the process proceeds to step S131.

[0148] When proceeding to connector a in Figure 10, a second amended claim data is created. Here, the second amended claim is an original claim amended to include a technical feature not included in the first document data and claim data but included in the specification data. The technical feature not included in the first document data and claim data but included in the specification data is also referred to as a second differentiable element.

[0149] Next, the series of processes following the connector a will be described in detail. Steps S142A to S145A shown in Fig. 11 differ from step S141 in Fig. 10 in the creation of amended claim data. First, in step S142A, a prompt (fifth prompt) for creating amended claim data is created.

[0150] A prompt for creating amended claim data includes, for example, first specification data, first literature data, and first claim data, and an instruction such as, "Please extract a second differentiable element based on the following specification, literature, and claim.Furthermore, please create an amended claim based on the following claim and the extracted second differentiable element so that it includes one or more second differentiable elements."

[0151] By sending the fifth prompt created in step S142A to the large-scale language model in step S143A, the large-scale language model can be caused to perform processing to create an amended claim in step S144A. Thereafter, in step S145A, amended claim data output from the large-scale language model is received, and the process can proceed to step S151 in FIG. 10.

[0152] One example of a situation in which the above-mentioned amended claim can be prepared is when the scope of the claim at the time of the patent application was set broader than necessary. In such a case, a part of the second differentiable element can be added to the original claim (the claim at the time of the patent application) to prepare an amended claim with a narrower scope of the claim. For example, by adding a second differentiable element, technical feature B, to technical feature A possessed by the original claim, an amended claim can be prepared that has both technical feature A and technical feature B.

[0153] When the series of processes shown in FIG. 11 is completed, the process proceeds to a connector b in FIG. 10, and then to step S151.

[0154] The processing of steps S131 to S161 in FIG. 10 is the same as the processing of steps S131 to S161 in FIG. 2, and therefore a description thereof will be omitted.

[0155] The above is the overall flow of an example of an information processing method according to one embodiment of the present invention.

[0156] In the information processing method of one embodiment of the present invention described using Figures 10 and 11, it will be explained using Figure 12 which device or terminal, information processing device 10, information processing device 40, or information terminal 20, performs the processing of each step.

[0157] As shown in FIG. 12, the information processing device 10 has a function to perform processing of step S112, a function to perform processing of step S113, a function to perform processing of step S115, a function to perform processing of step S122, a function to perform processing of step S123, a function to perform processing of step S125, a function to perform processing of step S130, a function to perform processing of step S131, a function to perform processing of step S142A, a function to perform processing of step S143A, a function to perform processing of step S145A, a function to perform processing of step S151, and a function to perform processing of step S152.

[0158] As shown in FIG. 12, the information processing device 40 has a function to perform the process of step S114, a function to perform the process of step S124, and a function to perform the process of step S144A.

[0159] As shown in FIG. 12, the information terminal 20 has a function to perform the process of step S101 and a function to perform the process of step S161.

[0160] 13A and 13B show an example of the output of step S161 after steps S142A to S145A. Figures 13A and 13B are different examples of Figures 6A and 6B, and the same reference numerals are used for corresponding functions. That is, Figure 13A is a diagram illustrating an example of a screen 200 displayed on the display unit of information terminal 20, and Figure 13B is a diagram illustrating details of area 220 in Figure 13A.

[0161] In Fig. 13A, the description of the parts that are the same as the configuration in Fig. 6A will be omitted. Also, in Fig. 13B, the description of the parts that are the same as the configuration in Fig. 6B will be omitted.

[0162] In FIG. 13B, the area 220 shown in FIG. 6B and the radio buttons (button 226a and button 226b) included in the area 254 are omitted.

[0163] As shown in Figure 13B, area 220 preferably includes area 252 showing technical features of the specification data and area 254 showing technical features of the amended claim data. Area 252 showing technical features of the specification data preferably includes table 253 showing the correspondence between claim data and literature data. In table 253 shown in Figure 13B, a check mark indicates that the technical feature is described in the claim data or literature data. A blank space indicates that the technical feature is not described in the claim data or literature data.

[0164] In addition, in the area 254 showing the technical features of the amended claim data, it is preferable to have a table (e.g., Table 255a and Table 255b) showing the correspondence between the claim data and the literature data for each of the multiple amended claim data created by the information processing system, as shown in Figure 13B.

[0165] The example of table 253 shown in Figure 13B indicates that technical feature A, technical feature B, and technical feature C possessed by the specification data are described in the claim data (independent claim 2), that technical feature A and technical feature B are described in document 1 (Ref1), and that technical feature A and technical feature C are described in document 2 (Ref2). Furthermore, the table indicates that technical feature D possessed by the specification data is not described in either document 1 or document 2, and that technical feature E is not described in either document 1 or document 2. In other words, in this case, technical feature D and technical feature E can be considered candidates for the second differentiable element.

[0166] In addition, in area 254, radio buttons (button 226a, button 226b) may be used to select whether to adopt technical feature D and technical feature E as second differentiable elements (YES) or not (NO).

[0167] In addition, the example of table 255a is a table showing technical features A, B, C, D, and E possessed by one of the plurality of amended claim data (independent claim 2a). Similarly, the example of table 255b is a table showing technical features A, B, C, and D possessed by one of the plurality of amended claim data (independent claim 2b). In addition, in area 254, document 1 and document 2 may be collectively displayed as document (Ref).

[0168] 14 and 15 are flowcharts each illustrating another example of the process continuing from the connector a in FIG.

[0169] [Step S261: Creating Amended Claim Data 2] As the first process shown in FIG. 14, in step S201, a prompt (sixth prompt) for extracting a second differentiable element from the specification data is created.

[0170] The prompt for extracting the second differentiable element includes, for example, first specification data, first literature data, and first claim data, and an instruction such as, "Please extract the second differentiable element based on the following specification, literature, and claims."

[0171] The sixth prompt created in step S201 is sent to the large-scale language model in step S211, which allows the large-scale language model to extract a second differentiable element in step S221. Thereafter, the second differentiable element extracted from the large-scale language model is received in step S231.

[0172] Next, in step S241 shown in FIG. 14, a prompt (seventh prompt) for creating corrected claim data is created from the second differentiable element.

[0173] The prompt for creating corrected claim data includes, for example, first claim data and a second differentiable element, and an instruction such as, "Please create corrected claim data based on the following claim and second differentiable element."

[0174] By transmitting the seventh prompt created in step S241 to the large-scale language model in step S251, the large-scale language model can be caused to perform processing to create amended claim data in step S261. Thereafter, in step S271, the amended claim data created from the large-scale language model is received. In Fig. 14, when the series of processes has been completed, the process proceeds to connector b in Fig. 10, and then to step S151.

[0175] [Step S341: Creating Claim Data] The processing of steps S201 to S231 shown in FIG. 15 is the same as the processing of steps S201 to S231 in FIG. 14, and therefore a description thereof will be omitted.

[0176] In step S341 shown in Fig. 15, the second differentiable element extracted in step S221 shown in Fig. 15 is added to the claim decomposition data created in step S111 shown in Fig. 10. This makes it possible to create claim data to which the second differentiable element has been added. In Fig. 15, when a series of processes has been completed, the process proceeds to connector c in Fig. 10, and then to step S121.

[0177] In the information processing method of one embodiment of the present invention described with reference to FIGS. 14 and 15 , which of the information processing device 10 and the information processing device 40 performs the processing of each step will be described with reference to FIG. 16 .

[0178] As shown in FIG. 16, the information processing device 10 has a function to perform processing of step S201, a function to perform processing of step S211, a function to perform processing of step S231, a function to perform processing of step S241, a function to perform processing of step S251, a function to perform processing of step S271, and a function to perform processing of step S341.

[0179] As shown in FIG. 16, the information processing device 40 has a function to perform the process of step S221 and a function to perform the process of step S261.

[0180] [Extracting Effects] It may be advantageous to describe the effects of the invention when communicating with the examiner. Therefore, it is preferable to understand the effects of the invention in advance. In addition, since the person in charge of the invention at the time of filing the application may be different from the person in charge at the time of requesting examination, it is preferable to create and save data summarizing the effects of the invention (also called invention effect data), as this will make it easier for future people to understand the effects of the invention more efficiently.

[0181] In order to create the effect data of the invention, it is preferable to extract the effect of the invention from the specification. This will be explained in detail using Figure 17A. Note that the process of extracting the effect of the invention from the specification does not have to be performed.

[0182] The process of step S231 in FIG. 17A is similar to step S231 in FIGS. 14 and 15, and therefore description thereof will be omitted.

[0183] In step S411 in FIG. 17A, a prompt (eighth prompt) is created to extract the effect (also called the effect of the invention) brought about by the second differentiable element received in step S231.

[0184] A prompt for extracting the effects of the invention includes, for example, first specification data, a second differentiable element, and an instruction such as, "Please extract the effects of the invention from the specification data below."

[0185] The eighth prompt created in step S411 is sent to the large-scale language model in step S421, and the large-scale language model can then perform a process of extracting the effects of the invention in step S431. Next, in step S441, the effects of the invention extracted in step S431 are received.

[0186] In step S451 of FIG. 17A, effect data of the invention is created, including the second differentiable element and the effect of the invention. It is more preferable that the effect data of the invention include a paragraph number describing the effect of the invention. Furthermore, the effect data of the invention may be stored in the information processing system of the present invention, or may be stored in a database or the like external to the information processing system. Then, the process can proceed to step S241 of FIG. 14 or step S341 of FIG. 15.

[0187] By creating the effect data of the invention in step S451, the person in charge can refer to the effect data of the invention when explaining the effect of the invention to the examiner in a written opinion, petition, etc. This makes it possible to efficiently explain the advantageous effects of the invention.

[0188] [Addition of Documents] As mentioned above, when requesting examination, claims may be amended by referring to prior art documents discovered after the patent application is filed. Here, since the second differentiable element is not considered as a component of the claim before the information processing, it is preferable to search for a new document (second document) containing the second differentiable element.

[0189] If the technical features of the invention are described in a prior art document, differentiating the invention from the prior art document before filing a request for examination will enable you to create claims that are more likely to be granted a patent. Also, if the technical features of the invention are described in a prior art document, it will be possible to reduce the number of notices of reasons for refusal from the examiner, thereby shortening the time it takes to obtain a patent.

[0190] The process of searching for the second document will be described in detail with reference to Fig. 17B. Note that the process of searching for the second document does not necessarily have to be performed.

[0191] The processing of step S151 in FIG. 17B is the same as the processing of step S151 shown in FIG. 10 when there is no unprocessed claim data, and therefore a description thereof will be omitted.

[0192] By performing steps S551 and S552 in Fig. 17B, it is determined that there are unprocessed documents in step S152 shown in Fig. 10. Therefore, after step S552, the process proceeds to step S111 (via step S152).

[0193] In step S551 shown in FIG. 17B, a process for searching for the second document is performed. At this time, the second document can be searched for using a database or search site for patents or papers. Specifically, for example, the search may be performed using a database such as the Patent Information Platform (J-PlatPat), or by accessing a paper search site via the Internet. Furthermore, if there is a database of independently collected patents or papers, that database may be searched. In this way, the means for searching for the second document are not limited.

[0194] If the second document is found in step S551, the process can proceed to step S552. Alternatively, if it is known in advance that the second document exists, the process can skip step S551 and proceed to step S552. Alternatively, if the second document is not found in step S551, the process proceeds to step S152 in FIG. 10.

[0195] In step S552 shown in Fig. 17B, the data of the second document is added as unprocessed document data to the document data input in step S101 shown in Fig. 10. Unprocessed document data refers to document data that has not been processed in steps S111 to S151 among the document data input in step S101 shown in Fig. 10. Thereafter, the process proceeds to step S111 in Fig. 10, where the unprocessed document data is processed.

[0196] In the information processing method of one embodiment of the present invention described with reference to FIGS. 17A and 17B, which of information processing device 10 and information processing device 40 performs the processing of each step will be described with reference to FIG. 18.

[0197] As shown in FIG. 18, the information processing device 10 has a function to perform processing of step S231, a function to perform processing of step S411, a function to perform processing of step S421, a function to perform processing of step S441, a function to perform processing of step S451, a function to perform processing of step S151, a function to perform processing of step S551, and a function to perform processing of step S552.

[0198] As shown in FIG. 18, the information processing device 40 has a function of performing the process of step S431.

[0199] A plurality of configuration examples shown in this embodiment mode can be combined as appropriate.

[0200] 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

having a first component, a second component, and a third component; The first component comprises: A function for accepting specification data, claim data, and literature data; transmitting the specification data, the claim data, and the literature data to a second component; and The second component comprises: creating a first prompt including the claim data; sending the first prompt to the third component; receiving claim resolution data from the third component; creating a second prompt that includes the claim decomposition data and the bibliographic data; sending the second prompt to the third component; a function of receiving, from the third component, a result of determining whether the technical features of the claim decomposition data are included in the document data; a function of generating a third prompt including the claim data and the two or more technical features when it is determined in the determination that the two or more technical features of the claim decomposition data are not included in the document data; sending the third prompt to the third component; a function of receiving, from the third component, amended claim data in which at least one of the two or more technical features is excluded in the determination; and The third component comprises: a function of decomposing the claim data into technical features based on an instruction of the first prompt, and creating the claim decomposition data; making the determination based on an instruction of the second prompt; a function of creating the amended claim data based on an instruction of the third prompt; and the claim decomposition data, the result of the determination, and the amended claim data are output to a first component; Information processing system. 　 In claim 1, The second component comprises: generating a fourth prompt including the claim data and the amended claim data; sending the fourth prompt to the third component; a function of receiving the claim data and the amended claim data with the recommendation order from the third component; and the third component has a function of assigning the recommendation order to each of the claim data and the amended claim data based on an instruction of the fourth prompt; The claim decomposition data, the determination result, the amended claim data, and the recommendation order are output to a first component. Information processing system. 　 having a first component, a second component, and a third component; The first component comprises: A function for accepting specification data, claim data, and literature data; transmitting the specification data, the claim data, and the literature data to a second component; and The second component comprises: creating a first prompt including the claim data; sending the first prompt to the third component; receiving claim resolution data from the third component; creating a second prompt that includes the claim decomposition data and the bibliographic data; sending the second prompt to the third component; a function of receiving, from the third component, a result of determining whether the technical features of the claim decomposition data are included in the document data; a function of generating a third prompt including the specification data, the literature data, and the claim data when it is determined in the determination that all technical features of the claim decomposition data are included in the literature data; sending the third prompt to the third component; receiving, from the third component, amended claim data including a first technical feature that is not included in the literature data and the claim data and is included in the specification data; and The third component comprises: a function of decomposing the claim data into technical features based on an instruction of the first prompt, and creating the claim decomposition data; making the determination based on an instruction of the second prompt; a function of creating the amended claim data based on an instruction of the third prompt; and the claim decomposition data, the determination result, the first technical feature, and the amended claim data are output to a first component; Information processing system. 　 having a first component, a second component, and a third component; The first component comprises: A function for accepting specification data, claim data, and literature data; transmitting the specification data, the claim data, and the literature data to a second component; and The second component comprises: creating a first prompt including the claim data; sending the first prompt to the third component; receiving claim resolution data from the third component; creating a second prompt that includes the claim decomposition data and the bibliographic data; sending the second prompt to the third component; a function of receiving, from the third component, a result of determining whether the technical features of the claim decomposition data are included in the document data; a function of generating a third prompt including the specification data, the literature data, and the claim data when it is determined in the determination that all technical features of the claim decomposition data are included in the literature data; sending the third prompt to the third component; receiving, from the third component, a first technical feature that is not included in the literature data and the claim data and that is included in the specification data; creating a fourth prompt including the claim data and the first technical feature; sending the fourth prompt to the third component; receiving, from the third component, amended claim data including the first technical feature; and The third component comprises: a function of breaking down the claim data into technical features based on an instruction from the first prompt, and creating claim breakdown data; making the determination based on an instruction of the second prompt; a function of acquiring the first technical feature that is not included in the literature data and the claim data and is included in the description data, based on an instruction of the third prompt; a function of creating the amended claim data based on the fourth prompt; and the claim decomposition data, the determination result, the first technical feature, and the amended claim data are output to a first component; Information processing system. 　 In claim 3 or claim 4, the first component has a function of creating a fifth prompt including the specification data and the first technical feature; sending the fifth prompt to the third component; a function of receiving the effect of the first technical feature from the third component; and the third component has a function of extracting the effect from the specification data based on an instruction of the fifth prompt; Information processing system. 　 In claim 5, the first component has a function of searching for literature data different from the literature data based on the first technical feature and the effect; Information processing system. 　 a first step of accepting specification data, claim data, and literature data; a second step of creating a first prompt including the claim data; a third step of decomposing the claim data into technical features based on the instruction of the first prompt, and creating claim decomposition data; a fourth step of creating a second prompt including the claim decomposition data and the bibliographic data; a fifth step of determining whether the technical features of the claim decomposition data are included in the document data based on the instruction of the second prompt; a sixth step of creating a third prompt including the claim data and a first technical feature not included in the literature data when it is determined in the determination that all technical features included in the claim decomposition data are included in the literature data; a seventh step of creating amended claim data based on instructions from the third prompt; an eighth step of outputting the claim decomposition data, the result of the determination, and the corrected claim data; A method of operating an information processing system comprising: 　 a first step of accepting specification data, claim data, and literature data; a second step of creating a first prompt including the claim data; a third step of decomposing the claim data into technical features based on the instruction of the first prompt, and creating claim decomposition data; a fourth step of creating a second prompt including the claim decomposition data and the bibliographic data; a fifth step of determining whether the technical features of the claim decomposition data are included in the document data based on the instruction of the second prompt; a sixth step of creating a third prompt including the description data, the literature data, and the claim data when it is determined in the determination that all technical features included in the claim decomposition data are included in the literature data; a seventh step of acquiring a first technical feature that is not included in the literature data and the claim data and is included in the description data, based on an instruction of the third prompt; an eighth step of creating a fourth prompt including the claim data and the first technical feature; a ninth step of creating amended claim data including the first technical feature based on an instruction of the fourth prompt; a tenth step of outputting the claim decomposition data, the result of the determination, and the corrected claim data; A method of operating an information processing system comprising: 　 In claim 8, Instead of the eighth step, an eleventh step of adding the first technical feature to the claim decomposition data is provided; A method for operating an information processing system, wherein after the processing of the eleventh step, the method returns to the fourth step and sequentially performs the processing of the fifth step to the tenth step.

Images