system

Abstract

The system according to this embodiment aims to streamline patent application processes and eliminate tasks that rely on individual expertise, require a large amount of effort, and result in duplicate patents. [Solution] The system according to the embodiment comprises a research unit, a creation unit, a proofreading unit, and a learning unit. The research unit conducts a prior art search. The creation unit initially creates application documents based on the duplicate cases listed by the research unit. The proofreading unit proofreads the application documents created by the creation unit for typographical errors. The learning unit learns the latest patent information based on the application documents proofread by the proofreading unit.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot performed by at least one processor, the method including: receiving a user utterance; adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot; encoding the prompt; and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there are problems such as personal business, large man-hours, and patent duplication in patent application operations.

[0005] The system according to the embodiment aims to improve the efficiency of patent application operations and eliminate personal business, large man-hours, and patent duplication.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a research unit, a creation unit, a proofreading unit, and a learning unit. The research unit conducts a prior art search. The creation unit initially prepares application documents based on the duplicate cases listed by the research unit. The proofreading unit proofreads the application documents prepared by the creation unit for typographical errors. The learning unit learns the latest patent information based on the application documents proofread by the proofreading unit. [Effects of the Invention]

[0007] The system according to this embodiment can streamline patent application procedures and eliminate tasks that rely on individual expertise, require a large amount of effort, and result in duplicate patents. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The patent application support system according to an embodiment of the present invention is a system that streamlines patent application work using generation AI. This patent application support system conducts prior art searches, lists duplicate cases, supports the initial creation of application documents, and reduces the workload. Furthermore, the generation AI proofreads for typographical errors and other mistakes, improving the quality of the documents. As a result, the man-hours required for patent application work are significantly reduced, the difference in working time between new and experienced workers is narrowed, and the quality of the search is improved. In addition, the number of search errors and rework is reduced, and the man-hours spent on document errors and rework are also reduced. The target users are corporate intellectual property departments, patent offices, and startup companies, and the system aims to reduce the time and cost of patent applications and streamline tasks that require specialized knowledge. Thus, the patent application support system can achieve both increased efficiency and improved quality in patent application work.

[0029] The patent application support system according to this embodiment comprises a research unit, a creation unit, a proofreading unit, and a learning unit. The research unit conducts a prior art search. The research unit, for example, searches a patent database and collects relevant patent documents. The research unit can narrow down the patent documents using, for example, keyword searches. The research unit can also classify patent documents using, for example, patent classification codes and efficiently search for patents in relevant technical fields. The creation unit initially creates application documents based on the duplicate cases listed by the research unit. The creation unit automatically generates application documents including, for example, the name of the idea, a description, a summary, etc. The creation unit can efficiently create application documents using, for example, templates. The creation unit can also automatically generate templates by referring to, for example, past successful patent application documents. The proofreading unit proofreads the application documents created by the creation unit for typographical errors. The proofreading unit detects typographical errors using, for example, spell checkers and grammar checkers. The proofreading unit can detect errors in specific technical terms based on, for example, patent classification codes. Furthermore, the proofreading unit can, for example, learn past patterns of typographical errors and automatically correct errors specific to a particular user. The learning unit learns the latest patent information based on application documents proofread by the proofreading unit. The learning unit can, for example, periodically obtain update information from the patent database and learn the latest patent information. The learning unit can, for example, perform specialized learning in a specific technical field based on patent classification codes. In addition, the learning unit can, for example, optimize its learning algorithm by referring to past patent application data. As a result, the patent application support system according to the embodiment can achieve increased efficiency and improved quality in patent application operations.

[0030] The research department conducts prior art searches. For example, the research department searches patent databases and collects relevant patent documents. Specifically, the research department can access multiple patent databases and efficiently narrow down relevant patent documents using keyword searches and patent classification codes. Keyword searches allow users to input specific technical terms or features of inventions and extract relevant patent documents. When using patent classification codes, patent documents classified under a specific technical field can be systematically searched. Furthermore, the research department can utilize natural language processing technology to automatically analyze the content of patent documents and prioritize listing highly relevant documents. For example, by analyzing the abstracts and claims of patent documents and extracting and comparing the technical features of inventions, it can efficiently identify patents with high overlap or similarity. In addition to patent databases, the research department also searches non-patent documents such as academic papers and technical reports, allowing it to collect a wider range of technical information. This improves the accuracy and efficiency of prior art searches and increases the success rate of patent applications. Furthermore, the research department provides a dashboard that visually displays the search results, enabling users to intuitively understand the results. For example, the number and distribution of related patent documents can be displayed in graphs and charts, allowing users to understand patent trends in a specific technological field. This enables the research department to provide users with comprehensive and visually easy-to-understand research results, supporting the efficiency of patent application work.

[0031] The drafting unit initially creates application documents based on duplicate cases listed by the research unit. The drafting unit automatically generates application documents, including, for example, the name, description, and summary of the idea. Specifically, the drafting unit can efficiently create application documents using templates. These templates have various items necessary for patent applications pre-configured, allowing users to complete the application documents simply by entering the required information. Furthermore, the drafting unit can automatically generate templates by referencing past successful patent applications. This allows the drafting unit to significantly reduce creation time while maintaining consistent quality in patent application documents. In addition, the drafting unit can use AI to analyze user input and suggest appropriate wording and expressions. For example, based on the user's input of the idea, it automatically completes appropriate technical terms and phrases, improving the completeness of the application documents. The drafting unit can also provide templates specialized for specific technical fields based on patent classification codes. This allows users to efficiently create application documents optimized for their own technical field. Furthermore, the drafting unit can collect user feedback and continuously improve templates and automatic generation algorithms. This allows the creation department to respond flexibly to user needs, thereby improving the efficiency and quality of patent application work.

[0032] The proofreading department reviews application documents prepared by the drafting department for typographical errors. The department detects errors using, for example, spell checkers and grammar checkers. Specifically, the department can utilize natural language processing technology to analyze the text of application documents and automatically detect typographical and grammatical errors. For example, it can check whether specific technical terms and phrases are used correctly and suggest corrections if errors are found. The department can also detect errors in specific technical terms based on patent classification codes. This allows the department to perform technically specialized proofreading, improving the accuracy of application documents. Furthermore, the department can learn past error patterns and automatically correct errors specific to particular users. For example, it can learn errors frequently made by a particular user and automatically correct them based on those patterns. The department can also continuously improve its proofreading algorithms based on user feedback. This allows the department to respond flexibly to user needs and improve the quality of patent application documents. Furthermore, the proofreading department provides a visual interface to display proofreading results, allowing users to intuitively understand the corrections needed. For example, it can highlight typographical errors and grammatical mistakes, and display correction suggestions in a pop-up window. This enables the proofreading department to provide users with efficient and effective proofreading support, thereby improving the quality of patent application work.

[0033] The learning unit learns the latest patent information based on application documents reviewed by the proofreading unit. For example, the learning unit periodically obtains update information from the patent database and learns the latest patent information. Specifically, the learning unit can use the patent database API to periodically obtain new patent information and incorporate it into its learning algorithm. This allows the learning unit to constantly learn based on the latest patent information, improving the accuracy of patent application work. Furthermore, the learning unit can perform specialized learning based on patent classification codes for specific technical fields. For example, it can learn patent trends and patterns in specific technical fields and use that information to help create and review patent application documents. In addition, the learning unit can optimize its learning algorithm by referring to past patent application data. For example, by analyzing past successful and rejected patent applications and learning the patterns, it can support the creation and review of more accurate patent applications. This enables the learning unit to improve the efficiency and quality of patent application work. Moreover, the learning unit can continuously improve its learning algorithm based on user feedback. This allows the learning unit to respond flexibly to user needs, improving the accuracy and efficiency of patent application work.

[0034] The research department can conduct prior art searches using keyword searches and list duplicate or similar cases. The research department can, for example, search patent databases and collect relevant patent documents. The research department can, for example, narrow down patent documents using keyword searches. Furthermore, the research department can, for example, classify patent documents using patent classification codes and efficiently search for patents in related technical fields. This makes efficient prior art searches possible by using keyword searches. Some or all of the above processing in the research department may be performed using a generative AI, or it may be performed without a generative AI. For example, the research department can input a prompt to search a patent database into the generative AI, and the generative AI can list relevant patent documents.

[0035] The creation unit can initially create application documents, including the name, description, and summary of the idea. For example, the creation unit can automatically generate the name of the idea. For example, the creation unit can automatically generate the description of the idea. Furthermore, the creation unit can automatically generate a summary of the idea. This streamlines the initial creation of application documents. Some or all of the above processes in the creation unit may be performed using a generation AI, or they may not be performed using a generation AI. For example, the creation unit can input the name, description, and summary of the idea into a generation AI, and the generation AI can initially create the application documents.

[0036] The proofreading department can perform proofreading for typographical errors and other mistakes. For example, the proofreading department can use a spell checker to detect typographical errors. For example, the proofreading department can use a grammar checker to detect grammatical errors. In addition, the proofreading department can detect errors in specific technical terms based on patent classification codes. This improves the quality of the application documents. Some or all of the above processes in the proofreading department may be performed using or without a generative AI. For example, the proofreading department can input the application documents into a generative AI, which can then proofread for typographical errors and other mistakes.

[0037] The learning unit can constantly learn the latest patent information and support optimal document creation. For example, the learning unit can periodically acquire update information from patent databases and learn the latest patent information. For example, the learning unit can perform specialized learning in a specific technical field based on patent classification codes. In addition, the learning unit can optimize its learning algorithm by referring to past patent application data. As a result, the accuracy of document creation is improved by learning the latest patent information. Some or all of the above processes in the learning unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the learning unit can input update information from patent databases into the generative AI, which can then learn the latest patent information.

[0038] The research unit can analyze the user's past patent application history during prior art searches and automatically generate optimal keywords. For example, the research unit can analyze keywords from patents previously filed by the user and automatically generate similar keywords. For example, the research unit can extract frequently used keywords from the user's past patent application history and use them in the research. Furthermore, the research unit can automatically generate keywords related to a specific technical field based on the user's patent application history. This enables the generation of optimal keywords based on past patent application history. Some or all of the above processes in the research unit may be performed using a generation AI, or they may not be performed using a generation AI. For example, the research unit can input the user's past patent application history into a generation AI, which can then automatically generate optimal keywords.

[0039] The research department can use patent classification codes to narrow the scope of the prior art search and improve accuracy. For example, the research department can prioritize searching for patents in relevant technical fields based on patent classification codes. For example, the research department can use patent classification codes to conduct a search focused on a specific technical field. Furthermore, for example, the research department can efficiently list duplicate and similar cases based on patent classification codes. Thus, by using patent classification codes, it is possible to narrow the scope of the search and improve accuracy. Some or all of the above processing in the research department may be performed using a generation AI, or it may be performed without a generation AI. For example, the research department can input patent classification codes into a generation AI, which can then narrow the scope of the search and improve accuracy.

[0040] The research department can customize keywords during prior art searches, taking into account the user's industry-specific terminology. For example, the research department can automatically generate keywords that include the user's industry-specific terminology. For example, the research department can narrow down the scope of the search based on the user's industry-specific terminology. Furthermore, the research department can display the search results, for example, taking into account the user's industry-specific terminology. This enables keyword customization that takes industry-specific terminology into account. Some or all of the above processes in the research department may be performed using a generation AI, or they may be performed without a generation AI. For example, the research department can input the user's industry-specific terminology into a generation AI, and the generation AI can customize the keywords.

[0041] The research unit can conduct prior art searches while considering the user's geographical patent application trends. For example, the research unit can prioritize the search for relevant patents based on the user's geographical patent application trends. For example, the research unit can narrow down the scope of the search while considering the user's geographical patent application trends. Furthermore, for example, the research unit can efficiently list duplicate and similar cases based on the user's geographical patent application trends. This makes it possible to conduct searches that take geographical patent application trends into account. Some or all of the above processes in the research unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the research unit can input the user's geographical patent application trends into a generation AI, and the generation AI can conduct the search.

[0042] The creation unit can automatically generate templates by referring to past successful patent application documents during the initial creation of application documents. For example, the creation unit can automatically generate templates based on past successful patent application documents. For example, the creation unit can initially create application documents by referring to the structure of past successful patent application documents. Furthermore, the creation unit can initially create application documents by referring to the expression methods of past successful patent application documents. This makes it possible to generate templates based on past successes. Some or all of the above processes in the creation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the creation unit can input past successful patent application documents into a generation AI, and the generation AI can automatically generate templates.

[0043] The creation unit can automatically insert appropriate sections based on patent classification codes during the initial creation of application documents. For example, the creation unit can automatically insert appropriate sections based on patent classification codes. For example, the creation unit can automatically determine the structure of application documents by referring to patent classification codes. Furthermore, the creation unit can automatically insert necessary information based on patent classification codes. This enables the insertion of appropriate sections based on patent classification codes. Some or all of the above-described processes in the creation unit may be performed using a generation AI, or not. For example, the creation unit can input patent classification codes into a generation AI, and the generation AI can automatically insert appropriate sections.

[0044] The creation unit can customize application documents during their initial creation, taking into account the user's industry-specific format. For example, the creation unit can customize application documents based on the user's industry-specific format. For example, the creation unit can initially create application documents by referring to the user's industry-specific format. Furthermore, the creation unit can determine the structure of application documents, taking into account the user's industry-specific format. This enables document customization that takes industry-specific formats into account. Some or all of the above processes in the creation unit may be performed using a generation AI, or not. For example, the creation unit can input the user's industry-specific format into a generation AI, and the generation AI can customize the document.

[0045] The creation unit can create application documents while considering the user's geographical patent application trends during the initial creation of the application documents. For example, the creation unit can create application documents based on the user's geographical patent application trends. For example, the creation unit can initially create application documents by referring to the user's geographical patent application trends. Furthermore, the creation unit can determine the structure of the application documents while considering the user's geographical patent application trends. This makes it possible to create documents that take geographical patent application trends into account. Some or all of the above-described processes in the creation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the creation unit can input the user's geographical patent application trends into a generation AI, and the generation AI can create the documents.

[0046] The proofreading department can learn past patterns of typos and grammatical errors during proofreading and automatically correct errors specific to a particular user. For example, the proofreading department can automatically correct typos and grammatical errors that the user has frequently made in the past. For example, the proofreading department can automatically correct specific errors based on the user's past patterns of typos and grammatical errors. Furthermore, the proofreading department can learn the user's past patterns of typos and grammatical errors and predict and correct specific errors. This enables automatic correction based on past patterns of typos and grammatical errors. Some or all of the above processes in the proofreading department may be performed using generative AI, or they may not be performed using generative AI. For example, the proofreading department can input the user's past patterns of typos and grammatical errors into a generative AI, which can then automatically correct specific errors.

[0047] The proofreading department can detect errors in specific technical terms based on patent classification codes during proofreading. For example, the proofreading department can detect errors in specific technical terms based on patent classification codes. For example, the proofreading department can automatically correct errors in technical terms by referring to patent classification codes. Furthermore, the proofreading department can predict and correct errors in technical terms based on patent classification codes. This makes it possible to detect errors in technical terms based on patent classification codes. Some or all of the above processes in the proofreading department may be performed using a generative AI, or they may not be performed using a generative AI. For example, the proofreading department can input patent classification codes into a generative AI, and the generative AI can detect errors in specific technical terms.

[0048] The proofreading department can correct typographical errors and grammatical errors while considering the user's industry-specific terminology during proofreading. For example, the proofreading department can correct typographical errors and grammatical errors based on the user's industry-specific terminology. For example, the proofreading department can automatically correct typographical errors and grammatical errors by referring to the user's industry-specific terminology. Furthermore, the proofreading department can predict and correct typographical errors and grammatical errors by considering the user's industry-specific terminology. This makes it possible to correct typographical errors and grammatical errors while considering industry-specific terminology. Some or all of the above processes in the proofreading department may be performed using a generative AI, or they may not be performed using a generative AI. For example, the proofreading department can input the user's industry-specific terminology into a generative AI, and the generative AI can correct typographical errors and grammatical errors.

[0049] The proofreading department can perform proofreading while considering the user's geographical patent application trends. For example, the proofreading department can perform proofreading based on the user's geographical patent application trends. For example, the proofreading department can determine the priority of proofreading by referring to the user's geographical patent application trends. Furthermore, the proofreading department can display the proofreading results while considering the user's geographical patent application trends. This makes it possible to perform proofreading that takes geographical patent application trends into account. Some or all of the above processes in the proofreading department may be performed using a generation AI, or they may be performed without a generation AI. For example, the proofreading department can input the user's geographical patent application trends into a generation AI, and the generation AI can perform proofreading.

[0050] The learning unit can optimize the learning algorithm by referring to past patent application data during the learning process. For example, the learning unit optimizes the learning algorithm based on past patent application data. For example, the learning unit can analyze trends in past patent application data and adjust the learning algorithm. Furthermore, the learning unit can improve the accuracy of the learning algorithm by referring to past patent application data. This makes it possible to optimize the learning algorithm based on past patent application data. Some or all of the above processing in the learning unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the learning unit can input past patent application data into a generative AI, and the generative AI can optimize the learning algorithm.

[0051] The learning unit can perform specialized learning in a specific technical field based on patent classification codes during the learning process. For example, the learning unit can perform specialized learning in a specific technical field based on patent classification codes. For example, the learning unit can select learning data by referring to patent classification codes. Furthermore, for example, the learning unit can focus on learning data related to a specific technical field based on patent classification codes. This makes it possible to learn specific technical fields based on patent classification codes. Some or all of the above-described processes in the learning unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the learning unit can input patent classification codes into a generative AI, which can then perform specialized learning in a specific technical field.

[0052] The learning unit can perform learning while considering data specific to the user's industry. For example, the learning unit can perform learning based on data specific to the user's industry. For example, the learning unit can adjust the learning algorithm by referring to data specific to the user's industry. Furthermore, the learning unit can select learning data while considering data specific to the user's industry. This makes it possible to perform learning that takes industry-specific data into account. Some or all of the above processes in the learning unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the learning unit can input data specific to the user's industry into a generative AI, and the generative AI can perform learning.

[0053] The learning unit can perform learning while considering the user's geographical patent application trends. For example, the learning unit can perform learning based on the user's geographical patent application trends. For example, the learning unit can adjust the learning algorithm by referring to the user's geographical patent application trends. Furthermore, the learning unit can select learning data by considering the user's geographical patent application trends. This makes it possible to perform learning that takes geographical patent application trends into account. Some or all of the above processing in the learning unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the learning unit can input the user's geographical patent application trends into a generative AI, and the generative AI can perform learning.

[0054] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0055] The patent application support system can analyze the user's past patent application data and automatically suggest the optimal format when creating patent application documents. For example, it can automatically generate a new application document format based on the format of a user's previously successful patent application documents. It can also extract frequently used sections and expressions from the user's past patent application data and reflect them in the application documents. Furthermore, it can suggest a format specific to a particular technical field based on the user's past patent application data. This makes it possible to suggest the optimal format by utilizing past data. Format suggestions may be made using a generation AI or not. For example, the system can input the user's past patent application data into a generation AI, which can then automatically suggest the optimal format.

[0056] The patent application support system can automatically suggest the most appropriate terminology when creating patent application documents, taking into account the user's industry-specific terminology. For example, it can refer to a database containing the user's industry-specific terminology and automatically insert appropriate terms into new application documents. It can also customize the expression of application documents based on the user's industry-specific terminology. Furthermore, it can automatically suggest terminology related to a specific technical field, taking into account the user's industry-specific terminology. This enables the suggestion of optimal terminology that takes industry-specific terms into account. Terminology suggestions may be performed using a generative AI or not. For example, the system can input the user's industry-specific terminology into a generative AI, which can then automatically suggest the most appropriate terminology.

[0057] The patent application support system can analyze the user's past patent application data and automatically suggest the most suitable sections when creating patent application documents. For example, it can automatically generate sections for a new application document based on the sections of successful patent applications the user has used in the past. It can also extract frequently used sections from the user's past patent application data and incorporate them into the application documents. Furthermore, it can suggest sections specialized for a particular technical field based on the user's past patent application data. This enables the suggestion of optimal sections by utilizing past data. Section suggestions may be made using a generation AI or not. For example, the system can input the user's past patent application data into a generation AI, which can then automatically suggest the most suitable sections.

[0058] The patent application support system can automatically suggest the optimal format when creating patent application documents, taking into account the user's industry-specific format. For example, it can refer to a database containing the user's industry-specific format and automatically insert the appropriate format into a new application document. It can also customize the presentation of the application document based on the user's industry-specific format. Furthermore, it can automatically suggest formats related to a specific technical field, taking into account the user's industry-specific format. This enables the suggestion of the optimal format while considering industry-specific formatting. Format suggestions may be made using a generative AI or not. For example, the system can input the user's industry-specific format into a generative AI, which can then automatically suggest the optimal format.

[0059] The patent application support system can automatically suggest the most suitable sections when creating patent application documents, taking into account the user's geographical patent application trends. For example, it can automatically generate sections for new application documents based on the user's geographical patent application trends. It can also extract frequently used sections from the user's geographical patent application trends and reflect them in the application documents. Furthermore, it can suggest sections specialized for specific technical fields based on the user's geographical patent application trends. This makes it possible to suggest the most suitable sections considering geographical patent application trends. Section suggestions may be made using a generation AI or not. For example, the system can input the user's geographical patent application trends into a generation AI, which can then automatically suggest the most suitable sections.

[0060] The following briefly describes the processing flow for example form 1.

[0061] Step 1: The research department conducts a prior art search. The research department searches patent databases and collects relevant patent documents. For example, patent documents can be narrowed down and classified using keyword searches or patent classification codes. Step 2: The drafting department initially prepares the application documents based on the duplicate cases listed by the research department. The drafting department automatically generates the application documents, including the name of the idea, description, and summary, and efficiently creates them by referring to templates and past successful patent applications. Step 3: The proofreading department reviews the application documents prepared by the drafting department for typographical errors. The proofreading department uses spell checkers and grammar checkers to detect errors and identifies errors in specific technical terms based on patent classification codes. It can also learn past error patterns and automatically correct errors specific to particular users. Step 4: The learning unit learns the latest patent information based on the application documents reviewed by the proofreading unit. The learning unit regularly obtains updated information from the patent database and performs specialized learning in specific technical fields based on patent classification codes. It also optimizes the learning algorithm by referring to past patent application data.

[0062] (Example of form 2) The patent application support system according to an embodiment of the present invention is a system that streamlines patent application work using generation AI. This patent application support system conducts prior art searches, lists duplicate cases, supports the initial creation of application documents, and reduces the workload. Furthermore, the generation AI proofreads for typographical errors and other mistakes, improving the quality of the documents. As a result, the man-hours required for patent application work are significantly reduced, the difference in working time between new and experienced workers is narrowed, and the quality of the search is improved. In addition, the number of search errors and rework is reduced, and the man-hours spent on document errors and rework are also reduced. The target users are corporate intellectual property departments, patent offices, and startup companies, and the system aims to reduce the time and cost of patent applications and streamline tasks that require specialized knowledge. Thus, the patent application support system can achieve both increased efficiency and improved quality in patent application work.

[0063] The patent application support system according to this embodiment comprises a research unit, a creation unit, a proofreading unit, and a learning unit. The research unit conducts a prior art search. The research unit, for example, searches a patent database and collects relevant patent documents. The research unit can narrow down the patent documents using, for example, keyword searches. The research unit can also classify patent documents using, for example, patent classification codes and efficiently search for patents in relevant technical fields. The creation unit initially creates application documents based on the duplicate cases listed by the research unit. The creation unit automatically generates application documents including, for example, the name of the idea, a description, a summary, etc. The creation unit can efficiently create application documents using, for example, templates. The creation unit can also automatically generate templates by referring to, for example, past successful patent application documents. The proofreading unit proofreads the application documents created by the creation unit for typographical errors. The proofreading unit detects typographical errors using, for example, spell checkers and grammar checkers. The proofreading unit can detect errors in specific technical terms based on, for example, patent classification codes. Furthermore, the proofreading unit can, for example, learn past patterns of typographical errors and automatically correct errors specific to a particular user. The learning unit learns the latest patent information based on application documents proofread by the proofreading unit. The learning unit can, for example, periodically obtain update information from the patent database and learn the latest patent information. The learning unit can, for example, perform specialized learning in a specific technical field based on patent classification codes. In addition, the learning unit can, for example, optimize its learning algorithm by referring to past patent application data. As a result, the patent application support system according to the embodiment can achieve increased efficiency and improved quality in patent application operations.

[0064] The research department conducts prior art searches. For example, the research department searches patent databases and collects relevant patent documents. Specifically, the research department can access multiple patent databases and efficiently narrow down relevant patent documents using keyword searches and patent classification codes. Keyword searches allow users to input specific technical terms or features of inventions and extract relevant patent documents. When using patent classification codes, patent documents classified under a specific technical field can be systematically searched. Furthermore, the research department can utilize natural language processing technology to automatically analyze the content of patent documents and prioritize listing highly relevant documents. For example, by analyzing the abstracts and claims of patent documents and extracting and comparing the technical features of inventions, it can efficiently identify patents with high overlap or similarity. In addition to patent databases, the research department also searches non-patent documents such as academic papers and technical reports, allowing it to collect a wider range of technical information. This improves the accuracy and efficiency of prior art searches and increases the success rate of patent applications. Furthermore, the research department provides a dashboard that visually displays the search results, enabling users to intuitively understand the results. For example, the number and distribution of related patent documents can be displayed in graphs and charts, allowing users to understand patent trends in a specific technological field. This enables the research department to provide users with comprehensive and visually easy-to-understand research results, supporting the efficiency of patent application work.

[0065] The drafting unit initially creates application documents based on duplicate cases listed by the research unit. The drafting unit automatically generates application documents, including, for example, the name, description, and summary of the idea. Specifically, the drafting unit can efficiently create application documents using templates. These templates have various items necessary for patent applications pre-configured, allowing users to complete the application documents simply by entering the required information. Furthermore, the drafting unit can automatically generate templates by referencing past successful patent applications. This allows the drafting unit to significantly reduce creation time while maintaining consistent quality in patent applications. In addition, the drafting unit can use AI to analyze user input and suggest appropriate wording and expressions. For example, based on the user's input of the idea, it automatically completes appropriate technical terms and phrases, improving the completeness of the application documents. The drafting unit can also provide templates specialized for specific technical fields based on patent classification codes. This allows users to efficiently create application documents optimized for their own technical field. Furthermore, the drafting unit can collect user feedback and continuously improve templates and automatic generation algorithms. This allows the creation department to respond flexibly to user needs, thereby improving the efficiency and quality of patent application work.

[0066] The proofreading department reviews application documents prepared by the drafting department for typographical errors. The department detects errors using, for example, spell checkers and grammar checkers. Specifically, the department can utilize natural language processing technology to analyze the text of application documents and automatically detect typographical and grammatical errors. For example, it can check whether specific technical terms and phrases are used correctly and suggest corrections if errors are found. The department can also detect errors in specific technical terms based on patent classification codes. This allows the department to perform technically specialized proofreading, improving the accuracy of application documents. Furthermore, the department can learn past error patterns and automatically correct errors specific to particular users. For example, it can learn errors frequently made by a particular user and automatically correct them based on those patterns. The department can also continuously improve its proofreading algorithms based on user feedback. This allows the department to respond flexibly to user needs and improve the quality of patent application documents. Furthermore, the proofreading department provides a visual interface to display proofreading results, allowing users to intuitively understand the corrections needed. For example, it can highlight typographical errors and grammatical mistakes, and display correction suggestions in a pop-up window. This enables the proofreading department to provide users with efficient and effective proofreading support, thereby improving the quality of patent application work.

[0067] The learning unit learns the latest patent information based on application documents reviewed by the proofreading unit. For example, the learning unit periodically obtains update information from the patent database and learns the latest patent information. Specifically, the learning unit can use the patent database API to periodically obtain new patent information and incorporate it into its learning algorithm. This allows the learning unit to constantly learn based on the latest patent information, improving the accuracy of patent application work. Furthermore, the learning unit can perform specialized learning based on patent classification codes for specific technical fields. For example, it can learn patent trends and patterns in specific technical fields and use that information to help create and review patent application documents. In addition, the learning unit can optimize its learning algorithm by referring to past patent application data. For example, by analyzing past successful and rejected patent applications and learning the patterns, it can support the creation and review of more accurate patent applications. This enables the learning unit to improve the efficiency and quality of patent application work. Moreover, the learning unit can continuously improve its learning algorithm based on user feedback. This allows the learning unit to respond flexibly to user needs, improving the accuracy and efficiency of patent application work.

[0068] The research department can conduct prior art searches using keyword searches and list duplicate or similar cases. The research department can, for example, search patent databases and collect relevant patent documents. The research department can, for example, narrow down patent documents using keyword searches. Furthermore, the research department can, for example, classify patent documents using patent classification codes and efficiently search for patents in related technical fields. This makes efficient prior art searches possible by using keyword searches. Some or all of the above processing in the research department may be performed using a generative AI, or it may be performed without a generative AI. For example, the research department can input a prompt to search a patent database into the generative AI, and the generative AI can list relevant patent documents.

[0069] The creation unit can initially create application documents, including the name, description, and summary of the idea. For example, the creation unit can automatically generate the name of the idea. For example, the creation unit can automatically generate the description of the idea. Furthermore, the creation unit can automatically generate a summary of the idea. This streamlines the initial creation of application documents. Some or all of the above processes in the creation unit may be performed using a generation AI, or they may not be performed using a generation AI. For example, the creation unit can input the name, description, and summary of the idea into a generation AI, and the generation AI can initially create the application documents.

[0070] The proofreading department can perform proofreading for typographical errors and other mistakes. For example, the proofreading department can use a spell checker to detect typographical errors. For example, the proofreading department can use a grammar checker to detect grammatical errors. In addition, the proofreading department can detect errors in specific technical terms based on patent classification codes. This improves the quality of the application documents. Some or all of the above processes in the proofreading department may be performed using or without a generative AI. For example, the proofreading department can input the application documents into a generative AI, which can then proofread for typographical errors and other mistakes.

[0071] The learning unit can constantly learn the latest patent information and support optimal document creation. For example, the learning unit can periodically acquire update information from patent databases and learn the latest patent information. For example, the learning unit can perform specialized learning in a specific technical field based on patent classification codes. In addition, the learning unit can optimize its learning algorithm by referring to past patent application data. As a result, the accuracy of document creation is improved by learning the latest patent information. Some or all of the above processes in the learning unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the learning unit can input update information from patent databases into the generative AI, which can then learn the latest patent information.

[0072] The research unit can estimate the user's emotions and adjust the priority of prior art searches based on the estimated emotions. For example, if the user is anxious, the research unit will prioritize investigating high-priority technical fields. If the user is relaxed, the research unit can investigate a wide range of technical fields evenly. Furthermore, if the user is feeling uneasy, the research unit can focus on investigating technical fields that have caused problems in the past. This makes it possible to adjust the research priority according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the research unit may be performed using or without generative AI. For example, the research unit can input user emotion data into a generative AI, which can estimate the emotions and adjust the research priority.

[0073] The research unit can analyze the user's past patent application history during prior art searches and automatically generate optimal keywords. For example, the research unit can analyze keywords from patents previously filed by the user and automatically generate similar keywords. For example, the research unit can extract frequently used keywords from the user's past patent application history and use them in the research. Furthermore, the research unit can automatically generate keywords related to a specific technical field based on the user's patent application history. This enables the generation of optimal keywords based on past patent application history. Some or all of the above processes in the research unit may be performed using a generation AI, or they may not be performed using a generation AI. For example, the research unit can input the user's past patent application history into a generation AI, which can then automatically generate optimal keywords.

[0074] The research department can use patent classification codes to narrow the scope of the prior art search and improve accuracy. For example, the research department can prioritize searching for patents in relevant technical fields based on patent classification codes. For example, the research department can use patent classification codes to conduct a search focused on a specific technical field. Furthermore, for example, the research department can efficiently list duplicate and similar cases based on patent classification codes. Thus, by using patent classification codes, it is possible to narrow the scope of the search and improve accuracy. Some or all of the above processing in the research department may be performed using a generation AI, or it may be performed without a generation AI. For example, the research department can input patent classification codes into a generation AI, which can then narrow the scope of the search and improve accuracy.

[0075] The research unit can estimate the user's emotions and adjust how the research results are displayed based on the estimated emotions. For example, if the user is anxious, the research unit can highlight important information. If the user is relaxed, the research unit can provide a display method that includes detailed information. Furthermore, if the user is feeling anxious, the research unit can provide a display method that provides reassurance. This makes it possible to adjust how the research results are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the research unit may be performed using generative AI or not. For example, the research unit can input user emotion data into a generative AI, which can estimate the emotions and adjust how the research results are displayed.

[0076] The research department can customize keywords during prior art searches, taking into account the user's industry-specific terminology. For example, the research department can automatically generate keywords that include the user's industry-specific terminology. For example, the research department can narrow down the scope of the search based on the user's industry-specific terminology. Furthermore, the research department can display the search results, for example, taking into account the user's industry-specific terminology. This enables keyword customization that takes industry-specific terminology into account. Some or all of the above processes in the research department may be performed using a generation AI, or they may be performed without a generation AI. For example, the research department can input the user's industry-specific terminology into a generation AI, and the generation AI can customize the keywords.

[0077] The research unit can conduct prior art searches while considering the user's geographical patent application trends. For example, the research unit can prioritize the search for relevant patents based on the user's geographical patent application trends. For example, the research unit can narrow down the scope of the search while considering the user's geographical patent application trends. Furthermore, for example, the research unit can efficiently list duplicate and similar cases based on the user's geographical patent application trends. This makes it possible to conduct searches that take geographical patent application trends into account. Some or all of the above processes in the research unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the research unit can input the user's geographical patent application trends into a generation AI, and the generation AI can conduct the search.

[0078] The creation unit can estimate the user's emotions and adjust the wording of the application documents based on the estimated emotions. For example, if the user is relaxed, the creation unit can provide a wording that includes detailed explanations. For example, if the user is in a hurry, the creation unit can provide a concise and to-the-point wording. Also, for example, if the user is feeling anxious, the creation unit can provide a wording that provides reassurance. This makes it possible to adjust the wording of the application documents according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the creation unit may be performed using a generative AI or not. For example, the creation unit can input user emotion data into a generative AI, which can estimate the emotions and adjust the wording of the application documents.

[0079] The creation unit can automatically generate templates by referring to past successful patent application documents during the initial creation of application documents. For example, the creation unit can automatically generate templates based on past successful patent application documents. For example, the creation unit can initially create application documents by referring to the structure of past successful patent application documents. Furthermore, the creation unit can initially create application documents by referring to the expression methods of past successful patent application documents. This makes it possible to generate templates based on past successes. Some or all of the above processes in the creation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the creation unit can input past successful patent application documents into a generation AI, and the generation AI can automatically generate templates.

[0080] The creation unit can automatically insert appropriate sections based on patent classification codes during the initial creation of application documents. For example, the creation unit can automatically insert appropriate sections based on patent classification codes. For example, the creation unit can automatically determine the structure of application documents by referring to patent classification codes. Furthermore, the creation unit can automatically insert necessary information based on patent classification codes. This enables the insertion of appropriate sections based on patent classification codes. Some or all of the above-described processes in the creation unit may be performed using a generation AI, or not. For example, the creation unit can input patent classification codes into a generation AI, and the generation AI can automatically insert appropriate sections.

[0081] The creation unit can estimate the user's emotions and adjust the length of the application document based on the estimated emotions. For example, if the user is in a hurry, the creation unit can provide a short, concise application document. For example, if the user is relaxed, the creation unit can provide a longer application document with detailed explanations. Also, for example, if the user is feeling anxious, the creation unit can provide a reassuring application document. This makes it possible to adjust the length of the application document according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the creation unit may be performed using or without a generative AI. For example, the creation unit can input user emotion data into a generative AI, which can estimate the emotions and adjust the length of the application document.

[0082] The creation unit can customize application documents during their initial creation, taking into account the user's industry-specific format. For example, the creation unit can customize application documents based on the user's industry-specific format. For example, the creation unit can initially create application documents by referring to the user's industry-specific format. Furthermore, the creation unit can determine the structure of application documents, taking into account the user's industry-specific format. This enables document customization that takes industry-specific formats into account. Some or all of the above processes in the creation unit may be performed using a generation AI, or not. For example, the creation unit can input the user's industry-specific format into a generation AI, and the generation AI can customize the document.

[0083] The creation unit can create application documents while considering the user's geographical patent application trends during the initial creation of the application documents. For example, the creation unit can create application documents based on the user's geographical patent application trends. For example, the creation unit can initially create application documents by referring to the user's geographical patent application trends. Furthermore, the creation unit can determine the structure of the application documents while considering the user's geographical patent application trends. This makes it possible to create documents that take geographical patent application trends into account. Some or all of the above-described processes in the creation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the creation unit can input the user's geographical patent application trends into a generation AI, and the generation AI can create the documents.

[0084] The proofreading department can estimate the user's emotions and adjust the proofreading priority based on the estimated emotions. For example, if the user is anxious, the proofreading department will prioritize proofreading important sections. If the user is relaxed, the proofreading department can proofread the entire document evenly. Also, if the user is feeling anxious, the proofreading department can focus on proofreading sections that have caused problems in the past. This allows for adjustment of proofreading priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the proofreading department may be performed using generative AI or not. For example, the proofreading department can input user emotion data into a generative AI, which can estimate the emotions and adjust the proofreading priority.

[0085] The proofreading department can learn past patterns of typos and grammatical errors during proofreading and automatically correct errors specific to a particular user. For example, the proofreading department can automatically correct typos and grammatical errors that the user has frequently made in the past. For example, the proofreading department can automatically correct specific errors based on the user's past patterns of typos and grammatical errors. Furthermore, the proofreading department can learn the user's past patterns of typos and grammatical errors and predict and correct specific errors. This enables automatic correction based on past patterns of typos and grammatical errors. Some or all of the above processes in the proofreading department may be performed using generative AI, or they may not be performed using generative AI. For example, the proofreading department can input the user's past patterns of typos and grammatical errors into a generative AI, which can then automatically correct specific errors.

[0086] The proofreading department can detect errors in specific technical terms based on patent classification codes during proofreading. For example, the proofreading department can detect errors in specific technical terms based on patent classification codes. For example, the proofreading department can automatically correct errors in technical terms by referring to patent classification codes. Furthermore, the proofreading department can predict and correct errors in technical terms based on patent classification codes. This makes it possible to detect errors in technical terms based on patent classification codes. Some or all of the above processes in the proofreading department may be performed using a generative AI, or they may not be performed using a generative AI. For example, the proofreading department can input patent classification codes into a generative AI, and the generative AI can detect errors in specific technical terms.

[0087] The proofreading unit can estimate the user's emotions and adjust how the proofreading results are displayed based on the estimated emotions. For example, if the user is anxious, the proofreading unit can highlight important errors. If the user is relaxed, the proofreading unit can display detailed proofreading results. Furthermore, if the user is feeling anxious, the proofreading unit can display reassuring proofreading results. This allows for adjustment of how proofreading results are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the proofreading unit may be performed using or without a generative AI. For example, the proofreading unit can input user emotion data into a generative AI, which can estimate the emotions and adjust how the proofreading results are displayed.

[0088] The proofreading department can correct typographical errors and grammatical errors while considering the user's industry-specific terminology during proofreading. For example, the proofreading department can correct typographical errors and grammatical errors based on the user's industry-specific terminology. For example, the proofreading department can automatically correct typographical errors and grammatical errors by referring to the user's industry-specific terminology. Furthermore, the proofreading department can predict and correct typographical errors and grammatical errors by considering the user's industry-specific terminology. This makes it possible to correct typographical errors and grammatical errors while considering industry-specific terminology. Some or all of the above processes in the proofreading department may be performed using a generative AI, or they may not be performed using a generative AI. For example, the proofreading department can input the user's industry-specific terminology into a generative AI, and the generative AI can correct typographical errors and grammatical errors.

[0089] The proofreading department can perform proofreading while considering the user's geographical patent application trends. For example, the proofreading department can perform proofreading based on the user's geographical patent application trends. For example, the proofreading department can determine the priority of proofreading by referring to the user's geographical patent application trends. Furthermore, the proofreading department can display the proofreading results while considering the user's geographical patent application trends. This makes it possible to perform proofreading that takes geographical patent application trends into account. Some or all of the above processes in the proofreading department may be performed using a generation AI, or they may be performed without a generation AI. For example, the proofreading department can input the user's geographical patent application trends into a generation AI, and the generation AI can perform proofreading.

[0090] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is relaxed, the learning unit will learn a wide range of data. If the user is in a hurry, for example, the learning unit can prioritize learning important data. Also, if the user is feeling anxious, for example, the learning unit can focus on learning data that has caused problems in the past. This makes it possible to select training data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using a generative AI or not. For example, the learning unit can input user emotion data into a generative AI, which can estimate the emotions and select training data.

[0091] The learning unit can optimize the learning algorithm by referring to past patent application data during the learning process. For example, the learning unit optimizes the learning algorithm based on past patent application data. For example, the learning unit can analyze trends in past patent application data and adjust the learning algorithm. Furthermore, the learning unit can improve the accuracy of the learning algorithm by referring to past patent application data. This makes it possible to optimize the learning algorithm based on past patent application data. Some or all of the above processing in the learning unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the learning unit can input past patent application data into a generative AI, and the generative AI can optimize the learning algorithm.

[0092] The learning unit can perform specialized learning in a specific technical field based on patent classification codes during the learning process. For example, the learning unit can perform specialized learning in a specific technical field based on patent classification codes. For example, the learning unit can select learning data by referring to patent classification codes. Furthermore, for example, the learning unit can focus on learning data related to a specific technical field based on patent classification codes. This makes it possible to learn specific technical fields based on patent classification codes. Some or all of the above-described processes in the learning unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the learning unit can input patent classification codes into a generative AI, which can then perform specialized learning in a specific technical field.

[0093] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, the learning unit can increase the learning frequency when the user is relaxed. For example, it can decrease the learning frequency when the user is in a hurry. Furthermore, if the user is feeling anxious, the learning unit can adjust the learning frequency to provide a sense of security. This makes it possible to adjust the learning frequency according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the learning unit may be performed using the generative AI or not. For example, the learning unit can input user emotion data into the generative AI, which can estimate the emotions and adjust the learning frequency.

[0094] The learning unit can perform learning while considering data specific to the user's industry. For example, the learning unit can perform learning based on data specific to the user's industry. For example, the learning unit can adjust the learning algorithm by referring to data specific to the user's industry. Furthermore, the learning unit can select learning data while considering data specific to the user's industry. This makes it possible to perform learning that takes industry-specific data into account. Some or all of the above processes in the learning unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the learning unit can input data specific to the user's industry into a generative AI, and the generative AI can perform learning.

[0095] The learning unit can perform learning while considering the user's geographical patent application trends. For example, the learning unit can perform learning based on the user's geographical patent application trends. For example, the learning unit can adjust the learning algorithm by referring to the user's geographical patent application trends. Furthermore, the learning unit can select learning data by considering the user's geographical patent application trends. This makes it possible to perform learning that takes geographical patent application trends into account. Some or all of the above processing in the learning unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the learning unit can input the user's geographical patent application trends into a generative AI, and the generative AI can perform learning.

[0096] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0097] The patent application support system can estimate the user's emotions and adjust the timing of patent application document submission based on those emotions. For example, if the user is anxious, the system can set an earlier submission deadline to give the user more time. If the user is relaxed, the system can set the submission deadline as usual and encourage detailed review. Furthermore, if the user is feeling uneasy, the system can flexibly adjust the submission deadline to provide reassurance. This makes it possible to adjust the submission timing according to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Adjustment of submission timing may be performed using generative AI or not. For example, the system can input user emotion data into a generative AI, which can estimate the emotions and adjust the submission timing.

[0098] The patent application support system can analyze the user's past patent application data and automatically suggest the optimal format when creating patent application documents. For example, it can automatically generate a new application document format based on the format of a user's previously successful patent application documents. It can also extract frequently used sections and expressions from the user's past patent application data and reflect them in the application documents. Furthermore, it can suggest a format specific to a particular technical field based on the user's past patent application data. This makes it possible to suggest the optimal format by utilizing past data. Format suggestions may be made using a generation AI or not. For example, the system can input the user's past patent application data into a generation AI, which can then automatically suggest the optimal format.

[0099] The patent application support system can estimate the user's emotions and adjust the proofreading method of the patent application documents based on the estimated emotions. For example, if the user is anxious, the system will prioritize proofreading important errors and make quick corrections. If the user is relaxed, the system can proofread the entire document evenly and make detailed corrections. Furthermore, if the user is feeling uneasy, the system can focus on proofreading sections that have caused problems in the past to provide reassurance. This makes it possible to adjust the proofreading method according to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Adjustment of the proofreading method may be done using generative AI or not. For example, the system can input user emotion data into a generative AI, which can estimate the emotions and adjust the proofreading method.

[0100] The patent application support system can automatically suggest the most appropriate terminology when creating patent application documents, taking into account the user's industry-specific terminology. For example, it can refer to a database containing the user's industry-specific terminology and automatically insert appropriate terms into new application documents. It can also customize the expression of application documents based on the user's industry-specific terminology. Furthermore, it can automatically suggest terminology related to a specific technical field, taking into account the user's industry-specific terminology. This enables the suggestion of optimal terminology that takes industry-specific terms into account. Terminology suggestions may be performed using a generative AI or not. For example, the system can input the user's industry-specific terminology into a generative AI, which can then automatically suggest the most appropriate terminology.

[0101] The patent application support system can estimate the user's emotions and customize patent application document templates based on those emotions. For example, if the user is relaxed, a detailed template can be provided, allowing the user to freely customize it. If the user is in a hurry, a concise and to-the-point template can be provided to support rapid creation. Furthermore, if the user is feeling anxious, a reassuring template can be provided to reduce the user's burden. This enables template customization according to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Template customization may be performed using generative AI or not. For example, the system can input user emotion data into a generative AI, which can estimate the emotions and customize the template.

[0102] The patent application support system can analyze the user's past patent application data and automatically suggest the most suitable sections when creating patent application documents. For example, it can automatically generate sections for a new application document based on the sections of successful patent applications the user has used in the past. It can also extract frequently used sections from the user's past patent application data and incorporate them into the application documents. Furthermore, it can suggest sections specialized for a particular technical field based on the user's past patent application data. This enables the suggestion of optimal sections by utilizing past data. Section suggestions may be made using a generation AI or not. For example, the system can input the user's past patent application data into a generation AI, which can then automatically suggest the most suitable sections.

[0103] The patent application support system can estimate the user's emotions and adjust the review method of the patent application documents based on the estimated emotions. For example, if the user is anxious, the system can prioritize reviewing important points and provide quick feedback. If the user is relaxed, it can review the entire document evenly and provide detailed feedback. Furthermore, if the user is feeling uneasy, it can focus on reviewing points that have caused problems in the past to provide reassurance. This makes it possible to adjust the review method according to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Adjustment of the review method may be done using generative AI or not. For example, the system can input user emotion data into a generative AI, which can estimate the emotions and adjust the review method.

[0104] The patent application support system can automatically suggest the optimal format when creating patent application documents, taking into account the user's industry-specific format. For example, it can refer to a database containing the user's industry-specific format and automatically insert the appropriate format into a new application document. It can also customize the presentation of the application document based on the user's industry-specific format. Furthermore, it can automatically suggest formats related to a specific technical field, taking into account the user's industry-specific format. This enables the suggestion of the optimal format while considering industry-specific formatting. Format suggestions may be made using a generative AI or not. For example, the system can input the user's industry-specific format into a generative AI, which can then automatically suggest the optimal format.

[0105] The patent application support system can estimate the user's emotions and adjust the feedback method for patent application documents based on the estimated emotions. For example, if the user is anxious, the system can prioritize providing important feedback and respond quickly. If the user is relaxed, it can provide feedback evenly and offer detailed responses. Furthermore, if the user is feeling uneasy, it can focus on feedback that has caused problems in the past to provide reassurance. This makes it possible to adjust the feedback method according to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Adjustment of the feedback method may be done using or without generative AI. For example, the system can input user emotion data into a generative AI, which can estimate the emotions and adjust the feedback method.

[0106] The patent application support system can automatically suggest the most suitable sections when creating patent application documents, taking into account the user's geographical patent application trends. For example, it can automatically generate sections for new application documents based on the user's geographical patent application trends. It can also extract frequently used sections from the user's geographical patent application trends and reflect them in the application documents. Furthermore, it can suggest sections specialized for specific technical fields based on the user's geographical patent application trends. This makes it possible to suggest the most suitable sections considering geographical patent application trends. Section suggestions may be made using a generation AI or not. For example, the system can input the user's geographical patent application trends into a generation AI, which can then automatically suggest the most suitable sections.

[0107] The following briefly describes the processing flow for example form 2.

[0108] Step 1: The research department conducts a prior art search. The research department searches patent databases and collects relevant patent documents. For example, patent documents can be narrowed down and classified using keyword searches or patent classification codes. Step 2: The drafting department initially prepares the application documents based on the duplicate cases listed by the research department. The drafting department automatically generates the application documents, including the name of the idea, description, and summary, and efficiently creates them by referring to templates and past successful patent applications. Step 3: The proofreading department reviews the application documents prepared by the drafting department for typographical errors. The proofreading department uses spell checkers and grammar checkers to detect errors and identifies errors in specific technical terms based on patent classification codes. It can also learn past error patterns and automatically correct errors specific to particular users. Step 4: The learning unit learns the latest patent information based on the application documents reviewed by the proofreading unit. The learning unit regularly obtains updated information from the patent database and performs specialized learning in specific technical fields based on patent classification codes. It also optimizes the learning algorithm by referring to past patent application data.

[0109] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0110] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0111] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0112] Each of the multiple elements described above, including the research unit, creation unit, proofreading unit, and learning unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the research unit is implemented by the specific processing unit 290 of the data processing unit 12, which searches the patent database and collects relevant patent documents. The creation unit is implemented by the control unit 46A of the smart device 14, which initially creates application documents based on the listed duplicate cases. The proofreading unit is implemented by the specific processing unit 290 of the data processing unit 12, which proofreads the created application documents for typographical errors. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12, which learns the latest patent information. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0113] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0114] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0115] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0116] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0117] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0118] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0119] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0120] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0121] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0122] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0123] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0124] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0125] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0126] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0127] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0128] Each of the multiple elements described above, including the research unit, creation unit, proofreading unit, and learning unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the research unit is implemented by the identification processing unit 290 of the data processing unit 12, which searches the patent database and collects relevant patent documents. The creation unit is implemented, for example, by the control unit 46A of the smart glasses 214, which initially creates application documents based on the listed duplicate cases. The proofreading unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, which proofreads the created application documents for typographical errors. The learning unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, which learns the latest patent information. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0129] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0130] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0131] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0132] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0133] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0135] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0136] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0137] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0138] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0139] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0140] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0141] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0142] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0143] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0144] Each of the multiple elements described above, including the research unit, creation unit, proofreading unit, and learning unit, is implemented, for example, by at least one of the headset terminal 314 and the data processing unit 12. For example, the research unit is implemented by the identification processing unit 290 of the data processing unit 12, which searches the patent database and collects relevant patent documents. The creation unit is implemented, for example, by the control unit 46A of the headset terminal 314, which initially creates application documents based on the listed duplicate cases. The proofreading unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, which proofreads the created application documents for typographical errors. The learning unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, which learns the latest patent information. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0145] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0146] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0147] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0148] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0149] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0150] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0151] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0152] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0153] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0154] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0155] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0156] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0157] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0158] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0159] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0160] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0161] Each of the multiple elements described above, including the research unit, creation unit, proofreading unit, and learning unit, is implemented, for example, by at least one of the robot 414 and the data processing unit 12. For example, the research unit is implemented by the identification processing unit 290 of the data processing unit 12, which searches the patent database and collects relevant patent documents. The creation unit is implemented, for example, by the control unit 46A of the robot 414, which initially creates application documents based on the listed duplicate cases. The proofreading unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, which proofreads the created application documents for typographical errors. The learning unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, which learns the latest patent information. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0162] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0163] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0164] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0165] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0166] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0167] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0168] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0169] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0170] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0171] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0172] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0173] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0174] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0175] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0176] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0177] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0178] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0179] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0180] (Note 1) The Research Department conducts prior art searches, The preparation department prepares the application documents based on the duplicate cases listed by the aforementioned investigation department, The proofreading department is responsible for reviewing the application documents prepared by the aforementioned preparation department for any typographical errors or omissions. The system includes a learning unit that learns the latest patent information based on application documents reviewed by the aforementioned review unit. A system characterized by the following features. (Note 2) The aforementioned investigation department, A prior art search is conducted using keyword searches to list duplicate and similar projects. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned creation unit, Initially, create application documents that include the name, description, and summary of the idea. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned proofreading department, Proofreading for typos and other errors. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned learning unit, We constantly learn the latest patent information and support optimal document creation. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned investigation department, It estimates user sentiment and adjusts the priority of prior art searches based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned investigation department, During prior art searches, the system analyzes the user's past patent application history and automatically generates optimal keywords. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned investigation department, During prior art searches, patent classification codes are used to narrow the scope of the search and improve accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned investigation department, We estimate the user's emotions and adjust how the survey results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned investigation department, When conducting a prior art search, customize keywords to take into account the user's industry-specific terminology. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned investigation department, When conducting a prior art search, the search should take into account the user's geographical patent application trends. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned creation unit, The system estimates the user's emotions and adjusts the wording of the application documents based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned creation unit, When initially creating application documents, templates are automatically generated by referencing past successful patent applications. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned creation unit, When initially creating application documents, the system automatically inserts the appropriate sections based on the patent classification code. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned creation unit, The system estimates the user's emotions and adjusts the length of the application form based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned creation unit, When initially creating application documents, customize them to take into account the user's industry-specific format. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned creation unit, When initially preparing application documents, we take into account the user's geographical patent application trends. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned proofreading department, Estimate user sentiment and adjust proofreading priorities based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned proofreading department, During proofreading, the system learns past patterns of typos and grammatical errors and automatically corrects errors specific to a particular user. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned proofreading department, During proofreading, errors in specific technical terms are detected based on patent classification codes. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned proofreading department, It estimates the user's sentiment and adjusts how the review results are displayed based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned proofreading department, During proofreading, correct typos and grammatical errors by taking into account the user's industry-specific terminology. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned proofreading department, During proofreading, we take into account the user's geographical patent application trends. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past patent application data. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned learning unit, During learning, specialized learning is performed based on patent classification codes for specific technical fields. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned learning unit, During training, the system takes into account data specific to the user's industry. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned learning unit, During training, the system takes into account the user's geographical patent application trends. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0181] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The Research Department conducts prior art searches, The preparation department prepares the application documents based on the duplicate cases listed by the aforementioned investigation department, The proofreading department is responsible for reviewing the application documents prepared by the aforementioned preparation department for any typographical errors or omissions. The system includes a learning unit that learns the latest patent information based on application documents reviewed by the aforementioned review unit. A system characterized by the following features.

2. The aforementioned investigation department, A prior art search is conducted using keyword searches to list duplicate and similar projects. The system according to feature 1.

3. The aforementioned creation unit, Initially, create application documents that include the name, description, and summary of the idea. The system according to feature 1.

4. The aforementioned proofreading department, Proofreading for typos and other errors. The system according to feature 1.

5. The aforementioned learning unit, We constantly learn the latest patent information and support optimal document creation. The system according to feature 1.

6. The aforementioned investigation department, It estimates user sentiment and adjusts the priority of prior art searches based on the estimated user sentiment. The system according to feature 1.

7. The aforementioned investigation department, During prior art searches, the system analyzes the user's past patent application history and automatically generates optimal keywords. The system according to feature 1.

8. The aforementioned investigation department, During prior art searches, patent classification codes are used to narrow the scope of the search and improve accuracy. The system according to feature 1.

9. The aforementioned investigation department, We estimate the user's emotions and adjust how the survey results are displayed based on those estimated emotions. The system according to feature 1.

10. The aforementioned investigation department, When conducting a prior art search, customize keywords to take into account the user's industry-specific terminology. The system according to feature 1.

Images