Information processing device, information processing method, and program

Abstract

To provide an information processing device capable of reducing the time required to complete a specification. [Solution] The information processing device includes a reception unit that receives information related to the invention and feedback related to the first specification, an instruction unit that issues a first instruction to a language model to instruct the creation of the first specification based on the information related to the invention and a second instruction to instruct the creation of a second specification that is more detailed than the first specification based on the feedback, and an output unit that outputs the results generated by the language model in response to the first instruction and the second instruction.

Description

[Technical Field]

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

[0002] When filing a patent application, a technology is known that uses a large language model (LLM) to create an application specification. By using an LLM, a specification can be automatically generated based on information about the invention entered by the user. Patent Document 1 discloses a specification creation support device that can significantly reduce the workload of a specification creator. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2023-006493 Summary of the Invention [Problem to be solved by the invention]

[0004] In specification creation systems using LLM, the generated specifications may differ from the user's intentions. In this case, the user must check the completed specifications and point out any corrections, which can take more time than necessary.

[0005] An object of the present disclosure is to provide an information processing device that can solve the above-mentioned problems. [Means for solving the problem]

[0006] The present disclosure provides an information processing device comprising: a receiving means for receiving information related to an invention and feedback related to a first specification; an instruction means for issuing to a language model a first instruction for instructing the creation of the first specification based on the information related to the invention; and a second instruction based on the feedback for instructing the creation of a second specification that is more detailed than the first specification; and an output means for outputting the results generated by the language model in response to the first instruction and the second instruction.

[0007] The present disclosure also provides an information processing method that receives information related to an invention and feedback related to a first specification, issues a first instruction to a language model to instruct the creation of the first specification based on the information related to the invention, and a second instruction based on the feedback to instruct the creation of a second specification that is more detailed than the first specification, and outputs the results generated by the language model in response to the first instruction and the second instruction.

[0008] The present disclosure also provides a program that causes a computer to execute the following processes: a process of receiving information related to an invention and feedback related to a first specification; a process of issuing a first instruction to a language model to instruct the creation of the first specification based on the information related to the invention; and a second instruction based on the feedback to instruct the creation of a second specification that is more detailed than the first specification; and a process of outputting the results generated by the language model in response to the first instruction and the second instruction. [Effects of the Invention]

[0009] The present disclosure can reduce the time it takes to complete a specification. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a block diagram showing a hardware configuration of an information processing device according to the present disclosure. [Figure 2] FIG. 10 is a block diagram illustrating another example of an information processing device according to the present disclosure. [Figure 3]FIG. 10 is a diagram showing an example in which a reception unit receives information related to an invention through a chat-style UI. [Figure 4] FIG. 10 is a diagram illustrating an example in which a reception unit receives feedback through a chat-style UI. [Figure 5] 10 is a flowchart illustrating another example of the procedure of the process performed by the information processing device according to the present disclosure. [Figure 6] FIG. 10 is a block diagram illustrating another example of an information processing device according to the present disclosure. [Figure 7] 10 is a flowchart illustrating another example of the procedure of the process performed by the information processing device according to the present disclosure. [Figure 8] FIG. 10 is a block diagram illustrating another example of an information processing device according to the present disclosure. [Figure 9] 10 is a flowchart illustrating another example of the procedure of the process performed by the information processing device according to the present disclosure. [Figure 10] FIG. 10 is a block diagram illustrating another example of an information processing device according to the present disclosure. [Figure 11] FIG. 10 is a diagram showing an example of outputting a query as to whether to apply a general technique to a portion where information is insufficient. [Figure 12] 10 is a flowchart illustrating another example of the procedure of the process performed by the information processing device according to the present disclosure. [Figure 13] FIG. 10 is a block diagram illustrating another example of an information processing device according to the present disclosure. [Figure 14] 10 is a flowchart illustrating another example of the procedure of the process performed by the information processing device according to the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0011] (Hardware configuration) Hereinafter, an embodiment of the present disclosure will be described with reference to the drawings. First, a hardware configuration for realizing an information processing device according to the present disclosure will be described. FIG. 1 is a block diagram showing the hardware configuration of the information processing device. The information processing device is realized by a computer 10.

[0012] The computer 10 includes a processor 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a storage device 14 such as a hard disk for storing programs, an input / output interface 15 for inputting and outputting data, and a communication interface 16 for network connection. Each component is connected via a bus 17.

[0013] The processor 11 runs an operating system to control the entire computer. Examples of the processor 11 include a CPU (Central Processing Unit), a DSP (Digital Signal Processor), and a GPU (Graphics Processing Unit). The processor 11 loads a program stored in, for example, the ROM 12 or the storage device 14. The processor 11 then executes each process coded in the program. The processor 11 may execute the processes or instructions in the illustrated flowchart based on the program.

[0014] The ROM 12 stores application programs, programs according to the embodiments, etc. The RAM 13 is used as a work area for the processor 11.

[0015] Examples of the storage device 14 include a semiconductor memory such as a flash memory, an HDD (Hard Disk Drive), etc. The storage device 14 stores, for example, an OS (Operating System) program, application programs, programs according to each embodiment, etc.

[0016] The input / output interface 15 is connected to peripheral devices (not shown) via a wired network or a wireless network.

[0017] The communication interface 16 is connected to a communication network (not shown), such as a LAN (Local Area Network) or a WAN (Wide Area Network), via a wireless or wired network. The communication network may be configured with multiple communication networks. As a result, the computer is connected to an external large-scale language model server that configures a large-scale language model LLM via the communication network. The computer 10 may have components other than those shown in FIG. 1. For example, the computer 10 may have a drive device or the like. For example, the processor 11 may be attached to a drive device or the like and read programs and data stored in a non-transitory tangible recording medium into the RAM 13.

[0018] The computer 10 that realizes the information processing device may be configured to include some of the components described in FIG. 1. For example, the computer 10 that realizes the information processing device may be configured to include only the processor 11, ROM 12, and RAM 13 among the components described above. In this case, the storage device 14, input / output interface 15, and communication interface 16 may each be provided as an external device. Also, some of the calculation functions may be realized by an external server, cloud, or the like. The language model 101 is provided outside the information processing device 100 and is connected to the information processing device 100 via a communication network. However, the information processing device 100 may have the language model 101 internally, and the specific manner of connection is not limited.

[0019] When using LLM to create a patent application specification, the output specification may differ from what was expected. In this case, the user must check the completed specification and point out any corrections, which can be unnecessarily time-consuming.

[0020] When creating a specification using an LLM, the information processing device 100 according to the present disclosure gives instructions to the LLM to create a provisional simplified specification. The information processing device then receives a specification creation instruction from the user based on the contents of the provisionally created simplified specification. The information processing device 100 then gives detailed specification creation instructions to the LLM based on the received instructions to create the specification. This makes it possible to create a specification in line with the user's intentions, thereby reducing the time required to complete the specification.

[0021] Hereinafter, the first specification is a provisional specification prepared at the initial stage of specification preparation by the information processing device 100. The first specification is sufficient if it allows the user to grasp the outline and direction of the description of the specification, and does not have to meet the description requirements of the Patent Act. In other words, the first specification does not need to include all of the description items of the specification, and the explanation may be partial. The first specification may also be called a provisional specification.

[0022] The second specification is a specification prepared based on the first specification. The second specification is a specification that has been added or amended to the first specification in accordance with the user's intentions, in response to instructions from the user who has referred to the first specification. It is assumed that the second specification satisfies the description requirements and other matters to the extent that it can be used in a patent application as is, or with further necessary additions or amendments. The second specification may also be referred to as the present specification.

[0023] 2 shows an example of an information processing device 100. The information processing device 100 includes a reception unit 110, an instruction unit 120, and an output unit 130. The information processing device 100 is also connected to a language model 101. In the example shown in FIG. 1, the language model 101 is provided outside the information processing device 100 and is connected to the information processing device 100 via a communication network. However, the information processing device 100 may include the language model 101 internally, and the specific mode of connection is not limited.

[0024] The receiving unit 110 is a receiving means for receiving information about the invention and feedback about the first specification from the user. The information about the invention is information that indicates the content of the invention and is used to create the first specification. The information about the invention is not particularly limited in format or detail as long as it is information that allows the content of the invention to be understood. The information about the invention may be an invention description that explains the specific configuration and operation of the invention, or an idea outline that concisely shows the main points of the invention.

[0025] The reception unit 110 receives information related to an invention through a user interface (UI). As an example, the reception unit 110 displays a message such as "Please enter an outline of the invention" on a chat-style UI and receives text input from the user. Figure 3 shows an example of the reception unit 110 receiving information related to an invention through a chat-style UI.

[0026] The receiving unit 110 may allow the user to input information about the invention in stages. For example, the receiving unit 110 may sequentially display specific questions such as "What problem does the invention aim to solve?", "How does it solve that problem?", and "What are the effects of this invention?" in a chat-style UI and accept the user's answers. This allows the user to input appropriate invention information even when the user is unable to adequately verbalize the outline of the invention or is unfamiliar with technical terms.

[0027] The feedback regarding the first specification is feedback for the user to make corrections or additions to the first specification output by the output unit 130 as described below. The feedback is created by the user who has referenced the output first specification. The receiving unit 110 receives, as feedback, for example, the content to be added or corrected, or the designation of the part to be added or corrected. FIG. 4 shows an example in which the receiving unit 110 receives feedback through a chat-style UI.

[0028] The feedback may also be evaluation information, which may be presented in a more structured format, including, for example, a rating for each part of the specification and a checklist of areas for improvement.

[0029] The receiving unit 110 receives feedback on the first specification via, for example, a chat-style UI. The receiving unit 110 may receive the feedback all at once, or may receive the feedback by having the user input it in stages.

[0030] The receiving unit 110 may receive information and feedback related to the invention from a UI that allows general text input, not limited to a chat-style UI. The receiving unit 110 may also receive information and feedback related to the invention through voice input or handwritten input, and is not particularly limited thereto.

[0031] The instruction unit 120 is an instruction means for issuing a first instruction to the language model 101, which instructs the creation of a first specification based on information about the invention, and a second instruction, which is an instruction based on feedback and instructs the creation of a second specification that is more detailed than the first specification. The first instruction and the second instruction are expressed, for example, as prompts to be input to the language model 101.

[0032] The first instruction instructs the preparation of the first specification, and includes, but is not limited to, referring to information based on the invention, instructing the preparation of descriptions for items to be described in the first specification, and specifying constraints on the description content or the description format. The first instruction is input to the language model 101 together with the information based on the invention. The information related to the invention and the first instruction may be input to the language model 101 as a single prompt or as multiple prompts. A specific example of the first instruction is, but is not limited to, "Based on the input summary of the invention, please prepare a specification including the following sections: 'Background Art,' 'Problem to be Solved by the Invention,' 'Means for Solving the Problem,' and 'Effectiveness of the Invention.' Each section should be written in 200 characters or more and include at least one specific example."

[0033] The first instruction may also be a plurality of instructions divided into sections of the specification (background art, problem, solution, effect). In this case, the instruction unit 120 may issue one of the individual instructions and wait for a response from the language model 101 to the transmitted instruction before issuing the next instruction. When the first instruction is a plurality of instructions, the individual instructions are not limited to the above example, and may be divided as appropriate.

[0034] The second instruction instructs the creation of a second specification. The second instruction may include, but is not limited to, referring to the first specification and the feedback, instructing additions or corrections to the first specification in response to the feedback, instructing the inclusion of matters not described in the first specification, and specifying constraints on the description content or the description format. The second specification and the second instruction may be input to the language model 101 as a single prompt or as multiple prompts.

[0035] An example of a second instruction is, "Please revise the first specification and create a more detailed second specification based on the feedback from users. In particular, please focus on improving the points pointed out in the feedback." The second instruction may be more specific.

[0036] Furthermore, similar to the first instruction, the second instruction may be a plurality of instructions separated by items of the specification (background art, problem, solution, effect). In this case, the instruction unit 120 may issue one of the individual instructions and wait for a response from the language model 101 to the transmitted instruction before issuing the next instruction. When the second instruction is a plurality of instructions, the individual instructions are not limited to the above example, and may be separated as appropriate.

[0037] Furthermore, the first instruction and the second instruction are not limited to prompts. For example, tokenized information corresponding to the above-described prompt may be input to the language model 101 as either the first instruction or the second instruction.

[0038] The language model 101 may be, for example, any of various general LLMs, but is not limited to these. The instruction unit 120 may issue the first instruction and the second instruction to the same language model, or may issue them to different language models.

[0039] The output unit 130 is an output means for outputting the results generated by the language model 101 in response to the first instruction and the second instruction. When the instruction unit 120 issues the first instruction, the result generated by the language model 101 is the first description. That is, in this case, the output unit 130 outputs the first description. Similarly, when the instruction unit 120 issues the second instruction, the result generated by the language model 101 is the second description. Therefore, in this case, the output unit 130 outputs the second description. The output first and second descriptions are displayed on a display, a printer, or the like.

[0040] Furthermore, when outputting the second specification, the output unit 130 may output it so that it can be compared with the first specification, which makes it easier to determine whether the user's feedback regarding the first specification has been reflected.

[0041] The operation of the information processing device 100 of the present invention will be described with reference to Fig. 5. Fig. 5 is a flowchart showing the procedure of the process (information processing method) performed by the information processing device 100.

[0042] First, the receiving unit 110 receives information about the invention from a user through a user interface (UI) (step S101).

[0043] Next, the instruction unit 120 issues a first instruction to the language model 101 to instruct the creation of a first specification based on the information about the invention received by the reception unit 110 (step S102).

[0044] When the language model 101 generates the first specification, the output unit 130 outputs the first specification generated by the language model 101 (step S103).

[0045] After the first specification is presented, the receiving unit 110 receives feedback from the user regarding the first specification (step S104).

[0046] After receiving the feedback, the instruction unit 120 issues a second instruction to the language model 101 to instruct the language model 101 to create a second specification based on the feedback (step S105).

[0047] The output unit 130 outputs the second specification generated by the language model 101 (step S106). This allows the user to go through a two-stage specification creation process from the initial input and obtain a more complete specification.

[0048] In this embodiment, as an example, the information processing device 100 starts the operation of step S101 upon receiving a user operation. For example, the series of processes shown in the flowchart of FIG. 2 starts when the user clicks a "Start creating specification" button via the UI. Furthermore, the information processing device 100 may automatically end the process upon completion of outputting the second specification in step S106. Furthermore, the operations from step S101 to step S103 or the operations from step S104 to step S106 may be executed repeatedly.

[0049] According to the information processing device 100 of this embodiment, the user can quickly obtain the first specification and provide feedback, thereby efficiently creating a more complete second specification. This reduces the time required to complete the specification. In other words, it reduces the time required to check the completed specification and point out any corrections.

[0050] For example, when using the information processing device 100 of this embodiment, a user inputs information about the invention that outlines the invention, and the language model 101 generates a first specification in response to a first instruction from the instruction unit 120. By referring to this first specification, the user can easily grasp the outline and direction of the description in the specification.

[0051] Furthermore, users can provide feedback on the first specification, resulting in a more detailed and accurate second specification. Users do not need to review the entire completed second specification from scratch and point out corrections, but can simply provide feedback focusing on shortcomings and areas for improvement in the first specification. This reduces the time and effort required to create specifications.

[0052] In addition, a specification that meets the user's intentions can be created by having the language model 101 generate a second specification that reflects the user's feedback in response to a second instruction from the instruction unit 120. This reduces the time required to check the completed specification and point out any corrections.

[0053] The second embodiment will be described below.

[0054] An information processing device of the second embodiment will be described with reference to the drawings. The information processing device of the second embodiment differs in part in configuration and operation from the information processing device of the first embodiment described above, but other parts may be the same as the information processing device of the first embodiment. Therefore, the following will describe in detail the parts that differ from the first embodiment, and will omit explanations of other overlapping parts as appropriate.

[0055] 6 is a block diagram showing an example of an information processing device 200. The information processing device 200 includes a reception unit 210, an instruction unit 220, and an output unit 230. The reception unit 210, the instruction unit 220, and the output unit 230 include the functions of the reception unit 110, the instruction unit 120, and the output unit 130, respectively, of the first embodiment. Furthermore, similar to the example of the information processing device 100, the information processing device 200 is connected to a language model 201.

[0056] The receiving unit 210 receives information about the invention and feedback about the first specification from the user via a user interface (UI).

[0057] The receiving unit 210 may receive a specification regarding the granularity of description in the first specification. The specification regarding the granularity of description is a specification that specifies the granularity of description in the first specification desired by the user. The granularity of description indicates the degree of detail of the contents of the first specification to be created. The granularity of description is expressed in three stages, for example, "detailed," "standard," and "summary." The expression of the granularity of description is not limited to this, and may be expressed in five stages, for example, "very detailed," "detailed," "standard," "summary," and "brief," and is not particularly limited. The granularity of description may also be expressed in sentences.

[0058] Furthermore, the description granularity may include a specification to have the language model 201 analyze the content of the invention and automatically adjust the granularity. In this case, the first instruction described below includes a specification to the language model 201 to set the granularity according to the content of the invention. By doing so, even if it is difficult for the user to specify an appropriate granularity, it becomes easy to create the first specification at a granularity according to the content of the invention.

[0059] As an example, if the user selects "standard" granularity of description at the receiving unit 210, the basic function of each component will be explained in about 50 characters. For example, the explanation of the receiving unit 210 will be as follows: "The receiving unit 210 has a function to receive invention information and feedback via a user interface, and further allows selection of granularity of description and description items." Note that the number of characters and the level of detail of the explanation according to the level of granularity of description are not limited to this and may be determined as appropriate.

[0060] The receiving unit 210 displays, for example, the following on a chat-style UI, and receives the user's designation regarding the granularity of description.

[0061] Please select the granularity described in the first specification. 1. Details (Explain the operation of each component in 100 characters or more) 2. Standard (Explain the basic functions of each component in about 50 characters) 3. Overview (Explain the overall system operation in about 200 characters)

[0062] The receiving unit 210 may receive a user's instruction regarding the description granularity via a UI in the form of a pull-down menu or a button. The receiving unit 210 may also receive an instruction regarding the description granularity expressed as a sentence.

[0063] The receiving unit 210 may receive a specification regarding the description items of the first specification. The specification regarding the description items is a specification specifying the description items that the user wants to include in the first specification. The description items of the specification are, for example, items defined in the description format of the specification. However, the description items of the specification here are not limited to the above examples, and may specify more specific description contents, such as a description of the configuration or operation in a mode for implementing the invention.

[0064] For example, the reception unit 210 displays the following options in a chat-style UI and accepts the user's designation of the description items desired for the specification. The options are, for example, "Please select the items to be included in the first specification (multiple selections allowed): □ Background art, □ Problems that the invention aims to solve, □ Means for solving the problems, □ Effects of the invention, □ Modes for implementing the invention, □ Industrial applicability." Note that the description items accepted by the reception unit 210 are, for example, predetermined in an item list, but are not limited to this, and the user may be able to add custom items or rearrange the items.

[0065] The receiving unit 210 may also receive a designation to generate an outline of a drawing.

[0066] During the preparation stage of the first specification, the outline of the drawings to be created may be determined, but the drawings may not have been created. In such cases, it may be difficult to describe the contents of the drawings in detail, or there may be a discrepancy between the detailed description of the contents of the drawings and the contents of the drawings that are actually created. The instruction unit 220 issues a first instruction to the language model 201, including an instruction to output an outline of the drawings to be created in the first specification, thereby making it easier to write an appropriate description of the drawings in the second specification. Furthermore, omitting the description of the drawings makes it easier to check the first specification.

[0067] For example, the receiving unit 210 displays a checkbox on the UI for specifying whether to generate an outline of an image, and receives a specification for generating an outline of a drawing. The specification for generating an outline of a drawing by the receiving unit 210 is not limited to this, and the receiving unit 210 may receive a specification in other formats. Furthermore, the receiving unit 210 may input the received information about the invention into the language model 201 to analyze the content of the invention and recommend appropriate items.

[0068] The instruction unit 220 issues a first instruction to the language model 201 to instruct the creation of a first specification and a second instruction to instruct the creation of a second specification.

[0069] The first instruction includes an instruction to create a first specification that corresponds to the received description granularity and description items. For example, when the receiving unit 210 receives both the description granularity and description items, the instruction unit 220 issues a first instruction to the language model 201 that includes the following content: "Based on the input invention summary, please create a first specification that includes the following items: 'Background Art,' 'Problem to be Solved by the Invention,' 'Means for Solving the Problem,' and 'Effects of the Invention.' Please use a 'standard' level of description granularity and explain the basic function of each component in approximately 50 characters."

[0070] The instruction unit 220 may issue a first instruction to the language model 201, including an instruction to generate an outline of a drawing, in response to an instruction from a user received by the reception unit 210. The instruction unit 220 issues the first instruction to the language model 201, including an instruction to omit detailed descriptions of the drawings when creating the first specification, and instead output an outline of the drawings that are expected to be described in the second specification.

[0071] An instruction to generate a drawing summary could be, for example, "Also, omit the detailed description of the drawings and instead output only the drawing summary." Alternatively, the instruction to generate a drawing summary could be more specific about each drawing to be generated, such as, "In the first specification, omit the detailed description of the drawings and instead output only the drawing summary, as follows: Figure 1: Block diagram of the entire system, Figure 2: Flowchart for creating the first specification, Figure 3: Flowchart for creating the second specification. Please briefly describe the contents of each figure in one or two sentences."

[0072] Furthermore, the outline of the drawings is described, for example, as follows: "Fig. 1: Block diagram showing the overall configuration of the information processing device 200. Expresses the relationship between the reception unit 210, instruction unit 220, and output unit 230. Fig. 2: Flowchart of the first specification preparation process. Illustrates the flow from inputting invention information to outputting the first specification. Fig. 3: Flowchart of the second specification preparation process. Illustrates the flow from inputting feedback to outputting the second specification." However, the outline of the drawings is not limited to this, and it is sufficient that an outline be described according to the instructions.

[0073] The output unit 230 outputs the results generated by the language model 201 in response to the first instruction and the second instruction. That is, the output unit 230 outputs the first specification when the instruction unit 220 issues the first instruction, and outputs the second specification when the instruction unit 220 issues the second instruction. The first specification includes items specified at a specified granularity in accordance with the received specification, and may also include an outline of drawings. The output first and second specifications are displayed on a display, printer, etc.

[0074] Next, a description will be given of the operation of the information processing device 200. FIG.

[0075] First, the receiving unit 210 receives information related to the invention from the user (step S201). At this time, the receiving unit 210 may receive from the user instructions regarding the granularity of the description in the first specification, or instructions regarding the description items to be included in the specification.

[0076] Next, the instruction unit 220 issues a first instruction to the language model 201 to instruct the creation of a first specification (step S202). The first instruction may include an instruction to output an outline of the drawings to the first specification.

[0077] Next, the output unit 230 outputs the first description generated by the language model 201 in response to the first instruction (step S203). The output first description has a granularity according to the description granularity received in step S201, and describes items according to the description items. In addition, the first description describes an outline of the drawings in response to the first instruction.

[0078] Thereafter, the accepting unit 210 accepts feedback regarding the first specification from the user (step S204).

[0079] Subsequently, the instruction unit 220 issues a second instruction to the language model 201 to instruct the language model 201 to create a second specification based on the feedback (step S205). In step S205, if the first instruction includes an instruction to generate an outline of the drawings, the second instruction may include an instruction to include a detailed description of the drawings.

[0080] In response to the second instruction, the output unit 230 outputs the second specification generated by the language model 201 (step S206).

[0081] According to this embodiment, by using the granularity of description and description items received by the receiving unit 210, a first specification is created that focuses on the required level of detail and items in response to the first instruction from the instruction unit 220. This prevents the creation of a first specification that is unnecessarily detailed and includes many description items, thereby reducing the time required to create the first specification. Furthermore, by referring to the first specification in which the required items are described at the desired granularity, the user can easily consider feedback for creating the second specification. In other words, the information processing device 200 of this embodiment makes it easy to obtain a final specification that more accurately reflects the user's intentions.

[0082] Furthermore, by generating detailed descriptions of drawings in the second specification, the description in the first specification is simplified, making it easier for the user to understand the contents of the first specification. This makes it easier for the user to consider feedback for creating the second specification. In other words, the information processing device 200 of this embodiment can reduce the time required to complete a specification. Furthermore, the information processing device 200 of this embodiment makes it easier to obtain a final specification that more accurately reflects the user's intentions.

[0083] Furthermore, a first specification including an outline of the drawings is generated in response to instructions from the user received by the reception unit 210. By including an outline description of the drawings in the first specification, it becomes easier to include an appropriate description of the drawings in the second specification. Furthermore, by omitting the description of the drawings, it becomes easier to check the first specification.

[0084] The third embodiment will be described below.

[0085] An information processing device of the third embodiment will be described with reference to the drawings. Note that the information processing device of the third embodiment differs in part in configuration and operation from the information processing devices of the first and second embodiments described above, but other parts may be the same as the information processing devices of the first and second embodiments. Therefore, hereinafter, parts that differ from the first and second embodiments will be described in detail, and explanations of other overlapping parts will be omitted as appropriate.

[0086] 8 is a block diagram showing an example of an information processing device 300. The information processing device 300 includes a reception unit 310, an instruction unit 320, and an output unit 330. These components have the same basic functions as those in the first and second embodiments, and the instruction unit 320 includes additional functions. Furthermore, similar to the example of the information processing device 100, the information processing device 300 is connected to a language model 301.

[0087] The instruction unit 320 analyzes the content of the feedback regarding the first specification received by the reception unit 310. Then, the instruction unit 320 issues a second instruction to the language model 301 to create a second specification based on the analysis result.

[0088] As explained above, feedback on the First Specification is feedback that allows the user to make corrections or additions to the First Specification. Feedback on the First Specification may include, for example, specific suggestions such as "the description of the background art is insufficient" or direct corrections to the text.

[0089] The instruction unit 320 analyzes the content of the feedback regarding the first specification so as to identify the portions of the first specification that need to be revised or added and the specific contents thereof. For example, the instruction unit 320 analyzes the content of the feedback by, for example, analyzing the intention of the user who input the feedback to revise the first specification. The intention of revision is the user's intention regarding the portions of the first specification that need to be revised or added and the specific contents thereof. For example, when the instruction unit 320 receives feedback that "the description of the background art is insufficient," the instruction unit 320 analyzes this as including the intention of revision that "the items in the background art need to be expanded in more detail and with more specific examples."

[0090] The instruction unit 320 may also analyze whether the feedback content regarding the first specification is applicable to other sections besides the section indicated. For example, if a correction instruction for a specific section is applicable to other similar sections, the instruction unit 320 analyzes that the correction instruction included in the feedback is applicable to the other sections. In this case, the scope of applicability may be the entire specification, or the same section as the correction instruction included in the feedback. For example, if the feedback includes a correction instruction for embodiment 1, the instruction unit 320 may analyze that the correction instruction is applicable to sections of embodiments such as embodiment 2 and embodiment 3. Applying the feedback content to the entire specification can improve the description of the specification as a whole. Furthermore, applying the feedback content to the same section reduces the possibility of unexpected descriptions.

[0091] The instruction unit 320 analyzes the content of the feedback by, for example, providing feedback regarding the first specification and a prompt instructing the language model 301 to analyze the intention of revision included in the feedback. The instruction unit 320 may analyze the content of the feedback using other machine learning techniques, rule-based analysis techniques, text analysis techniques based on natural language processing technology, etc.

[0092] In addition, there may be cases where the feedback regarding the first specification is unclear or insufficient, such as "I would like it to be more detailed." Another example is when the feedback regarding the first specification contradicts each other, or when a request for revision is inconsistent with other statements in the specification, such as when a part of a related statement has feedback to "be more concise" and a part of another related statement has feedback to "be more detailed."

[0093] In this case, the instruction unit 320 may further use the additional feedback to analyze the content of the feedback. As an example, the instruction unit 320 first evaluates the clarity and specificity of the received feedback regarding the first specification using the language model 301, etc. If the feedback regarding the first specification is evaluated as unclear or insufficient, the instruction unit 320 generates a message requesting additional information or specific instructions from the user.

[0094] For example, if the feedback on the first specification is "I would like more detail," a message such as "Which parts should be described in more detail? Please let us know the specific items and the type of information that should be added (e.g., numerical data, concrete examples, comparative explanations, etc.)" can be generated. Also, a message such as "A more detailed explanation is required in the 'Background Art' section, but a concise description is required in the 'Problem to be Solved by the Invention' section. Which policy should be prioritized to maintain overall consistency?" can be generated.

[0095] The instruction unit 320 further uses the additional feedback received for the message to analyze the content of the feedback. In this case, the message to the user is output by the output unit 330. The additional feedback for the message from the user is then received by the receiving unit 310.

[0096] The instruction unit 320 issues a second instruction to the language model 301 to create a second specification based on the analysis result of the feedback regarding the first specification. For example, if the instruction unit 320 analyzes that the feedback regarding the first specification includes a revision intention such as "The background art section needs to be expanded in more detail and with specific examples," the instruction unit 320 issues a second instruction including content to explain the background art in more detail and with specific examples. As another example, the second instruction may be an instruction such as "Expand the background art section to 500 characters or more, and specifically list at least three prior arts. For each prior art, clearly explain the technical content and its relevance to the present invention."

[0097] The instruction unit 320 may issue a second instruction to the language model 301, which includes an instruction to display the sentence before and after application side by side and clarify the changes. In this case, the second instruction may include, for example, "Please revise the following sentence to include a more specific example. Please display the sentence before and after revision side by side and underline the changes. Before revision: 'The present invention relates to document creation using AI.' Example after revision: 'The present invention relates to the automatic creation of patent specifications using artificial intelligence (AI) technology, particularly large-scale language models (LLMs). Specifically, the present invention relates to a system that generates high-quality patent specifications from inventor input by utilizing LLMs such as OpenAI's GPT-3 and Google's BERT.'"

[0098] When the receiving unit 310 receives only specific revision suggestions from the user, the instruction unit 320 may compare the sentences before and after the revisions and analyze the user's intention in making the revisions. For example, the specific revision suggestions here are the first specification revised by the user.

[0099] When outputting the second specification generated from the language model 301 in response to the second instruction, the output unit 330 may output the analysis results and application results of the feedback using graphs or diagrams. By using graphs or diagrams, the user can more intuitively understand the impact of the feedback and the degree of improvement.

[0100] The operation of the information processing device 300 in this embodiment will be described with reference to the drawings. In the flowchart shown in Fig. 9, the operations from step S301 to step S303 are the same as the operations from step S101 to step S103 in embodiment 1, respectively, and detailed description thereof will be omitted.

[0101] In step S304, first, the receiving unit 310 receives feedback from the user regarding the first specification.

[0102] Next, in step S305, the instruction unit 320 analyzes the received feedback, and issues a second instruction to the language model 301 based on the analysis result.

[0103] Then, in step S306, the output unit 330 outputs the second description, which is the result of generation by the language model 301 and reflects the analyzed feedback.

[0104] In this way, the information processing device 300 of the third embodiment makes it easy for the instruction unit 320 to analyze the user's feedback regarding the first specification, thereby appropriately reflecting that feedback in the entire specification, thereby making it possible to efficiently create a second specification that more accurately reflects the user's intentions.

[0105] The fourth embodiment will be described below.

[0106] An information processing device of the fourth embodiment will be described with reference to the drawings. The information processing device of the fourth embodiment differs in part in configuration and operation from the information processing device of the first embodiment described above, but other parts may be the same as the information processing device of the first embodiment. Therefore, the following will describe in detail the parts that differ from the first embodiment, and will omit explanations of other overlapping parts as appropriate.

[0107] In addition to the basic configuration of the first embodiment, the information processing device of the fourth embodiment has a function to identify areas where information is lacking when creating the first specification and process those areas. Specifically, functions related to identifying areas where information is lacking, outputting blanks, and inquiries about general technology application have been added.

[0108] Fig. 10 is a block diagram showing the functional configuration of an information processing device 400. As shown in Fig. 10, the information processing device 400 of this embodiment includes a reception unit 410, an instruction unit 420, and an output unit 430. The reception unit 410, the instruction unit 420, and the output unit 430 include the same basic functions as the reception unit 110, the instruction unit 120, and the output unit 130 of the first embodiment, respectively. Furthermore, similar to the example of the information processing device 100, the information processing device 400 is connected to a language model 401.

[0109] The instruction unit 420 issues a first instruction that further includes specifying a portion where information is lacking when creating the first specification and an instruction to output the portion where information is lacking.

[0110] A section lacking information is one in which the content of the invention may become unclear due to insufficient information. For example, if the "Problem to be Solved by the Invention" section lacks any of the following three points: 1) the problem(s) in the prior art, 2) the reason(s) for the problem(s), and 3) the necessity for the solution, the description of that section may be insufficient. Therefore, the first instruction may include content identifying such sections as lacking information. In the above example, the first instruction may include, for example, "Please identify the sections lacking information by comparing them with the list of minimum information required for each section. For example, in the "Problem to be Solved by the Invention" section, please confirm that the following three points are included: 1) the problem(s) in the prior art, 2) the reason(s) for the problem(s), and 3) the necessity for the solution." Note that the definition of a lacking information is not limited to this; it may also be a section lacking content that could support an inventive step or a section that hinders the interpretation of the right, as appropriate.

[0111] The first instruction also includes an instruction to output information regarding the missing information. The information regarding the missing information is a message, separate from the first specification, that explains the item or paragraph in the first specification where information is missing and requests additional information. For example, a message explaining the item or paragraph where information is missing is a sentence such as, "In the item 'Problem to be Solved by the Invention,' there is a lack of information regarding the reason why a problem occurs." The message requesting additional information may be a message requesting the addition of information to the missing information, or may be a question regarding the content of the missing information.

[0112] Additionally, information regarding missing information may be indicated as blank spaces in the first specification. For example, if the "Problem to be Solved by the Invention" section describes a problem with the prior art but does not explain why that problem exists, the first specification may include a blank space like the following: "The problem to be solved by the present invention is that, in a conventional specification drafting system using LLM, the generated specification may differ from the user's intention. The reason for this problem is __________." The blank space may be filled in with highlighting or a comment may be added. For example, the missing information may be highlighted in yellow in the first specification, with a comment such as "Additional information is required" next to it.

[0113] Furthermore, information regarding the missing information may be displayed as a blank space in the first specification together with a message such as, "In the section 'Problem to be Solved by the Invention,' there is a lack of information regarding the reason for the problem. Please add appropriate information to the blank space." The instruction unit 420 issues a first instruction including these contents.

[0114] The first instruction may further include an instruction to inquire whether to apply general technology to a portion where information is lacking. For example, the first instruction is an instruction to output a message saying, "Do you want to apply general technical knowledge to fill in this portion where information is lacking?"

[0115] The first instruction may also be an instruction to inquire whether to apply general technology to a description based on the relevance of the missing information to the content of the invention. That is, the first instruction may inquire whether to apply general technology to a portion of the missing information that is not related to the key points of the invention, and may provide a blank space or question for a portion related to the key points of the invention. In this case, the key points of the invention may be points input by the receiving unit 410 from the user, or may be determined by the language model 401. That is, the first instruction may be an instruction including the key points of the invention input by the user, or may include an instruction to have the language model 401 determine whether the key points are related to the key points of the invention.

[0116] The first instruction may include an instruction to have the language model 401 determine the applicability of the general technology to a portion where information is lacking. In this case, the first instruction may include an instruction to generate the content described in the first specification and specify the portion where the general technology is applicable, if the general technology is applicable.

[0117] In this way, since the first instruction is an instruction to inquire whether to make a description that applies the application of general technology, it is possible to reduce the time it takes for the user to respond to areas where information is missing.

[0118] Output unit 430 outputs the first description and information relating to the portions where information is missing. The first description and information relating to the portions where information is missing are generated by language model 401 in response to the first instruction given by instruction unit 420 as described above. In this case, the first description output may show the portions where information is missing as blanks.

[0119] The output unit 430 may also output a query asking whether to apply general technology to a section where information is lacking. When the first instruction is an instruction to ask whether to apply general technology to a section where information is lacking based on the relevance of the section to the content of the invention, the output unit 430 may output a message suggesting different responses depending on the level of importance. For example, for a section where information related to the key points of the invention is lacking, the output unit 430 may output a message such as, "This section relates to the essential part of the invention, so please enter as much specific information as possible." For a section that is not related to the key points of the invention, the output unit 430 may also output a suggestion such as, "We recommend supplementing with general technical knowledge." This makes it easier for users with limited technical expertise to make appropriate decisions. The output unit 430 may generate this message based on the output from the language model 401, or the first instruction may include an instruction to generate a message. Figure 11 shows an example of outputting a query asking whether to apply general technology to a section where information is lacking through a chat-style UI.

[0120] Furthermore, the receiving unit 410 further receives additional information for areas where information is lacking as feedback regarding the first specification. The additional information is, for example, but is not limited to, answers to the questions outputted, text to be written in blank spaces indicated in the first specification, or an answer to an inquiry about whether to write a description that applies general technology.

[0121] Furthermore, when the receiving unit 410 receives additional information for the missing information, the instruction unit 420 issues a second instruction to generate a second specification including the received additional information and completing the missing information.

[0122] Before issuing the second instruction, the instruction unit 420 may analyze the received input and evaluate the specificity and sufficiency of the information. In this case, the instruction unit 420 may issue the second instruction if it determines that the specificity and sufficiency of the information are appropriate. On the other hand, if the input information consists only of abstract expressions, the instruction unit 420 may output instructions to the user to input more detailed information via the output unit 430 and the receiving unit 410, and issue the second instruction after receiving the information. In this case, the output unit 430 may output a suggestion such as, "The quality of the specification will improve if you include more specific examples and numerical values. Would you like to add specific examples?" This improves the quality of the user's input and enables the creation of a more comprehensive specification.

[0123] In response to the second instruction, output unit 430 outputs the second description generated by language model 401. In this case, the second description is a description generated by supplementing the missing information.

[0124] Next, the operation of the information processing device of this embodiment will be described with reference to the flowchart of FIG.

[0125] The receiving unit 410 receives information related to the invention (step S401). The instruction unit 420 issues a first instruction to the language model 401 to instruct the creation of a first specification based on information related to the invention (step S402). At this time, the first instruction includes an instruction to identify areas where information is lacking when creating the first specification and an instruction to output the areas where information is lacking.

[0126] The output unit 430 outputs the first description generated by the language model 401 (step S403). In step S403, the output unit 430 outputs information about the portions of the description that are lacking information generated by the language model 401. Furthermore, the portions of the description that are lacking information may be indicated by blank spaces. The output unit 430 may output a query about whether to apply general technology to the portions of the description that are lacking information. The query about whether to apply general technology is in the form of, for example, "Would you like to apply general technical knowledge to fill in the portions of the description that are lacking information? [Yes / No]."

[0127] The receiving unit 410 receives feedback regarding the first specification (step S404). In step S404, the feedback includes additional information for areas where information is lacking.

[0128] The instruction unit 420 issues a second instruction to the language model 401 to instruct the creation of a second specification (step S405). In step S405, the second instruction includes the information received in step S404 for the parts where feedback information is lacking.

[0129] For example, assume that in step S403, the output unit 403 outputs a query regarding whether or not to apply the general technology, and in step S404, the receiving unit 410 receives a response indicating that the general technology should be applied. In this case, the instructing unit 420 issues a second instruction, including an instruction to apply the general technology to fill in the missing information and generate a second specification. For example, the second instruction includes an instruction such as, "Please fill in the missing 'reason for the problem' in the 'Problem to be Solved by the Invention' section by considering the general problems of specification drafting systems using LLM." The language model 401 that received the second instruction fills in the information based on this instruction. For example, "The reason for this problem is that it is difficult for the LLM to fully understand human intent, and it is possible that the LLM has not fully learned the format and requirements specific to patent specifications."

[0130] On the other hand, if the receiving unit 410 receives a response in step S404 that the invention does not apply, or if the missing information is related to a key point of the invention, the instruction unit 420 issues a second instruction to, for example, supplement the missing information based on other received feedback and generate a second specification.

[0131] The output unit 430 outputs the second specification generated by the language model 401 in response to the second instruction (step S406).

[0132] In this way, in the information processing device 400 in the fourth embodiment, the instruction unit 420 issues an instruction to identify areas where information is lacking when creating the first specification, which allows the user to easily address the areas where information is lacking, making it possible to efficiently create a more complete specification.

[0133] The first instruction may also include an instruction to output blanks for areas where information is missing when creating the first specification, and to generate a message requesting the user to provide additional information, thereby enabling the user to easily identify missing areas in the specification and efficiently add the required information.

[0134] The first instruction may also include an instruction to inquire whether to apply general technology to areas where information is lacking. This makes it easier to address areas where information is lacking and reduces the burden on the user. Furthermore, additional information from the user may be accepted for parts related to the key points of the invention, and the content may be supplemented by applying general technology to other parts. This makes it possible to create a high-quality specification that meets the user's intentions while reducing the burden on the user.

[0135] The fifth embodiment will be described below.

[0136] An information processing device of the fifth embodiment will be described with reference to the drawings. The information processing device of the fifth embodiment differs in part in configuration and operation from the information processing device of the first embodiment described above, but other parts may be the same as the information processing device of the first embodiment. Therefore, the following will describe in detail the parts that differ from the first embodiment, and will omit explanations of other overlapping parts as appropriate.

[0137] 13 is a block diagram showing an example of an information processing device 500. The information processing device 500 includes a reception unit 510, an instruction unit 520, and an output unit 530. The reception unit 510, the instruction unit 520, and the output unit 530 include basic functions similar to those of the reception unit 110, the instruction unit 120, and the output unit 130 of the first embodiment, respectively. Furthermore, similar to the example of the information processing device 100, the information processing device 500 is connected to a language model 501.

[0138] The instruction unit 520 issues a first instruction that further includes an instruction to identify a portion that will be expressed in an abstract manner when creating the first specification, and to output a question to the user about the portion that will be expressed in an abstract manner.

[0139] Abstract expressions are those that are ambiguous in terms of the scope or degree of the expression, and that may make the content of the invention unclear. Abstract expressions may be, for example, expressions exemplified in laws and regulations or expressions that are generally considered abstract in patent practice, but they may be determined as appropriate.

[0140] The instructions included in the first instruction for identifying portions of the first specification that will be considered abstract expressions are as follows: "When creating the first specification, please refer to the list of keywords below and identify abstract expressions, such as 'efficient,' 'quickly,' 'high quality,' 'easy to use,' and 'innovative.' When you find portions where these words are used, please generate questions requesting their specific meanings and numerical support." Note that the specific expressions in the instructions are not limited to these. Furthermore, the examples of abstract expressions listed in this example are not limited to these. Furthermore, the specific abstract expressions listed in the first instruction are stored in advance as a keyword list, for example. This keyword list is created by analyzing the Patent Law examination guidelines and past notices of reasons for refusal, and automatically extracting new abstract expressions and expressions that are likely to be problematic. Machine learning technology is used for the analysis as appropriate. The keyword list may be updated periodically.

[0141] The first instruction also includes an instruction to output a question to the portion that is an abstract expression. The question is intended to obtain information necessary to clarify the scope and degree of the expression for the portion that is determined to be an abstract expression.

[0142] For example, if the question states, "The present invention allows specifications to be prepared efficiently," and "efficiently" is used as an abstract expression, a possible question would be something like, "What specific indicators are used to measure 'preparing specifications efficiently,' and how much improvement can be seen? For example, please let me know if there are any specific numerical examples, such as how many percent the preparation time is reduced compared to conventional methods." The first instruction includes an instruction to output such a question.

[0143] The output unit 530 outputs the first specification, a list of abstract expressions, and questions to the parts that become abstract expressions. The first specification and the questions to the parts that become abstract expressions are generated by the language model 501 in response to the first instruction given by the instruction unit 520 as described above.

[0144] Furthermore, the receiving unit 510 further receives, as feedback regarding the first specification, answers to questions about portions that are abstract expressions. The instructing unit 520 issues a second instruction to the language model 501 to instruct the creation of a second specification, using the answers to the questions about portions that are abstract expressions.

[0145] The operation of the information processing device 500 of the present invention will be described with reference to Fig. 14. Fig. 14 is a flowchart showing the procedure of the process performed by the information processing device 500.

[0146] First, the receiving unit 510 receives information about the invention from the user (step S501).

[0147] The instruction unit 520 issues a first instruction to the language model 501 to instruct the creation of a first specification based on information related to the invention (step S502). At this time, the first instruction includes an instruction to identify an abstract expression and generate a question.

[0148] The output unit 530 outputs the first specification generated by the language model 501 (step S503). In step S503, the output unit 530 outputs a list of abstract expressions generated by the language model 501 and a list of questions.

[0149] The receiving unit 510 receives feedback regarding the first specification (step S504), including the user's answer to the question output in step S503.

[0150] The instruction unit 520 instructs the language model 501 to create a second specification based on the answer and feedback (step S505).

[0151] The output unit 530 outputs the second specification generated by the language model 501 (step S506).

[0152] According to this embodiment, the information processing device 500 can identify abstract expressions when preparing the first specification and encourage the user to make them more concrete. This improves the quality of the final second specification and reduces grounds for rejection during patent examination. Furthermore, the user has the opportunity to express their invention more specifically, enabling them to more clearly communicate the essence of their invention.

[0153] For example, the information processing device 500 supports the user in clearly explaining the details of an invention by having the instruction unit 520 automatically detect abstract expressions and instruct the language model 501 to generate specific questions in response to those expressions. This allows the "Mode for carrying out the invention," which is a description item in a patent specification, to be more comprehensive, thereby increasing the chances of obtaining a patent.

[0154] Note that the information processing device 500 identifies abstract expressions and generates questions after creating the first specification, but this is not limiting. For example, the instruction unit 520 may directly identify abstract expressions and generate questions for invention information input by a user using the language model 501, and ask the user for an answer via the output unit 530. The instruction unit 520 may then be configured to issue a first instruction to instruct the creation of the first specification based on the answer.

[0155] In addition, there are cases where the user cannot provide a specific explanation or numerical evidence for an abstract expression in the information processing device 500. In such cases, it may be difficult to concretize the abstract expression even in the second specification.

[0156] In this case, the instruction unit 520 may have a function of suggesting an alternative approach when the user is unable to provide a specific explanation or numerical values. For example, the instruction unit 520 can include the following instruction in the first instruction or the second instruction to the language model 501: "If the user is unable to provide a specific explanation or numerical values, please suggest the following alternatives: 1. Provide examples of general improvement rates or effects in similar technical fields. 2. Use relative expressions (e.g., 'approximately twice as efficient as conventional technology'). 3. Provide more detailed qualitative explanations (e.g., change 'efficient' to 'achieve both reduced processing time and improved accuracy')."

[0157] This makes it easier for the information processing device 500 to create a specification with improved abstract expression.

[0158] Furthermore, the instruction unit 520 may instruct the user to present experiments and measurement methods for obtaining specific data in the future, along with alternatives, thereby enabling the user to prepare for amendments and addition of examples after the patent application has been filed.

[0159] In this way, the information processing device 500 can improve the quality of specifications even in situations where it is difficult to concretize abstract expressions, making it possible to deal with inventions in various technical fields and at various stages of development.

[0160] Additionally, in the information processing device 500, the timing for identifying an abstract expression and generating a question may be sequentially performed not only after the first specification is created, but also at the stage when the user inputs invention information. For example, the instruction unit 520 may instruct the language model 501 to identify an abstract expression and generate a question before issuing the first instruction. The instruction unit 520 may then receive a response from the user via the reception unit 510 and issue the first instruction using the result. This allows the abstract expression to be concretized at an earlier stage, further improving the quality of the first specification.

[0161] Furthermore, in the information processing device 500, the instruction unit 520 may be configured to extend the question generation function and instruct the language model 501 to generate questions regarding the novelty and inventive step of the invention, rather than simply requesting the concrete realization of an abstract expression. For example, the instruction unit 520 can make the language model 501 aware of the features of the invention and support the acquisition of a patent by generating a question such as "What are the specific differences between this invention and the closest prior art?"

[0162] The present disclosure may be realized by recording a program for realizing the above-described functions on a computer-readable recording medium, and reading and executing the program recorded on the recording medium into a computer system.

[0163] The term "computer system" here includes hardware such as the OS and peripheral devices, and "computer-readable recording media" refers to portable media such as flexible disks, optical magnetic disks, ROMs, and CD-ROMs, as well as storage devices such as hard disks built into computer systems.

[0164] Furthermore, "computer-readable recording medium" may also include something that dynamically stores a program for a short period of time, such as a communication line when transmitting a program via a network such as the Internet or a communication line such as a telephone line, or something that stores a program for a certain period of time, such as volatile memory inside a computer system that serves as a server or client in that case.

[0165] Furthermore, the above program may be one that realizes part of the above-mentioned functions, or may be one that can realize the above-mentioned functions in combination with a program already recorded in a computer system, or may be one that is realized using a programmable logic device such as an FPGA (Field Programmable Gate Array).

[0166] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0167] Some or all of the above embodiments can be described as, but are not limited to, the following supplementary notes. (Appendix 1) a receiving means for receiving information about the invention and feedback regarding the first specification; instruction means for issuing to a language model a first instruction to instruct the creation of the first specification based on information about the invention, and a second instruction based on the feedback to instruct the creation of a second specification that is more detailed than the first specification; an output means for outputting a result generated by the language model in response to the first instruction and the second instruction; An information processing device comprising: (Appendix 2) The first instruction includes an instruction to omit the description of the drawings and an instruction to output an outline of the drawings that are assumed to be described in the second specification. 2. The information processing device according to claim 1. (Appendix 3) The receiving means receives an instruction regarding the granularity described in the first specification, The first instructions include instructions for creating the first specification in accordance with the granularity of the description of the first specification; 3. The information processing device according to claim 1 or 2. (Appendix 4) the receiving means receives instructions regarding items to be described in the specification; The first instructions include instructions for preparing the first specification corresponding to the items described. 4. The information processing device according to claim 1. (Appendix 5) the second instructions include instructions for preparing the second specification based on an analysis result of the feedback; 5. The information processing device according to any one of claims 1 to 4. (Appendix 6) The second instructions include instructions to apply the content of the feedback to a part other than the part of the feedback to create the second specification. 6. The information processing device according to claim 5. (Appendix 7) the second instructions include instructions to apply the content of the feedback to a description other than the portion of the feedback within the same description item to create the second specification; 7. The information processing device according to claim 6. (Appendix 8) The first instruction includes an instruction to identify a portion where information is lacking in creating the first specification and an instruction to output the portion where information is lacking. 7. An information processing device according to any one of claims 1 to 6. (Appendix 9) the first instruction includes an instruction to output a blank space in the portion where the information is missing, 9. The information processing device according to claim 8. (Appendix 10) The first instruction includes an instruction to inquire whether to write a description that applies general technology to the part where the information is lacking. 9. The information processing device according to claim 8. (Appendix 11) The first instruction includes an instruction to inquire whether to make a description applying general technology to the part where the information is lacking, when the part where the information is lacking is related to the invention, 11. The information processing device according to claim 10. (Appendix 12) The first instruction includes an instruction to identify a portion that will be an abstract expression when creating the first specification, and to output a question to the user regarding the portion that will be an abstract expression. 2. The information processing device according to claim 1. (Appendix 13) Accepting information about the invention and feedback on the first specification; issuing a first instruction to a language model to instruct the creation of the first specification based on information about the invention, and a second instruction based on the feedback to instruct the creation of a second specification that is more detailed than the first specification; outputting the generation results by the language model for the first instruction and the second instruction; Information processing methods. (Appendix 14) On the computer, a process for receiving information about the invention and feedback regarding the first specification; a process of issuing to a language model a first instruction to instruct the creation of the first specification based on information about the invention, and a second instruction based on the feedback to instruct the creation of a second specification that is more detailed than the first specification; a process of outputting a generation result by the language model in response to the first instruction and the second instruction; A program that executes the following.

[0168] Note that part or all of the configurations described in Supplementary Notes 2 to 12, which are dependent on Supplementary Note 1, may also be dependent on Supplementary Notes 13 and 14 in the same dependent relationship as Supplementary Notes 2 to 12. Furthermore, not limited to Supplementary Notes 1, 13, and 14, part or all of the configurations described as Supplements may be made dependent on various hardware, software, various recording means for recording software, or systems, within the scope of each of the above-mentioned embodiments. [Explanation of symbols]

[0169] 100, 200, 300, 400, 500 Information processing equipment 101, 201, 301, 401, 501 language models 110, 210, 310, 410, 510 Reception 120, 220, 320, 420, 520 Indicator 130, 230, 330, 430, 530 Output section

Claims

1. a receiving means for receiving information about the invention and feedback regarding the first specification; an instruction means for issuing to a language model a first instruction to instruct the creation of the first specification based on information about the invention, and a second instruction based on the feedback to instruct the creation of a second specification that is more detailed than the first specification; an output means for outputting a generation result by the language model in response to the first instruction and the second instruction; Equipped with the second instructions are instructions for preparing the second specification based on the analysis results of the feedback, and include instructions for preparing the second specification by applying the content of the feedback to a part other than the part of the feedback; 1. An information processing device comprising:

2. The information processing device according to claim 1 , wherein the first instruction includes an instruction to omit description of drawings and an instruction to output an outline of drawings that are expected to be described in the second specification.

3. The receiving means receives an instruction regarding the granularity described in the first specification, The information processing device according to claim 1 , wherein the first instruction includes an instruction to create the first specification in accordance with the granularity of the description of the first specification.

4. the receiving means receives instructions regarding items to be described in the specification; The information processing device according to claim 1 , wherein the first instruction includes an instruction to create the first specification corresponding to the description item.

5. The information processing device according to claim 1 , wherein the second instruction includes an instruction to create the second specification by applying the content of the feedback to a description other than the portion of the feedback within the same description item.

6. The information processing device according to claim 1 , wherein the first instruction includes an instruction to identify a portion where information is lacking in creating the first specification, and an instruction to output the portion where information is lacking.

7. The information processing apparatus according to claim 6 , wherein the first instruction includes an instruction to output a blank space for the portion where the information is missing.

8. The information processing device according to claim 1 , wherein the first instruction includes an instruction to identify a portion that will be expressed in an abstract manner when creating the first specification, and an instruction to output a question to the user regarding the portion that will be expressed in an abstract manner.

9. A computer comprising: Accepting information about inventions, issuing a first instruction to a language model to instruct the creation of a first specification based on the information about the invention; outputting a result generated by the language model in response to the first instruction; Accepting feedback regarding said first specification; providing a second instruction to the language model based on the feedback, the second instruction instructing the language model to create a second specification that is more detailed than the first specification; outputting a result generated by the language model in response to the second instruction; Execute the process, the second instructions are instructions for preparing the second specification based on the analysis results of the feedback, and include instructions for preparing the second specification by applying the content of the feedback to a part other than the part of the feedback; Information processing methods.

10. On the computer, a process for receiving information about the invention and feedback regarding the first specification; a process of issuing to a language model a first instruction to instruct the creation of the first specification based on information about the invention and a second instruction to instruct the creation of a second specification that is more detailed than the first specification, the second instruction being based on the feedback; a process of outputting a generation result by the language model in response to the first instruction and the second instruction; Execute the second instructions are instructions for preparing the second specification based on the analysis results of the feedback, and include instructions for preparing the second specification by applying the content of the feedback to a part other than the part of the feedback; program.

Images