System

Abstract

To provide a system which can efficiently perform the entire process from collecting patent data to preparing an application document.SOLUTION: A system according to an embodiment includes a collection unit, a summary generation unit, an analysis unit, a draft generation unit, a review unit, and a drawing generation unit. The collection unit collects patent data. The summary generation unit summarizes the patent data collected by the collection unit. The analysis unit evaluates the inventive step and the novelty of a patent on the basis of the summary generated by the summary generation unit. The draft generation unit generates a draft of a patent application document on the basis of the result of the evaluation obtained by the analysis unit. The review unit reviews the application document generated by the draft generation unit. The drawing generation unit creates a drawing necessary for the application document reviewed by the review unit by using an image generative AI.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding the chatbot character, 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, the process from collecting patent data to preparing application documents was complicated and difficult to carry out efficiently.

[0005] The system according to the embodiment aims to efficiently carry out the process from collecting patent data to preparing application documents. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a summary generation unit, an analysis unit, a draft generation unit, a review unit, and a drawing generation unit. The collection unit collects patent data. The summary generation unit summarizes the patent data collected by the collection unit. The analysis unit evaluates the novelty and inventive step of the patent based on the summary generated by the summary generation unit. The draft generation unit drafts patent application documents based on the evaluation results obtained by the analysis unit. The review unit reviews the application documents generated by the draft generation unit. The drawing generation unit creates drawings required for the application documents reviewed by the review unit using an image generation AI. Effect of the Invention

[0007] The system according to the embodiment can efficiently carry out processes from collecting patent data to preparing application documents. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 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." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

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

[0017] 1, a 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. The database 24 and the communication I / F 26 are also 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 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

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

[0025] The storage 32 stores a data generation model 58 and an 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

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

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The patent business support system according to the embodiment of the present invention is a system for supporting patent-related business, which is particularly important for technology companies. The purpose of this system is to enable intellectual property officers, new business development officers, investment officers, and others to grasp patent data from around the world and provide effective support. The system has the function of confirming and summarizing existing patents. When a user searches for a specific patent, the system obtains detailed information about the patent and generates a summary. For example, when a patent related to a specific technical field is searched for, a summary of the patent is automatically generated and provided to the user. Next, it has a wall-hitting function when applying for a new patent. When a user applies for a new patent, the system analyzes the contents of the patent and compares it with existing patents to evaluate its novelty and inventiveness. This allows the user to check the strength of the patent before applying. In addition, it also has a function for drafting and reviewing application documents. When a user creates patent application documents, the system automatically generates a draft and suggests necessary corrections. For example, the claim portion of the patent is automatically generated and provided to the user. In addition, the application document review function allows the user to check and correct the contents of the document before submission. Finally, by combining it with image generation AI, drawings for application documents can also be automatically created. When a user specifies the drawings required for patent application documents, the system automatically creates the drawings using image generation AI and incorporates them into the application documents. This streamlines the patent application process. This patent work support system is a key tool for patent work and plays a very important role for technology companies. This allows the patent work support system to consistently perform everything from collecting patent data to creating application documents, reviewing them, and generating drawings.

[0029] The patent business support system according to the embodiment includes a collection unit, a summary generation unit, an analysis unit, a draft generation unit, a review unit, and a drawing generation unit. The collection unit collects patent data. The collection unit can collect patent data from, for example, a patent database. The patent database includes a public patent database and a commercial patent database. The collection unit accesses the patent database and collects patent data such as patent documents, patent application information, and patent classification information. The summary generation unit summarizes the patent data collected by the collection unit. The summary generation unit, for example, analyzes the collected patent data, extracts important information, and generates a summary. The summary generation unit generates a summary based on the length of the sentence and the importance of the information to be summarized. The analysis unit evaluates the novelty and inventive step of the patent based on the summary generated by the summary generation unit. The analysis unit uses, for example, an algorithm for evaluating the novelty and inventive step by comparing with existing patents. The analysis unit evaluates the technical features of the patent and the differences from existing technologies to determine the novelty and inventive step. The draft generation unit drafts patent application documents based on the evaluation results obtained by the analysis unit. The draft generation unit, for example, automatically generates the claim portion of a patent and provides it to the user. The draft generation unit generates a draft based on the format of the patent application documents and the level of detail of the contents. The review unit reviews the application documents generated by the draft generation unit. The review unit, for example, checks the contents of the application documents and proposes necessary corrections. The review unit reviews the application documents based on the check items and review procedures. The drawing generation unit automatically creates drawings required for the application documents reviewed by the review unit using an image generation AI. The drawing generation unit, for example, automatically creates drawings specified by the user using an image generation AI and incorporates them into the application documents. The image generation AI generates drawings based on the algorithm used and the format of the image to be generated. This allows the patent business support system to consistently perform operations from collecting patent data to creating application documents, reviewing them, and generating drawings.

[0030] The collection unit collects patent data. The collection unit can collect patent data from, for example, a patent database. The patent database includes a public patent database and a commercial patent database. The collection unit accesses the patent database and collects patent data such as patent documents, patent application information, and patent classification information. Specifically, the collection unit connects to the patent database through an API and searches for data based on specific keywords and classification codes. For example, when collecting patent documents related to a specific technical field, a search is performed using the corresponding IPC (International Patent Classification) code. The collection unit also has an internal database for centrally managing data acquired from the patent database, and efficiently stores and manages the collected data. Furthermore, the collection unit has a function to periodically crawl the patent database and automatically acquire newly published patent documents and updated information. This allows the collection unit to always hold the latest patent data and quickly provide information required by other departments. The collection unit also analyzes metadata of the patent data (for example, the inventor's name, application date, publication date, etc.) and organizes and classifies the data. This allows the collected patent data to be provided in a format that can be efficiently used by the subsequent summary generation unit and analysis unit.

[0031] The summary generation unit summarizes the patent data collected by the collection unit. For example, the summary generation unit analyzes the collected patent data, extracts important information, and generates a summary. The summary generation unit generates a summary based on the length of the sentences and the importance of the information to be summarized. Specifically, the summary generation unit analyzes the contents of the patent document using natural language processing (NLP) technology and extracts the gist and technical features of the invention. For example, important sections such as the purpose, solution, and effect of the invention are identified from the patent document and summarized briefly. The summary generation unit can also understand the structure of the patent document and generate a summary for each specific section (for example, background art, examples, claims, etc.). Furthermore, the summary generation unit checks the accuracy and consistency of the summary using an evaluation index (for example, ROUGE score) for evaluating the quality of the generated summary. In this way, the summary generation unit provides a high-quality summary and assists in quickly understanding the contents of the patent document. The summary generation unit also has a function of adjusting the detail level of the summary according to the user's request. For example, if a concise summary is required, a short summary is generated, and if a detailed analysis is required, a longer summary is provided. This enables the summary generation unit to flexibly generate summaries according to the needs of the user.

[0032] The analysis unit evaluates the novelty and inventive step of the patent based on the summary generated by the summary generation unit. The analysis unit uses an algorithm for evaluating the novelty and inventive step by, for example, comparing with existing patents. The analysis unit evaluates the technical features of the patent and the differences from existing technologies to determine the novelty and inventive step. Specifically, the analysis unit uses a machine learning algorithm to extract the technical features of the patent document and compares them with an existing patent database. For example, the claim portion of the patent document is analyzed to evaluate whether it matches the technical features described in the existing patent document. The analysis unit also quantitatively evaluates the novelty and inventive step by vectorizing the technical features of the patent document and performing a similarity calculation. Furthermore, the analysis unit hierarchically classifies the technical features of the patent document to grasp the progress of technology in a specific technical field. This allows the analysis unit to evaluate in detail how much the technical features of the patent document differ from existing technology. The analysis unit also has a function to visualize the technical features of the patent document, and provides support for intuitive understanding of the progress of technology and the novelty and inventive step of the patent. For example, it can generate a similarity map of technical features and visually show the degree to which the technical features of a patent document are similar to existing technologies. This allows the analysis unit to evaluate the novelty and inventive step of a patent with high accuracy and support the planning of a patent application strategy.

[0033] The draft generation unit drafts the patent application documents based on the evaluation results obtained by the analysis unit. The draft generation unit automatically generates, for example, the claims of a patent and provides it to the user. The draft generation unit generates the draft based on the format of the patent application documents and the level of detail of the description. Specifically, the draft generation unit automatically generates each section of the patent application documents using natural language generation (NLG) technology. For example, in the claims section, an appropriate claim sentence is generated based on the technical features of the patent document. The draft generation unit also automatically creates sections such as background art, summary of the invention, and examples according to the format of the patent application documents. Furthermore, the draft generation unit has a function of customizing the contents of the patent application documents based on the information input by the user and the evaluation results provided by the analysis unit. This allows the user to flexibly adjust the contents of the patent application documents and create optimal application documents. The draft generation unit also checks the accuracy and consistency of the draft using an evaluation index for evaluating the quality of the generated patent application documents. This allows the draft generation unit to provide high-quality patent application documents and improve the success rate of patent applications. Furthermore, the draft generation unit provides an interface for users to confirm and modify the draft, and can improve the draft by reflecting user feedback, thereby enabling the draft generation unit to realize flexible draft generation according to user needs.

[0034] The review section reviews the application documents generated by the draft generation section. For example, the review section checks the contents of the application documents and proposes necessary corrections. The review section reviews the application documents based on the check items and review procedures. Specifically, the review section checks each section of the patent application documents in detail to check the accuracy and consistency of the description. For example, in the claim section, it checks whether the technical features of the patent are properly described and whether there is no overlap with existing patent documents. In addition, in sections such as the background art, the outline of the invention, and the examples, it checks whether the description is clear and easy to understand, and whether all necessary information is described. Furthermore, the review section checks whether the format and description rules of the patent application documents are followed, and suggests corrections as necessary. This allows the review section to provide high-quality patent application documents and improve the success rate of patent applications. In addition, the review section has a function of improving the contents of the application documents based on feedback submitted by the user. For example, it reflects the corrections pointed out by the user and updates the contents of the application documents. This allows the review section to realize flexible reviews according to the needs of the user. Furthermore, the review department can improve the efficiency of reviews by managing the review history of patent application documents and referring to past review results, which enables the review department to continuously improve the quality of patent application documents.

[0035] The drawing generation unit automatically creates drawings required for the application documents reviewed by the review unit using image generation AI. For example, the drawing generation unit automatically creates drawings specified by the user using image generation AI and incorporates them into the application documents. The image generation AI generates drawings based on the algorithm used and the format of the image generated. Specifically, the drawing generation unit analyzes the contents of the patent application documents and identifies the type and details of the required drawings. For example, a structural diagram and an operation flow diagram of the device are required for patent application documents for a mechanical device. In order to generate these drawings, the drawing generation unit automatically creates drawings using image generation AI. The image generation AI uses deep learning technology to generate high-quality drawings based on the contents of the patent application documents. For example, when generating a structural diagram of a mechanical device, the shape and arrangement of each part of the device are accurately drawn to create a drawing that is visually easy to understand. In addition, when generating an operation flow diagram, a drawing that clearly shows the operation procedure of the device and the details of each step is created. In addition, the drawing generation unit checks the accuracy and consistency of the drawings using evaluation indicators for evaluating the quality of the generated drawings. This allows the drawing generation unit to provide high-quality drawings and complement the contents of the patent application documents. The drawing generator also provides an interface for users to check and modify drawings, and can improve drawings based on user feedback, allowing the drawing generator to flexibly generate drawings according to user needs.

[0036] The collection unit can collect patent data from a patent database. The collection unit, for example, collects patent data from a patent database. The patent database includes a public patent database and a commercial patent database. The collection unit accesses the patent database and collects patent data such as patent documents, patent application information, and patent classification information. This allows efficient collection of patent data from the patent database. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can collect patent data using an AI model for accessing the patent database.

[0037] The summary generation unit can summarize the collected patent data. For example, the summary generation unit analyzes the collected patent data, extracts important information, and generates a summary. The summary generation unit generates a summary based on the length of the sentence and the importance of the information to be summarized. For example, the summary generation unit extracts the main points of the patent document and generates a concise summary. The summary generation unit can also summarize the technical features of the patent and provide it to the user. This allows the collected patent data to be efficiently summarized. A part or all of the above-mentioned processing in the summary generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the summary generation unit can input the collected patent data into the generation AI and generate a summary. The generation AI uses a text generation AI (for example, LLM) to generate a summary of the patent data.

[0038] The analysis unit can evaluate the novelty and inventive step of the patent based on the summary generated by the summary generation unit. The analysis unit evaluates the novelty and inventive step of the patent based on, for example, the summary generated by the summary generation unit. The analysis unit uses an algorithm for evaluating the novelty and inventive step by comparing with existing patents. For example, the analysis unit evaluates the technical features of the patent and the difference from existing technologies to determine the novelty and inventive step. The analysis unit can also evaluate the technical impact and market value of the patent. This makes it possible to efficiently evaluate the novelty and inventive step of the patent. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the summary generated by the summary generation unit to the generation AI and cause the generation AI to perform the evaluation of the novelty and inventive step. The generation AI evaluates the novelty and inventive step of the patent using a text generation AI (for example, LLM).

[0039] The draft generation unit can draft the patent application documents based on the evaluation results obtained by the analysis unit. The draft generation unit drafts the patent application documents based on, for example, the evaluation results obtained by the analysis unit. The draft generation unit automatically generates the claims of the patent and provides them to the user. For example, the draft generation unit generates a draft based on the format of the patent application documents and the level of detail of the description. The draft generation unit can also automatically generate each section of the patent application documents (for example, background art, detailed description of the invention, claims, etc.). This allows the patent application documents to be drafted efficiently. A part or all of the above-mentioned processing in the draft generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the draft generation unit can input the evaluation results obtained by the analysis unit to the generation AI and cause the generation AI to execute drafting of the patent application documents. The generation AI generates a draft of the patent application documents using a text generation AI (for example, LLM).

[0040] The review unit can review the application documents generated by the draft generation unit. For example, the review unit checks the contents of the application documents generated by the draft generation unit and proposes necessary corrections. The review unit reviews the application documents based on the check items and review procedures. For example, the review unit checks the contents of the claims of the patent and proposes corrections. The review unit can also check the format of the patent application documents and the level of detail of the contents and propose corrections. This allows the patent application documents to be reviewed efficiently. Some or all of the above-mentioned processing in the review unit may be performed, for example, using AI or may be performed without using AI. For example, the review unit can input the application documents generated by the draft generation unit into AI and have the AI ​​perform the review.

[0041] The drawing generation unit can automatically create drawings required for the application documents reviewed by the review unit using an image generation AI. For example, the drawing generation unit can automatically create drawings specified by a user using an image generation AI and incorporate them into the application documents. The image generation AI generates drawings based on the algorithm used and the format of the image to be generated. For example, the drawing generation unit automatically creates technical drawings required for patent application documents using an image generation AI. The drawing generation unit can also automatically create flowcharts and block diagrams required for patent application documents using an image generation AI. This allows drawings required for patent application documents to be efficiently and automatically created. A part or all of the above-mentioned processing in the drawing generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the drawing generation unit can input the application documents reviewed by the review unit into the generation AI and cause the generation AI to generate the necessary drawings. The generation AI generates drawings required for patent application documents using an image generation AI.

[0042] The collection unit can analyze the user's past patent search history and select the optimal collection method. For example, the collection unit analyzes the user's past patent search history and selects the optimal collection method. The collection unit preferentially collects patent fields that the user has frequently searched in the past. The collection unit can also preferentially collect patent data containing specific keywords from the user's past search history. Furthermore, the collection unit can analyze the user's past search patterns and suggest the optimal collection timing. This makes it possible to select the optimal patent data collection method based on the user's past search history. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the user's past patent search history into AI and have the AI ​​select the optimal collection method.

[0043] The collection unit can filter the patent data based on the user's current project and field of interest when collecting the patent data. For example, the collection unit filters the patent data based on the user's current project and field of interest when collecting the patent data. The collection unit preferentially collects patent data related to the user's ongoing project. The collection unit can also filter and collect highly relevant patent data based on the user's field of interest. Furthermore, the collection unit can dynamically collect necessary patent data according to the progress of the user's project. This makes it possible to filter the patent data based on the user's current project and field of interest. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's project information and field of interest into AI and have the AI ​​perform filtering of the patent data.

[0044] The collection unit can preferentially collect highly relevant data in consideration of the geographical location information of the user when collecting patent data. For example, the collection unit preferentially collects highly relevant data in consideration of the geographical location information of the user when collecting patent data. The collection unit preferentially collects patent data in the region where the user is located. The collection unit can also filter and collect related patent data based on the geographical location information of the user. Furthermore, the collection unit can also collect patent data specific to the region based on the location information of the user. This makes it possible to preferentially collect highly relevant patent data based on the geographical location information of the user. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the geographical location information of the user to AI and cause the AI ​​to collect patent data.

[0045] The collection unit can analyze the user's social media activities and collect related data when collecting patent data. For example, the collection unit analyzes the user's social media activities and collects related data when collecting patent data. The collection unit analyzes the user's comments and posts on social media and collects related patent data. The collection unit can also preferentially collect patent data of experts and companies followed by the user. Furthermore, the collection unit can identify a technical field of interest from the user's social media activities and collect related patent data. This makes it possible to collect related patent data based on the user's social media activities. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input the user's social media activities into AI and cause AI to collect patent data.

[0046] The summary generation unit can adjust the level of detail of the summary based on the importance of the patent when generating the summary. The summary generation unit adjusts the level of detail of the summary based on the importance of the patent, for example, when generating the summary. The summary generation unit generates a detailed summary for a patent with high importance. The summary generation unit can also generate a concise summary for a patent with low importance. Furthermore, the summary generation unit can adjust the length and content of the summary according to the importance of the patent. This makes it possible to adjust the level of detail of the summary according to the importance of the patent. A part or all of the above-mentioned processing in the summary generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the summary generation unit can input the importance of the patent to AI and cause AI to adjust the level of detail of the summary.

[0047] The summary generation unit can apply different summarization algorithms depending on the patent category when generating a summary. For example, the summary generation unit applies different summarization algorithms depending on the patent category when generating a summary. The summary generation unit applies an optimal summarization algorithm for each technical field to generate a highly accurate summary. The summary generation unit can also select and apply different summarization algorithms depending on the patent category. Furthermore, the summary generation unit can adjust the content and format of the summary for each patent category. This makes it possible to apply an optimal summarization algorithm depending on the patent category. Some or all of the above-mentioned processing in the summary generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the summary generation unit can input patent category information to AI and cause AI to apply the summarization algorithm.

[0048] The summary generation unit can determine the priority of the summaries based on the filing dates of the patents when generating the summaries. The summary generation unit, for example, determines the priority of the summaries based on the filing dates of the patents when generating the summaries. The summary generation unit generates summaries preferentially for the newest patents. The summary generation unit can also postpone generating summaries for patents that were submitted earlier. Furthermore, the summary generation unit can adjust the order of generation of summaries based on the filing dates. This makes it possible to determine the priority of the summaries based on the filing dates of the patents. Some or all of the above-mentioned processing in the summary generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the summary generation unit can input patent submission date information to AI and have the AI ​​execute the determination of the priority of the summaries.

[0049] The summary generation unit can adjust the order of summaries based on the relevance of patents when generating summaries. The summary generation unit, for example, adjusts the order of summaries based on the relevance of patents when generating summaries. The summary generation unit generates summaries preferentially for highly relevant patents. Also, the summary generation unit can generate summaries for less relevant patents at a later date. Furthermore, the summary generation unit can adjust the order of summaries generated based on the relevance of patents. This makes it possible to adjust the order of summaries based on the relevance of patents. A part or all of the above-mentioned processing in the summary generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the summary generation unit can input patent relevance information to AI and cause AI to adjust the order of summaries.

[0050] The analysis unit can improve the accuracy of the analysis by taking into account the interrelationships of patents during the analysis. For example, the analysis unit can improve the accuracy of the analysis by taking into account the interrelationships of patents during the analysis. The analysis unit can improve the accuracy of the analysis by taking into account the citation relationships of patents. The analysis unit can also improve the accuracy of the analysis by taking into account the relevance of the technical fields of the patents. Furthermore, the analysis unit can analyze the interrelationships of patents and reflect them in the analysis results. This improves the accuracy of the analysis by taking into account the interrelationships of patents. A part or all of the above-mentioned processing in the analysis unit can be performed, for example, using AI or can be performed without using AI. For example, the analysis unit can input patent interrelationship information into AI and cause AI to improve the accuracy of the analysis.

[0051] The analysis unit can perform the analysis while taking into account the attribute information of the patent submitter. For example, the analysis unit performs the analysis while taking into account the attribute information of the patent submitter. The analysis unit takes into account the specialty of the patent submitter and reflects it in the analysis result. The analysis unit can also improve the accuracy of the analysis while taking into account the submitter's past patent application history. Furthermore, the analysis unit can evaluate the novelty and inventive step of the patent based on the attribute information of the submitter. This improves the accuracy of the analysis by taking into account the attribute information of the patent submitter. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the attribute information of the submitter to AI and have AI execute the analysis.

[0052] The analysis unit can perform the analysis while taking into consideration the geographical distribution of patents. For example, the analysis unit performs the analysis while taking into consideration the geographical distribution of patents. The analysis unit takes into consideration the country or region of the patent application and reflects it in the analysis result. The analysis unit can also evaluate the relevance of the patent based on the geographical distribution. Furthermore, the analysis unit can analyze the geographical distribution of patents and reflect it in the analysis result. This improves the accuracy of the analysis by taking into consideration the geographical distribution of patents. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the geographical distribution information of patents to AI and have AI execute the analysis.

[0053] The analysis unit can improve the accuracy of the analysis by referring to related documents of the patent during the analysis. The analysis unit, for example, improves the accuracy of the analysis by referring to related documents of the patent during the analysis. The analysis unit refers to cited documents of the patent and reflects them in the analysis result. The analysis unit can also evaluate the novelty and inventive step of the patent based on the related documents. Furthermore, the analysis unit can analyze related documents of the patent and improve the accuracy of the analysis. As a result, the accuracy of the analysis is improved by referring to related documents of the patent. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input related document information of the patent into AI and have AI execute the analysis.

[0054] The draft generation unit can adjust the level of detail of the draft based on the importance of the patent when generating the draft. For example, the draft generation unit adjusts the level of detail of the draft based on the importance of the patent when generating the draft. The draft generation unit generates a detailed draft for a patent with high importance. The draft generation unit can also generate a concise draft for a patent with low importance. Furthermore, the draft generation unit can adjust the length and contents of the draft according to the importance of the patent. This makes it possible to adjust the level of detail of the draft according to the importance of the patent. A part or all of the above-mentioned processing in the draft generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the draft generation unit can input the importance of the patent to AI and cause AI to adjust the level of detail of the draft.

[0055] The draft generation unit can apply different draft algorithms depending on the patent category when generating the draft. For example, the draft generation unit applies different draft algorithms depending on the patent category when generating the draft. The draft generation unit applies the optimal draft algorithm for each technical field to generate a highly accurate draft. The draft generation unit can also select and apply different draft algorithms depending on the patent category. Furthermore, the draft generation unit can adjust the content and format of the draft for each patent category. This makes it possible to apply the optimal draft algorithm depending on the patent category. A part or all of the above-mentioned processing in the draft generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the draft generation unit can input patent category information to AI and cause AI to apply the draft algorithm.

[0056] The draft generation unit can determine the priority of the draft based on the patent submission time when generating the draft. For example, the draft generation unit determines the priority of the draft based on the patent submission time when generating the draft. The draft generation unit generates the draft with priority for the latest patent. In addition, the draft generation unit can generate the draft for the patent with the older submission time at a later time. Furthermore, the draft generation unit can adjust the draft generation order based on the submission time. This makes it possible to determine the priority of the draft based on the patent submission time. A part or all of the above-mentioned processing in the draft generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the draft generation unit can input patent submission time information to AI and cause AI to execute the determination of the priority of the draft.

[0057] The draft generation unit can adjust the order of the drafts based on the relevance of the patents when generating the drafts. For example, the draft generation unit adjusts the order of the drafts based on the relevance of the patents when generating the drafts. The draft generation unit generates the drafts preferentially for patents with high relevance. In addition, the draft generation unit can generate the drafts later for patents with low relevance. Furthermore, the draft generation unit can adjust the order of the drafts based on the relevance of the patents. This makes it possible to adjust the order of the drafts based on the relevance of the patents. A part or all of the above-mentioned processing in the draft generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the draft generation unit can input patent relevance information to AI and cause AI to adjust the order of the drafts.

[0058] The review unit can improve the accuracy of the review by considering the interrelationships of patents during the review. For example, the review unit improves the accuracy of the review by considering the interrelationships of patents during the review. The review unit improves the accuracy of the review by considering the citation relationships of patents. The review unit can also improve the accuracy of the review by considering the relevance of the technical fields of the patents. Furthermore, the review unit can analyze the interrelationships of patents and reflect them in the review results. This improves the accuracy of the review by considering the interrelationships of patents. A part or all of the above-mentioned processing in the review unit may be performed, for example, using AI, or may be performed without using AI. For example, the review unit can input patent interrelationship information into AI and cause AI to improve the accuracy of the review.

[0059] The review department can conduct a review while taking into consideration the geographical distribution of patents. For example, the review department conducts a review while taking into consideration the geographical distribution of patents. The review department takes into consideration the country or region of application of the patent and reflects it in the review results. The review department can also evaluate the relevance of the patent based on the geographical distribution. Furthermore, the review department can analyze the geographical distribution of the patent and reflect it in the review results. In this way, the accuracy of the review is improved by taking into consideration the geographical distribution of the patent. A part or all of the above-mentioned processing in the review department may be performed, for example, using AI, or may be performed without using AI. For example, the review department can input the geographical distribution information of the patent into AI and have the AI ​​perform the review.

[0060] The drawing generation unit can adjust the level of detail of the drawing based on the importance of the patent when generating the drawing. For example, the drawing generation unit adjusts the level of detail of the drawing based on the importance of the patent when generating the drawing. The drawing generation unit generates detailed drawings for patents with high importance. In addition, the drawing generation unit can also generate concise drawings for patents with low importance. Furthermore, the drawing generation unit can adjust the length and content of the drawing according to the importance of the patent. This makes it possible to adjust the level of detail of the drawing according to the importance of the patent. Part or all of the above-mentioned processing in the drawing generation unit may be performed, for example, using AI or may be performed without using AI. For example, the drawing generation unit can input the importance of the patent to AI and cause AI to adjust the level of detail of the drawing.

[0061] The drawing generation unit can apply different drawing generation algorithms depending on the patent category when generating drawings. For example, the drawing generation unit applies different drawing generation algorithms depending on the patent category when generating drawings. The drawing generation unit applies an optimal drawing generation algorithm for each technical field to generate highly accurate drawings. The drawing generation unit can also select and apply different drawing generation algorithms depending on the patent category. Furthermore, the drawing generation unit can adjust the content and format of the drawing for each patent category. This makes it possible to apply an optimal drawing generation algorithm depending on the patent category. Some or all of the above-mentioned processing in the drawing generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the drawing generation unit can input patent category information to AI and cause AI to apply the drawing generation algorithm.

[0062] The drawing generation unit can determine the priority of the drawings based on the filing date of the patent when generating the drawings. For example, the drawing generation unit determines the priority of the drawings based on the filing date of the patent when generating the drawings. The drawing generation unit generates drawings preferentially for the latest patents. In addition, the drawing generation unit can generate drawings for patents with older filing dates at a later date. Furthermore, the drawing generation unit can adjust the order of drawing generation based on the filing date. This makes it possible to determine the priority of the drawings based on the filing date of the patent. Part or all of the above-mentioned processing in the drawing generation unit may be performed, for example, using AI or may be performed without using AI. For example, the drawing generation unit can input patent filing date information to AI and have AI execute the determination of the priority of the drawings.

[0063] The drawing generation unit can adjust the order of the drawings based on the relevance of the patents when generating the drawings. For example, the drawing generation unit adjusts the order of the drawings based on the relevance of the patents when generating the drawings. The drawing generation unit generates drawings preferentially for patents with high relevance. In addition, the drawing generation unit can generate drawings for patents with low relevance at a later date. Furthermore, the drawing generation unit can adjust the order of drawing generation based on the relevance of the patents. This makes it possible to adjust the order of the drawings based on the relevance of the patents. A part or all of the above-mentioned processing in the drawing generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the drawing generation unit can input patent relevance information to AI and cause AI to adjust the order of the drawings.

[0064] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0065] The patent business support system may further include a prediction unit that analyzes the user's past patent application data and predicts the success rate of the patent application. The prediction unit predicts the success rate of the patent application based on the past patent application data. For example, the prediction unit analyzes the success rate and failure rate of past patent applications and predicts the success rate of a patent application in a specific technical field. The prediction unit may also predict the success rate based on the content and format of the patent application. Furthermore, the prediction unit may predict the success rate taking into account the market value and technical impact of the patent application. This allows the user to grasp the success rate of the patent application in advance and develop an application strategy.

[0066] When collecting patent data, the collection unit can prioritize collecting highly relevant data in consideration of the user's industry trends. For example, the collection unit analyzes the latest trends in the industry to which the user belongs and prioritizes collecting related patent data. The collection unit can also filter and collect patent data based on industry trends and technological innovations. Furthermore, the collection unit can collect highly relevant patent data in consideration of the patent application status of competitors in the industry. This allows patent data to be efficiently collected based on the user's industry trends.

[0067] The analysis unit can take into account the number of citations and the number of citations of a patent to evaluate the technical impact of the patent. For example, the analysis unit evaluates the technical impact of a patent based on the number of citations of the patent. The analysis unit can also analyze how many other patents cite a patent and evaluate the technical impact. Furthermore, the analysis unit can evaluate the technical impact by taking into account the technical field and market value of the patent. This allows the technical impact of a patent to be evaluated efficiently.

[0068] The review unit can improve the accuracy of the review when reviewing patent application documents by taking into account the user's past review history. For example, the review unit analyzes the user's past review history and identifies specific patterns and trends. The review unit can also prioritize checking specific check items and corrections based on the past review history. Furthermore, the review unit can adjust the review procedure and standards based on the user's past review history. This makes it possible to improve the accuracy of the review based on the user's past review history.

[0069] The collection unit can preferentially collect highly relevant data in consideration of the geographical location information of the user when collecting patent data. For example, the collection unit preferentially collects highly relevant data in consideration of the geographical location information of the user when collecting patent data. The collection unit preferentially collects patent data in the region where the user is located. The collection unit can also filter and collect related patent data based on the geographical location information of the user. Furthermore, the collection unit can also collect patent data specific to the region based on the location information of the user. This makes it possible to preferentially collect highly relevant patent data based on the geographical location information of the user. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the geographical location information of the user to AI and cause the AI ​​to collect patent data.

[0070] The collection unit can analyze the user's social media activities and collect related data when collecting patent data. For example, the collection unit analyzes the user's social media activities and collects related data when collecting patent data. The collection unit analyzes the user's comments and posts on social media and collects related patent data. The collection unit can also preferentially collect patent data of experts and companies followed by the user. Furthermore, the collection unit can identify a technical field of interest from the user's social media activities and collect related patent data. This makes it possible to collect related patent data based on the user's social media activities. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input the user's social media activities into AI and cause AI to collect patent data.

[0071] The process flow of the first embodiment will be briefly described below.

[0072] Step 1: The collection unit collects patent data. The collection unit can collect patent data from, for example, a patent database. The patent database includes a public patent database and a commercial patent database. The collection unit accesses the patent database and collects patent data such as patent documents, patent application information, and patent classification information. Step 2: The summary generator summarizes the patent data collected by the collector. For example, the summary generator analyzes the collected patent data, extracts important information, and generates a summary. The summary generator generates a summary based on the length of the text and the importance of the information to be summarized. Step 3: The analysis unit evaluates the novelty and inventive step of the patent based on the summary generated by the summary generation unit. The analysis unit uses an algorithm to evaluate the novelty and inventive step, for example, by comparing it with existing patents. The analysis unit evaluates the technical features of the patent and its differences from existing technologies to determine the novelty and inventive step. Step 4: The draft generation unit creates a draft of the patent application document based on the evaluation results obtained by the analysis unit. The draft generation unit automatically generates, for example, a patent claim portion and provides it to the user. The draft generation unit generates a draft based on the format of the patent application document and the level of detail of the description. Step 5: The review section reviews the application documents generated by the draft generation section. For example, the review section checks the contents of the application documents and proposes necessary corrections. The review section reviews the application documents based on the check items and review procedures. Step 6: The drawing generation unit automatically creates drawings required for the application documents reviewed by the review unit using image generation AI. For example, the drawing generation unit automatically creates drawings specified by the user using image generation AI and incorporates them into the application documents. The image generation AI generates drawings based on the algorithm used and the format of the image to be generated.

[0073] (Example 2) The patent business support system according to the embodiment of the present invention is a system for supporting patent-related business, which is particularly important for technology companies. The purpose of this system is to enable intellectual property officers, new business development officers, investment officers, and others to grasp patent data from around the world and provide effective support. The system has the function of confirming and summarizing existing patents. When a user searches for a specific patent, the system obtains detailed information about the patent and generates a summary. For example, when a patent related to a specific technical field is searched for, a summary of the patent is automatically generated and provided to the user. Next, it has a wall-hitting function when applying for a new patent. When a user applies for a new patent, the system analyzes the contents of the patent and compares it with existing patents to evaluate its novelty and inventiveness. This allows the user to check the strength of the patent before applying. In addition, it also has a function for drafting and reviewing application documents. When a user creates patent application documents, the system automatically generates a draft and suggests necessary corrections. For example, the claim portion of the patent is automatically generated and provided to the user. In addition, the application document review function allows the user to check and correct the contents of the document before submission. Finally, by combining it with image generation AI, drawings for application documents can also be automatically created. When a user specifies the drawings required for patent application documents, the system automatically creates the drawings using image generation AI and incorporates them into the application documents. This streamlines the patent application process. This patent work support system is a key tool for patent work and plays a very important role for technology companies. This allows the patent work support system to consistently perform everything from collecting patent data to creating application documents, reviewing them, and generating drawings.

[0074] The patent business support system according to the embodiment includes a collection unit, a summary generation unit, an analysis unit, a draft generation unit, a review unit, and a drawing generation unit. The collection unit collects patent data. The collection unit can collect patent data from, for example, a patent database. The patent database includes a public patent database and a commercial patent database. The collection unit accesses the patent database and collects patent data such as patent documents, patent application information, and patent classification information. The summary generation unit summarizes the patent data collected by the collection unit. The summary generation unit, for example, analyzes the collected patent data, extracts important information, and generates a summary. The summary generation unit generates a summary based on the length of the sentence and the importance of the information to be summarized. The analysis unit evaluates the novelty and inventive step of the patent based on the summary generated by the summary generation unit. The analysis unit uses, for example, an algorithm for evaluating the novelty and inventive step by comparing with existing patents. The analysis unit evaluates the technical features of the patent and the differences from existing technologies to determine the novelty and inventive step. The draft generation unit drafts patent application documents based on the evaluation results obtained by the analysis unit. The draft generation unit, for example, automatically generates the claim portion of a patent and provides it to the user. The draft generation unit generates a draft based on the format of the patent application documents and the level of detail of the contents. The review unit reviews the application documents generated by the draft generation unit. The review unit, for example, checks the contents of the application documents and proposes necessary corrections. The review unit reviews the application documents based on the check items and review procedures. The drawing generation unit automatically creates drawings required for the application documents reviewed by the review unit using an image generation AI. The drawing generation unit, for example, automatically creates drawings specified by the user using an image generation AI and incorporates them into the application documents. The image generation AI generates drawings based on the algorithm used and the format of the image to be generated. This allows the patent business support system to consistently perform operations from collecting patent data to creating application documents, reviewing them, and generating drawings.

[0075] The collection unit collects patent data. The collection unit can collect patent data from, for example, a patent database. The patent database includes a public patent database and a commercial patent database. The collection unit accesses the patent database and collects patent data such as patent documents, patent application information, and patent classification information. Specifically, the collection unit connects to the patent database through an API and searches for data based on specific keywords and classification codes. For example, when collecting patent documents related to a specific technical field, a search is performed using the corresponding IPC (International Patent Classification) code. The collection unit also has an internal database for centrally managing data acquired from the patent database, and efficiently stores and manages the collected data. Furthermore, the collection unit has a function to periodically crawl the patent database and automatically acquire newly published patent documents and updated information. This allows the collection unit to always hold the latest patent data and quickly provide information required by other departments. The collection unit also analyzes metadata of the patent data (for example, the inventor's name, application date, publication date, etc.) and organizes and classifies the data. This allows the collected patent data to be provided in a format that can be efficiently used by the subsequent summary generation unit and analysis unit.

[0076] The summary generation unit summarizes the patent data collected by the collection unit. For example, the summary generation unit analyzes the collected patent data, extracts important information, and generates a summary. The summary generation unit generates a summary based on the length of the sentences and the importance of the information to be summarized. Specifically, the summary generation unit analyzes the contents of the patent document using natural language processing (NLP) technology and extracts the gist and technical features of the invention. For example, important sections such as the purpose, solution, and effect of the invention are identified from the patent document and summarized briefly. The summary generation unit can also understand the structure of the patent document and generate a summary for each specific section (for example, background art, examples, claims, etc.). Furthermore, the summary generation unit checks the accuracy and consistency of the summary using an evaluation index (for example, ROUGE score) for evaluating the quality of the generated summary. In this way, the summary generation unit provides a high-quality summary and assists in quickly understanding the contents of the patent document. The summary generation unit also has a function of adjusting the detail level of the summary according to the user's request. For example, if a concise summary is required, a short summary is generated, and if a detailed analysis is required, a longer summary is provided. This enables the summary generation unit to flexibly generate summaries according to the needs of the user.

[0077] The analysis unit evaluates the novelty and inventive step of the patent based on the summary generated by the summary generation unit. The analysis unit uses an algorithm for evaluating the novelty and inventive step by, for example, comparing with existing patents. The analysis unit evaluates the technical features of the patent and the differences from existing technologies to determine the novelty and inventive step. Specifically, the analysis unit uses a machine learning algorithm to extract the technical features of the patent document and compares them with an existing patent database. For example, the claim portion of the patent document is analyzed to evaluate whether it matches the technical features described in the existing patent document. The analysis unit also quantitatively evaluates the novelty and inventive step by vectorizing the technical features of the patent document and performing a similarity calculation. Furthermore, the analysis unit hierarchically classifies the technical features of the patent document to grasp the progress of technology in a specific technical field. This allows the analysis unit to evaluate in detail how much the technical features of the patent document differ from existing technology. The analysis unit also has a function to visualize the technical features of the patent document, and provides support for intuitive understanding of the progress of technology and the novelty and inventive step of the patent. For example, it can generate a similarity map of technical features and visually show the degree to which the technical features of a patent document are similar to existing technologies. This allows the analysis unit to evaluate the novelty and inventive step of a patent with high accuracy and support the planning of a patent application strategy.

[0078] The draft generation unit drafts the patent application documents based on the evaluation results obtained by the analysis unit. The draft generation unit automatically generates, for example, the claims of a patent and provides it to the user. The draft generation unit generates the draft based on the format of the patent application documents and the level of detail of the description. Specifically, the draft generation unit automatically generates each section of the patent application documents using natural language generation (NLG) technology. For example, in the claims section, an appropriate claim sentence is generated based on the technical features of the patent document. The draft generation unit also automatically creates sections such as background art, summary of the invention, and examples according to the format of the patent application documents. Furthermore, the draft generation unit has a function of customizing the contents of the patent application documents based on the information input by the user and the evaluation results provided by the analysis unit. This allows the user to flexibly adjust the contents of the patent application documents and create optimal application documents. The draft generation unit also checks the accuracy and consistency of the draft using an evaluation index for evaluating the quality of the generated patent application documents. This allows the draft generation unit to provide high-quality patent application documents and improve the success rate of patent applications. Furthermore, the draft generation unit provides an interface for users to confirm and modify the draft, and can improve the draft by reflecting user feedback, thereby enabling the draft generation unit to realize flexible draft generation according to user needs.

[0079] The review section reviews the application documents generated by the draft generation section. For example, the review section checks the contents of the application documents and proposes necessary corrections. The review section reviews the application documents based on the check items and review procedures. Specifically, the review section checks each section of the patent application documents in detail to check the accuracy and consistency of the description. For example, in the claim section, it checks whether the technical features of the patent are properly described and whether there is no overlap with existing patent documents. In addition, in sections such as the background art, the outline of the invention, and the examples, it checks whether the description is clear and easy to understand, and whether all necessary information is described. Furthermore, the review section checks whether the format and description rules of the patent application documents are followed, and suggests corrections as necessary. This allows the review section to provide high-quality patent application documents and improve the success rate of patent applications. In addition, the review section has a function of improving the contents of the application documents based on feedback submitted by the user. For example, it reflects the corrections pointed out by the user and updates the contents of the application documents. This allows the review section to realize flexible reviews according to the needs of the user. Furthermore, the review department can improve the efficiency of reviews by managing the review history of patent application documents and referring to past review results, which enables the review department to continuously improve the quality of patent application documents.

[0080] The drawing generation unit automatically creates drawings required for the application documents reviewed by the review unit using image generation AI. For example, the drawing generation unit automatically creates drawings specified by the user using image generation AI and incorporates them into the application documents. The image generation AI generates drawings based on the algorithm used and the format of the image generated. Specifically, the drawing generation unit analyzes the contents of the patent application documents and identifies the type and details of the required drawings. For example, a structural diagram and an operation flow diagram of the device are required for patent application documents for a mechanical device. In order to generate these drawings, the drawing generation unit automatically creates drawings using image generation AI. The image generation AI uses deep learning technology to generate high-quality drawings based on the contents of the patent application documents. For example, when generating a structural diagram of a mechanical device, the shape and arrangement of each part of the device are accurately drawn to create a drawing that is visually easy to understand. In addition, when generating an operation flow diagram, a drawing that clearly shows the operation procedure of the device and the details of each step is created. In addition, the drawing generation unit checks the accuracy and consistency of the drawings using evaluation indicators for evaluating the quality of the generated drawings. This allows the drawing generation unit to provide high-quality drawings and complement the contents of the patent application documents. The drawing generator also provides an interface for users to check and modify drawings, and can improve drawings based on user feedback, allowing the drawing generator to flexibly generate drawings according to user needs.

[0081] The collection unit can collect patent data from a patent database. The collection unit, for example, collects patent data from a patent database. The patent database includes a public patent database and a commercial patent database. The collection unit accesses the patent database and collects patent data such as patent documents, patent application information, and patent classification information. This allows efficient collection of patent data from the patent database. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can collect patent data using an AI model for accessing the patent database.

[0082] The summary generation unit can summarize the collected patent data. For example, the summary generation unit analyzes the collected patent data, extracts important information, and generates a summary. The summary generation unit generates a summary based on the length of the sentence and the importance of the information to be summarized. For example, the summary generation unit extracts the main points of the patent document and generates a concise summary. The summary generation unit can also summarize the technical features of the patent and provide it to the user. This allows the collected patent data to be efficiently summarized. A part or all of the above-mentioned processing in the summary generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the summary generation unit can input the collected patent data into the generation AI and generate a summary. The generation AI uses a text generation AI (for example, LLM) to generate a summary of the patent data.

[0083] The analysis unit can evaluate the novelty and inventive step of the patent based on the summary generated by the summary generation unit. The analysis unit evaluates the novelty and inventive step of the patent based on, for example, the summary generated by the summary generation unit. The analysis unit uses an algorithm for evaluating the novelty and inventive step by comparing with existing patents. For example, the analysis unit evaluates the technical features of the patent and the difference from existing technologies to determine the novelty and inventive step. The analysis unit can also evaluate the technical impact and market value of the patent. This makes it possible to efficiently evaluate the novelty and inventive step of the patent. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the summary generated by the summary generation unit to the generation AI and cause the generation AI to perform the evaluation of the novelty and inventive step. The generation AI evaluates the novelty and inventive step of the patent using a text generation AI (for example, LLM).

[0084] The draft generation unit can draft the patent application documents based on the evaluation results obtained by the analysis unit. The draft generation unit drafts the patent application documents based on, for example, the evaluation results obtained by the analysis unit. The draft generation unit automatically generates the claims of the patent and provides them to the user. For example, the draft generation unit generates a draft based on the format of the patent application documents and the level of detail of the description. The draft generation unit can also automatically generate each section of the patent application documents (for example, background art, detailed description of the invention, claims, etc.). This allows the patent application documents to be drafted efficiently. A part or all of the above-mentioned processing in the draft generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the draft generation unit can input the evaluation results obtained by the analysis unit to the generation AI and cause the generation AI to execute drafting of the patent application documents. The generation AI generates a draft of the patent application documents using a text generation AI (for example, LLM).

[0085] The review unit can review the application documents generated by the draft generation unit. For example, the review unit checks the contents of the application documents generated by the draft generation unit and proposes necessary corrections. The review unit reviews the application documents based on the check items and review procedures. For example, the review unit checks the contents of the claims of the patent and proposes corrections. The review unit can also check the format of the patent application documents and the level of detail of the contents and propose corrections. This allows the patent application documents to be reviewed efficiently. Some or all of the above-mentioned processing in the review unit may be performed, for example, using AI or may be performed without using AI. For example, the review unit can input the application documents generated by the draft generation unit into AI and have the AI ​​perform the review.

[0086] The drawing generation unit can automatically create drawings required for the application documents reviewed by the review unit using an image generation AI. For example, the drawing generation unit can automatically create drawings specified by a user using an image generation AI and incorporate them into the application documents. The image generation AI generates drawings based on the algorithm used and the format of the image to be generated. For example, the drawing generation unit automatically creates technical drawings required for patent application documents using an image generation AI. The drawing generation unit can also automatically create flowcharts and block diagrams required for patent application documents using an image generation AI. This allows drawings required for patent application documents to be efficiently and automatically created. A part or all of the above-mentioned processing in the drawing generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the drawing generation unit can input the application documents reviewed by the review unit into the generation AI and cause the generation AI to generate the necessary drawings. The generation AI generates drawings required for patent application documents using an image generation AI.

[0087] The collection unit can estimate the user's emotions and adjust the timing of collecting patent data based on the estimated user's emotions. The collection unit, for example, estimates the user's emotions and adjusts the timing of collecting patent data based on the estimated emotions. When the user is stressed, the collection unit delays the collection timing to reduce the burden on the user. In addition, when the user is relaxed, the collection unit can also advance the collection timing to efficiently provide data. Furthermore, when the user is in a hurry, the collection unit can instantly collect patent data and provide it quickly. This makes it possible to adjust the timing of collecting patent data according to the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the timing of collecting patent data.

[0088] The collection unit can analyze the user's past patent search history and select the optimal collection method. For example, the collection unit analyzes the user's past patent search history and selects the optimal collection method. The collection unit preferentially collects patent fields that the user has frequently searched in the past. The collection unit can also preferentially collect patent data containing specific keywords from the user's past search history. Furthermore, the collection unit can analyze the user's past search patterns and suggest the optimal collection timing. This makes it possible to select the optimal patent data collection method based on the user's past search history. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the user's past patent search history into AI and have the AI ​​select the optimal collection method.

[0089] The collection unit can filter the patent data based on the user's current project and field of interest when collecting the patent data. For example, the collection unit filters the patent data based on the user's current project and field of interest when collecting the patent data. The collection unit preferentially collects patent data related to the user's ongoing project. The collection unit can also filter and collect highly relevant patent data based on the user's field of interest. Furthermore, the collection unit can dynamically collect necessary patent data according to the progress of the user's project. This makes it possible to filter the patent data based on the user's current project and field of interest. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's project information and field of interest into AI and have the AI ​​perform filtering of the patent data.

[0090] The collection unit can estimate the user's emotion and determine the priority order of the patent data to be collected based on the estimated user's emotion. The collection unit, for example, estimates the user's emotion and determines the priority order of the patent data to be collected based on the estimated emotion. When the user is stressed, the collection unit preferentially collects patent data with high importance. In addition, when the user is relaxed, the collection unit can also collect a wide range of patent data and provide options. Furthermore, when the user is in a hurry, the collection unit can also collect the most relevant patent data immediately. This makes it possible to determine the priority order of the patent data according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the user's emotion data to the generation AI and cause the generation AI to execute the determination of the priority order of the patent data.

[0091] The collection unit can preferentially collect highly relevant data in consideration of the geographical location information of the user when collecting patent data. For example, the collection unit preferentially collects highly relevant data in consideration of the geographical location information of the user when collecting patent data. The collection unit preferentially collects patent data in the region where the user is located. The collection unit can also filter and collect related patent data based on the geographical location information of the user. Furthermore, the collection unit can also collect patent data specific to the region based on the location information of the user. This makes it possible to preferentially collect highly relevant patent data based on the geographical location information of the user. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the geographical location information of the user to AI and cause the AI ​​to collect patent data.

[0092] The collection unit can analyze the user's social media activities and collect related data when collecting patent data. For example, the collection unit analyzes the user's social media activities and collects related data when collecting patent data. The collection unit analyzes the user's comments and posts on social media and collects related patent data. The collection unit can also preferentially collect patent data of experts and companies followed by the user. Furthermore, the collection unit can identify a technical field of interest from the user's social media activities and collect related patent data. This makes it possible to collect related patent data based on the user's social media activities. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input the user's social media activities into AI and cause AI to collect patent data.

[0093] The summary generation unit can estimate the user's emotion and adjust the expression method of the summary based on the estimated user's emotion. The summary generation unit, for example, estimates the user's emotion and adjusts the expression method of the summary based on the estimated emotion. When the user is stressed, the summary generation unit generates a concise summary that covers the main points. When the user is relaxed, the summary generation unit can also generate a summary including detailed information. Furthermore, when the user is in a hurry, the summary generation unit can also generate a summary that can be understood in a short time. This makes it possible to adjust the expression method of the summary according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the summary generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the summary generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the expression method of the summary.

[0094] The summary generation unit can adjust the level of detail of the summary based on the importance of the patent when generating the summary. The summary generation unit adjusts the level of detail of the summary based on the importance of the patent, for example, when generating the summary. The summary generation unit generates a detailed summary for a patent with high importance. The summary generation unit can also generate a concise summary for a patent with low importance. Furthermore, the summary generation unit can adjust the length and content of the summary according to the importance of the patent. This makes it possible to adjust the level of detail of the summary according to the importance of the patent. A part or all of the above-mentioned processing in the summary generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the summary generation unit can input the importance of the patent to AI and cause AI to adjust the level of detail of the summary.

[0095] The summary generation unit can apply different summarization algorithms depending on the patent category when generating a summary. For example, the summary generation unit applies different summarization algorithms depending on the patent category when generating a summary. The summary generation unit applies an optimal summarization algorithm for each technical field to generate a highly accurate summary. The summary generation unit can also select and apply different summarization algorithms depending on the patent category. Furthermore, the summary generation unit can adjust the content and format of the summary for each patent category. This makes it possible to apply an optimal summarization algorithm depending on the patent category. Some or all of the above-mentioned processing in the summary generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the summary generation unit can input patent category information to AI and cause AI to apply the summarization algorithm.

[0096] The summary generation unit can estimate the user's emotion and adjust the length of the summary based on the estimated user's emotion. The summary generation unit, for example, estimates the user's emotion and adjusts the length of the summary based on the estimated emotion. The summary generation unit generates a short summary that covers the main points when the user is stressed. The summary generation unit can also generate a longer summary including detailed information when the user is relaxed. Furthermore, the summary generation unit can also generate a summary that can be understood in a short time when the user is in a hurry. This allows the length of the summary to be adjusted according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the summary generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the summary generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the length of the summary.

[0097] The summary generation unit can determine the priority of the summaries based on the filing dates of the patents when generating the summaries. The summary generation unit, for example, determines the priority of the summaries based on the filing dates of the patents when generating the summaries. The summary generation unit generates summaries preferentially for the newest patents. The summary generation unit can also postpone generating summaries for patents that were submitted earlier. Furthermore, the summary generation unit can adjust the order of generation of summaries based on the filing dates. This makes it possible to determine the priority of the summaries based on the filing dates of the patents. Some or all of the above-mentioned processing in the summary generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the summary generation unit can input patent submission date information to AI and have the AI ​​execute the determination of the priority of the summaries.

[0098] The summary generation unit can adjust the order of summaries based on the relevance of patents when generating summaries. The summary generation unit, for example, adjusts the order of summaries based on the relevance of patents when generating summaries. The summary generation unit generates summaries preferentially for highly relevant patents. Also, the summary generation unit can generate summaries for less relevant patents at a later date. Furthermore, the summary generation unit can adjust the order of summaries generated based on the relevance of patents. This makes it possible to adjust the order of summaries based on the relevance of patents. A part or all of the above-mentioned processing in the summary generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the summary generation unit can input patent relevance information to AI and cause AI to adjust the order of summaries.

[0099] The analysis unit can estimate the user's emotion and adjust the analysis criteria based on the estimated user's emotion. The analysis unit, for example, estimates the user's emotion and adjusts the analysis criteria based on the estimated emotion. The analysis unit provides a concise and to-the-point analysis result when the user is stressed. The analysis unit can also provide a detailed analysis result when the user is relaxed. Furthermore, the analysis unit can also provide an analysis result that can be understood in a short time when the user is in a hurry. This allows the analysis criteria to be adjusted according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the analysis criteria.

[0100] The analysis unit can improve the accuracy of the analysis by taking into account the interrelationships of patents during the analysis. For example, the analysis unit can improve the accuracy of the analysis by taking into account the interrelationships of patents during the analysis. The analysis unit can improve the accuracy of the analysis by taking into account the citation relationships of patents. The analysis unit can also improve the accuracy of the analysis by taking into account the relevance of the technical fields of the patents. Furthermore, the analysis unit can analyze the interrelationships of patents and reflect them in the analysis results. This improves the accuracy of the analysis by taking into account the interrelationships of patents. A part or all of the above-mentioned processing in the analysis unit can be performed, for example, using AI or can be performed without using AI. For example, the analysis unit can input patent interrelationship information into AI and cause AI to improve the accuracy of the analysis.

[0101] The analysis unit can perform the analysis while taking into account the attribute information of the patent submitter. For example, the analysis unit performs the analysis while taking into account the attribute information of the patent submitter. The analysis unit takes into account the specialty of the patent submitter and reflects it in the analysis result. The analysis unit can also improve the accuracy of the analysis while taking into account the submitter's past patent application history. Furthermore, the analysis unit can evaluate the novelty and inventive step of the patent based on the attribute information of the submitter. This improves the accuracy of the analysis by taking into account the attribute information of the patent submitter. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the attribute information of the submitter to AI and have AI execute the analysis.

[0102] The analysis unit can estimate the user's emotion and adjust the order in which the analysis results are displayed based on the estimated user's emotion. The analysis unit, for example, estimates the user's emotion and adjusts the order in which the analysis results are displayed based on the estimated emotion. When the user is stressed, the analysis unit preferentially displays analysis results with high importance. In addition, when the user is relaxed, the analysis unit can also display detailed analysis results in an orderly manner. Furthermore, when the user is in a hurry, the analysis unit can also preferentially display analysis results that focus on the main points. This makes it possible to adjust the display order of the analysis results according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display order of the analysis results.

[0103] The analysis unit can perform the analysis while taking into consideration the geographical distribution of patents. For example, the analysis unit performs the analysis while taking into consideration the geographical distribution of patents. The analysis unit takes into consideration the country or region of the patent application and reflects it in the analysis result. The analysis unit can also evaluate the relevance of the patent based on the geographical distribution. Furthermore, the analysis unit can analyze the geographical distribution of patents and reflect it in the analysis result. This improves the accuracy of the analysis by taking into consideration the geographical distribution of patents. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the geographical distribution information of patents to AI and have AI execute the analysis.

[0104] The analysis unit can improve the accuracy of the analysis by referring to related documents of the patent during the analysis. The analysis unit, for example, improves the accuracy of the analysis by referring to related documents of the patent during the analysis. The analysis unit refers to cited documents of the patent and reflects them in the analysis result. The analysis unit can also evaluate the novelty and inventive step of the patent based on the related documents. Furthermore, the analysis unit can analyze related documents of the patent and improve the accuracy of the analysis. As a result, the accuracy of the analysis is improved by referring to related documents of the patent. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input related document information of the patent into AI and have AI execute the analysis.

[0105] The draft generation unit can estimate the user's emotion and adjust the expression method of the draft based on the estimated user's emotion. The draft generation unit, for example, estimates the user's emotion and adjusts the expression method of the draft based on the estimated emotion. When the user is stressed, the draft generation unit generates a concise draft that covers the main points. In addition, when the user is relaxed, the draft generation unit can also generate a draft that includes detailed information. Furthermore, when the user is in a hurry, the draft generation unit can also generate a draft that can be understood in a short time. This makes it possible to adjust the expression method of the draft according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the draft generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the draft generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the expression method of the draft.

[0106] The draft generation unit can adjust the level of detail of the draft based on the importance of the patent when generating the draft. For example, the draft generation unit adjusts the level of detail of the draft based on the importance of the patent when generating the draft. The draft generation unit generates a detailed draft for a patent with high importance. The draft generation unit can also generate a concise draft for a patent with low importance. Furthermore, the draft generation unit can adjust the length and contents of the draft according to the importance of the patent. This makes it possible to adjust the level of detail of the draft according to the importance of the patent. A part or all of the above-mentioned processing in the draft generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the draft generation unit can input the importance of the patent to AI and cause AI to adjust the level of detail of the draft.

[0107] The draft generation unit can apply different draft algorithms depending on the patent category when generating the draft. For example, the draft generation unit applies different draft algorithms depending on the patent category when generating the draft. The draft generation unit applies the optimal draft algorithm for each technical field to generate a highly accurate draft. The draft generation unit can also select and apply different draft algorithms depending on the patent category. Furthermore, the draft generation unit can adjust the content and format of the draft for each patent category. This makes it possible to apply the optimal draft algorithm depending on the patent category. A part or all of the above-mentioned processing in the draft generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the draft generation unit can input patent category information to AI and cause AI to apply the draft algorithm.

[0108] The draft generation unit can estimate the user's emotion and adjust the length of the draft based on the estimated user's emotion. The draft generation unit, for example, estimates the user's emotion and adjusts the length of the draft based on the estimated emotion. The draft generation unit generates a short draft that covers the main points when the user is stressed. The draft generation unit can also generate a longer draft that includes detailed information when the user is relaxed. Furthermore, the draft generation unit can also generate a draft that can be understood in a short time when the user is in a hurry. This allows the length of the draft to be adjusted according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the draft generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the draft generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the length of the draft.

[0109] The draft generation unit can determine the priority of the draft based on the patent submission time when generating the draft. For example, the draft generation unit determines the priority of the draft based on the patent submission time when generating the draft. The draft generation unit generates the draft with priority for the latest patent. In addition, the draft generation unit can generate the draft for the patent with the older submission time at a later time. Furthermore, the draft generation unit can adjust the draft generation order based on the submission time. This makes it possible to determine the priority of the draft based on the patent submission time. A part or all of the above-mentioned processing in the draft generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the draft generation unit can input patent submission time information to AI and cause AI to execute the determination of the priority of the draft.

[0110] The draft generation unit can adjust the order of the drafts based on the relevance of the patents when generating the drafts. For example, the draft generation unit adjusts the order of the drafts based on the relevance of the patents when generating the drafts. The draft generation unit generates the drafts preferentially for patents with high relevance. In addition, the draft generation unit can generate the drafts later for patents with low relevance. Furthermore, the draft generation unit can adjust the order of the drafts based on the relevance of the patents. This makes it possible to adjust the order of the drafts based on the relevance of the patents. A part or all of the above-mentioned processing in the draft generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the draft generation unit can input patent relevance information to AI and cause AI to adjust the order of the drafts.

[0111] The review unit can estimate the user's emotion and adjust the review criteria based on the estimated user's emotion. The review unit, for example, estimates the user's emotion and adjusts the review criteria based on the estimated emotion. When the user is stressed, the review unit provides a concise review that covers the main points. When the user is relaxed, the review unit can also provide a detailed review. When the user is in a hurry, the review unit can also provide a review that can be understood in a short time. This allows the review criteria to be adjusted according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the review unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the review unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the review criteria.

[0112] The review unit can improve the accuracy of the review by considering the interrelationships of patents during the review. For example, the review unit improves the accuracy of the review by considering the interrelationships of patents during the review. The review unit improves the accuracy of the review by considering the citation relationships of patents. The review unit can also improve the accuracy of the review by considering the relevance of the technical fields of the patents. Furthermore, the review unit can analyze the interrelationships of patents and reflect them in the review results. This improves the accuracy of the review by considering the interrelationships of patents. A part or all of the above-mentioned processing in the review unit may be performed, for example, using AI, or may be performed without using AI. For example, the review unit can input patent interrelationship information into AI and cause AI to improve the accuracy of the review.

[0113] The review unit can estimate the user's emotion and adjust the order in which the review results are displayed based on the estimated user's emotion. The review unit, for example, estimates the user's emotion and adjusts the order in which the review results are displayed based on the estimated emotion. When the user is stressed, the review unit preferentially displays review results with a high level of importance. In addition, when the user is relaxed, the review unit can also display detailed review results in an orderly manner. Furthermore, when the user is in a hurry, the review unit can also preferentially display review results that focus on the main points. This makes it possible to adjust the display order of the review results according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the review unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the review unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display order of the review results.

[0114] The review department can conduct a review while taking into consideration the geographical distribution of patents. For example, the review department conducts a review while taking into consideration the geographical distribution of patents. The review department takes into consideration the country or region of application of the patent and reflects it in the review results. The review department can also evaluate the relevance of the patent based on the geographical distribution. Furthermore, the review department can analyze the geographical distribution of the patent and reflect it in the review results. In this way, the accuracy of the review is improved by taking into consideration the geographical distribution of the patent. A part or all of the above-mentioned processing in the review department may be performed, for example, using AI, or may be performed without using AI. For example, the review department can input the geographical distribution information of the patent into AI and have the AI ​​perform the review.

[0115] The drawing generation unit can estimate the user's emotion and adjust the expression method of the drawing based on the estimated user's emotion. The drawing generation unit, for example, estimates the user's emotion and adjusts the expression method of the drawing based on the estimated emotion. The drawing generation unit generates a simple and highly visible drawing when the user is stressed. The drawing generation unit can also generate a drawing including detailed information when the user is relaxed. Furthermore, the drawing generation unit can also generate a drawing that can be understood in a short time when the user is in a hurry. This makes it possible to adjust the expression method of the drawing according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the drawing generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the drawing generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the expression method of the drawing.

[0116] The drawing generation unit can adjust the level of detail of the drawing based on the importance of the patent when generating the drawing. For example, the drawing generation unit adjusts the level of detail of the drawing based on the importance of the patent when generating the drawing. The drawing generation unit generates detailed drawings for patents with high importance. In addition, the drawing generation unit can also generate concise drawings for patents with low importance. Furthermore, the drawing generation unit can adjust the length and content of the drawing according to the importance of the patent. This makes it possible to adjust the level of detail of the drawing according to the importance of the patent. Part or all of the above-mentioned processing in the drawing generation unit may be performed, for example, using AI or may be performed without using AI. For example, the drawing generation unit can input the importance of the patent to AI and cause AI to adjust the level of detail of the drawing.

[0117] The drawing generation unit can apply different drawing generation algorithms depending on the patent category when generating drawings. For example, the drawing generation unit applies different drawing generation algorithms depending on the patent category when generating drawings. The drawing generation unit applies an optimal drawing generation algorithm for each technical field to generate highly accurate drawings. The drawing generation unit can also select and apply different drawing generation algorithms depending on the patent category. Furthermore, the drawing generation unit can adjust the content and format of the drawing for each patent category. This makes it possible to apply an optimal drawing generation algorithm depending on the patent category. Some or all of the above-mentioned processing in the drawing generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the drawing generation unit can input patent category information to AI and cause AI to apply the drawing generation algorithm.

[0118] The drawing generation unit can estimate the user's emotion and adjust the length of the drawing based on the estimated user's emotion. The drawing generation unit, for example, estimates the user's emotion and adjusts the length of the drawing based on the estimated emotion. The drawing generation unit generates a short drawing that is to the point when the user is stressed. The drawing generation unit can also generate a longer drawing that includes detailed information when the user is relaxed. Furthermore, the drawing generation unit can also generate a drawing that can be understood in a short time when the user is in a hurry. This allows the length of the drawing to be adjusted according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the drawing generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the drawing generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the length of the drawing.

[0119] The drawing generation unit can determine the priority of the drawings based on the filing date of the patent when generating the drawings. For example, the drawing generation unit determines the priority of the drawings based on the filing date of the patent when generating the drawings. The drawing generation unit generates drawings preferentially for the latest patents. In addition, the drawing generation unit can generate drawings for patents with older filing dates at a later date. Furthermore, the drawing generation unit can adjust the order of drawing generation based on the filing date. This makes it possible to determine the priority of the drawings based on the filing date of the patent. Part or all of the above-mentioned processing in the drawing generation unit may be performed, for example, using AI or may be performed without using AI. For example, the drawing generation unit can input patent filing date information to AI and have AI execute the determination of the priority of the drawings.

[0120] The drawing generation unit can adjust the order of the drawings based on the relevance of the patents when generating the drawings. For example, the drawing generation unit adjusts the order of the drawings based on the relevance of the patents when generating the drawings. The drawing generation unit generates drawings preferentially for patents with high relevance. In addition, the drawing generation unit can generate drawings for patents with low relevance at a later date. Furthermore, the drawing generation unit can adjust the order of drawing generation based on the relevance of the patents. This makes it possible to adjust the order of the drawings based on the relevance of the patents. A part or all of the above-mentioned processing in the drawing generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the drawing generation unit can input patent relevance information to AI and cause AI to adjust the order of the drawings.

[0121] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0122] The patent business support system may further include a prediction unit that analyzes the user's past patent application data and predicts the success rate of the patent application. The prediction unit predicts the success rate of the patent application based on the past patent application data. For example, the prediction unit analyzes the success rate and failure rate of past patent applications and predicts the success rate of a patent application in a specific technical field. The prediction unit may also predict the success rate based on the content and format of the patent application. Furthermore, the prediction unit may predict the success rate taking into account the market value and technical impact of the patent application. This allows the user to grasp the success rate of the patent application in advance and develop an application strategy.

[0123] When collecting patent data, the collection unit can prioritize collecting highly relevant data in consideration of the user's industry trends. For example, the collection unit analyzes the latest trends in the industry to which the user belongs and prioritizes collecting related patent data. The collection unit can also filter and collect patent data based on industry trends and technological innovations. Furthermore, the collection unit can collect highly relevant patent data in consideration of the patent application status of competitors in the industry. This allows patent data to be efficiently collected based on the user's industry trends.

[0124] The summary generation unit can estimate the user's emotion and adjust the expression method of the summary based on the estimated user's emotion. For example, when the user is stressed, the summary generation unit generates a concise summary that covers the main points. In addition, when the user is relaxed, the summary generation unit can also generate a summary that includes detailed information. Furthermore, when the user is in a hurry, the summary generation unit can also generate a summary that can be understood in a short time. This makes it possible to adjust the expression method of the summary according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the summary generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the summary generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the expression method of the summary.

[0125] The analysis unit can take into account the number of citations and the number of citations of a patent to evaluate the technical impact of the patent. For example, the analysis unit evaluates the technical impact of a patent based on the number of citations of the patent. The analysis unit can also analyze how many other patents cite a patent and evaluate the technical impact. Furthermore, the analysis unit can evaluate the technical impact by taking into account the technical field and market value of the patent. This allows the technical impact of a patent to be evaluated efficiently.

[0126] The draft generation unit can estimate the user's emotion and adjust the expression method of the draft based on the estimated user's emotion. For example, when the user is stressed, the draft generation unit generates a concise draft that covers the main points. In addition, when the user is relaxed, the draft generation unit can also generate a draft that includes detailed information. Furthermore, when the user is in a hurry, the draft generation unit can also generate a draft that can be understood in a short time. This allows the expression method of the draft to be adjusted according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the draft generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the draft generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the expression method of the draft.

[0127] The review unit can improve the accuracy of the review when reviewing patent application documents by taking into account the user's past review history. For example, the review unit analyzes the user's past review history and identifies specific patterns and trends. The review unit can also prioritize checking specific check items and corrections based on the past review history. Furthermore, the review unit can adjust the review procedure and standards based on the user's past review history. This makes it possible to improve the accuracy of the review based on the user's past review history.

[0128] The drawing generation unit can estimate the user's emotion and adjust the expression method of the drawing based on the estimated user's emotion. For example, when the user is stressed, the drawing generation unit generates a simple and highly visible drawing. In addition, when the user is relaxed, the drawing generation unit can also generate a drawing including detailed information. Furthermore, when the user is in a hurry, the drawing generation unit can also generate a drawing that can be understood in a short time. This makes it possible to adjust the expression method of the drawing according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the drawing generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the drawing generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the expression method of the drawing.

[0129] The collection unit can preferentially collect highly relevant data in consideration of the geographical location information of the user when collecting patent data. For example, the collection unit preferentially collects highly relevant data in consideration of the geographical location information of the user when collecting patent data. The collection unit preferentially collects patent data in the region where the user is located. The collection unit can also filter and collect related patent data based on the geographical location information of the user. Furthermore, the collection unit can also collect patent data specific to the region based on the location information of the user. This makes it possible to preferentially collect highly relevant patent data based on the geographical location information of the user. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the geographical location information of the user to AI and cause the AI ​​to collect patent data.

[0130] The collection unit can analyze the user's social media activities and collect related data when collecting patent data. For example, the collection unit analyzes the user's social media activities and collects related data when collecting patent data. The collection unit analyzes the user's comments and posts on social media and collects related patent data. The collection unit can also preferentially collect patent data of experts and companies followed by the user. Furthermore, the collection unit can identify a technical field of interest from the user's social media activities and collect related patent data. This makes it possible to collect related patent data based on the user's social media activities. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input the user's social media activities into AI and cause AI to collect patent data.

[0131] The collection unit can estimate the user's emotion and determine the priority order of the patent data to be collected based on the estimated user's emotion. The collection unit, for example, estimates the user's emotion and determines the priority order of the patent data to be collected based on the estimated emotion. When the user is stressed, the collection unit preferentially collects patent data with high importance. In addition, when the user is relaxed, the collection unit can also collect a wide range of patent data and provide options. Furthermore, when the user is in a hurry, the collection unit can also collect the most relevant patent data immediately. This makes it possible to determine the priority order of the patent data according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the user's emotion data to the generation AI and cause the generation AI to execute the determination of the priority order of the patent data.

[0132] The process flow of the second embodiment will be briefly described below.

[0133] Step 1: The collection unit collects patent data. The collection unit can collect patent data from, for example, a patent database. The patent database includes a public patent database and a commercial patent database. The collection unit accesses the patent database and collects patent data such as patent documents, patent application information, and patent classification information. Step 2: The summary generator summarizes the patent data collected by the collector. For example, the summary generator analyzes the collected patent data, extracts important information, and generates a summary. The summary generator generates a summary based on the length of the text and the importance of the information to be summarized. Step 3: The analysis unit evaluates the novelty and inventive step of the patent based on the summary generated by the summary generation unit. The analysis unit uses an algorithm to evaluate the novelty and inventive step, for example, by comparing it with existing patents. The analysis unit evaluates the technical features of the patent and its differences from existing technologies to determine the novelty and inventive step. Step 4: The draft generation unit creates a draft of the patent application document based on the evaluation results obtained by the analysis unit. The draft generation unit automatically generates, for example, a patent claim portion and provides it to the user. The draft generation unit generates a draft based on the format of the patent application document and the level of detail of the description. Step 5: The review section reviews the application documents generated by the draft generation section. For example, the review section checks the contents of the application documents and proposes necessary corrections. The review section reviews the application documents based on the check items and review procedures. Step 6: The drawing generation unit automatically creates drawings required for the application documents reviewed by the review unit using image generation AI. For example, the drawing generation unit automatically creates drawings specified by the user using image generation AI and incorporates them into the application documents. The image generation AI generates drawings based on the algorithm used and the format of the image to be generated.

[0134] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the 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 voice data.

[0135] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0136] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0137] Each of the plurality of elements including the above-mentioned collection unit, summary generation unit, analysis unit, draft generation unit, review unit, and drawing generation unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects patent data by the control unit 46A of the smart device 14, and analyzes the collected data by the specific processing unit 290 of the data processing device 12. The summary generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and summarizes the collected patent data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and evaluates the novelty and inventive step of the patent based on the summary generated by the summary generation unit. The draft generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and drafts patent application documents. The review unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and reviews the application documents generated by the draft generation unit. The drawing generation unit is realized, for example, by the control unit 46A of the smart device 14, and automatically creates drawings required for the application documents using image generation AI. The collection unit has a function of, for example, estimating the user's emotions and adjusting the timing of collecting patent data based on the estimated emotions. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[0138] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0139] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0140] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0141] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0142] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0144] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0145] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0146] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0147] The storage 32 stores a data generation model 58 and an 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0148] In the smart glasses 214, the 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 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0149] Note that a device other than the data processing device 12 may 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 a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0150] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0151] The data generation model 58 is a so-called generative AI. An example of the 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0152] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed 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 required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0153] Each of the multiple elements including the above-mentioned collection unit, summary generation unit, analysis unit, draft generation unit, review unit, and drawing generation unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects patent data by the control unit 46A of the smart glasses 214, and analyzes the collected data by the specific processing unit 290 of the data processing device 12. The summary generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and summarizes the collected patent data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and evaluates the novelty and inventive step of the patent based on the summary generated by the summary generation unit. The draft generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and drafts patent application documents. The review unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and reviews the application documents generated by the draft generation unit. The drawing generation unit is realized, for example, by the control unit 46A of the smart glasses 214, and automatically creates drawings required for application documents using an image generation AI. The collection unit has a function of, for example, estimating the user's emotions and adjusting the timing of patent data collection based on the estimated emotions. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0154] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0155] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0156] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0157] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0158] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0159] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0160] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0161] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0162] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0163] The storage 32 stores a data generation model 58 and an 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0164] In the headset type terminal 314, the 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 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0165] Note that a device other than the data processing device 12 may 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 a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0166] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0167] The data generation model 58 is a so-called generative AI. An example of the 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0168] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0169] Each of the multiple elements including the above-mentioned collection unit, summary generation unit, analysis unit, draft generation unit, review unit, and drawing generation unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit collects patent data by the control unit 46A of the headset type terminal 314, and analyzes the collected data by the specific processing unit 290 of the data processing device 12. The summary generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and summarizes the collected patent data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and evaluates the novelty and inventive step of the patent based on the summary generated by the summary generation unit. The draft generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and drafts patent application documents. The review unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and reviews the application documents generated by the draft generation unit. The drawing generation unit is realized, for example, by the control unit 46A of the headset terminal 314, and automatically creates drawings required for application documents using image generation AI. The collection unit has a function of, for example, estimating the user's emotions and adjusting the timing of patent data collection based on the estimated emotions. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[0170] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0171] 7, a 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.

[0172] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0173] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0174] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0175] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0176] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0177] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0178] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0179] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0180] The storage 32 stores a data generation model 58 and an 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0181] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0182] Note that a device other than the data processing device 12 may 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 a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0183] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0184] The data generation model 58 is a so-called generative AI. An example of the 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0185] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed 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 required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0186] Each of the plurality of elements including the above-mentioned collection unit, summary generation unit, analysis unit, draft generation unit, review unit, and drawing generation unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects patent data by the control unit 46A of the robot 414, and analyzes the collected data by the specific processing unit 290 of the data processing device 12. The summary generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and summarizes the collected patent data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and evaluates the novelty and inventive step of the patent based on the summary generated by the summary generation unit. The draft generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and drafts patent application documents. The review unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and reviews the application documents generated by the draft generation unit. The drawing generation unit is realized, for example, by the control unit 46A of the robot 414, and automatically creates drawings required for the application documents using image generation AI. The collection unit has a function of, for example, estimating the user's emotions and adjusting the timing of collecting patent data based on the estimated emotions. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[0187] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0188] FIG. 9 is a diagram showing an emotion map 400 on 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 emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0189] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0190] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0191] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0192] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this 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 positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0193] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0194] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0195] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0196] In addition, 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 upon request from the data processing device 12.

[0197] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0198] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0199] The hardware resource that executes the specific process may be one of these various processors, or may be 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). Also, the hardware resource that executes the specific process may be a single processor.

[0200] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0201] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0202] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0203] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0204] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0205] (Appendix 1) A collection unit that collects patent data; a summary generating unit that summarizes the patent data collected by the collecting unit; an analysis unit for evaluating the novelty and inventive step of a patent based on the abstract generated by the abstract generation unit; a draft generation unit that generates a draft of a patent application document based on the evaluation result obtained by the analysis unit; a review unit that reviews the application documents generated by the draft generation unit; A drawing generation unit that generates drawings necessary for the application documents reviewed by the review unit using an image generation AI. A system characterized by: (Appendix 2) The collecting unit includes: Collect patent data from patent databases 2. The system of claim 1, (Appendix 3) The summary generation unit Summarize the collected patent data 2. The system of claim 1, (Appendix 4) The analysis unit is Evaluating the novelty and inventive step of a patent based on the abstract generated by the abstract generation unit 2. The system of claim 1, (Appendix 5) The draft generation unit includes: Drafting patent application documents based on the evaluation results obtained by the analysis section 2. The system of claim 1, (Appendix 6) The review unit includes: Review the application documents generated by the Draft Generation Department 2. The system of claim 1, (Appendix 7) The drawing generating unit includes: Automatically create drawings required for application documents reviewed by the review department using image generation AI 2. The system of claim 1, (Appendix 8) The collecting unit includes: To estimate user sentiment and adjust timing of patent data collection based on the estimated user sentiment. 2. The system of claim 1, (Appendix 9) The collecting unit includes: Analyze users' past patent search history and select the appropriate collection method 2. The system of claim 1, (Appendix 10) The collecting unit includes: Filter patent data as it is collected based on your current projects and areas of interest 2. The system of claim 1, (Appendix 11) The collecting unit includes: To estimate user sentiment and determine the priority of patent data to be collected based on the estimated user sentiment. 2. The system of claim 1, (Appendix 12) The collecting unit includes: When collecting patent data, the system takes into account the user's geographic location information to prioritize collection of highly relevant data. 2. The system of claim 1, (Appendix 13) The collecting unit includes: When collecting patent data, analyze users' social media activity and collect relevant data. 2. The system of claim 1, (Appendix 14) The summary generation unit To estimate a user's emotion and adjust a method of expressing a summary based on the estimated user's emotion. 2. The system of claim 1, (Appendix 15) The summary generation unit When generating abstracts, adjust the level of detail of the abstract based on the importance of the patent 2. The system of claim 1, (Appendix 16) The summary generation unit When generating abstracts, appropriate summarization algorithms are applied depending on the patent category. 2. The system of claim 1, (Appendix 17) The summary generation unit To estimate a user's emotion and adjust a length of a summary based on the estimated user's emotion. 2. The system of claim 1, (Appendix 18) The summary generation unit During abstract generation, abstracts are prioritized based on when the patent was filed 2. The system of claim 1, (Appendix 19) The summary generation unit Adjust the order of abstracts based on patent relevance during abstract generation 2. The system of claim 1, (Appendix 20) The analysis unit is Inferring a user's emotion and adjusting analysis criteria based on the estimated user's emotion. 2. The system of claim 1, (Appendix 21) The analysis unit is During analysis, the accuracy of the analysis is improved by taking into account the correlation between patents. 2. The system of claim 1, (Appendix 22) The analysis unit is When analyzing, the attribute information of the patent submitter is taken into consideration. 2. The system of claim 1, (Appendix 23) The analysis unit is Inferring user emotion and adjusting the order in which analysis results are displayed based on the estimated user emotion. 2. The system of claim 1, (Appendix 24) The analysis unit is When analyzing, the geographical distribution of patents is taken into account. 2. The system of claim 1, (Appendix 25) The analysis unit is During analysis, refer to related patent documents to improve the accuracy of the analysis 2. The system of claim 1, (Appendix 26) The draft generation unit includes: To estimate a user's emotion and adjust a method of expressing a draft based on the estimated user's emotion. 2. The system of claim 1, (Appendix 27) The draft generation unit includes: Adjust the draft detail level based on the importance of the patent when generating the draft 2. The system of claim 1, (Appendix 28) The draft generation unit includes: During draft generation, appropriate drafting algorithms are applied depending on the patent category 2. The system of claim 1, (Appendix 29) The draft generation unit includes: Inferring a user's emotion and adjusting the length of the draft based on the estimated user's emotion 2. The system of claim 1, (Appendix 30) The draft generation unit includes: During draft generation, drafts are prioritized based on when the patent was submitted 2. The system of claim 1, (Appendix 31) The draft generation unit includes: During draft generation, adjust the order of drafts based on patent relevance 2. The system of claim 1, (Appendix 32) The review unit includes: Inferring user sentiment and adjusting review criteria based on the inferred user sentiment 2. The system of claim 1, (Appendix 33) The review unit includes: During review, patent correlations are taken into account to improve review accuracy 2. The system of claim 1, (Appendix 34) The review unit includes: To estimate a user's sentiment and adjust the order in which review results are displayed based on the estimated user's sentiment. 2. The system of claim 1, (Appendix 35) The review unit includes: During the review, the geographical distribution of patents is taken into account. 2. The system of claim 1, (Appendix 36) The drawing generating unit includes: To estimate a user's emotion and adjust a method of expressing a drawing based on the estimated user's emotion. 2. The system of claim 1, (Appendix 37) The drawing generating unit includes: Adjust the level of detail in drawings based on the importance of the patent when generating the drawings 2. The system of claim 1, (Appendix 38) The drawing generating unit includes: During drawing generation, different drawing generation algorithms are applied depending on the patent category 2. The system of claim 1, (Appendix 39) The drawing generating unit includes: To estimate a user's emotion and adjust the length of a drawing based on the estimated user's emotion. 2. The system of claim 1, (Appendix 40) The drawing generating unit includes: During drawing generation, drawings are prioritized based on when the patent was filed 2. The system of claim 1, (Appendix 41) The drawing generating unit includes: Adjust drawing order based on patent relevance during drawing generation 2. The system of claim 1, [Explanation of symbols]

[0206] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A collection unit that collects patent data; a summary generating unit that summarizes the patent data collected by the collecting unit; an analysis unit for evaluating the novelty and inventive step of a patent based on the abstract generated by the abstract generation unit; a draft generation unit that generates a draft of a patent application document based on the evaluation result obtained by the analysis unit; a review unit that reviews the application documents generated by the draft generation unit; A drawing generation unit that generates drawings necessary for the application documents reviewed by the review unit using an image generation AI. A system characterized by:

2. The collecting unit includes: Collect patent data from patent databases 2. The system of claim 1 .

3. The drawing generating unit includes: Drawings required for application documents reviewed by the review department are automatically created using image generation AI.

2. The system of claim 1 .

4. The collecting unit includes: To estimate user sentiment and adjust timing of patent data collection based on the estimated user sentiment. The system of claim 1 .

5. The draft generation unit includes: When generating a draft, a drafting algorithm is applied according to the patent category.

2. The system of claim 1 .

6. The draft generation unit includes: Inferring a user's emotion and adjusting the length of the draft based on the estimated user's emotion The system of claim 1 .

Images