system

Abstract

We provide the system. [Solution] A means for accessing a past document database and analyzing the document data to extract characteristic information, A means for running an artificial intelligence model to generate a draft of a corresponding document based on conditions entered by the user, A means of providing a draft of the generated document to the user terminal and enabling the user to make modifications, A method for improving the accuracy of an artificial intelligence model by training it again with corrected documents, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the creation of contracts, when there are no past similar cases, it is not clear how to create them, and there is a problem that it takes time for confirmation and correction. For this reason, efficient communication with relevant departments within the company becomes difficult, and the overall contract creation process is delayed. In addition, each company has its own format and way of speaking, and there is also a problem that it is difficult to reflect this. Ultimately, there is a lack of the ability to create contracts quickly and accurately, and an improvement in productivity and accuracy is required.

Means for Solving the Problems

[0005] This invention provides a means for accessing a database of past documents and extracting characteristic information about business partners and contract details. Furthermore, it runs an artificial intelligence model using machine learning to automatically generate a draft contract based on conditions entered by the user. This model learns company-specific formats and expressions through repeated learning, improving its accuracy. The generated draft is provided to the user and made editable to support smooth communication with the legal department and other relevant departments. The final revised document is used for retraining, updating the model and further improving the efficiency and accuracy of future contract creation. This series of means enables the rapid and accurate creation of contracts.

[0006] A "historical document database" is a database system for storing and managing contracts and related documents generated in the past. This database functions as a source for extracting information about specific contracts or cases.

[0007] "Characteristic information" refers to metadata extracted from document data, such as contract details, trading partners, and date information, as well as information that is an important element in the draft of newly generated documents.

[0008] "User-entered conditions" refers to specific requirements and elements specified by the user during the contract creation process, such as the name of the contracting party, contract type, contract period, and special conditions.

[0009] An "artificial intelligence model" is a computer program that uses machine learning algorithms to generate documents. It learns trends and patterns from past document data and is a model used to create drafts of new contracts.

[0010] A "user terminal" refers to a computer device used by a user to generate, revise, and review draft contracts, and includes various types of hardware such as PCs, tablets, and smartphones.

[0011] A "revised document" refers to a document that reflects the revisions made by users and relevant departments to the initial draft contract, and is saved in a form that reflects the final agreed-upon content.

[0012] "Retraining" is a process to improve the performance and accuracy of an artificial intelligence model by adding the completed and revised contract documents as new training data to the model. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units 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), and the like.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] The contract draft generation system of the present invention creates a draft contract based on a database of past documents using conditions entered by the user, and reflects the company's internal formatting and expression characteristics.

[0035] The server first stores past contracts accumulated within the company into a database. This database contains detailed information about each contract, including the contracting party, date information, and related metadata. This allows the server to quickly search and extract various characteristics of each contract.

[0036] Users access a contract creation interface through their device and enter necessary information such as the name of the contracting party, contract period, and product type. The device interface is intuitive and designed to allow users to smoothly provide the necessary information.

[0037] When the server receives input data from a user, it uses an artificial intelligence model to analyze similar past contracts and generate a draft of the corresponding contract. This AI model is retrained at regular intervals using machine learning techniques, ensuring that it is always up-to-date with the company's formatting and expression trends.

[0038] The generated draft is presented to the user via a terminal, allowing the user to review and make revisions. The user then shares the draft with legal staff and other relevant departments to make necessary adjustments. Finally, the revised contract is uploaded to the server and recorded in the database.

[0039] This revised contract will be used by the server as new training data to improve the accuracy of future draft generation. For example, in the case of a sales contract for supplying electronic components, if the user inputs information such as "electronic components," "1-year contract," and "Company A," the server will generate a draft based on the past contract that best matches these criteria, and create the optimal contract.

[0040] Thus, the system of the present invention can significantly streamline the entire contract process by rapidly generating contracts and streamlining the revision process.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server collects contracts previously created within the company and stores them in a database in digital format. This database will include the content of the contract, the contracting party, the contract date, and related metadata.

[0044] Step 2:

[0045] The server preprocesses the contract data in the database and converts it into a format suitable for machine learning. In this process, OCR technology is used to convert paper contracts into text data, and natural language processing such as tokenization is performed as needed.

[0046] Step 3:

[0047] Users access a contract creation interface using their device and input basic contract information, such as the contracting party, contract period, and contract type. The interface is designed to allow users to intuitively input information.

[0048] Step 4:

[0049] The server receives input data provided by the user and begins searching the database for similar contracts based on this data. It extracts the features of highly relevant contracts, and the artificial intelligence model then operates based on these features.

[0050] Step 5:

[0051] The server uses a machine learning model to generate appropriate contract drafts based on historical similar contract data. This model reflects the company's specific format and style, and the generated drafts are prepared for user approval and revision.

[0052] Step 6:

[0053] The user receives the draft contract generated on their device and makes revisions as needed in consultation with legal personnel and other stakeholders. The revised version is then sent back to the server for further adjustments toward finalization.

[0054] Step 7:

[0055] The server stores the revised contracts submitted by users in a database and uses this data to retrain the artificial intelligence model. By adding new contract data, the accuracy of subsequent draft generation will be improved.

[0056] (Example 1)

[0057] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] There is a need to enable the efficient generation and editing of documents, thereby speeding up operations and improving accuracy. In particular, a challenge is to quickly create drafts of new documents by utilizing a large number of past documents and to improve their accuracy.

[0059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0060] In this invention, the server includes means for accessing a historical electronic database and analyzing the electronic data to extract characteristic information; means for executing a generative AI model to analyze similar past records based on conditions entered by the user and generate a draft of the corresponding record; and means for providing the generated draft of the record to an information terminal and enabling editing by the user. This makes it possible to generate highly accurate drafts based on a large number of past documents and to quickly modify them.

[0061] An "electronic database" is a form of information aggregation that systematically stores various types of electronic data accumulated in the past, making it accessible and searchable.

[0062] "Feature information" refers to key characteristics or patterns extracted from a specific dataset or document that are used to identify similar data.

[0063] A "generative AI model" is a collection of algorithms that use artificial intelligence to generate new data and information by analyzing and learning from past data, and then generating appropriate output based on the results.

[0064] An "information terminal" is an electronic device used by a user to input, output, or process data, and specifically includes computers and smartphones.

[0065] "Training data" refers to a collection of empirical data used by artificial intelligence models to learn the patterns and rules necessary to generate new information.

[0066] "Style" refers to a specific form or layout that is consistently used within a particular organization or environment, and represents a standardized structure in documents and communications.

[0067] "Expression patterns" refer to specific phrases and styles used in communication, particularly in document creation, within a particular organization or culture.

[0068] The system of this invention enables users to efficiently generate and edit documents. This system consists of a server and terminals, each with a specific role. Specifically, it has the following configuration and operation.

[0069] The server first stores past contracts and related documents accumulated within the organization into an electronic database. This requires the use of database management software to organize and store detailed information and related metadata for each document. For this purpose, computer hardware with high processing power is recommended.

[0070] Users access a document creation interface using an information terminal. This interface is designed for intuitive operation, allowing users to easily input contract terms and other necessary information. The terminal typically consists of a personal computer or tablet device.

[0071] Upon receiving user input, the server uses a generative AI model to analyze similar past records and generate a draft of a new document. The generative AI model learns organizational-specific styles and expression patterns, enabling it to create documents that reflect the latest information. The necessary software includes machine learning frameworks and natural language processing libraries.

[0072] The generated document is presented to the user on their device, and the user can edit it. The edited document is then uploaded back to the server, and the AI ​​model used to generate the document is automatically retrained based on it. This process continuously improves the efficiency and accuracy of similar tasks.

[0073] For example, when creating a sales contract for electronic components, the user inputs basic conditions such as "electronic components," "1-year contract," and "Company B." The server analyzes past records that best match these conditions and uses that data to generate an optimal draft.

[0074] An example of a prompt might be: "Draft a sales contract based on the following conditions: Contract subject: electronic components, Contract period: 1 year, Contracting party: Company B." Using this prompt allows the AI ​​generation model to generate documents accurately and efficiently.

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] The server stores historical document data accumulated within the company into an electronic database. Input includes detailed digital data of contracts and documents. Based on this, the server analyzes the content of each document, extracts characteristic information, and stores it in an organized format. Specifically, it uses database management software to classify the data into categories, enabling efficient searching.

[0078] Step 2:

[0079] The user accesses the document creation interface using an information terminal. Inputs include contract terms, such as the contracting party and duration. The user enters this information into the interface. Specific operations include selecting from dropdown menus and directly entering text into text fields.

[0080] Step 3:

[0081] The terminal sends the entered conditions to the server. Here, the input information is packetized and transferred to the server via a secure protocol. As output, data in a format easily received by the server is generated.

[0082] Step 4:

[0083] The server utilizes a generative AI model to search the database for similar past documents that match the user's criteria and performs analysis. Input consists of user-provided criteria and historical document data. Output is a draft document suitable for the criteria. Specific operations include analysis processing using machine learning algorithms.

[0084] Step 5:

[0085] The generated draft is presented to the user via the terminal. The output is a draft contract that the user can review and modify. The user can make necessary changes through the terminal's interface. Specific operations include editing text and adding comments.

[0086] Step 6:

[0087] The document, after the user has finished editing it, is uploaded back to the server. The input is the edited document data. The server takes this as training data and uses it to improve the performance of the generative AI model. Specific actions include adding documents to the database and the model retraining process.

[0088] (Application Example 1)

[0089] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0090] With the increase in online transactions and digital contracts, the creation of contracts and terms of service is becoming more complex. Traditional methods are time-consuming, hindering the rapid progress of transactions. Furthermore, accurately drafting documents based on company-specific formats and expressions is not easy. In this situation, the need for efficient and accurate document generation systems is growing.

[0091] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0092] In this invention, the server includes means for accessing a historical data database and analyzing the data to extract characteristic information; means for executing an artificial intelligence model for generating a draft of a corresponding document based on conditions entered by the user; and means for providing the generated draft document to an endpoint device and enabling the user to make modifications. This enables the rapid and accurate generation of contracts, including the creation of terms and conditions for online transactions.

[0093] A "data database" is an information system that systematically stores and searches / analyzes data accumulated in the past.

[0094] "Feature information" refers to important attributes and patterns in extracted data or documents, and is an indicator used for analysis and learning.

[0095] An "endpoint device" refers to a device or terminal that a user directly operates or uses, and is capable of displaying or inputting information.

[0096] An "artificial intelligence model" is an algorithm or system that uses machine learning and data analysis techniques to make judgments and predictions based on input information.

[0097] "Online transactions" refer to a general term for commercial transactions and service contracts conducted via the internet, and are a form of transaction that is completed electronically.

[0098] "Format" refers to the layout, style, and other formatting elements used when creating a document, and is a standard for providing a unified format for expression.

[0099] A "business" refers to commercial activities or projects carried out based on specific purposes or goals, and is an activity aimed at providing value in the market.

[0100] The system that implements this application example uses an artificial intelligence model to access a historical data database and generate draft contracts and terms of service. The server is located in the cloud and runs the AI ​​model, which utilizes Python and TensorFlow®. TensorFlow is a platform for data analysis and learning, and it plays a role in extracting feature information from historical data and generating draft contracts.

[0101] Users utilize their smartphones as terminals, entering the necessary contract terms through an intuitive interface. The smartphone acts as an endpoint device, sending the input data to a server and receiving a draft of the generated document. Throughout this process, a web application built with Django serves as the user interface, providing a smooth user experience.

[0102] As a concrete example, if a user enters information such as "e-book sales," "3-year contract," and "publisher" on their smartphone, the server analyzes transaction data related to e-books, generates an optimal draft contract, and sends it to the device. In this process, the artificial intelligence model utilizes past similar transaction information to provide a draft that matches the company's specific format and expression. Furthermore, the revised document is used again as training data, contributing to improved accuracy in future draft generation.

[0103] An example of a prompt message might be: "Use the contract draft generation system to create a contract that meets the following conditions: Conditions: Contract type: ebook sales, Contract period: 3 years, Counterparty: Publisher." This system configuration enables the rapid and accurate creation of digital contracts.

[0104] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0105] Step 1:

[0106] The device (smartphone) receives the necessary contract conditions (contract type, duration, trading partner, etc.) from the user as input. This input is done through a form in the web application. The information entered by the user is then prepared by a Django-based frontend to be sent to the server in JSON format.

[0107] Step 2:

[0108] The server analyzes the received input data and searches its historical data database. Based on the entered conditions, it extracts the most relevant data. This process uses SQL queries to retrieve similar contract information from the database (e.g., PostgreSQL) and identify the dataset that most closely matches the input.

[0109] Step 3:

[0110] The server runs a pre-trained generative AI model using TensorFlow based on the identified similar data. The model generates a draft contract that best matches the user's input based on the extracted feature information. At this stage, natural language generation and document structure optimization are performed, and the generated draft is formatted as a provisional contract.

[0111] Step 4:

[0112] The generated draft contract is sent from the server to the terminal as output. The terminal displays the draft to the user and provides an interface that allows for additional modifications and adjustments. This interface allows the user to easily review the draft and make necessary corrections.

[0113] Step 5:

[0114] After the user completes the corrections, the device sends the corrected document back to the server. The server receives this corrected data and uses it to retrain the generating AI model. New data points are extracted from the corrections and incorporated into the training process to improve the model's accuracy.

[0115] This series of processes enables the rapid and efficient generation of draft contracts and allows for easy modification by the user.

[0116] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0117] This invention is a system that aims to improve the user experience by combining an emotion engine with an existing contract creation system. This system consists of a database of past documents, an artificial intelligence model, and an emotion engine.

[0118] The server manages historical document data accumulated within the company and quickly searches and extracts information based on user input, including metadata such as contract details, counterparty information, and date information. This allows artificial intelligence models that generate draft documents based on similar past contracts to easily produce optimal documents.

[0119] The user accesses the contract creation screen via their device and enters the necessary conditions. During this process, an emotion engine is installed in the device, recognizing the user's emotional state in real time and transmitting that information to the server. Emotion recognition is performed by analyzing the user's facial expressions, voice tone, and input speed, enabling natural interaction.

[0120] The server adjusts the expression of the generated document based on the emotional information sent from the emotion engine. For example, if the user is feeling anxious, the document's tone can be changed to a more friendly one, or important points can be explained in more detail. This reduces user stress and supports efficient contract creation.

[0121] As a concrete example, when a user creates a new contract, the system uses an emotion engine to detect the user's tension and anxiety. As a result, the server softens the tone of the document and includes more examples, making it easier for the user to review the contract with confidence. This approach reduces the number of revisions the user needs to make to the final document, allowing the contract process to proceed smoothly.

[0122] Thus, the system of the present invention incorporates the user's emotions throughout the entire process, from document generation to revision and finalization, ultimately achieving the creation of high-quality and user-friendly contracts.

[0123] The following describes the processing flow.

[0124] Step 1:

[0125] Users access a contract creation interface through their device and enter the necessary information. The interface includes fields such as the name of the contracting party, the contract period, and detailed contract terms, and is designed for quick user input.

[0126] Step 2:

[0127] The emotion engine built into the device analyzes the user's facial expressions and voice tone in real time while they are inputting data, and evaluates their emotional state. This data is sent from the device to the server as emotion parameters.

[0128] Step 3:

[0129] The server references past contract documents in the database and searches for the most similar contract that best matches the user's input criteria. It extracts feature information from the found similar contracts and uses an AI model to generate a new draft contract.

[0130] Step 4:

[0131] The server adjusts the wording of the generated contract draft, taking into account the emotional parameters obtained by the emotion engine. For example, if the user is feeling stressed, the wording is simplified and adjusted to make it easier to read.

[0132] Step 5:

[0133] The generated, revised draft contract is sent to the user's device. The user can review the draft on their device and make revisions as needed. Once the user has finished reviewing and revising the contract, they send it to the server for finalization.

[0134] Step 6:

[0135] The server stores the revised final contract in a database and uses this data as a dataset for subsequent generation and learning processes. It also accumulates data from the emotion engine and continues to improve the emotion recognition algorithm to a higher accuracy.

[0136] (Example 2)

[0137] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0138] In information generation, there is a challenge in creating user-friendly and high-quality documents because there is no document generation process that reflects the user's emotional state. Furthermore, because the generated documents are not presented in a way that suits the user's emotional state, it can cause stress.

[0139] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0140] In this invention, the server includes means for accessing past information sets and analyzing the information to extract characteristic information; means for executing an artificial intelligence model for generating draft information corresponding to conditions entered by the user; and means for analyzing the user's emotional state and adjusting the expression of the generated information based on that information. This makes it possible to create appropriate and high-quality documents while taking the user's emotional state into consideration.

[0141] An "information set" is a collection of data accumulated through past transactions and exchanges, and includes contract details, counterparty information, date information, and related incidental information.

[0142] "Characteristic information" refers to distinctive data extracted from a set of information, used to identify and analyze important elements in document generation.

[0143] "User-entered conditions" refer to the requirements and specifications that users set when creating contracts or other documents, and serve as guidelines in the document generation process.

[0144] An "artificial intelligence model" is a learning algorithm that operates using a computer, and is a means of automatically generating results and predictions based on input data.

[0145] "User's emotional state" refers to the psychological situation or mood estimated from the user's facial expressions, tone of voice, typing speed, etc.

[0146] "Means of adjusting expression" refer to processes and methods for modifying the tone and phrasing of a generated document to match the user's emotional state.

[0147] This invention is a system aimed at improving the user experience in the document generation process. This system consists of a server, terminals, and artificial intelligence technology.

[0148] The server manages data stored in past information sets and has the function of extracting necessary information based on conditions sent from the user's terminal. This data includes supplementary information such as contract details, counterparty information, and date information. Based on past document examples, the server sends prompt messages to the generation AI model. For example, a prompt message in the format of "The contract start date is November 1, 2023, generate a draft document based on the content."

[0149] The terminal provides an interface for users to access the contract creation screen and input the necessary information. The terminal has an emotion engine built in that analyzes the user's facial expressions, voice tone, input speed, etc., to recognize their emotional state in real time. This emotional information is sent to a server and used to adjust the wording of the document.

[0150] The generation AI model automatically generates a draft document based on prompts from the server. The generated document is then adjusted to take into account the user's emotional state; for example, if tension is detected, the tone is softened. Through this process, users can perform final checks and revisions of the document without feeling stressed, allowing the entire process to proceed efficiently.

[0151] Specifically, when a user is creating a new contract, if the emotion engine detects the user's anxiety, the server will make the document more user-friendly and include numerous concrete examples to make it easier for the user to review and understand the content with confidence. In this way, the number of revisions the user needs to make to the final document can be reduced, helping to streamline the contract process.

[0152] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0153] Step 1:

[0154] User input processing

[0155] The user accesses the contract creation screen on their device and enters necessary information such as contract details, counterparty information, and date information. This input data is sent from the device to the server. At this stage, the specific input consists of the conditions set by the user, and the output is the transmission of data to the server.

[0156] Step 2:

[0157] Server-based database search

[0158] The server searches a historical data set based on the user's input. This process executes database queries to quickly extract relevant data regarding contract details and counterparty information. The input is the user's criteria data, and the output is filtered historical document data.

[0159] Step 3:

[0160] Generating draft documents using generative AI models

[0161] The server, while referencing filtered historical document data, sends prompt messages to the generative AI model. These prompt messages contain conditions in text format. Based on these prompts, the generative AI model generates a new document draft. The input consists of historical document data and prompt messages, and the output is the generated document draft.

[0162] Step 4:

[0163] Analysis of user emotions using an emotion engine

[0164] An emotion engine built into the device generates emotional information by analyzing the user's facial expressions and voice tone in real time. This emotional information is sent to a server and used to adjust documents. The input is the user's biometric information, and the output is the analyzed emotional state data.

[0165] Step 5:

[0166] Server-based document representation adjustment

[0167] The server adjusts the wording of the generated document draft based on emotional information. For example, if the user is feeling anxious, the document is rewritten to a more friendly tone. The input is the generated document draft and emotional state data, and the output is the adjusted document.

[0168] Step 6:

[0169] User feedback and final confirmation

[0170] The revised document is returned to the user's terminal, where the user reviews the contract. Additional revisions can be made if necessary. The formal contract is finalized only when the user is satisfied with the document's content. The input is the revised document, and the output is the user's feedback and final document approval.

[0171] (Application Example 2)

[0172] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0173] When drafting contracts and other documents, users often experience anxiety and tension due to the complexity of the content or unclear wording. Such emotions can impair the efficiency of the entire contracting process and increase the likelihood of misunderstandings and the need for revisions. This invention aims to make the document creation process more user-friendly and stress-free by understanding the user's emotional state in real time and appropriately adjusting the content and tone of the document.

[0174] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0175] In this invention, the server includes means for accessing a past document information recording device and analyzing the data of the information recording device to extract feature information; means for executing a machine learning model to generate a draft of a corresponding document based on conditions entered by the user; and means for using an emotion analysis device to recognize the user's emotional state and adjust the document expression. This enables efficient and highly satisfying contract creation while providing optimal document suggestions that respond to the user's emotions, thereby reducing anxiety and misunderstandings.

[0176] An "information recording device" is a system for storing and managing data from past contracts and related documents, and for accessing and analyzing it as needed.

[0177] A "machine learning model" is a model that has learned from past cases to generate draft contracts, and it is a technology that proposes the optimal document according to the conditions.

[0178] A "user display device" is a device that provides an interface that allows users to review the generated draft of a contract and make revisions as needed.

[0179] An "emotion analysis device" is a device that analyzes the tone of a user's voice and input behavior to grasp their emotions and stress levels in real time, and adjusts the wording of documents based on that analysis.

[0180] "Supplementary information" refers to a group of incidental information, such as dates and metadata, related to the contract details and counterparty information, which clarifies the context of the document.

[0181] "Format" refers to the general term for document formats and writing styles that are conventionally used within an organization or industry.

[0182] "Expression patterns" are types of wording and phrasing commonly used within a particular organization or culture, and are utilized to enhance the consistency and credibility of documents.

[0183] This system is designed to generate optimal contracts tailored to the user's emotions. The server performs the following main functions: First, it uses an information recording device to access past document data, such as contracts, and analyzes it to extract characteristic information. Next, it uses a machine learning model to generate a draft document based on the conditions entered by the user. This document generation process utilizes a model learned from past cases, enabling it to suggest the most suitable document.

[0184] Furthermore, the emotion analysis device analyzes the user's voice tone and input speed in real time to recognize the user's emotional state. This emotional information is used to adjust the document's expression, enabling flexible document generation that reduces the user's anxiety and tension. A draft of the generated document is presented to the user through a user display device, and the user can make revisions as needed. The revised document is then used for further training, contributing to the improvement of the machine learning model's accuracy.

[0185] Specifically, a speech recognition system (such as Google's Speech-to-Text API) is used to convert what the user says into text, and an emotion recognition API, combined with OpenCV and other technologies, is used to estimate the user's emotions. This allows the system to, for example, if a user wants to create a mortgage contract, detect their anxiety and guide them in a gentle tone, saying, "Buying a home is a big decision, so we've summarized the necessary information concisely. Please let us know if you have any questions."

[0186] An example of a prompt message is: "If the user is nervous, provide explanations in a concise and friendly tone. Highlight key points and provide specific examples as needed."

[0187] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0188] Step 1:

[0189] The server retrieves historical document data from the information recording device. The input consists of user-specified criteria. Based on these criteria, the server searches the database and extracts relevant document data. The output is document data containing specific contract details and counterparty information.

[0190] Step 2:

[0191] The server analyzes the document data extracted using a machine learning model and extracts feature information. The input is the document data obtained in step 1. The server analyzes the data and identifies common patterns and frequently occurring expressions in the contracts. The output is a list of feature information for document generation.

[0192] Step 3:

[0193] The terminal receives condition input from the user and sends it to the server. The input consists of requirements and special notes for the contract that the user wants to generate. The server receives this and inputs it into the generation AI model.

[0194] Step 4:

[0195] The server runs a generative AI model to generate a draft document based on the user's conditions. The input consists of the user's conditions and the feature information obtained in step 2. The AI ​​model uses these to generate the optimal document draft. The output is the draft document for the user to review.

[0196] Step 5:

[0197] An emotion analysis device on the terminal senses the user's voice tone and input speed in real time. Input consists of the user's voice information and input from the interface. Based on this information, the emotion analysis device infers the user's emotional state. Output is the user's emotional state data.

[0198] Step 6:

[0199] The server adjusts the wording of the draft document generated based on the emotional state data. The inputs are the draft document from step 4 and the emotional state data from step 5. The tone and explanation of the document are adjusted according to the emotion. The output is the final draft document presented to the user.

[0200] Step 7:

[0201] The user reviews the final draft document on the terminal and makes revisions as needed. The input is the draft document adjusted in step 6. The user reviews this and makes changes or additions to the content. The output is the final version of the document with the user's revisions.

[0202] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0203] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0204] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0205] [Second Embodiment]

[0206] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0207] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0208] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0209] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0210] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0211] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0212] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0213] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0214] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0215] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0216] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0217] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0218] The contract draft generation system of the present invention creates a draft contract based on a database of past documents using conditions entered by the user, and reflects the company's internal formatting and expression characteristics.

[0219] The server first stores past contracts accumulated within the company into a database. This database contains detailed information about each contract, including the contracting party, date information, and related metadata. This allows the server to quickly search and extract various characteristics of each contract.

[0220] Users access a contract creation interface through their device and enter necessary information such as the name of the contracting party, contract period, and product type. The device interface is intuitive and designed to allow users to smoothly provide the necessary information.

[0221] When the server receives input data from a user, it uses an artificial intelligence model to analyze similar past contracts and generate a draft of the corresponding contract. This AI model is retrained at regular intervals using machine learning techniques, ensuring that it is always up-to-date with the company's formatting and expression trends.

[0222] The generated draft is presented to the user via a terminal, allowing the user to review and make revisions. The user then shares the draft with legal staff and other relevant departments to make necessary adjustments. Finally, the revised contract is uploaded to the server and recorded in the database.

[0223] This revised contract will be used by the server as new training data to improve the accuracy of future draft generation. For example, in the case of a sales contract for supplying electronic components, if the user inputs information such as "electronic components," "1-year contract," and "Company A," the server will generate a draft based on the past contract that best matches these criteria, and create the optimal contract.

[0224] Thus, the system of the present invention can significantly streamline the entire contract process by rapidly generating contracts and streamlining the revision process.

[0225] The following describes the processing flow.

[0226] Step 1:

[0227] The server collects contracts previously created within the company and stores them in a database in digital format. This database will include the content of the contract, the contracting party, the contract date, and related metadata.

[0228] Step 2:

[0229] The server preprocesses the contract data in the database and converts it into a format suitable for machine learning. In this process, OCR technology is used to convert paper contracts into text data, and natural language processing such as tokenization is performed as needed.

[0230] Step 3:

[0231] Users access a contract creation interface using their device and input basic contract information, such as the contracting party, contract period, and contract type. The interface is designed to allow users to intuitively input information.

[0232] Step 4:

[0233] The server receives input data provided by the user and begins searching the database for similar contracts based on this data. It extracts the features of highly relevant contracts, and the artificial intelligence model then operates based on these features.

[0234] Step 5:

[0235] The server uses a machine learning model to generate appropriate contract drafts based on historical similar contract data. This model reflects the company's specific format and style, and the generated drafts are prepared for user approval and revision.

[0236] Step 6:

[0237] The user receives the draft contract generated on their device and makes revisions as needed in consultation with legal personnel and other stakeholders. The revised version is then sent back to the server for further adjustments toward finalization.

[0238] Step 7:

[0239] The server stores the revised contracts submitted by users in a database and uses this data to retrain the artificial intelligence model. By adding new contract data, the accuracy of subsequent draft generation will be improved.

[0240] (Example 1)

[0241] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0242] There is a need to enable the efficient generation and editing of documents, thereby speeding up operations and improving accuracy. In particular, a challenge is to quickly create drafts of new documents by utilizing a large number of past documents and to improve their accuracy.

[0243] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0244] In this invention, the server includes means for accessing a historical electronic database and analyzing the electronic data to extract characteristic information; means for executing a generative AI model to analyze similar past records based on conditions entered by the user and generate a draft of the corresponding record; and means for providing the generated draft of the record to an information terminal and enabling editing by the user. This makes it possible to generate highly accurate drafts based on a large number of past documents and to quickly modify them.

[0245] An "electronic database" is a form of information aggregation that systematically stores various types of electronic data accumulated in the past, making it accessible and searchable.

[0246] "Feature information" refers to key characteristics or patterns extracted from a specific dataset or document that are used to identify similar data.

[0247] A "generative AI model" is a collection of algorithms that use artificial intelligence to generate new data and information by analyzing and learning from past data, and then generating appropriate output based on the results.

[0248] An "information terminal" is an electronic device used by a user to input, output, or process data, and specifically includes computers and smartphones.

[0249] "Training data" refers to a collection of empirical data used by artificial intelligence models to learn the patterns and rules necessary to generate new information.

[0250] "Style" refers to a specific form or layout that is consistently used within a particular organization or environment, and represents a standardized structure in documents and communications.

[0251] "Expression patterns" refer to specific phrases and styles used in communication, particularly in document creation, within a particular organization or culture.

[0252] The system of this invention enables users to efficiently generate and edit documents. This system consists of a server and terminals, each with a specific role. Specifically, it has the following configuration and operation.

[0253] The server first stores past contracts and related documents accumulated within the organization into an electronic database. This requires the use of database management software to organize and store detailed information and related metadata for each document. For this purpose, computer hardware with high processing power is recommended.

[0254] Users access a document creation interface using an information terminal. This interface is designed for intuitive operation, allowing users to easily input contract terms and other necessary information. The terminal typically consists of a personal computer or tablet device.

[0255] Upon receiving user input, the server uses a generative AI model to analyze similar past records and generate a draft of a new document. The generative AI model learns organizational-specific styles and expression patterns, enabling it to create documents that reflect the latest information. The necessary software includes machine learning frameworks and natural language processing libraries.

[0256] The generated document is presented to the user on their device, and the user can edit it. The edited document is then uploaded back to the server, and the AI ​​model used to generate the document is automatically retrained based on it. This process continuously improves the efficiency and accuracy of similar tasks.

[0257] For example, when creating a sales contract for electronic components, the user inputs basic conditions such as "electronic components," "1-year contract," and "Company B." The server analyzes past records that best match these conditions and uses that data to generate an optimal draft.

[0258] An example of a prompt might be: "Draft a sales contract based on the following conditions: Contract subject: electronic components, Contract period: 1 year, Contracting party: Company B." Using this prompt allows the AI ​​generation model to generate documents accurately and efficiently.

[0259] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0260] Step 1:

[0261] The server stores historical document data accumulated within the company into an electronic database. Input includes detailed digital data of contracts and documents. Based on this, the server analyzes the content of each document, extracts characteristic information, and stores it in an organized format. Specifically, it uses database management software to classify the data into categories, enabling efficient searching.

[0262] Step 2:

[0263] The user accesses the document creation interface using an information terminal. Inputs include contract terms, such as the contracting party and duration. The user enters this information into the interface. Specific operations include selecting from dropdown menus and directly entering text into text fields.

[0264] Step 3:

[0265] The terminal sends the entered conditions to the server. Here, the input information is packetized and transferred to the server via a secure protocol. As output, data in a format easily received by the server is generated.

[0266] Step 4:

[0267] The server utilizes a generative AI model to search the database for similar past documents that match the user's criteria and performs analysis. Input consists of user-provided criteria and historical document data. Output is a draft document suitable for the criteria. Specific operations include analysis processing using machine learning algorithms.

[0268] Step 5:

[0269] The generated draft is presented to the user via the terminal. The output is a draft contract that the user can review and modify. The user can make necessary changes through the terminal's interface. Specific operations include editing text and adding comments.

[0270] Step 6:

[0271] The document, after the user has finished editing it, is uploaded back to the server. The input is the edited document data. The server takes this as training data and uses it to improve the performance of the generative AI model. Specific actions include adding documents to the database and the model retraining process.

[0272] (Application Example 1)

[0273] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0274] With the increase in online transactions and digital contracts, the creation of contracts and terms of service is becoming more complex. Traditional methods are time-consuming, hindering the rapid progress of transactions. Furthermore, accurately drafting documents based on company-specific formats and expressions is not easy. In this situation, the need for efficient and accurate document generation systems is growing.

[0275] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0276] In this invention, the server includes means for accessing a historical data database and analyzing the data to extract characteristic information; means for executing an artificial intelligence model for generating a draft of a corresponding document based on conditions entered by the user; and means for providing the generated draft document to an endpoint device and enabling the user to make modifications. This enables the rapid and accurate generation of contracts, including the creation of terms and conditions for online transactions.

[0277] A "data database" is an information system that systematically stores and searches / analyzes data accumulated in the past.

[0278] "Feature information" refers to important attributes and patterns in extracted data or documents, and is an indicator used for analysis and learning.

[0279] An "endpoint device" refers to a device or terminal that a user directly operates or uses, and is capable of displaying or inputting information.

[0280] An "artificial intelligence model" is an algorithm or system that makes judgments or predictions from input information by leveraging machine learning and data analysis techniques.

[0281] "Online transaction" refers to the general term for commercial transactions and service contracts conducted via the Internet, which is a transaction form that is electronically completed.

[0282] "Format" refers to the layout, style, and other formats when creating a document, which is a standard for providing a unified expression form.

[0283] "Business" refers to commercial activities or projects carried out based on specific purposes or goals, which are activities aimed at providing value in the market.

[0284] The system that realizes this application example accesses the past data database and uses an artificial intelligence model to generate drafts of contract documents and terms of use. The server is deployed on the cloud and runs an artificial intelligence model that utilizes Python and TensorFlow. TensorFlow is a platform for data analysis and learning, which plays a role in extracting feature information from past data and generating contract drafts.

[0285] The user uses a smartphone as a terminal and inputs the necessary contract conditions through an intuitive interface. The smartphone functions as an endpoint device that sends the input data to the server and receives the generated document draft. In this process, a web application using Django operates as the user interface, providing a smooth user experience.

[0286] As a specific example, when a user inputs information such as "e-book sales", "3-year contract", and "publishing house" on a smartphone, the server analyzes the transaction data related to e-books, generates an optimal contract draft, and sends it to the terminal. In this process, the artificial intelligence model utilizes past similar transaction information to provide a draft that conforms to the company-specific format and expression. Also, the revised document is used as learning data again, contributing to the improvement of the accuracy of the next draft generation.

[0287] As an example of the prompt text, an instruction such as "Using the contract draft generation system, create a contract that meets the following conditions. Conditions: Contract type: e-book sales, Contract period: 3 years, Counterparty company: publishing house." is used. With such a system configuration, the creation of quick and accurate digital contracts is realized.

[0288] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0289] Step 1:

[0290] The terminal (smartphone) receives from the user the conditions necessary for the contract (contract type, period, trading partner, etc.) as input. This input is made through the form of the web application. The information input by the user is prepared for the front-end using Django to send it to the server in JSON format.

[0291] Step 2:

[0292] The server analyzes the received input data and searches the past data database. Based on the input conditions, highly relevant data is extracted. In this process, SQL queries are used to obtain similar contract information from the database (e.g., PostgreSQL) and identify the data set closest to the input.

[0293] Step 3:

[0294] The server runs a pre-trained generative AI model using TensorFlow based on the identified similar data. The model generates a draft contract that best matches the user's input based on the extracted feature information. At this stage, natural language generation and document structure optimization are performed, and the generated draft is formatted as a provisional contract.

[0295] Step 4:

[0296] The generated draft contract is sent from the server to the terminal as output. The terminal displays the draft to the user and provides an interface that allows for additional modifications and adjustments. This interface allows the user to easily review the draft and make necessary corrections.

[0297] Step 5:

[0298] After the user completes the corrections, the device sends the corrected document back to the server. The server receives this corrected data and uses it to retrain the generating AI model. New data points are extracted from the corrections and incorporated into the training process to improve the model's accuracy.

[0299] This series of processes enables the rapid and efficient generation of draft contracts and allows for easy modification by the user.

[0300] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0301] This invention is a system that aims to improve the user experience by combining an emotion engine with an existing contract creation system. This system consists of a database of past documents, an artificial intelligence model, and an emotion engine.

[0302] The server manages the past document data stored within the company and can quickly search for and extract information based on user input, including metadata such as contract content, counterpart information, and date information. This enables an artificial intelligence model that generates a draft document by referring to similar past contracts to easily perform optimal document generation.

[0303] The user accesses the contract creation screen through the terminal and enters the necessary conditions. At this time, an emotion engine is installed on the terminal to recognize the user's emotional state in real-time and transmit that information to the server. Emotion recognition is performed by analyzing the user's facial expression, voice tone, input speed, etc., enabling natural interaction.

[0304] Based on the emotion information sent from the emotion engine, the server adjusts the expression of the generated document. For example, when the user is feeling anxious, it is possible to change the document expression to a more friendly tone or to make the explanation of important parts more detailed. This reduces the user's stress and supports efficient contract creation.

[0305] As a specific example, when the user creates a new contract, the system uses the emotion engine to detect the user's tension and anxiety. As a result, the server softens the tone of the document and includes more examples, making it easier for the user to confirm the contract content with peace of mind. This approach can reduce the number of revisions to the final document by the user and enable the contract process to proceed smoothly.

[0306] In this way, the system of the present invention incorporates the user's emotions throughout the entire process from document generation to revision and finalization, ultimately realizing the creation of a high-quality and user-friendly contract.

[0307] The following explains the processing flow.

[0308] Step 1:

[0309] Users access a contract creation interface through their device and enter the necessary information. The interface includes fields such as the name of the contracting party, the contract period, and detailed contract terms, and is designed for quick user input.

[0310] Step 2:

[0311] The emotion engine built into the device analyzes the user's facial expressions and voice tone in real time while they are inputting data, and evaluates their emotional state. This data is sent from the device to the server as emotion parameters.

[0312] Step 3:

[0313] The server references past contract documents in the database and searches for the most similar contract that best matches the user's input criteria. It extracts feature information from the found similar contracts and uses an AI model to generate a new draft contract.

[0314] Step 4:

[0315] The server adjusts the wording of the generated contract draft, taking into account the emotional parameters obtained by the emotion engine. For example, if the user is feeling stressed, the wording is simplified and adjusted to make it easier to read.

[0316] Step 5:

[0317] The generated, revised draft contract is sent to the user's device. The user can review the draft on their device and make revisions as needed. Once the user has finished reviewing and revising the contract, they send it to the server for finalization.

[0318] Step 6:

[0319] The server stores the revised final contract in a database and uses this data as a dataset for subsequent generation and learning processes. It also accumulates data from the emotion engine and continues to improve the emotion recognition algorithm to a higher accuracy.

[0320] (Example 2)

[0321] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0322] In information generation, there is a challenge in creating user-friendly and high-quality documents because there is no document generation process that reflects the user's emotional state. Furthermore, because the generated documents are not presented in a way that suits the user's emotional state, it can cause stress.

[0323] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0324] In this invention, the server includes means for accessing past information sets and analyzing the information to extract characteristic information; means for executing an artificial intelligence model for generating draft information corresponding to conditions entered by the user; and means for analyzing the user's emotional state and adjusting the expression of the generated information based on that information. This makes it possible to create appropriate and high-quality documents while taking the user's emotional state into consideration.

[0325] An "information set" is a collection of data accumulated through past transactions and exchanges, and includes contract details, counterparty information, date information, and related incidental information.

[0326] "Characteristic information" refers to distinctive data extracted from a set of information, used to identify and analyze important elements in document generation.

[0327] "User-entered conditions" refer to the requirements and specifications that users set when creating contracts or other documents, and serve as guidelines in the document generation process.

[0328] An "artificial intelligence model" is a learning algorithm that operates using a computer, and is a means of automatically generating results and predictions based on input data.

[0329] "User's emotional state" refers to the psychological situation or mood estimated from the user's facial expressions, tone of voice, typing speed, etc.

[0330] "Means of adjusting expression" refer to processes and methods for modifying the tone and phrasing of a generated document to match the user's emotional state.

[0331] This invention is a system aimed at improving the user experience in the document generation process. This system consists of a server, terminals, and artificial intelligence technology.

[0332] The server manages data stored in past information sets and has the function of extracting necessary information based on conditions sent from the user's terminal. This data includes supplementary information such as contract details, counterparty information, and date information. Based on past document examples, the server sends prompt messages to the generation AI model. For example, a prompt message in the format of "The contract start date is November 1, 2023, generate a draft document based on the content."

[0333] The terminal provides an interface for users to access the contract creation screen and input the necessary information. The terminal has an emotion engine built in that analyzes the user's facial expressions, voice tone, input speed, etc., to recognize their emotional state in real time. This emotional information is sent to a server and used to adjust the wording of the document.

[0334] The generation AI model automatically generates a draft document based on prompts from the server. The generated document is then adjusted to take into account the user's emotional state; for example, if tension is detected, the tone is softened. Through this process, users can perform final checks and revisions of the document without feeling stressed, allowing the entire process to proceed efficiently.

[0335] Specifically, when a user is creating a new contract, if the emotion engine detects the user's anxiety, the server will make the document more user-friendly and include numerous concrete examples to make it easier for the user to review and understand the content with confidence. In this way, the number of revisions the user needs to make to the final document can be reduced, helping to streamline the contract process.

[0336] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0337] Step 1:

[0338] User input processing

[0339] The user accesses the contract creation screen on their device and enters necessary information such as contract details, counterparty information, and date information. This input data is sent from the device to the server. At this stage, the specific input consists of the conditions set by the user, and the output is the transmission of data to the server.

[0340] Step 2:

[0341] Server-based database search

[0342] The server searches a historical data set based on the user's input. This process executes database queries to quickly extract relevant data regarding contract details and counterparty information. The input is the user's criteria data, and the output is filtered historical document data.

[0343] Step 3:

[0344] Generating draft documents using generative AI models

[0345] The server, while referencing filtered historical document data, sends prompt messages to the generative AI model. These prompt messages contain conditions in text format. Based on these prompts, the generative AI model generates a new document draft. The input consists of historical document data and prompt messages, and the output is the generated document draft.

[0346] Step 4:

[0347] Analysis of user emotions using an emotion engine

[0348] An emotion engine built into the device generates emotional information by analyzing the user's facial expressions and voice tone in real time. This emotional information is sent to a server and used to adjust documents. The input is the user's biometric information, and the output is the analyzed emotional state data.

[0349] Step 5:

[0350] Server-based document representation adjustment

[0351] The server adjusts the wording of the generated document draft based on emotional information. For example, if the user is feeling anxious, the document is rewritten to a more friendly tone. The input is the generated document draft and emotional state data, and the output is the adjusted document.

[0352] Step 6:

[0353] User feedback and final confirmation

[0354] The revised document is returned to the user's terminal, where the user reviews the contract. Additional revisions can be made if necessary. The formal contract is finalized only when the user is satisfied with the document's content. The input is the revised document, and the output is the user's feedback and final document approval.

[0355] (Application Example 2)

[0356] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0357] When drafting contracts and other documents, users often experience anxiety and tension due to the complexity of the content or unclear wording. Such emotions can impair the efficiency of the entire contracting process and increase the likelihood of misunderstandings and the need for revisions. This invention aims to make the document creation process more user-friendly and stress-free by understanding the user's emotional state in real time and appropriately adjusting the content and tone of the document.

[0358] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0359] In this invention, the server includes means for accessing a past document information recording device and analyzing the data of the information recording device to extract feature information; means for executing a machine learning model to generate a draft of a corresponding document based on conditions entered by the user; and means for using an emotion analysis device to recognize the user's emotional state and adjust the document expression. This enables efficient and highly satisfying contract creation while providing optimal document suggestions that respond to the user's emotions, thereby reducing anxiety and misunderstandings.

[0360] An "information recording device" is a system for storing and managing data from past contracts and related documents, and for accessing and analyzing it as needed.

[0361] A "machine learning model" is a model that has learned from past cases to generate draft contracts, and it is a technology that proposes the optimal document according to the conditions.

[0362] A "user display device" is a device that provides an interface that allows users to review the generated draft of a contract and make revisions as needed.

[0363] An "emotion analysis device" is a device that analyzes the tone of a user's voice and input behavior to grasp their emotions and stress levels in real time, and adjusts the wording of documents based on that analysis.

[0364] "Supplementary information" refers to a group of incidental information, such as dates and metadata, related to the contract details and counterparty information, which clarifies the context of the document.

[0365] "Format" refers to the general term for document formats and writing styles that are conventionally used within an organization or industry.

[0366] "Expression patterns" are types of wording and phrasing commonly used within a particular organization or culture, and are utilized to enhance the consistency and credibility of documents.

[0367] This system is designed to generate optimal contracts tailored to the user's emotions. The server performs the following main functions: First, it uses an information recording device to access past document data, such as contracts, and analyzes it to extract characteristic information. Next, it uses a machine learning model to generate a draft document based on the conditions entered by the user. This document generation process utilizes a model learned from past cases, enabling it to suggest the most suitable document.

[0368] Furthermore, the emotion analysis device analyzes the user's voice tone and input speed in real time to recognize the user's emotional state. This emotional information is used to adjust the document's expression, enabling flexible document generation that reduces the user's anxiety and tension. A draft of the generated document is presented to the user through a user display device, and the user can make revisions as needed. The revised document is then used for further training, contributing to the improvement of the machine learning model's accuracy.

[0369] Specifically, a speech recognition system (such as the Google Speech-to-Text API) is used to convert what the user says into text, and an emotion recognition API, combined with OpenCV, is used to estimate the user's emotions. This allows the system to, for example, if a user wants to create a mortgage contract, sense their anxiety and guide them in a gentle tone, saying, "Buying a home is a big decision, so we've summarized the necessary information concisely. Please let us know if you have any questions."

[0370] An example of a prompt message is: "If the user is nervous, provide explanations in a concise and friendly tone. Highlight key points and provide specific examples as needed."

[0371] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0372] Step 1:

[0373] The server retrieves historical document data from the information recording device. The input consists of user-specified criteria. Based on these criteria, the server searches the database and extracts relevant document data. The output is document data containing specific contract details and counterparty information.

[0374] Step 2:

[0375] The server analyzes the document data extracted using a machine learning model and extracts feature information. The input is the document data obtained in step 1. The server analyzes the data and identifies common patterns and frequently occurring expressions in the contracts. The output is a list of feature information for document generation.

[0376] Step 3:

[0377] The terminal receives condition input from the user and sends it to the server. The input consists of requirements and special notes for the contract that the user wants to generate. The server receives this and inputs it into the generation AI model.

[0378] Step 4:

[0379] The server runs a generative AI model to generate a draft document based on the user's conditions. The input consists of the user's conditions and the feature information obtained in step 2. The AI ​​model uses these to generate the optimal document draft. The output is the draft document for the user to review.

[0380] Step 5:

[0381] An emotion analysis device on the terminal senses the user's voice tone and input speed in real time. Input consists of the user's voice information and input from the interface. Based on this information, the emotion analysis device infers the user's emotional state. Output is the user's emotional state data.

[0382] Step 6:

[0383] The server adjusts the wording of the draft document generated based on the emotional state data. The inputs are the draft document from step 4 and the emotional state data from step 5. The tone and explanation of the document are adjusted according to the emotion. The output is the final draft document presented to the user.

[0384] Step 7:

[0385] The user reviews the final draft document on the terminal and makes revisions as needed. The input is the draft document adjusted in step 6. The user reviews this and makes changes or additions to the content. The output is the final version of the document with the user's revisions.

[0386] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0387] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0388] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0389] [Third Embodiment]

[0390] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0391] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0392] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0393] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0394] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0395] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0396] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0397] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0398] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0399] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0400] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0401] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0402] The contract draft generation system of the present invention creates a draft contract based on a database of past documents using conditions entered by the user, and reflects the company's internal formatting and expression characteristics.

[0403] The server first stores past contracts accumulated within the company into a database. This database contains detailed information about each contract, including the contracting party, date information, and related metadata. This allows the server to quickly search and extract various characteristics of each contract.

[0404] Users access a contract creation interface through their device and enter necessary information such as the name of the contracting party, contract period, and product type. The device interface is intuitive and designed to allow users to smoothly provide the necessary information.

[0405] When the server receives input data from a user, it uses an artificial intelligence model to analyze similar past contracts and generate a draft of the corresponding contract. This AI model is retrained at regular intervals using machine learning techniques, ensuring that it is always up-to-date with the company's formatting and expression trends.

[0406] The generated draft is presented to the user via a terminal, allowing the user to review and make revisions. The user then shares the draft with legal staff and other relevant departments to make necessary adjustments. Finally, the revised contract is uploaded to the server and recorded in the database.

[0407] This revised contract will be used by the server as new training data to improve the accuracy of future draft generation. For example, in the case of a sales contract for supplying electronic components, if the user inputs information such as "electronic components," "1-year contract," and "Company A," the server will generate a draft based on the past contract that best matches these criteria, and create the optimal contract.

[0408] Thus, the system of the present invention can significantly streamline the entire contract process by rapidly generating contracts and streamlining the revision process.

[0409] The following describes the processing flow.

[0410] Step 1:

[0411] The server collects contracts previously created within the company and stores them in a database in digital format. This database will include the content of the contract, the contracting party, the contract date, and related metadata.

[0412] Step 2:

[0413] The server preprocesses the contract data in the database and converts it into a format suitable for machine learning. In this process, OCR technology is used to convert paper contracts into text data, and natural language processing such as tokenization is performed as needed.

[0414] Step 3:

[0415] Users access a contract creation interface using their device and input basic contract information, such as the contracting party, contract period, and contract type. The interface is designed to allow users to intuitively input information.

[0416] Step 4:

[0417] The server receives input data provided by the user and begins searching the database for similar contracts based on this data. It extracts the features of highly relevant contracts, and the artificial intelligence model then operates based on these features.

[0418] Step 5:

[0419] The server uses a machine learning model to generate appropriate contract drafts based on historical similar contract data. This model reflects the company's specific format and style, and the generated drafts are prepared for user approval and revision.

[0420] Step 6:

[0421] The user receives the draft contract generated on their device and makes revisions as needed in consultation with legal personnel and other stakeholders. The revised version is then sent back to the server for further adjustments toward finalization.

[0422] Step 7:

[0423] The server stores the revised contracts submitted by users in a database and uses this data to retrain the artificial intelligence model. By adding new contract data, the accuracy of subsequent draft generation will be improved.

[0424] (Example 1)

[0425] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0426] There is a need to enable the efficient generation and editing of documents, thereby speeding up operations and improving accuracy. In particular, a challenge is to quickly create drafts of new documents by utilizing a large number of past documents and to improve their accuracy.

[0427] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0428] In this invention, the server includes means for accessing a historical electronic database and analyzing the electronic data to extract characteristic information; means for executing a generative AI model to analyze similar past records based on conditions entered by the user and generate a draft of the corresponding record; and means for providing the generated draft of the record to an information terminal and enabling editing by the user. This makes it possible to generate highly accurate drafts based on a large number of past documents and to quickly modify them.

[0429] An "electronic database" is a form of information aggregation that systematically stores various types of electronic data accumulated in the past, making it accessible and searchable.

[0430] "Feature information" refers to key characteristics or patterns extracted from a specific dataset or document that are used to identify similar data.

[0431] A "generative AI model" is a collection of algorithms that use artificial intelligence to generate new data and information by analyzing and learning from past data, and then generating appropriate output based on the results.

[0432] An "information terminal" is an electronic device used by a user to input, output, or process data, and specifically includes computers and smartphones.

[0433] "Training data" refers to a collection of empirical data used by artificial intelligence models to learn the patterns and rules necessary to generate new information.

[0434] "Style" refers to a specific form or layout that is consistently used within a particular organization or environment, and represents a standardized structure in documents and communications.

[0435] "Expression patterns" refer to specific phrases and styles used in communication, particularly in document creation, within a particular organization or culture.

[0436] The system of this invention enables users to efficiently generate and edit documents. This system consists of a server and terminals, each with a specific role. Specifically, it has the following configuration and operation.

[0437] The server first stores past contracts and related documents accumulated within the organization into an electronic database. This requires the use of database management software to organize and store detailed information and related metadata for each document. For this purpose, computer hardware with high processing power is recommended.

[0438] Users access a document creation interface using an information terminal. This interface is designed for intuitive operation, allowing users to easily input contract terms and other necessary information. The terminal typically consists of a personal computer or tablet device.

[0439] Upon receiving user input, the server uses a generative AI model to analyze similar past records and generate a draft of a new document. The generative AI model learns organizational-specific styles and expression patterns, enabling it to create documents that reflect the latest information. The necessary software includes machine learning frameworks and natural language processing libraries.

[0440] The generated document is presented to the user on their device, and the user can edit it. The edited document is then uploaded back to the server, and the AI ​​model used to generate the document is automatically retrained based on it. This process continuously improves the efficiency and accuracy of similar tasks.

[0441] For example, when creating a sales contract for electronic components, the user inputs basic conditions such as "electronic components," "1-year contract," and "Company B." The server analyzes past records that best match these conditions and uses that data to generate an optimal draft.

[0442] An example of a prompt might be: "Draft a sales contract based on the following conditions: Contract subject: electronic components, Contract period: 1 year, Contracting party: Company B." Using this prompt allows the AI ​​generation model to generate documents accurately and efficiently.

[0443] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0444] Step 1:

[0445] The server stores historical document data accumulated within the company into an electronic database. Input includes detailed digital data of contracts and documents. Based on this, the server analyzes the content of each document, extracts characteristic information, and stores it in an organized format. Specifically, it uses database management software to classify the data into categories, enabling efficient searching.

[0446] Step 2:

[0447] The user accesses the document creation interface using an information terminal. Inputs include contract terms, such as the contracting party and duration. The user enters this information into the interface. Specific operations include selecting from dropdown menus and directly entering text into text fields.

[0448] Step 3:

[0449] The terminal sends the entered conditions to the server. Here, the input information is packetized and transferred to the server via a secure protocol. As output, data in a format easily received by the server is generated.

[0450] Step 4:

[0451] The server utilizes a generative AI model to search the database for similar past documents that match the user's criteria and performs analysis. Input consists of user-provided criteria and historical document data. Output is a draft document suitable for the criteria. Specific operations include analysis processing using machine learning algorithms.

[0452] Step 5:

[0453] The generated draft is presented to the user via the terminal. The output is a draft contract that the user can review and modify. The user can make necessary changes through the terminal's interface. Specific operations include editing text and adding comments.

[0454] Step 6:

[0455] The document, after the user has finished editing it, is uploaded back to the server. The input is the edited document data. The server takes this as training data and uses it to improve the performance of the generative AI model. Specific actions include adding documents to the database and the model retraining process.

[0456] (Application Example 1)

[0457] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0458] With the increase in online transactions and digital contracts, the creation of contracts and terms of service is becoming more complex. Traditional methods are time-consuming, hindering the rapid progress of transactions. Furthermore, accurately drafting documents based on company-specific formats and expressions is not easy. In this situation, the need for efficient and accurate document generation systems is growing.

[0459] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0460] In this invention, the server includes means for accessing a historical data database and analyzing the data to extract characteristic information; means for executing an artificial intelligence model for generating a draft of a corresponding document based on conditions entered by the user; and means for providing the generated draft document to an endpoint device and enabling the user to make modifications. This enables the rapid and accurate generation of contracts, including the creation of terms and conditions for online transactions.

[0461] A "data database" is an information system that systematically stores and searches / analyzes data accumulated in the past.

[0462] "Feature information" refers to important attributes and patterns in extracted data or documents, and is an indicator used for analysis and learning.

[0463] An "endpoint device" refers to a device or terminal that a user directly operates or uses, and is capable of displaying or inputting information.

[0464] An "artificial intelligence model" is an algorithm or system that uses machine learning and data analysis techniques to make judgments and predictions based on input information.

[0465] "Online transactions" refer to a general term for commercial transactions and service contracts conducted via the internet, and are a form of transaction that is completed electronically.

[0466] "Format" refers to the layout, style, and other formatting elements used when creating a document, and is a standard for providing a unified format for expression.

[0467] A "business" refers to commercial activities or projects carried out based on specific purposes or goals, and is an activity aimed at providing value in the market.

[0468] The system that implements this application example uses an artificial intelligence model to access a historical data database and generate draft contracts and terms of service. The server is located in the cloud and runs the AI ​​model, which utilizes Python and TensorFlow. TensorFlow is a platform for data analysis and training, and it is responsible for extracting feature information from historical data and generating draft contracts.

[0469] Users utilize their smartphones as terminals, entering the necessary contract terms through an intuitive interface. The smartphone acts as an endpoint device, sending the input data to a server and receiving a draft of the generated document. Throughout this process, a web application built with Django serves as the user interface, providing a smooth user experience.

[0470] As a concrete example, if a user enters information such as "e-book sales," "3-year contract," and "publisher" on their smartphone, the server analyzes transaction data related to e-books, generates an optimal draft contract, and sends it to the device. In this process, the artificial intelligence model utilizes past similar transaction information to provide a draft that matches the company's specific format and expression. Furthermore, the revised document is used again as training data, contributing to improved accuracy in future draft generation.

[0471] An example of a prompt message might be: "Use the contract draft generation system to create a contract that meets the following conditions: Conditions: Contract type: ebook sales, Contract period: 3 years, Counterparty: Publisher." This system configuration enables the rapid and accurate creation of digital contracts.

[0472] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0473] Step 1:

[0474] The device (smartphone) receives the necessary contract conditions (contract type, duration, trading partner, etc.) from the user as input. This input is done through a form in the web application. The information entered by the user is then prepared by a Django-based frontend to be sent to the server in JSON format.

[0475] Step 2:

[0476] The server analyzes the received input data and searches its historical data database. Based on the entered conditions, it extracts the most relevant data. This process uses SQL queries to retrieve similar contract information from the database (e.g., PostgreSQL) and identify the dataset that most closely matches the input.

[0477] Step 3:

[0478] The server runs a pre-trained generative AI model using TensorFlow based on the identified similar data. The model generates a draft contract that best matches the user's input based on the extracted feature information. At this stage, natural language generation and document structure optimization are performed, and the generated draft is formatted as a provisional contract.

[0479] Step 4:

[0480] The generated draft contract is sent from the server to the terminal as output. The terminal displays the draft to the user and provides an interface that allows for additional modifications and adjustments. This interface allows the user to easily review the draft and make necessary corrections.

[0481] Step 5:

[0482] After the user completes the corrections, the device sends the corrected document back to the server. The server receives this corrected data and uses it to retrain the generating AI model. New data points are extracted from the corrections and incorporated into the training process to improve the model's accuracy.

[0483] This series of processes enables the rapid and efficient generation of draft contracts and allows for easy modification by the user.

[0484] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0485] This invention is a system that aims to improve the user experience by combining an emotion engine with an existing contract creation system. This system consists of a database of past documents, an artificial intelligence model, and an emotion engine.

[0486] The server manages historical document data accumulated within the company and quickly searches and extracts information based on user input, including metadata such as contract details, counterparty information, and date information. This allows artificial intelligence models that generate draft documents based on similar past contracts to easily produce optimal documents.

[0487] The user accesses the contract creation screen via their device and enters the necessary conditions. During this process, an emotion engine is installed in the device, recognizing the user's emotional state in real time and transmitting that information to the server. Emotion recognition is performed by analyzing the user's facial expressions, voice tone, and input speed, enabling natural interaction.

[0488] The server adjusts the expression of the generated document based on the emotional information sent from the emotion engine. For example, if the user is feeling anxious, the document's tone can be changed to a more friendly one, or important points can be explained in more detail. This reduces user stress and supports efficient contract creation.

[0489] As a concrete example, when a user creates a new contract, the system uses an emotion engine to detect the user's tension and anxiety. As a result, the server softens the tone of the document and includes more examples, making it easier for the user to review the contract with confidence. This approach reduces the number of revisions the user needs to make to the final document, allowing the contract process to proceed smoothly.

[0490] Thus, the system of the present invention incorporates the user's emotions throughout the entire process, from document generation to revision and finalization, ultimately achieving the creation of high-quality and user-friendly contracts.

[0491] The following describes the processing flow.

[0492] Step 1:

[0493] Users access a contract creation interface through their device and enter the necessary information. The interface includes fields such as the name of the contracting party, the contract period, and detailed contract terms, and is designed for quick user input.

[0494] Step 2:

[0495] The emotion engine built into the device analyzes the user's facial expressions and voice tone in real time while they are inputting data, and evaluates their emotional state. This data is sent from the device to the server as emotion parameters.

[0496] Step 3:

[0497] The server references past contract documents in the database and searches for the most similar contract that best matches the user's input criteria. It extracts feature information from the found similar contracts and uses an AI model to generate a new draft contract.

[0498] Step 4:

[0499] The server adjusts the wording of the generated contract draft, taking into account the emotional parameters obtained by the emotion engine. For example, if the user is feeling stressed, the wording is simplified and adjusted to make it easier to read.

[0500] Step 5:

[0501] The generated, revised draft contract is sent to the user's device. The user can review the draft on their device and make revisions as needed. Once the user has finished reviewing and revising the contract, they send it to the server for finalization.

[0502] Step 6:

[0503] The server stores the revised final contract in a database and uses this data as a dataset for subsequent generation and learning processes. It also accumulates data from the emotion engine and continues to improve the emotion recognition algorithm to a higher accuracy.

[0504] (Example 2)

[0505] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0506] In information generation, there is a challenge in creating user-friendly and high-quality documents because there is no document generation process that reflects the user's emotional state. Furthermore, because the generated documents are not presented in a way that suits the user's emotional state, it can cause stress.

[0507] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0508] In this invention, the server includes means for accessing past information sets and analyzing the information to extract characteristic information; means for executing an artificial intelligence model for generating draft information corresponding to conditions entered by the user; and means for analyzing the user's emotional state and adjusting the expression of the generated information based on that information. This makes it possible to create appropriate and high-quality documents while taking the user's emotional state into consideration.

[0509] An "information set" is a collection of data accumulated through past transactions and exchanges, and includes contract details, counterparty information, date information, and related incidental information.

[0510] "Characteristic information" refers to distinctive data extracted from a set of information, used to identify and analyze important elements in document generation.

[0511] "User-entered conditions" refer to the requirements and specifications that users set when creating contracts or other documents, and serve as guidelines in the document generation process.

[0512] An "artificial intelligence model" is a learning algorithm that operates using a computer, and is a means of automatically generating results and predictions based on input data.

[0513] "User's emotional state" refers to the psychological situation or mood estimated from the user's facial expressions, tone of voice, typing speed, etc.

[0514] "Means of adjusting expression" refer to processes and methods for modifying the tone and phrasing of a generated document to match the user's emotional state.

[0515] This invention is a system aimed at improving the user experience in the document generation process. This system consists of a server, terminals, and artificial intelligence technology.

[0516] The server manages data stored in past information sets and has the function of extracting necessary information based on conditions sent from the user's terminal. This data includes supplementary information such as contract details, counterparty information, and date information. Based on past document examples, the server sends prompt messages to the generation AI model. For example, a prompt message in the format of "The contract start date is November 1, 2023, generate a draft document based on the content."

[0517] The terminal provides an interface for users to access the contract creation screen and input the necessary information. The terminal has an emotion engine built in that analyzes the user's facial expressions, voice tone, input speed, etc., to recognize their emotional state in real time. This emotional information is sent to a server and used to adjust the wording of the document.

[0518] The generation AI model automatically generates a draft document based on prompts from the server. The generated document is then adjusted to take into account the user's emotional state; for example, if tension is detected, the tone is softened. Through this process, users can perform final checks and revisions of the document without feeling stressed, allowing the entire process to proceed efficiently.

[0519] Specifically, when a user is creating a new contract, if the emotion engine detects the user's anxiety, the server will make the document more user-friendly and include numerous concrete examples to make it easier for the user to review and understand the content with confidence. In this way, the number of revisions the user needs to make to the final document can be reduced, helping to streamline the contract process.

[0520] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0521] Step 1:

[0522] User input processing

[0523] The user accesses the contract creation screen on their device and enters necessary information such as contract details, counterparty information, and date information. This input data is sent from the device to the server. At this stage, the specific input consists of the conditions set by the user, and the output is the transmission of data to the server.

[0524] Step 2:

[0525] Server-based database search

[0526] The server searches a historical data set based on the user's input. This process executes database queries to quickly extract relevant data regarding contract details and counterparty information. The input is the user's criteria data, and the output is filtered historical document data.

[0527] Step 3:

[0528] Generating draft documents using generative AI models

[0529] The server, while referencing filtered historical document data, sends prompt messages to the generative AI model. These prompt messages contain conditions in text format. Based on these prompts, the generative AI model generates a new document draft. The input consists of historical document data and prompt messages, and the output is the generated document draft.

[0530] Step 4:

[0531] Analysis of user emotions using an emotion engine

[0532] An emotion engine built into the device generates emotional information by analyzing the user's facial expressions and voice tone in real time. This emotional information is sent to a server and used to adjust documents. The input is the user's biometric information, and the output is the analyzed emotional state data.

[0533] Step 5:

[0534] Server-based document representation adjustment

[0535] The server adjusts the wording of the generated document draft based on emotional information. For example, if the user is feeling anxious, the document is rewritten to a more friendly tone. The input is the generated document draft and emotional state data, and the output is the adjusted document.

[0536] Step 6:

[0537] User feedback and final confirmation

[0538] The revised document is returned to the user's terminal, where the user reviews the contract. Additional revisions can be made if necessary. The formal contract is finalized only when the user is satisfied with the document's content. The input is the revised document, and the output is the user's feedback and final document approval.

[0539] (Application Example 2)

[0540] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0541] When drafting contracts and other documents, users often experience anxiety and tension due to the complexity of the content or unclear wording. Such emotions can impair the efficiency of the entire contracting process and increase the likelihood of misunderstandings and the need for revisions. This invention aims to make the document creation process more user-friendly and stress-free by understanding the user's emotional state in real time and appropriately adjusting the content and tone of the document.

[0542] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0543] In this invention, the server includes means for accessing a past document information recording device and analyzing the data of the information recording device to extract feature information; means for executing a machine learning model to generate a draft of a corresponding document based on conditions entered by the user; and means for using an emotion analysis device to recognize the user's emotional state and adjust the document expression. This enables efficient and highly satisfying contract creation while providing optimal document suggestions that respond to the user's emotions, thereby reducing anxiety and misunderstandings.

[0544] An "information recording device" is a system for storing and managing data from past contracts and related documents, and for accessing and analyzing it as needed.

[0545] A "machine learning model" is a model that has learned from past cases to generate draft contracts, and it is a technology that proposes the optimal document according to the conditions.

[0546] A "user display device" is a device that provides an interface that allows users to review the generated draft of a contract and make revisions as needed.

[0547] An "emotion analysis device" is a device that analyzes the tone of a user's voice and input behavior to grasp their emotions and stress levels in real time, and adjusts the wording of documents based on that analysis.

[0548] "Supplementary information" refers to a group of incidental information, such as dates and metadata, related to the contract details and counterparty information, which clarifies the context of the document.

[0549] "Format" refers to the general term for document formats and writing styles that are conventionally used within an organization or industry.

[0550] "Expression patterns" are types of wording and phrasing commonly used within a particular organization or culture, and are utilized to enhance the consistency and credibility of documents.

[0551] This system is designed to generate optimal contracts tailored to the user's emotions. The server performs the following main functions: First, it uses an information recording device to access past document data, such as contracts, and analyzes it to extract characteristic information. Next, it uses a machine learning model to generate a draft document based on the conditions entered by the user. This document generation process utilizes a model learned from past cases, enabling it to suggest the most suitable document.

[0552] Furthermore, the emotion analysis device analyzes the user's voice tone and input speed in real time to recognize the user's emotional state. This emotional information is used to adjust the document's expression, enabling flexible document generation that reduces the user's anxiety and tension. A draft of the generated document is presented to the user through a user display device, and the user can make revisions as needed. The revised document is then used for further training, contributing to the improvement of the machine learning model's accuracy.

[0553] Specifically, a speech recognition system (such as the Google Speech-to-Text API) is used to convert what the user says into text, and an emotion recognition API, combined with OpenCV, is used to estimate the user's emotions. This allows the system to, for example, if a user wants to create a mortgage contract, sense their anxiety and guide them in a gentle tone, saying, "Buying a home is a big decision, so we've summarized the necessary information concisely. Please let us know if you have any questions."

[0554] An example of a prompt message is: "If the user is nervous, provide explanations in a concise and friendly tone. Highlight key points and provide specific examples as needed."

[0555] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0556] Step 1:

[0557] The server retrieves historical document data from the information recording device. The input consists of user-specified criteria. Based on these criteria, the server searches the database and extracts relevant document data. The output is document data containing specific contract details and counterparty information.

[0558] Step 2:

[0559] The server analyzes the document data extracted using a machine learning model and extracts feature information. The input is the document data obtained in step 1. The server analyzes the data and identifies common patterns and frequently occurring expressions in the contracts. The output is a list of feature information for document generation.

[0560] Step 3:

[0561] The terminal receives condition input from the user and sends it to the server. The input consists of requirements and special notes for the contract that the user wants to generate. The server receives this and inputs it into the generation AI model.

[0562] Step 4:

[0563] The server runs a generative AI model to generate a draft document based on the user's conditions. The input consists of the user's conditions and the feature information obtained in step 2. The AI ​​model uses these to generate the optimal document draft. The output is the draft document for the user to review.

[0564] Step 5:

[0565] An emotion analysis device on the terminal senses the user's voice tone and input speed in real time. Input consists of the user's voice information and input from the interface. Based on this information, the emotion analysis device infers the user's emotional state. Output is the user's emotional state data.

[0566] Step 6:

[0567] The server adjusts the wording of the draft document generated based on the emotional state data. The inputs are the draft document from step 4 and the emotional state data from step 5. The tone and explanation of the document are adjusted according to the emotion. The output is the final draft document presented to the user.

[0568] Step 7:

[0569] The user reviews the final draft document on the terminal and makes revisions as needed. The input is the draft document adjusted in step 6. The user reviews this and makes changes or additions to the content. The output is the final version of the document with the user's revisions.

[0570] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0571] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0572] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0573] [Fourth Embodiment]

[0574] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0575] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0576] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0577] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0578] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0579] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0580] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0581] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0582] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0583] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0584] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0585] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0586] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0587] The contract draft generation system of the present invention creates a draft contract based on a database of past documents using conditions entered by the user, and reflects the company's internal formatting and expression characteristics.

[0588] The server first stores past contracts accumulated within the company into a database. This database contains detailed information about each contract, including the contracting party, date information, and related metadata. This allows the server to quickly search and extract various characteristics of each contract.

[0589] Users access a contract creation interface through their device and enter necessary information such as the name of the contracting party, contract period, and product type. The device interface is intuitive and designed to allow users to smoothly provide the necessary information.

[0590] When the server receives input data from a user, it uses an artificial intelligence model to analyze similar past contracts and generate a draft of the corresponding contract. This AI model is retrained at regular intervals using machine learning techniques, ensuring that it is always up-to-date with the company's formatting and expression trends.

[0591] The generated draft is presented to the user via a terminal, allowing the user to review and make revisions. The user then shares the draft with legal staff and other relevant departments to make necessary adjustments. Finally, the revised contract is uploaded to the server and recorded in the database.

[0592] This revised contract will be used by the server as new training data to improve the accuracy of future draft generation. For example, in the case of a sales contract for supplying electronic components, if the user inputs information such as "electronic components," "1-year contract," and "Company A," the server will generate a draft based on the past contract that best matches these criteria, and create the optimal contract.

[0593] Thus, the system of the present invention can significantly streamline the entire contract process by rapidly generating contracts and streamlining the revision process.

[0594] The following describes the processing flow.

[0595] Step 1:

[0596] The server collects contracts previously created within the company and stores them in a database in digital format. This database will include the content of the contract, the contracting party, the contract date, and related metadata.

[0597] Step 2:

[0598] The server preprocesses the contract data in the database and converts it into a format suitable for machine learning. In this process, OCR technology is used to convert paper contracts into text data, and natural language processing such as tokenization is performed as needed.

[0599] Step 3:

[0600] Users access a contract creation interface using their device and input basic contract information, such as the contracting party, contract period, and contract type. The interface is designed to allow users to intuitively input information.

[0601] Step 4:

[0602] The server receives input data provided by the user and begins searching the database for similar contracts based on this data. It extracts the features of highly relevant contracts, and the artificial intelligence model then operates based on these features.

[0603] Step 5:

[0604] The server uses a machine learning model to generate appropriate contract drafts based on historical similar contract data. This model reflects the company's specific format and style, and the generated drafts are prepared for user approval and revision.

[0605] Step 6:

[0606] The user receives the draft contract generated on their device and makes revisions as needed in consultation with legal personnel and other stakeholders. The revised version is then sent back to the server for further adjustments toward finalization.

[0607] Step 7:

[0608] The server stores the revised contracts submitted by users in a database and uses this data to retrain the artificial intelligence model. By adding new contract data, the accuracy of subsequent draft generation will be improved.

[0609] (Example 1)

[0610] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0611] There is a need to enable the efficient generation and editing of documents, thereby speeding up operations and improving accuracy. In particular, a challenge is to quickly create drafts of new documents by utilizing a large number of past documents and to improve their accuracy.

[0612] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0613] In this invention, the server includes means for accessing a historical electronic database and analyzing the electronic data to extract characteristic information; means for executing a generative AI model to analyze similar past records based on conditions entered by the user and generate a draft of the corresponding record; and means for providing the generated draft of the record to an information terminal and enabling editing by the user. This makes it possible to generate highly accurate drafts based on a large number of past documents and to quickly modify them.

[0614] An "electronic database" is a form of information aggregation that systematically stores various types of electronic data accumulated in the past, making it accessible and searchable.

[0615] "Feature information" refers to key characteristics or patterns extracted from a specific dataset or document that are used to identify similar data.

[0616] A "generative AI model" is a collection of algorithms that use artificial intelligence to generate new data and information by analyzing and learning from past data, and then generating appropriate output based on the results.

[0617] An "information terminal" is an electronic device used by a user to input, output, or process data, and specifically includes computers and smartphones.

[0618] "Training data" refers to a collection of empirical data used by artificial intelligence models to learn the patterns and rules necessary to generate new information.

[0619] "Style" refers to a specific form or layout that is consistently used within a particular organization or environment, and represents a standardized structure in documents and communications.

[0620] "Expression patterns" refer to specific phrases and styles used in communication, particularly in document creation, within a particular organization or culture.

[0621] The system of this invention enables users to efficiently generate and edit documents. This system consists of a server and terminals, each with a specific role. Specifically, it has the following configuration and operation.

[0622] The server first stores past contracts and related documents accumulated within the organization into an electronic database. This requires the use of database management software to organize and store detailed information and related metadata for each document. For this purpose, computer hardware with high processing power is recommended.

[0623] Users access a document creation interface using an information terminal. This interface is designed for intuitive operation, allowing users to easily input contract terms and other necessary information. The terminal typically consists of a personal computer or tablet device.

[0624] Upon receiving user input, the server uses a generative AI model to analyze similar past records and generate a draft of a new document. The generative AI model learns organizational-specific styles and expression patterns, enabling it to create documents that reflect the latest information. The necessary software includes machine learning frameworks and natural language processing libraries.

[0625] The generated document is presented to the user on their device, and the user can edit it. The edited document is then uploaded back to the server, and the AI ​​model used to generate the document is automatically retrained based on it. This process continuously improves the efficiency and accuracy of similar tasks.

[0626] For example, when creating a sales contract for electronic components, the user inputs basic conditions such as "electronic components," "1-year contract," and "Company B." The server analyzes past records that best match these conditions and uses that data to generate an optimal draft.

[0627] An example of a prompt might be: "Draft a sales contract based on the following conditions: Contract subject: electronic components, Contract period: 1 year, Contracting party: Company B." Using this prompt allows the AI ​​generation model to generate documents accurately and efficiently.

[0628] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0629] Step 1:

[0630] The server stores historical document data accumulated within the company into an electronic database. Input includes detailed digital data of contracts and documents. Based on this, the server analyzes the content of each document, extracts characteristic information, and stores it in an organized format. Specifically, it uses database management software to classify the data into categories, enabling efficient searching.

[0631] Step 2:

[0632] The user accesses the document creation interface using an information terminal. Inputs include contract terms, such as the contracting party and duration. The user enters this information into the interface. Specific operations include selecting from dropdown menus and directly entering text into text fields.

[0633] Step 3:

[0634] The terminal sends the entered conditions to the server. Here, the input information is packetized and transferred to the server via a secure protocol. As output, data in a format easily received by the server is generated.

[0635] Step 4:

[0636] The server utilizes a generative AI model to search the database for similar past documents that match the user's criteria and performs analysis. Input consists of user-provided criteria and historical document data. Output is a draft document suitable for the criteria. Specific operations include analysis processing using machine learning algorithms.

[0637] Step 5:

[0638] The generated draft is presented to the user via the terminal. The output is a draft contract that the user can review and modify. The user can make necessary changes through the terminal's interface. Specific operations include editing text and adding comments.

[0639] Step 6:

[0640] The document, after the user has finished editing it, is uploaded back to the server. The input is the edited document data. The server takes this as training data and uses it to improve the performance of the generative AI model. Specific actions include adding documents to the database and the model retraining process.

[0641] (Application Example 1)

[0642] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0643] With the increase in online transactions and digital contracts, the creation of contracts and terms of service is becoming more complex. Traditional methods are time-consuming, hindering the rapid progress of transactions. Furthermore, accurately drafting documents based on company-specific formats and expressions is not easy. In this situation, the need for efficient and accurate document generation systems is growing.

[0644] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0645] In this invention, the server includes means for accessing a historical data database and analyzing the data to extract characteristic information; means for executing an artificial intelligence model for generating a draft of a corresponding document based on conditions entered by the user; and means for providing the generated draft document to an endpoint device and enabling the user to make modifications. This enables the rapid and accurate generation of contracts, including the creation of terms and conditions for online transactions.

[0646] A "data database" is an information system that systematically stores and searches / analyzes data accumulated in the past.

[0647] "Feature information" refers to important attributes and patterns in extracted data or documents, and is an indicator used for analysis and learning.

[0648] An "endpoint device" refers to a device or terminal that a user directly operates or uses, and is capable of displaying or inputting information.

[0649] An "artificial intelligence model" is an algorithm or system that uses machine learning and data analysis techniques to make judgments and predictions based on input information.

[0650] "Online transactions" refer to a general term for commercial transactions and service contracts conducted via the internet, and are a form of transaction that is completed electronically.

[0651] "Format" refers to the layout, style, and other formatting elements used when creating a document, and is a standard for providing a unified format for expression.

[0652] A "business" refers to commercial activities or projects carried out based on specific purposes or goals, and is an activity aimed at providing value in the market.

[0653] The system that implements this application example uses an artificial intelligence model to access a historical data database and generate draft contracts and terms of service. The server is located in the cloud and runs the AI ​​model, which utilizes Python and TensorFlow. TensorFlow is a platform for data analysis and training, and it is responsible for extracting feature information from historical data and generating draft contracts.

[0654] Users utilize their smartphones as terminals, entering the necessary contract terms through an intuitive interface. The smartphone acts as an endpoint device, sending the input data to a server and receiving a draft of the generated document. Throughout this process, a web application built with Django serves as the user interface, providing a smooth user experience.

[0655] As a concrete example, if a user enters information such as "e-book sales," "3-year contract," and "publisher" on their smartphone, the server analyzes transaction data related to e-books, generates an optimal draft contract, and sends it to the device. In this process, the artificial intelligence model utilizes past similar transaction information to provide a draft that matches the company's specific format and expression. Furthermore, the revised document is used again as training data, contributing to improved accuracy in future draft generation.

[0656] An example of a prompt message might be: "Use the contract draft generation system to create a contract that meets the following conditions: Conditions: Contract type: ebook sales, Contract period: 3 years, Counterparty: Publisher." This system configuration enables the rapid and accurate creation of digital contracts.

[0657] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0658] Step 1:

[0659] The device (smartphone) receives the necessary contract conditions (contract type, duration, trading partner, etc.) from the user as input. This input is done through a form in the web application. The information entered by the user is then prepared by a Django-based frontend to be sent to the server in JSON format.

[0660] Step 2:

[0661] The server analyzes the received input data and searches its historical data database. Based on the entered conditions, it extracts the most relevant data. This process uses SQL queries to retrieve similar contract information from the database (e.g., PostgreSQL) and identify the dataset that most closely matches the input.

[0662] Step 3:

[0663] The server runs a pre-trained generative AI model using TensorFlow based on the identified similar data. The model generates a draft contract that best matches the user's input based on the extracted feature information. At this stage, natural language generation and document structure optimization are performed, and the generated draft is formatted as a provisional contract.

[0664] Step 4:

[0665] The generated draft contract is sent from the server to the terminal as output. The terminal displays the draft to the user and provides an interface that allows for additional modifications and adjustments. This interface allows the user to easily review the draft and make necessary corrections.

[0666] Step 5:

[0667] After the user completes the corrections, the device sends the corrected document back to the server. The server receives this corrected data and uses it to retrain the generating AI model. New data points are extracted from the corrections and incorporated into the training process to improve the model's accuracy.

[0668] This series of processes enables the rapid and efficient generation of draft contracts and allows for easy modification by the user.

[0669] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0670] This invention is a system that aims to improve the user experience by combining an emotion engine with an existing contract creation system. This system consists of a database of past documents, an artificial intelligence model, and an emotion engine.

[0671] The server manages historical document data accumulated within the company and quickly searches and extracts information based on user input, including metadata such as contract details, counterparty information, and date information. This allows artificial intelligence models that generate draft documents based on similar past contracts to easily produce optimal documents.

[0672] The user accesses the contract creation screen via their device and enters the necessary conditions. During this process, an emotion engine is installed in the device, recognizing the user's emotional state in real time and transmitting that information to the server. Emotion recognition is performed by analyzing the user's facial expressions, voice tone, and input speed, enabling natural interaction.

[0673] The server adjusts the expression of the generated document based on the emotional information sent from the emotion engine. For example, if the user is feeling anxious, the document's tone can be changed to a more friendly one, or important points can be explained in more detail. This reduces user stress and supports efficient contract creation.

[0674] As a concrete example, when a user creates a new contract, the system uses an emotion engine to detect the user's tension and anxiety. As a result, the server softens the tone of the document and includes more examples, making it easier for the user to review the contract with confidence. This approach reduces the number of revisions the user needs to make to the final document, allowing the contract process to proceed smoothly.

[0675] Thus, the system of the present invention incorporates the user's emotions throughout the entire process, from document generation to revision and finalization, ultimately achieving the creation of high-quality and user-friendly contracts.

[0676] The following describes the processing flow.

[0677] Step 1:

[0678] Users access a contract creation interface through their device and enter the necessary information. The interface includes fields such as the name of the contracting party, the contract period, and detailed contract terms, and is designed for quick user input.

[0679] Step 2:

[0680] The emotion engine built into the device analyzes the user's facial expressions and voice tone in real time while they are inputting data, and evaluates their emotional state. This data is sent from the device to the server as emotion parameters.

[0681] Step 3:

[0682] The server references past contract documents in the database and searches for the most similar contract that best matches the user's input criteria. It extracts feature information from the found similar contracts and uses an AI model to generate a new draft contract.

[0683] Step 4:

[0684] The server adjusts the wording of the generated contract draft, taking into account the emotional parameters obtained by the emotion engine. For example, if the user is feeling stressed, the wording is simplified and adjusted to make it easier to read.

[0685] Step 5:

[0686] The generated, revised draft contract is sent to the user's device. The user can review the draft on their device and make revisions as needed. Once the user has finished reviewing and revising the contract, they send it to the server for finalization.

[0687] Step 6:

[0688] The server stores the revised final contract in a database and uses this data as a dataset for subsequent generation and learning processes. It also accumulates data from the emotion engine and continues to improve the emotion recognition algorithm to a higher accuracy.

[0689] (Example 2)

[0690] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0691] In information generation, there is a challenge in creating user-friendly and high-quality documents because there is no document generation process that reflects the user's emotional state. Furthermore, because the generated documents are not presented in a way that suits the user's emotional state, it can cause stress.

[0692] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0693] In this invention, the server includes means for accessing past information sets and analyzing the information to extract characteristic information; means for executing an artificial intelligence model for generating draft information corresponding to conditions entered by the user; and means for analyzing the user's emotional state and adjusting the expression of the generated information based on that information. This makes it possible to create appropriate and high-quality documents while taking the user's emotional state into consideration.

[0694] An "information set" is a collection of data accumulated through past transactions and exchanges, and includes contract details, counterparty information, date information, and related incidental information.

[0695] "Characteristic information" refers to distinctive data extracted from a set of information, used to identify and analyze important elements in document generation.

[0696] "User-entered conditions" refer to the requirements and specifications that users set when creating contracts or other documents, and serve as guidelines in the document generation process.

[0697] An "artificial intelligence model" is a learning algorithm that operates using a computer, and is a means of automatically generating results and predictions based on input data.

[0698] "User's emotional state" refers to the psychological situation or mood estimated from the user's facial expressions, tone of voice, typing speed, etc.

[0699] "Means of adjusting expression" refer to processes and methods for modifying the tone and phrasing of a generated document to match the user's emotional state.

[0700] This invention is a system aimed at improving the user experience in the document generation process. This system consists of a server, terminals, and artificial intelligence technology.

[0701] The server manages data stored in past information sets and has the function of extracting necessary information based on conditions sent from the user's terminal. This data includes supplementary information such as contract details, counterparty information, and date information. Based on past document examples, the server sends prompt messages to the generation AI model. For example, a prompt message in the format of "The contract start date is November 1, 2023, generate a draft document based on the content."

[0702] The terminal provides an interface for users to access the contract creation screen and input the necessary information. The terminal has an emotion engine built in that analyzes the user's facial expressions, voice tone, input speed, etc., to recognize their emotional state in real time. This emotional information is sent to a server and used to adjust the wording of the document.

[0703] The generation AI model automatically generates a draft document based on prompts from the server. The generated document is then adjusted to take into account the user's emotional state; for example, if tension is detected, the tone is softened. Through this process, users can perform final checks and revisions of the document without feeling stressed, allowing the entire process to proceed efficiently.

[0704] Specifically, when a user is creating a new contract, if the emotion engine detects the user's anxiety, the server will make the document more user-friendly and include numerous concrete examples to make it easier for the user to review and understand the content with confidence. In this way, the number of revisions the user needs to make to the final document can be reduced, helping to streamline the contract process.

[0705] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0706] Step 1:

[0707] User input processing

[0708] The user accesses the contract creation screen on their device and enters necessary information such as contract details, counterparty information, and date information. This input data is sent from the device to the server. At this stage, the specific input consists of the conditions set by the user, and the output is the transmission of data to the server.

[0709] Step 2:

[0710] Server-based database search

[0711] The server searches a historical data set based on the user's input. This process executes database queries to quickly extract relevant data regarding contract details and counterparty information. The input is the user's criteria data, and the output is filtered historical document data.

[0712] Step 3:

[0713] Generating draft documents using generative AI models

[0714] The server, while referencing filtered historical document data, sends prompt messages to the generative AI model. These prompt messages contain conditions in text format. Based on these prompts, the generative AI model generates a new document draft. The input consists of historical document data and prompt messages, and the output is the generated document draft.

[0715] Step 4:

[0716] Analysis of user emotions using an emotion engine

[0717] An emotion engine built into the device generates emotional information by analyzing the user's facial expressions and voice tone in real time. This emotional information is sent to a server and used to adjust documents. The input is the user's biometric information, and the output is the analyzed emotional state data.

[0718] Step 5:

[0719] Server-based document representation adjustment

[0720] The server adjusts the wording of the generated document draft based on emotional information. For example, if the user is feeling anxious, the document is rewritten to a more friendly tone. The input is the generated document draft and emotional state data, and the output is the adjusted document.

[0721] Step 6:

[0722] User feedback and final confirmation

[0723] The revised document is returned to the user's terminal, where the user reviews the contract. Additional revisions can be made if necessary. The formal contract is finalized only when the user is satisfied with the document's content. The input is the revised document, and the output is the user's feedback and final document approval.

[0724] (Application Example 2)

[0725] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0726] When drafting contracts and other documents, users often experience anxiety and tension due to the complexity of the content or unclear wording. Such emotions can impair the efficiency of the entire contracting process and increase the likelihood of misunderstandings and the need for revisions. This invention aims to make the document creation process more user-friendly and stress-free by understanding the user's emotional state in real time and appropriately adjusting the content and tone of the document.

[0727] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0728] In this invention, the server includes means for accessing a past document information recording device and analyzing the data of the information recording device to extract feature information; means for executing a machine learning model to generate a draft of a corresponding document based on conditions entered by the user; and means for using an emotion analysis device to recognize the user's emotional state and adjust the document expression. This enables efficient and highly satisfying contract creation while providing optimal document suggestions that respond to the user's emotions, thereby reducing anxiety and misunderstandings.

[0729] An "information recording device" is a system for storing and managing data from past contracts and related documents, and for accessing and analyzing it as needed.

[0730] A "machine learning model" is a model that has learned from past cases to generate draft contracts, and it is a technology that proposes the optimal document according to the conditions.

[0731] A "user display device" is a device that provides an interface that allows users to review the generated draft of a contract and make revisions as needed.

[0732] An "emotion analysis device" is a device that analyzes the tone of a user's voice and input behavior to grasp their emotions and stress levels in real time, and adjusts the wording of documents based on that analysis.

[0733] "Supplementary information" refers to a group of incidental information, such as dates and metadata, related to the contract details and counterparty information, which clarifies the context of the document.

[0734] "Format" refers to the general term for document formats and writing styles that are conventionally used within an organization or industry.

[0735] "Expression patterns" are types of wording and phrasing commonly used within a particular organization or culture, and are utilized to enhance the consistency and credibility of documents.

[0736] This system is designed to generate optimal contracts tailored to the user's emotions. The server performs the following main functions: First, it uses an information recording device to access past document data, such as contracts, and analyzes it to extract characteristic information. Next, it uses a machine learning model to generate a draft document based on the conditions entered by the user. This document generation process utilizes a model learned from past cases, enabling it to suggest the most suitable document.

[0737] Furthermore, the emotion analysis device analyzes the user's voice tone and input speed in real time to recognize the user's emotional state. This emotional information is used to adjust the document's expression, enabling flexible document generation that reduces the user's anxiety and tension. A draft of the generated document is presented to the user through a user display device, and the user can make revisions as needed. The revised document is then used for further training, contributing to the improvement of the machine learning model's accuracy.

[0738] Specifically, a speech recognition system (such as the Google Speech-to-Text API) is used to convert what the user says into text, and an emotion recognition API, combined with OpenCV, is used to estimate the user's emotions. This allows the system to, for example, if a user wants to create a mortgage contract, sense their anxiety and guide them in a gentle tone, saying, "Buying a home is a big decision, so we've summarized the necessary information concisely. Please let us know if you have any questions."

[0739] An example of a prompt message is: "If the user is nervous, provide explanations in a concise and friendly tone. Highlight key points and provide specific examples as needed."

[0740] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0741] Step 1:

[0742] The server retrieves historical document data from the information recording device. The input consists of user-specified criteria. Based on these criteria, the server searches the database and extracts relevant document data. The output is document data containing specific contract details and counterparty information.

[0743] Step 2:

[0744] The server analyzes the document data extracted using a machine learning model and extracts feature information. The input is the document data obtained in step 1. The server analyzes the data and identifies common patterns and frequently occurring expressions in the contracts. The output is a list of feature information for document generation.

[0745] Step 3:

[0746] The terminal receives condition input from the user and sends it to the server. The input consists of requirements and special notes for the contract that the user wants to generate. The server receives this and inputs it into the generation AI model.

[0747] Step 4:

[0748] The server runs a generative AI model to generate a draft document based on the user's conditions. The input consists of the user's conditions and the feature information obtained in step 2. The AI ​​model uses these to generate the optimal document draft. The output is the draft document for the user to review.

[0749] Step 5:

[0750] An emotion analysis device on the terminal senses the user's voice tone and input speed in real time. Input consists of the user's voice information and input from the interface. Based on this information, the emotion analysis device infers the user's emotional state. Output is the user's emotional state data.

[0751] Step 6:

[0752] The server adjusts the wording of the draft document generated based on the emotional state data. The inputs are the draft document from step 4 and the emotional state data from step 5. The tone and explanation of the document are adjusted according to the emotion. The output is the final draft document presented to the user.

[0753] Step 7:

[0754] The user reviews the final draft document on the terminal and makes revisions as needed. The input is the draft document adjusted in step 6. The user reviews this and makes changes or additions to the content. The output is the final version of the document with the user's revisions.

[0755] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0756] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0757] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0758] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0759] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0760] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0761] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0762] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0763] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0764] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0765] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0766] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0767] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0768] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0769] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0770] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0771] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0772] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0773] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0774] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0775] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0776] The following is further disclosed regarding the embodiments described above.

[0777] (Claim 1)

[0778] A means for accessing a past document database and analyzing the document data to extract characteristic information,

[0779] A means for running an artificial intelligence model to generate a draft of a corresponding document based on conditions entered by the user,

[0780] A means of providing a draft of the generated document to the user terminal and enabling the user to make modifications,

[0781] A method for improving the accuracy of an artificial intelligence model by training it again with corrected documents,

[0782] A system that includes this.

[0783] (Claim 2)

[0784] The system according to claim 1, wherein the document database includes contract details, counterparty information, date information, and related metadata.

[0785] (Claim 3)

[0786] The system according to claim 1, wherein the artificial intelligence model has learned company-specific formats and expression patterns.

[0787] "Example 1"

[0788] (Claim 1)

[0789] A means for accessing past electronic databases and analyzing the electronic data to extract characteristic information,

[0790] A means for running a generative AI model to analyze similar past records based on conditions entered by the user and generate a draft of the corresponding record,

[0791] A means of providing a draft of the generated record to an information terminal and enabling editing by the user,

[0792] A method for improving the accuracy of the generated AI model by adding edited records back as training data,

[0793] A system that includes this.

[0794] (Claim 2)

[0795] The system according to claim 1, wherein the electronic database includes content details, counterparty information, date information, and related additional information.

[0796] (Claim 3)

[0797] The system according to claim 1, wherein the generating AI model learns organization-specific styles and expression patterns.

[0798] "Application Example 1"

[0799] (Claim 1)

[0800] A means for accessing a past data database, analyzing the data, and extracting characteristic information,

[0801] A means for running an artificial intelligence model to generate a draft of a corresponding document based on conditions entered by the user,

[0802] A means of providing a draft of the generated document to an endpoint device and enabling user modification,

[0803] A method for improving the accuracy of an artificial intelligence model by training it again with corrected documents,

[0804] Means for providing a function to use the generated draft document as a contract for online transactions,

[0805] A system that includes this.

[0806] (Claim 2)

[0807] The system according to claim 1, wherein the data database includes contract information, related entity information, time information, and related metadata.

[0808] (Claim 3)

[0809] The system according to claim 1, wherein the artificial intelligence model learns internally specific formats and expression patterns.

[0810] "Example 2 of combining an emotion engine"

[0811] (Claim 1)

[0812] A means for accessing past information sets, analyzing the said information, and extracting characteristic information,

[0813] A means for running an artificial intelligence model to generate a draft of corresponding information based on conditions entered by the user,

[0814] A means of providing a draft of the generated information to the user's device and enabling the user to make modifications,

[0815] A method to improve the accuracy of an artificial intelligence model by training it again with corrected information,

[0816] A means for analyzing the emotional state of a user and adjusting the representation of information generated based on that information,

[0817] A system that includes this.

[0818] (Claim 2)

[0819] The system according to claim 1, wherein the information set includes contract details, counterparty information, date information, and related incidental information.

[0820] (Claim 3)

[0821] The system according to claim 1, wherein the artificial intelligence model has the ability to learn organizational-specific forms and expression patterns and to further adjust information according to the emotional state of the user.

[0822] "Application example 2 when combining with an emotional engine"

[0823] (Claim 1)

[0824] A means for accessing past document information recording devices and analyzing the data of said information recording devices to extract characteristic information,

[0825] A means for running a machine learning model to generate a draft of a corresponding document based on conditions entered by the user,

[0826] A means for providing a draft of the generated document to a user display device and enabling user modification,

[0827] A method to improve the accuracy of a machine learning model by training it again with the corrected document,

[0828] A means of using an emotion analysis device to recognize the user's emotional state and adjust the document expression,

[0829] A system that includes this.

[0830] (Claim 2)

[0831] The system according to claim 1, wherein the information recording device includes transaction details, counterparty information, date information, and related supplementary information.

[0832] (Claim 3)

[0833] The system according to claim 1, wherein the machine learning model has learned organization-specific styles and expression patterns. [Explanation of Symbols]

[0834] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for accessing a past document database and analyzing the document data to extract characteristic information, A means for running an artificial intelligence model to generate a draft of a corresponding document based on conditions entered by the user, A means of providing a draft of the generated document to the user terminal and enabling the user to make modifications, A method for improving the accuracy of an artificial intelligence model by training it again with corrected documents, A system that includes this.

2. The system according to claim 1, wherein the document database includes contract details, counterparty information, date information, and related metadata.

3. The system according to claim 1, wherein the artificial intelligence model has learned company-specific formats and expression patterns.

Images