Device, method, and program for assisting creation of explanation related to invention

Abstract

A method for assisting creation of an explanation related to an invention, wherein the labor in creation of the explanation is saved. First, a device 100 receives the definition of an invention which is in a text format using a predetermined syntax from a user terminal 110 (S201). The device 100 then requests a generative AI model to generate an explanation about the invention by using the definition (S202). An explanation about of the invention is generated by the generative AI model (S203) and transmitted to the device 100 (S204). Meanwhile, the device 100 stores the received explanation in a storage unit 103, and transmits at least part of the explanation to the user terminal 110 as necessary (S205).

Description

Apparatus, method and program for supporting the creation of invention descriptions

[0001] The present invention relates to an apparatus, a method and a program for supporting the creation of an invention description.

[0002] In order to obtain a patent for an invention, it is necessary to file a patent application. A patent application can be made by submitting application documents to the Japan Patent Office, including a claim that specifies the invention for which rights are sought and a description of the invention.

[0003] Since the description of the invention forms the basis for the claims, it is desirable that it be comprehensive. However, writing the logically organized text required for this purpose places a heavy burden on attorneys and other persons preparing application documents.

[0004] The present invention has been made in consideration of these points, and its object is to reduce the effort required to create an explanation of an invention in an apparatus, method, or program for supporting the creation of the explanation.

[0005] To achieve this object, a first aspect of the present invention is a method for assisting in the creation of an explanation of an invention, comprising the steps of obtaining a definition of a diagram representing multiple actions of the invention in a text format using a predetermined syntax, creating first instructions for generating an explanation of the invention using the definition, making a first request including the first instructions to a first generative AI model, and storing at least a portion of the generated explanation of the multiple actions, wherein the explanation includes descriptions not included in the definition.

[0006] A second aspect of the present invention is the method of the first aspect, wherein the predetermined syntax is a syntax of a scripting language.

[0007] A third aspect of the present invention is the method of the first aspect, wherein the predetermined syntax is the syntax of a graphics drawing language.

[0008] A fourth aspect of the present invention is the method according to the second or third aspect, wherein the syntax is Mermaid syntax.

[0009] A fifth aspect of the present invention is a method according to any one of the first to fourth aspects, wherein the first instructions include a variable whose value is set to the definition or the result of analyzing or modifying the definition.

[0010] A sixth aspect of the present invention is the method of any one of the first to fifth aspects, and the figure is a sequence diagram.

[0011] A seventh aspect of the present invention is a method according to any one of the first to fifth aspects, wherein the generated description of the plurality of operations includes logic required for each of the plurality of operations.

[0012] An eighth aspect of the present invention is the method of the seventh aspect, wherein the diagram is a sequence diagram, and the number of the generated operations is the same as the number of steps included in the sequence diagram.

[0013] A ninth aspect of the present invention is the method according to any one of the first to eighth aspects, wherein the request includes instructions that differ depending on the type of the drawing.

[0014] A tenth aspect of the present invention is the method according to any one of the first to ninth aspects, wherein the request includes using knowledge in a set technical field.

[0015] An eleventh aspect of the present invention is the method of any one of the first to tenth aspects, wherein the invention is a software-related invention.

[0016] A twelfth aspect of the present invention is the method of the eleventh aspect, wherein the generated description of the plurality of operations includes logic required to implement each of the plurality of operations as software.

[0017] A thirteenth aspect of the present invention is the method according to any one of the first to twelfth aspects, wherein the request includes specifying an output format.

[0018] Furthermore, a fourteenth aspect of the present invention is the method of any one of the first to thirteenth aspects, wherein the generative AI model is a model to which a Transformer architecture is applied.

[0019] A fifteenth aspect of the present invention is the method of any one of the first to fourteenth aspects, further comprising the step of receiving the definition from a user terminal.

[0020] In addition, a sixteenth aspect of the present invention is a program for causing a computer to execute a method for assisting in the creation of an explanation of an invention, the method including the steps of: obtaining a definition of a diagram representing multiple actions of the invention in a text format using a predetermined syntax; creating a first instruction to generate an explanation of the multiple actions of the invention using the definition; making a first request including the first instruction to a generative AI model; and storing the generated explanation of the multiple actions.

[0021] Furthermore, a seventeenth aspect of the present invention is an apparatus for executing a method for assisting in the creation of an explanation of an invention, the apparatus being configured to obtain a definition of a diagram representing a plurality of actions of the invention in a text format using a predetermined syntax, create first instructions for using the definition to generate an explanation of the plurality of actions of the invention, make a first request including the first instructions to a generative AI model, and store the generated explanation of the plurality of actions.

[0022] An eighteenth aspect of the present invention is a method for assisting in the creation of a description of an invention, comprising the steps of obtaining a definition of the invention in text form using a predetermined syntax, creating first instructions for generating a description of the invention using the definition, making a first request including the first instructions to a first generative AI model, and storing at least a portion of the generated description of the invention, wherein the description includes descriptions not included in the definition.

[0023] A nineteenth aspect of the present invention is the method of the eighteenth aspect, wherein the first instructions include a variable whose value is set to the definition or a result of analyzing or modifying the definition.

[0024] A twentieth aspect of the present invention is a program for causing a computer to execute a method for assisting in the creation of a description of an invention, the method including the steps of: obtaining a definition of the invention in text format using a predetermined syntax; creating first instructions for generating a description of the invention using the definition; making a first request including the first instructions to a first generative AI model; and storing at least a portion of the generated description of the invention, the description including a description not included in the definition.

[0025] Furthermore, a 21st aspect of the present invention is an apparatus for assisting in the creation of a description of an invention, configured to obtain a definition of the invention in text format using a predetermined syntax, create first instructions for using the definition to generate a description of the invention, make a first request including the first instructions to a first generative AI model, and store at least a portion of the generated description of the invention, wherein the description includes descriptions not included in the definition.

[0026] In addition, a 22nd aspect of the present invention is a method for assisting in the creation of an explanation of an invention, comprising the steps of obtaining a definition of the invention in text format using a predetermined syntax, creating first instructions for generating an explanation of the invention using the definition, making a first request including the first instructions to a first generative AI model, creating second instructions for generating a new explanation based on the generated explanation of the invention or a modified explanation thereof, making a second request including the second instructions to a second generative AI model, and storing the generated new explanation.

[0027] A twenty-third aspect of the present invention is the method of the twenty-second aspect, wherein the second instruction includes a problem to be solved by the invention.

[0028] In addition, a 24th aspect of the present invention is a program for causing a computer to execute a method for assisting in the creation of descriptions of an invention, the method including the steps of obtaining a definition of the invention in text format using a predetermined syntax, creating first instructions to generate a description of the invention using the definition, making a first request including the first instructions to a first generative AI model, creating second instructions to generate a new description based on the generated description of the invention or a modified description thereof, making a second request including the second instructions to a second generative AI model, and storing the generated new description.

[0029] In addition, a 25th aspect of the present invention is an apparatus for assisting in the creation of an explanation of an invention, configured to obtain a definition of the invention in text format using a predetermined syntax, create a first instruction to generate an explanation of the invention using the definition, make a first request including the first instruction to a first generative AI model, create second instructions to generate a new explanation based on the generated explanation of the invention or a modified explanation thereof, make a second request including the second instruction to a second generative AI model, and store the generated new explanation.

[0030] According to one aspect of the present invention, by obtaining a textual definition of a diagram using a predetermined syntax and requesting a generative AI model to generate an explanation of the multiple actions of the invention represented by the diagram, it is possible to obtain an orderly explanation of the multiple actions of the invention in just a few tens of seconds.

[0031] 1 is a diagram illustrating a system according to an embodiment of the present invention; 2 is a diagram illustrating a flow of a method according to an embodiment of the present invention; 3 is an example of a portion of a request for a generative AI model according to an embodiment of the present invention; and 4 is an example of a diagram definition included in a request for a generative AI model according to an embodiment of the present invention.

[0032] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

[0033] 1 shows a system according to an embodiment of the present invention. Device 100 communicates with a user terminal 110 used by a user to assist in creating an explanation of the invention, and with a platform 120 that provides a generative AI model, via an IP network such as the Internet. While the AI ​​model is illustratively described as being provided by platform 120 that can communicate with device 100, an application for providing the AI ​​model can also be executed on device 100, causing device 100 to provide the AI ​​model.

[0034] The device 100 includes a communication unit 101 such as a communication interface, a processing unit 102 such as a processor or CPU, and a storage unit 103 including a storage device or storage medium such as a memory or hard disk. The device 100 may be configured by executing a program for each process or operation in the processing unit 102. The device 100 may include one or more devices, computers, or servers. The program may include one or more programs, and may be recorded on a computer-readable storage medium to form a non-transitory program product. The program may be stored in the storage unit 103 or in a storage device or storage medium 104 accessible from the device 100 via an IP network, and instructions included in the program may be executed by at least one processor in the processing unit 102. Data described below as being stored in the storage unit 103 may also be stored in the storage device or storage medium 104, and vice versa. For convenience, the storage device or storage medium 104 is illustrated in FIG. 1 as a database.

[0035] First, the device 100 receives from the user terminal 110 a definition of a diagram representing an invention, in a text format using a predetermined syntax (S201). The predetermined syntax may be, for example, the syntax of a scripting language or a graphics drawing language, such as the syntax of Mermaid. The invention represented by the diagram may be, for example, a software-related invention, and in this case, the diagram is preferably a sequence diagram.

[0036] The apparatus 100 then requests the generative AI model to generate an explanation for the operations of the invention represented by the diagram (S202). The request may include different instructions depending on the type of diagram.

[0037] FIG. 3 shows an example of a portion of code for a request to a generative AI model according to one embodiment of the present invention. The example in FIG. 3 is a portion of code written in the programming language Python. By executing this code, the OpenAI API can be called and a generative AI model provided on the platform 120 can generate an explanation of the invention. Here, the variable "model" represents the type of generative AI model to be used, and the variable "temperature" represents the diversity of the output. The OpenAI API is an example, and other APIs may be used. Furthermore, the programming language Python is an example, and other languages ​​may be used. The code is stored in the storage unit 103, and the device 100 retrieves it and executes code containing instructions obtained by setting values ​​to variables included in the code.

[0038] In the example of Figure 3, technical knowledge in the technical field set in the variable "technicalFields" is extracted and used to generate logic, a series of instructions, for each operation of the invention described in Mermaid notation set in the variable "mermaid." The output format can also be set in the variable "outputFormat." In this example, a diagram definition in Mermaid notation is received from the user terminal 110. However, the description of the invention received from the user terminal 110 may be converted into a diagram definition in the device 100 and set to the variable "mermaid." While the example of Figure 3 sets the acquired diagram definition as a value, it is also possible to set the result of analyzing the definition or the result of modifying the definition. For example, the device 100 may verify whether the definition complies with a specified syntax and make modifications as necessary. The device 100 may also function as the user terminal 110. In such cases, the device 100 may simply acquire the diagram definition in some manner.

[0039] If the diagram is a sequence diagram, an explanation may be generated for multiple operations together, or the number of operations for which an explanation is generated may be the same as the number of steps included in the sequence diagram. If the invention is software-related, the details of the multiple operations of the invention can be generated by including instructions in the request to the generative AI model to generate the logic required to implement each of the multiple operations of the invention as software. In addition to the conditions shown in Figure 3, the conditions imposed on the generative AI model can be specified by including variables in the code and setting the variables according to specifications received from the user terminal 110.

[0040] While the explanation will be centered on the example of a diagram showing multiple actions of an invention, if the diagram shows multiple components of an invention, a request including an instruction to generate an explanation for those components can be made to the generative AI model. More generally, a textual definition using a predetermined syntax can be given as a definition other than the diagram definition, in which case a request including an instruction to generate an explanation for the invention defined by that definition can be made to the generative AI model.

[0041] Then, in the generative AI model, an explanation of the multiple actions of the invention is generated (S203) and transmitted to the device 100 (S204).

[0042] Figure 4 shows an example of a diagram definition according to one embodiment of the present invention. The following table shows an example of the output obtained by assigning this definition to the variable "mermaid" in the code shown in Figure 3. The variable "technicalFields" was set to "generative AI, OpenAI." It took 75 seconds to obtain output in Japanese, although the English output took less time. It can be seen that the sequence of commands given to the device for each of several actions is clearly explained.

[0043]

[0044]

[0045] Since the output of the generative AI model is not necessarily the same each time, a condition may be imposed on the generative AI model that it generates an explanation based on multiple output results. Alternatively, multiple requests may be made to the generative AI model, and the device 100 may create an explanation of the invention based on multiple responses to those requests.

[0046] When requesting multiple outputs from a generative AI model, for example, the first explanation output or generated by the first request or a modified explanation may be included in the second request. The second request may then include instructions to add an explanation to the first explanation or a user-modified explanation. In this case, including in the second request the problem to be solved by the invention and, if necessary, instructions to generate a new explanation taking the problem into consideration makes it possible to generate an explanation more suitable for a patent application that takes the problem into consideration. When the first explanation or a modified explanation is included in the second request, the definition of the diagram or its analysis results may not be included. Here, "new explanation" includes changes to the first explanation or the modified explanation.

[0047] As used herein, "AI model" refers to a machine learning model trained to predict an output for a given input, and "generative AI model" refers to a large-scale language model (LLM) trained using text data to generate an output not included in the input. While LLMs incorporating the Transformer architecture are particularly preferred as generative AI models, the name of the architecture is expected to change as technology advances. Therefore, as used herein, "Transformer architecture" encompasses architectures that incorporate one or more features of the Transformer architecture or improvements thereof. While the example in Figure 3 illustrates a single API call to fulfill a desired request, it is also possible to split the request into multiple requests and fulfill them with multiple API calls. In this case, the multiple API calls may be directed to the same or different generative AI models. As used herein, whether "generative AI models" are identical is determined by whether the types of generative AI models specified by the user are identical. In the example in Figure 3, if the value of the variable "model" is the same, the generative AI models are considered identical. If multiple generative AI models are not identical, they may be hosted on the same platform 120. If multiple requests are directed to generative AI models hosted on the same platform 120, those requests may be fulfilled by a single call to the API.

[0048] The device 100 then stores the received explanation in the storage unit 103, and transmits at least a part of the explanation to the user terminal 110 as necessary (S205).

[0049] Thus, according to one embodiment of the present invention, by obtaining a textual definition of a diagram using a predetermined syntax and requesting a generative AI model to generate an explanation of the actions of the invention represented by the diagram, a well-organized explanation of the actions of the invention can be obtained in just a few tens of seconds. The ability to instantly verbalize the actions of the invention represented by the diagram based on the diagram definition significantly reduces the burden of preparing application documents. This previously unimaginable automation is made possible by focusing on the structured definition of the diagram according to a predetermined syntax, and the generative AI model supplements the logic as needed to obtain a well-organized explanation.

[0050] In the above embodiments, it should be noted that unless the word "only" is used, such as "based only on," "depending only on," or "only in the case of," the specification assumes that additional information may also be taken into consideration. Also, as an example, it should be noted that the phrase "do b when a" does not necessarily mean "do b always when a" or "do b immediately after a" unless explicitly stated otherwise. Also, the phrase "each a constituting A" does not necessarily mean that A is composed of multiple components, but includes the case where the component is singular.

[0051] Also, just to be clear, even if there is an aspect of a method, program, terminal, device, server, or system (hereinafter referred to as a "method, etc.") that performs an operation different from that described in this specification, each aspect of the present invention is directed to an operation that is identical to one of the operations described in this specification, and the existence of an operation different from that described in this specification does not make the method, etc. outside the scope of each aspect of the present invention.

[0052] 100 Device 101 Communication unit 102 Processing unit 103 Storage unit 104 Database 110 User terminal 120 Platform

Claims

1. A method for assisting in the creation of a description of an invention, comprising the steps of: obtaining a definition of said invention in text form using a predetermined syntax; creating instructions for generating a description of said invention using said definition; making a request including said instructions to a generative AI model; and storing at least a portion of the generated description of said invention, said description including statements not included in said definition.

2. A method according to claim 1, wherein said instructions include variables whose values are set to said definitions or the results of analyzing or modifying them.

3. A method according to claim 1, wherein the predetermined syntax is the syntax of a scripting language.

4. A method according to claim 1, wherein said predetermined syntax is the syntax of a graphics drawing language.

5. A method according to claim 3 or 4, wherein the syntax is Mermaid syntax.

6. A method according to any one of claims 1 to 5, wherein the definition is a definition of a diagram showing a plurality of operations of the invention.

7. A method according to claim 6, wherein the diagram is a sequence diagram.

8. A method according to claim 6 or 7, wherein the request includes different instructions depending on the type of the drawing.

9. A method according to any one of claims 1 to 8, wherein the request involves using knowledge in a set technical field.

10. A method according to any one of claims 1 to 9, wherein the invention is a software-related invention.

11. The method of claim 10, wherein the generated description of the invention includes logic required to implement each of a plurality of operations of the invention in software.

12. A method according to any one of claims 1 to 11, wherein the request includes a specification of an output format.

13. A method according to any one of claims 1 to 12, further comprising the step of receiving said definition from a user terminal.

14. A program for causing a computer to execute a method for assisting in the creation of a description of an invention, the method comprising the steps of: obtaining a definition of the invention in text form using a predetermined syntax; creating instructions for generating a description of the invention using the definition; making a request including the instructions to a generative AI model; and storing at least a portion of the generated description of the invention, the description including statements not included in the definition.

15. An apparatus for assisting in the creation of a description of an invention, the apparatus being configured to: obtain a definition of said invention, the definition being in text form using a predetermined syntax; create instructions for generating a description of said invention using said definition; make a request including said instructions to a generative AI model; and store at least a portion of the generated description of said invention, said description including statements not included in said definition.

Images