system

Abstract

Provide a system. [Solution] A data collection means for collecting and storing materials related to litigation; An OCR method to scan collected materials and convert them into text data; an analysis means for analyzing the text data and determining whether or not there is fraud; a document generation means for quickly generating litigation documents based on the analysis results; A system including:

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Currently, when bringing a small-scale fraud case to court, the fact-finding process requires a great deal of effort, making it difficult for plaintiffs' attorneys to pursue the case. As a result, many fraudulent activities are overlooked. This problem is particularly pronounced when lawsuits are filed by vulnerable members of society. There is a need for a system that can quickly and efficiently identify fraud and prepare legal documents. [Means for solving the problem]

[0005] The present invention provides a system that includes a data collection means for collecting and storing litigation-related materials, an OCR means for scanning the collected materials and converting them into text data, an analysis means for analyzing the text data and determining whether or not there is fraud, and a document generation means for quickly generating litigation documents based on the analysis results. This enables the rapid processing of litigation materials and the effective identification of fraudulent acts, enabling the socially vulnerable to effectively file lawsuits.

[0006] A "data collection instrument" is a device or system capable of collecting and storing materials relevant to a litigation.

[0007] "OCR means" means a device or system that has the function of extracting text from image data and converting it into character data using optical character recognition technology.

[0008] The "analysis means" is a device or system that has the function of learning the criteria for judging litigation documents, analyzing the contents of the documents based on the converted text data, and determining whether or not there is any fraud.

[0009] "Document generation means" refers to a device or system that has the function of automatically generating litigation documents quickly and efficiently based on the analysis results. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0011] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0012] First, the terms used in the following description will be explained.

[0013] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0014] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0015] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0016] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0017] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0018] [First embodiment]

[0019] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0020] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0021] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0022] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0023] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0024] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0025] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0026] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0027] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0028] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0029] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0030] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0031] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[0032] System Configuration

[0033] The present invention is comprised of a system including a user terminal, a server, data collection means, OCR means, analysis means, and document generation means. This system is designed to digitize litigation-related materials and rapidly analyze and generate documents.

[0034] Program processing overview

[0035] Data collection

[0036] Users use their devices to scan or upload documents related to the case (e.g., invoices and construction records) in electronic format, which are then sent to the server and stored in the appropriate folders.

[0037] Example: A user uploads "Lawsuit Invoice.pdf" from their device. The server receives it and saves it in a specified folder.

[0038] OCR processing

[0039] The server passes the stored data to an OCR device (using optical character recognition technology), which extracts the text from the image data and converts it into character data.

[0040] Example: The OCR tool scans "Litigation Invoice.pdf" and extracts text data such as "Company A, Construction Cost, 500,000 yen." The server acquires this text data and saves it linked to the original file.

[0041] Analysis of data

[0042] The server passes the text data to the analysis means, which analyzes the content based on the criteria for litigation materials. The analysis means determines whether there is any possibility of fraudulent activity and returns the results to the server.

[0043] Example: The analysis means analyzes the text data "Company A, construction cost, 500,000 yen" and compares it with the market price. This determines that the billing amount may be fraudulent, and sends the result to the server. The server stores this in a database.

[0044] Document Generation

[0045] When a user requests the creation of litigation documents from a terminal, the server activates the document generation means based on the analysis results, which automatically generates the necessary litigation documents quickly and efficiently.

[0046] Example: A user makes a request from the litigation document creation screen. The server uses the generation means to create litigation documents based on the analysis results and source materials, and provides them to the user in a downloadable format.

[0047] effect

[0048] This system automates the collection, analysis, and document generation of materials required for litigation, significantly reducing the time and effort required for litigation preparation. It also enables the rapid detection of fraudulent activity and appropriate responses, thereby providing support to the socially vulnerable in particular in effectively filing lawsuits.

[0049] The processing flow will be explained below.

[0050] Step 1:

[0051] The user prepares documents related to the lawsuit (such as invoices and construction records) in electronic format or scans them using the terminal, then clicks the "Upload" button on the terminal, selects the documents from the file selection dialog, and uploads them.

[0052] Step 2:

[0053] The server receives the data sent from the device, stores it in the appropriate format (e.g., PDF or image file), and records the data's metadata (upload date and time, original file name, etc.) in a database.

[0054] Step 3:

[0055] The server passes the stored data to the AI-OCR module, which extracts text from the image data and converts it into character data. During the OCR process, image preprocessing (such as noise reduction and contrast adjustment) is performed to improve the accuracy of character recognition.

[0056] Step 4:

[0057] The AI-OCR module extracts text data such as "Company A, construction cost, 500,000 yen" from the image data and returns this text data to the server.

[0058] Step 5:

[0059] The server links the acquired text data to the original material and stores it in a database, allowing the necessary data to be quickly retrieved for subsequent processing.

[0060] Step 6:

[0061] The server passes the saved text data to an analysis tool that incorporates pre-trained criteria for judging litigation documents, and analyzes the contents of the documents based on these criteria to determine whether or not there is any fraud.

[0062] Step 7:

[0063] The analysis tool evaluates the text data and determines whether each document is likely to contain fraud. For example, it may determine that "Company A, construction cost, 500,000 yen" is higher than the market price and evaluate it as likely to contain fraud.

[0064] Step 8:

[0065] The server stores the analysis results in a database and links them to the original documents, allowing for centralized management of all the information needed for litigation.

[0066] Step 9:

[0067] The user requests the creation of litigation documents from their terminal. On the litigation document creation screen, they enter the necessary information and click the "Generate" button.

[0068] Step 10:

[0069] The server retrieves the relevant materials and analysis results from the database and activates the document generation means, which automatically generates the necessary documents (litigation documents, evidence lists, analysis result reports, etc.) in template format.

[0070] Step 11:

[0071] The server provides the generated litigation materials in a format that can be downloaded by the user. The user can check the generated documents on their device and download them as needed to use them in litigation preparations.

[0072] This processing flow automates the process from collecting materials required for litigation to analyzing them and generating documents, enabling litigation preparation to be carried out quickly and efficiently.

[0073] Example 1

[0074] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0075] In conventional litigation document collection and analysis systems, the process of digitizing and analyzing documents was often done manually, which was time-consuming and labor-intensive. It was also difficult to quickly and accurately detect any misconduct in documents, placing a significant burden on litigation preparation. As a result, it was difficult for vulnerable groups, especially those in society, to file lawsuits effectively.

[0076] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0077] In this invention, the server includes a data collection means for collecting and storing litigation-related materials, an optical character recognition means for scanning the collected materials and converting them into text data, an analysis means for analyzing the text data and determining whether or not there is any fraud, and a document generation means for generating litigation documents based on the analysis results upon request from the user. This makes it possible to automate the entire process from collecting litigation materials to analyzing them and generating documents.

[0078] A "data collection instrument" is a device or system for collecting and storing materials relevant to a litigation.

[0079] An "optical character recognition means" is a device or system that uses technology to extract text from scanned image data and convert it into digital character data.

[0080] The "analysis means" is a device or system that analyzes the extracted text data and evaluates the content of the material based on the presence or absence of fraud or other specific criteria.

[0081] The "document generation means" is a device or system that quickly and automatically generates litigation documents based on the analysis results.

[0082] A "server" is a device or system that includes a data collection means, an optical character recognition means, an analysis means, and a document generation means, and that integrates and manages these functions.

[0083] "User" means any person or entity that utilizes the System to manage, analyze, and request document generation related to litigation.

[0084] "Documents" refers to documents, records, and electronic data containing information relevant to the litigation.

[0085] A "folder" is a virtual storage location within a server where data is systematically organized and saved.

[0086] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[0087] System Configuration

[0088] The present invention comprises a system including a user terminal, a server, a data collection means, an optical character recognition means, an analysis means, and a document generation means, and is intended to digitize litigation-related materials and rapidly analyze and generate documents.

[0089] Program processing overview

[0090] Data collection

[0091] Users use their devices to scan or upload documents related to the case (e.g., invoices and construction records) in electronic format, which are then sent to the server and stored in the appropriate folders.

[0092] Example: A user uploads "Lawsuit Invoice.pdf" from their device. The server receives it and saves it in a specified folder.

[0093] Optical Character Recognition Processing

[0094] The server passes the stored data to an optical character recognition (OCR) tool, which extracts the text in the image data and converts it into character data.

[0095] Example: The OCR tool scans "Litigation Invoice.pdf" and extracts text data such as "Company A, Construction Cost, 500,000 yen." The server acquires this text data and saves it linked to the original file.

[0096] Analysis of data

[0097] The server passes the text data to the analysis means, which analyzes the content based on the criteria for litigation materials. The analysis means determines whether there is any possibility of fraudulent activity and returns the results to the server.

[0098] Example: The analysis means analyzes the text data "Company A, construction cost, 500,000 yen" and compares it with the market price. This determines that the billing amount may be fraudulent, and sends the result to the server. The server stores this in a database.

[0099] Document Generation

[0100] When a user requests the creation of litigation documents from a terminal, the server activates the document generation means based on the analysis results, which automatically generates the necessary litigation documents quickly and efficiently.

[0101] Example: A user makes a request from the litigation document creation screen. The server uses the generation means to create litigation documents based on the analysis results and source materials, and provides them to the user in a downloadable format.

[0102] effect

[0103] This system automates the collection, analysis, and document generation of materials required for litigation, significantly reducing the time and effort required for litigation preparation. It also enables the rapid detection of fraudulent activity and appropriate responses, thereby providing support to the socially vulnerable in particular in effectively filing lawsuits.

[0104] Prompt Sentence Examples

[0105] "Please tell me the specific steps to upload a litigation claim form to the system, run OCR and analysis, and ultimately generate the litigation document."

[0106] Hardware and software used

[0107] A scanner or camera is connected to the user terminal, and relevant documents are scanned as electronic data. The server is equipped with a powerful processor and large-capacity storage, and is installed with data collection means, optical character recognition means, analysis means, and document generation means. OCR technologies used include Tesseract and Google (registered trademark) Cloud Vision. Natural language processing models and generative AI models are used for analysis means.

[0108] Based on the above system configuration and processing overview, litigation-related materials are automatically digitized, analyzed, and litigation documents are quickly generated.

[0109] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0110] Step 1:

[0111] A user uses the device to upload materials related to the case.

[0112] Specific behavior:

[0113] The user opens the file selection screen on the terminal and selects the electronic file of the litigation materials (e.g., "Litigation Invoice.pdf").

[0114] The user clicks the "Upload" button.

[0115] Input: Electronic format document files

[0116] Output: Sending a file from the terminal to the server

[0117] Step 2:

[0118] The server stores the received materials.

[0119] Specific behavior:

[0120] The server receives the file sent from the terminal.

[0121] The server stores the received file in the "New Litigation Documents" folder.

[0122] Input: Data file sent from the terminal

[0123] Output: Document files saved in the "New Litigation Documents" folder

[0124] Step 3:

[0125] The server passes the stored material to an optical character recognition (OCR) facility.

[0126] Specific behavior:

[0127] The server scans the "New Case Files" folder for new files.

[0128] The server passes the scanned file to the OCR means.

[0129] Input: Saved document file

[0130] Output: Image data passed to the OCR tool

[0131] Step 4:

[0132] An OCR means extracts text from the image data.

[0133] Specific behavior:

[0134] The OCR means processes the scanned image data and converts it into text data (e.g., "Company A, construction cost, 500,000 yen").

[0135] The extracted character data is converted into a text file.

[0136] Input: Image data passed to the OCR tool

[0137] Output: Extracted text data file

[0138] Step 5:

[0139] The server stores the text data file and links it to the original file.

[0140] Specific behavior:

[0141] The server receives the text data obtained from the OCR means.

[0142] Save the text data file and link it to the original scan file.

[0143] Input: Text data file from OCR tool

[0144] Output: Linked text data files and scan files

[0145] Step 6:

[0146] The server passes the text data to the analysis means.

[0147] Specific behavior:

[0148] The server passes the linked text data file to the analysis means.

[0149] Input: Linked text data file

[0150] Output: Text data passed to the analysis tool

[0151] Step 7:

[0152] The analysis means analyzes the text data and determines whether or not there is any fraud.

[0153] Specific behavior:

[0154] The analysis means compares the text data with standards such as market prices.

[0155] Determines the possibility of fraud and generates a result (e.g., "Company A, construction cost, 500,000 yen" is compared with the market price and determined to be a possible indication of fraud).

[0156] Input: Text data passed to the analysis tool

[0157] Output: Analysis results including whether or not there was fraud

[0158] Step 8:

[0159] The server stores the analysis results and activates the document generation means when requested by the user.

[0160] Specific behavior:

[0161] The server stores the analysis results obtained from the analysis means in a database.

[0162] When a user requests document generation from a terminal, the server activates document generation means based on the analysis results.

[0163] Input: Analysis results, document generation request from user

[0164] Output: Invokes the document generation method

[0165] Step 9:

[0166] A document generation means automatically generates a litigation document.

[0167] Specific behavior:

[0168] The document generation means creates litigation documents based on the analysis results and the original materials.

[0169] The generated documentation is made available to users in a downloadable format.

[0170] Input: Analysis results, source data

[0171] Output: Generated legal document

[0172] Step 10:

[0173] The user downloads the generated litigation document.

[0174] Specific behavior:

[0175] The server provides the user with a download link or button.

[0176] The user clicks on the download link or button to obtain the generated litigation document.

[0177] Input: Generated legal documents

[0178] Output: The case documents downloaded by the user

[0179] (Application example 1)

[0180] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0181] Modern logistics centers handle a wide variety of documents, and manual management and input errors reduce operational efficiency while requiring a great deal of time and effort. There are also many challenges in early detection of fraudulent activity and appropriate response. Therefore, there is a need for a method to efficiently digitize, analyze, and automatically generate documents, thereby reducing errors and improving operational efficiency.

[0182] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0183] In this invention, the server includes a data collection means for collecting and storing documents, an OCR means for scanning the collected documents and converting them into text data, an analysis means for analyzing the text data and determining whether or not there is fraud, a document generation means for quickly generating business documents based on the analysis results, and a classification means for automatically classifying input documents and generating business documents accordingly. This enables complete automation and optimization of document management in a logistics center.

[0184] "Data collection means" means means for collecting and storing data.

[0185] "OCR Method" means a method that uses optical character recognition technology to scan collected materials and convert them into text data.

[0186] The "analysis means" is a means for analyzing text data and determining whether or not there is fraud.

[0187] The "document generation means" is a means for quickly generating business documents based on the analysis results.

[0188] The "classification means" is a means for automatically classifying input materials and generating business documents accordingly.

[0189] System Configuration

[0190] This invention aims to improve the efficiency of document management in logistics centers by providing a system for digitizing, analyzing, and automatically generating documents. This system consists of a user terminal, a server, data collection means, OCR means, analysis means, document generation means, and classification means.

[0191] Program processing overview

[0192] Data collection

[0193] Users use their smartphones or robots to scan or electronically submit documents such as delivery notes and shipping instructions, which are then sent to the server and stored in the appropriate folders.

[0194] OCR processing

[0195] The server passes the saved documents to the OCR tool, which extracts the text from the image data. The OCR tool uses the Google Vision API or similar to convert the images of delivery notes and shipping instructions into text data.

[0196] Analysis of data

[0197] The server analyzes the extracted text data using analytical tools to determine whether there is any fraud and to extract information necessary for business purposes. This analysis is performed using the Python pandas library, etc.

[0198] Document Generation

[0199] When a user requests the creation of a business document from a terminal, the server activates the document generation means based on the analysis results. The document generation means uses LaTeX, Word API, etc. to quickly and automatically generate the required document.

[0200] Data classification

[0201] The server automatically classifies the input materials using a classification means and generates documents according to specific business processes. For example, it automatically extracts data necessary for inventory management or purchase order generation and generates corresponding documents.

[0202] Hardware and software used

[0203] Hardware: Smartphones (e.g., iPhone (registered trademark)), robots (e.g., autonomous driving carriers at logistics centers), servers (e.g., Amazon Web Services, Google Cloud)

[0204] Software: OCR tools (e.g., Google Vision API), data analysis tools (e.g., Python's pandas library), document generation tools (e.g., LaTeX, Word API)

[0205] Specific examples

[0206] Take a delivery note as an example. A user scans the delivery note using their smartphone camera and uploads it as an image to the server. The server receives the image and extracts text data using the Google Vision API. This text data is then parsed using Python's pandas library to obtain the necessary information for inventory management and purchase order generation. Finally, the inventory list and purchase order are automatically generated using LaTeX or Word APIs and made available for download by the user.

[0207] Prompt Sentence Examples

[0208] For example, give the generative AI model the following prompt:

[0209] Design an inventory management system for use in a distribution center. This system will digitize paper delivery notes and shipping instructions using a camera, extract text data using OCR technology, and then use analysis technology to update inventory lists and automatically generate purchase orders based on product information. The generated digital documents will be made available to users in a downloadable format.

[0210] In this way, the present invention can improve the efficiency of document management in a logistics center, and can also improve the speed and accuracy of operations.

[0211] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0212] Step 1:

[0213] Users use smartphones or robots to scan or send documents such as delivery notes and shipping instructions in electronic format. The input data is the paper delivery note or shipping instruction, and the output is the scanned image data or a file in electronic format.

[0214] Step 2:

[0215] The server stores the received image data and electronic format files. The input data is the scanned image or electronic format file in step 1, and the output is the file saved in an appropriate folder on the server.

[0216] Step 3:

[0217] The server passes the stored documents to an OCR tool and extracts the text from the image data. Specifically, it uses an OCR tool (for example, Google Vision API) to convert images of delivery notes and shipping instructions into text data. The input data is the stored image data, and the output is the extracted text data.

[0218] Step 4:

[0219] The server uses analysis tools to analyze the extracted text data and extract information necessary for business purposes, such as whether there is any fraud. Specifically, it uses the Python pandas library to analyze the contents of delivery notes and shipping instructions and extract the necessary data. The input data is text data generated by OCR tools, and the output is the analyzed information necessary for business purposes.

[0220] Step 5:

[0221] The server automatically classifies the input materials using the classification means. Based on the data obtained by the analysis means, it generates documents corresponding to specific business processes (e.g., inventory management or purchase order generation). The input data is the analyzed information required for the business, and the output is the classified data and documents corresponding to the specific business process.

[0222] Step 6:

[0223] When a user requests the creation of a business document from a terminal, the server activates the document generation means and automatically generates the required document. Specifically, it uses LaTeX and Word APIs to generate inventory lists, purchase orders, etc. The input data are the analysis and classification results, and the output is the automatically generated business document.

[0224] Step 7:

[0225] The server provides the generated business document in a format that can be downloaded by the user. The input data is the automatically generated business document, and the output is a download link to the user's terminal.

[0226] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0227] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[0228] System Configuration

[0229] The present invention is composed of a system including a user terminal, a server, data collection means, OCR means, analysis means, document generation means, and an emotion engine that recognizes the user's emotions. This system digitizes and analyzes documents related to litigation, and further supports litigation preparation by taking into account the user's emotional state.

[0230] Program processing overview

[0231] Data collection

[0232] The user scans or electronically prepares documents related to the lawsuit (such as invoices and construction records) using a terminal. Then, they click the "Upload" button on the terminal, select the target documents from the file selection dialog, and upload them. The server receives the documents sent from the terminal, saves them in the appropriate folder, and records the metadata in the database.

[0233] Example: A user uploads "Lawsuit Invoice.pdf" from their device. The server receives it and saves it in a specified folder.

[0234] OCR processing

[0235] The server passes the stored data to an OCR tool (using optical character recognition technology), which extracts the text from the image data and converts it into character data. During this process, image preprocessing (noise removal, contrast adjustment, etc.) is performed to improve the accuracy of character recognition.

[0236] Example: The OCR tool scans "Litigation Invoice.pdf" and extracts text data such as "Company A, Construction Cost, 500,000 yen." The server acquires this text data and saves it linked to the original file.

[0237] Analysis of data

[0238] The server passes the text data to the analysis means, which analyzes the content based on the criteria for legal documents. The analysis means determines whether there is any possibility of fraud and returns the results to the server. In addition, feedback from the emotion engine is also taken into account.

[0239] Example: The analysis means analyzes the text data "Company A, construction cost, 500,000 yen" and compares it with the market price. This determines that the billing amount may be fraudulent, and sends the result to the server. The server stores this in a database.

[0240] Emotion engine processing

[0241] The emotion engine evaluates the inputs and actions of the user when operating the device (e.g., click speed, text entry speed, etc.). The emotion engine then feeds back the user's emotional state (stress, anxiety, relief, etc.) to the analysis means. The analysis means can incorporate this emotional data into the analysis results of the litigation materials.

[0242] Example: If the emotion engine determines that anxiety is increasing based on the user's input data, the server will provide feedback to the analysis means.

[0243] Document Generation

[0244] When a user requests the creation of litigation documents from a terminal, the server activates the document generation means based on the analysis results. The document generation means automatically generates the necessary litigation documents quickly and efficiently. The display method and document structure may be adjusted based on the user's emotional state.

[0245] Example: A user makes a request from the litigation document creation screen. The server uses generation means to create litigation documents based on the analysis results and source materials, and provides them in a format that the user can download. If the user's anxiety is increasing, kind language and concise explanations are used.

[0246] effect

[0247] This system automates the collection, analysis, and document generation of materials necessary for litigation, significantly reducing the time and effort required for litigation preparation. It also enables the rapid detection of fraudulent activity and appropriate responses, helping particularly vulnerable people to file lawsuits effectively. The introduction of an emotion engine allows for litigation preparation that takes into account the user's emotional state, providing more effective support.

[0248] The processing flow will be explained below.

[0249] Step 1:

[0250] The user prepares documents related to the lawsuit (such as invoices and construction records) in electronic format or scans them using the terminal, then clicks the "Upload" button on the terminal, selects the documents from the file selection dialog, and uploads them.

[0251] Step 2:

[0252] The server receives the data sent from the device, saves it in the appropriate folder, and records the data's metadata (upload date and time, original file name, etc.) in a database.

[0253] Step 3:

[0254] The server passes the stored data to the OCR tool, which uses optical character recognition technology to extract text from the image data and convert it into character data. During this process, preprocessing such as noise removal and contrast adjustment is performed to improve the accuracy of character recognition.

[0255] Step 4:

[0256] The OCR means extracts text data such as "Company A, construction cost, 500,000 yen" from the image data and returns this text data to the server.

[0257] Step 5:

[0258] The server links the acquired text data to the original material and stores it in a database.

[0259] Step 6:

[0260] The server passes the saved text data to the analysis means, which analyzes the content of the documents based on pre-trained criteria for litigation documents and determines whether or not there is any fraud.

[0261] Step 7:

[0262] The analysis means evaluates the text data and determines that "Company A, construction cost, 500,000 yen" may be fraudulent when compared to the market price. Based on this, the analysis results are sent to the server.

[0263] Step 8:

[0264] The server stores the analysis results in a database and links them to the original materials.

[0265] Step 9:

[0266] While the user is operating the device, the emotion engine evaluates the user's inputs and actions (e.g., click speed, text entry speed, mouse movements, etc.).

[0267] Step 10:

[0268] The emotion engine analyzes the user's emotional state (e.g., stress, anxiety, impatience, etc.) and feeds the results back to the server.

[0269] Step 11:

[0270] When a user requests the creation of a lawsuit document from a terminal, the server receives this request. The user enters the necessary information on the lawsuit document creation screen and clicks the "Generate" button.

[0271] Step 12:

[0272] The server retrieves the relevant materials and analysis results from the database and activates the document generation means, which automatically generates the necessary litigation documents (such as a complaint, a list of evidence, and a report on the analysis results) based on the analysis results and feedback from the emotion engine.

[0273] Step 13:

[0274] The server provides the generated litigation materials to the user in a format that can be downloaded. The user can review the generated documents on their device and download them as needed to use them in litigation preparations. The way the content is displayed may be adjusted based on the user's emotional state (for example, if the user is feeling anxious, explanations may be displayed in simple, gentle language).

[0275] This process automates the collection, analysis, emotional feedback, and document generation of materials necessary for litigation, allowing for fast and efficient litigation preparation. Furthermore, the introduction of an emotion engine enables support that takes into account the user's emotional state, resulting in more effective litigation preparation.

[0276] Example 2

[0277] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0278] In recent years, the digitization and analysis of litigation-related materials has become an important issue, but it is often extremely time-consuming and labor-intensive. Furthermore, detecting fraud requires advanced analysis, and support that takes into account the user's emotional state is also required. However, conventional systems cannot effectively meet these requirements, making litigation preparation particularly difficult for vulnerable members of society. Therefore, there is a need for a system that can efficiently perform data collection, analysis, and document generation, while also taking into account the user's emotional state.

[0279] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0280] In this invention, the server includes a data collection means for collecting and storing litigation-related records, an optical character recognition means for scanning the collected records and converting them into text data, an analysis means for analyzing the text data and determining whether or not there is any fraud, a document generation means for quickly generating litigation documents based on the analysis results, and an emotion engine means for analyzing the user's emotional state and providing feedback to the analysis means. This automates the process from digitizing materials to analyzing them, enabling fast and efficient document generation. Furthermore, the emotion engine analyzes the user's emotional state and provides support based on that analysis, thereby providing support for litigation preparation, particularly for the socially vulnerable.

[0281] "Litigation-related records" are document information such as invoices, contracts, and construction records collected in connection with litigation.

[0282] A "data collection tool" is a function or interface that allows a user to submit records related to a lawsuit to a server.

[0283] "Optical character recognition" refers to techniques and processes for extracting characters from image data and converting them into text data.

[0284] "Analysis means" refers to algorithms or systems that analyze the content of text data and determine whether or not there is fraudulent activity.

[0285] "Document generation means" refers to a function or system that automatically generates litigation documents quickly and efficiently based on the analysis results.

[0286] The "emotion engine means" is a system that analyzes the emotional state based on the user's input data and actions, and provides feedback to the analysis means.

[0287] "Emotional state" refers to the psychological state such as stress, anxiety, or relief that a user feels when operating a system.

[0288] "Feedback" refers to emotion analysis data provided by emotion engine means to analysis means.

[0289] "Litigation documents" are documents that contain information necessary for litigation and are required for legal proceedings.

[0290] System Configuration

[0291] The present invention comprises a system including a user terminal, a server, a data collection means, an optical character recognition means (OCR), an analysis means, a document generation means, and an emotion engine that recognizes the user's emotions. The system digitizes and analyzes records related to litigation, and further supports litigation preparation by taking into account the user's emotional state.

[0292] Program processing

[0293] The system of the present invention operates through the following main processing steps: Specific hardware and software names are also specified.

[0294] Data collection

[0295] The user prepares records related to the lawsuit (invoices, construction records, etc.) and scans them, or saves records already in electronic format to the device. The user uses the device's browser or a dedicated app to click the "Upload" button. Then, the user selects the target records from the file selection dialog and clicks the "Send File" button to send the documents to the server. As a concrete example, the user uploads "Lawsuit Invoice.pdf" from the device.

[0296] The server receives the records sent from the device and saves them in a designated folder. The server also records the metadata of the document in a database. For example, the server receives "Lawsuit Invoice.pdf" and saves it in the folder " / uploaded_documents / ", and records the file name "Lawsuit Invoice.pdf", upload date and time "2023-10-05 14:30", and user ID "user123" as metadata in the database.

[0297] OCR processing

[0298] The server passes the saved documents to the OCR means. The OCR means extracts text from the image data in the documents and converts it into character data. At this time, noise removal and contrast adjustment are performed as pre-processing of the image. As a concrete example, the OCR means processes "Litigation Invoice.pdf" and extracts text data such as "Company A, Construction Cost, 500,000 yen."

[0299] The server receives the text data sent from the OCR means, links it to the original record file, and saves it in the database. For example, the server receives the text data "Company A, construction cost, 500,000 yen," links it to "Litigation invoice.pdf," and saves it in the database.

[0300] Analysis of data

[0301] The server passes the acquired text data to the analysis means, which analyzes the content using criteria based on the litigation materials. The analysis means evaluates it by comparing it with market rates, legal standards, and patterns of fraudulent activity. As a specific example, the server passes the text data "Company A, construction cost, 500,000 yen" to the analysis means and determines whether this is higher than the market rate or whether there is a possibility of fraud. The analysis means compares it with market rates and returns a result stating that there is a "high possibility of fraud."

[0302] The server receives the analysis results from the analysis means and stores them in a database, incorporating feedback from the emotion engine. For example, the server receives a result from the analysis means that "high probability of fraud" and associates it with "Lawsuit Invoice.pdf" and stores it in the database.

[0303] Emotion engine processing

[0304] The emotion engine collects input data and behavioral information (click speed, text input speed, etc.) in real time when the user operates the device. The emotion engine analyzes the user's emotional state based on this data and feeds the results back to the analysis means. In concrete terms, if a user clicks quickly when uploading documents, the emotion engine collects this information and determines that the user is in a hurry.

[0305] Document Generation

[0306] When a user requests the creation of documents from the litigation document creation screen on the terminal, the server activates the document generation means based on the analysis results and feedback from the emotion engine, and automatically generates the necessary litigation documents.As a specific example, when a user requests the creation of documents from the litigation document creation screen, the server uses the document generation means to create litigation documents using gentle language based on the analysis result "Possibility of fraud" and the emotion engine's feedback "The user is feeling anxious."

[0307] effect

[0308] This system automates the process from digitizing materials to analyzing them, enabling fast and efficient document generation. Furthermore, an emotion engine analyzes the user's emotional state and provides support based on that analysis, thereby supporting litigation preparation, particularly for vulnerable members of society. It also enables early detection of fraudulent activity and appropriate responses, significantly reducing the overall time and effort required for litigation preparation.

[0309] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0310] Step 1:

[0311] The user scans records relevant to the lawsuit (e.g., invoices or construction records) or prepares records already in electronic format and saves them on the device. Next, the user clicks the "Upload" button using the device's browser or a dedicated app. A file selection dialog appears, and the user selects the target record file and clicks the "Send File" button to send the document to the server.

[0312] Input: Record file saved on the device (e.g., litigation claim form.pdf)

[0313] Output: Record file sent to server

[0314] Specific operation: The user selects "Litigation Invoice.pdf" from the terminal and clicks the upload button to send the file to the server.

[0315] Step 2:

[0316] The server receives the records sent from the terminal and saves them in a designated folder. In addition, the server records the metadata of the uploaded records (e.g., file name, upload date and time, user ID, etc.) in a database.

[0317] Input: The submitted record file

[0318] Output: Saved recording files and recording metadata

[0319] Specific operation: The server receives "Lawsuit Invoice.pdf" and saves it in the folder " / uploaded_documents / ". It also records the file name "Lawsuit Invoice.pdf", the upload date and time "2023-10-05 14:30", and the user ID "user123" in the database.

[0320] Step 3:

[0321] The server passes the stored records to an optical character recognition (OCR) tool, which detects text from the image data in the records and converts it into character data. Image preprocessing such as noise reduction and contrast adjustment improves the accuracy of character recognition.

[0322] Input: Saved recording file

[0323] Output: Text converted to character data

[0324] Specific operation: The OCR tool processes "Litigation Invoice.pdf", removes noise and adjusts contrast, and then extracts text data such as "Company A, construction cost, 500,000 yen."

[0325] Step 4:

[0326] The server receives the text data sent from the OCR means, links it to the original recording file, and stores it in a database.

[0327] Input: Text data sent from the OCR tool

[0328] Output: Saved text data and link information

[0329] Specific operation: The server receives the text data "Company A, construction cost, 500,000 yen" from the OCR means, links it to "Litigation invoice.pdf" and saves it in the database.

[0330] Step 5:

[0331] The server passes the acquired text data to an analysis means, which performs a content analysis based on the text data. The analysis means evaluates the data by comparing it with market rates, legal standards, patterns of fraudulent activity, etc.

[0332] Input: Received text data

[0333] Output: Analyzed data and evaluation results

[0334] Specific operation: The server passes the text data "Company A, construction cost, 500,000 yen" to the analysis means, compares it with the market price, and receives an evaluation result such as "high possibility of fraud."

[0335] Step 6:

[0336] The server receives the evaluation results from the analysis means and stores them in a database, while also incorporating feedback from the emotion engine.

[0337] Input: Evaluation results from the analysis means and feedback from the emotion engine

[0338] Output: Evaluation results stored in a database

[0339] Specific operation: The server receives the evaluation result of "high possibility of fraud," associates it with "Lawsuit Invoice.pdf," and stores it in the database. It also records the feedback information from the emotion engine.

[0340] Step 7:

[0341] The emotion engine collects input data and behavioral information (e.g., click speed, text input speed, etc.) when the user operates the device. Based on this data, it analyzes the user's emotional state and feeds the results back to the analysis means.

[0342] Input: User operation data

[0343] Output: Parsed emotion data

[0344] Specific operation: If a user clicks quickly when uploading documents, the emotion engine analyzes the data and determines that the user is in a hurry.

[0345] Step 8:

[0346] The user performs an operation to request the creation of documents from the litigation document creation screen on the terminal.

[0347] Input: Request for document creation

[0348] Output: The server that received the create request

[0349] Specific operation: The user opens the litigation document creation screen on the terminal and clicks the "Create Document" button.

[0350] Step 9:

[0351] The server activates the document generation means based on the analysis results and feedback from the emotion engine, and automatically generates the necessary litigation documents. The generated documents are then provided to users in a downloadable format.

[0352] Input: Analysis results, emotional feedback, document creation request

[0353] Output: Generated case documents

[0354] Specific operation: Based on the analysis result that "there is a possibility of fraud" and the emotional feedback that "the user is feeling anxious," the server uses a document generation means to create a gently worded lawsuit document and makes it available for the user to download.

[0355] (Application example 2)

[0356] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0357] While conventional litigation preparation systems automate the digitization and analysis of documents, they lack support that takes into account the user's emotional state. Furthermore, they have difficulty responding to situations where security risks must be identified in addition to fraud detection. This makes it difficult to provide appropriate risk avoidance measures when users feel anxious, resulting in the problem of being unable to provide optimal support.

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

[0359] In this invention, the server includes a data collection means for collecting and storing litigation-related materials, an OCR means for scanning the collected materials and converting them into text data, an analysis means for analyzing the text data to determine whether or not there is fraud and the risk level, a document generation means for quickly generating litigation documents based on the analysis results and adjusting the display method based on the user's emotional state, and an emotion engine for analyzing the user's emotional state from input and behavior. This makes it possible to automate litigation preparation and security risk identification, and also to provide risk avoidance measures that take the user's emotional state into consideration.

[0360] "Data collection instrument" means any device or software capable of collecting and storing materials relevant to a litigation.

[0361] "OCR tool" means a device or software that uses optical character recognition technology to scan collected materials and convert image data into text data.

[0362] "Analysis means" refers to a device or software that has the function of analyzing text data and determining whether or not there is fraud and the risk level.

[0363] "Document generation means" refers to a device or software that generates rapid legal documents based on the analysis results and adjusts the presentation based on the user's emotional state.

[0364] An "emotion engine" is a device or software that has the function of analyzing a user's emotional state from their input and actions.

[0365] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[0366] System Configuration

[0367] The present invention comprises a system including a data collection means, an OCR means, an analysis means, a document generation means, and an emotion engine, which digitizes and analyzes materials related to litigation and security risks, and further supports litigation preparation and risk management by taking into account the user's emotional state.

[0368] Program processing overview

[0369] Data collection methods

[0370] The user scans or electronically prepares documents related to litigation or security risks (e.g., reports, invoices, etc.) using a terminal. Then, the user clicks the "Upload" button on the terminal, selects the target documents from the file selection dialog, and uploads them. The server receives the documents sent from the terminal, saves them in the appropriate folder, and records the metadata in a database.

[0371] OCR means

[0372] The server passes the stored data to an OCR tool (using optical character recognition technology), which extracts the text from the image data and converts it into character data. During this process, image preprocessing (noise removal, contrast adjustment, etc.) is performed to improve the accuracy of character recognition.

[0373] Analysis means

[0374] The server passes the text data to the analysis means, which analyzes the content based on the legal documents and security risk criteria. The analysis means determines the possibility of fraud and the risk level, and returns the results to the server.

[0375] Emotion Engine

[0376] The emotion engine evaluates the inputs and actions of users when operating their devices (e.g., click speed, text entry speed, etc.). The emotion engine then feeds back the user's emotional state (e.g., stress, anxiety, relief) to the analysis means. The analysis means can incorporate this emotional data into litigation documents and risk analysis results.

[0377] Document Generation Method

[0378] When a user requests the creation of litigation materials and risk avoidance measures from a terminal, the server activates a document generation means based on the analysis results. The document generation means automatically generates the necessary documents quickly and efficiently. The display method and document structure may be adjusted based on the user's emotional state.

[0379] Specific examples

[0380] For example, if a user submits a scanned image of a report about unauthorized access and comments, "I'm very worried about the current situation. I need help," the system will process the scanned image with OCR and analyze the extracted text data to determine the risk level. At the same time, the emotion engine will detect the user's anxiety and, based on the analysis results, determine that the risk is high and provide advice to stay calm.

[0381] Example of a generative AI model prompt:

[0382] Input: "I'm really worried about my current situation. I need help."

[0383] Output: "We understand your concerns. The risks are high, so take appropriate measures immediately."

[0384] The system enables users to receive appropriate support that is efficient and takes into account their emotional state.

[0385] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0386] Step 1:

[0387] The user uses a terminal to prepare documents related to litigation or security risks in scanned or electronic format. When the user clicks the document upload button, a file selection dialog appears, allowing the user to select and upload the desired documents. The server receives the documents sent from the terminal and stores them in the appropriate folder. The metadata is recorded in a database. The input is the documents uploaded by the user, and the output is the digital documents stored on the server.

[0388] Step 2:

[0389] The server passes the stored material to the OCR means. The OCR means extracts the text in the image data and converts it into character data. During this process, image preprocessing such as noise removal and contrast adjustment is performed to improve the accuracy of character recognition. The input is the stored image data, and the output is text data. Specifically, the OCR means analyzes the image and extracts the text.

[0390] Step 3:

[0391] The server passes the text data to the analysis means, which analyzes the content based on litigation materials and security risk criteria. The analysis means determines the possibility of fraud and the risk level, and returns the results to the server. The input is text data, and the output is the analysis result. Specifically, the analysis means analyzes the text and evaluates it against the criteria.

[0392] Step 4:

[0393] The emotion engine evaluates the inputs and actions (e.g., click speed, text input speed, etc.) made by the user when operating the device. The emotion engine then feeds back the user's emotional state (stress, anxiety, relief, etc.) to the analysis means. The input is the user's behavioral data, and the output is emotional state data. Specifically, the emotion engine analyzes the behavioral data in real time and estimates emotions.

[0394] Step 5:

[0395] When a user requests the creation of litigation materials and risk avoidance measures from a terminal, the server activates the document generation means based on the analysis results. The document generation means automatically generates the required documents quickly and efficiently. The display method and document structure may be adjusted based on the user's emotional state. The input is the user's request and the analysis results, and the output is the generated document. In concrete terms, the document generation means creates a document based on the result data and provides it to the user.

[0396] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0397] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0398] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0399] [Second embodiment]

[0400] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0401] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0402] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0403] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0404] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0405] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0406] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0407] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0408] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0409] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0410] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0411] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0412] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[0413] System Configuration

[0414] The present invention is comprised of a system including a user terminal, a server, data collection means, OCR means, analysis means, and document generation means. This system is designed to digitize litigation-related materials and rapidly analyze and generate documents.

[0415] Program processing overview

[0416] Data collection

[0417] Users use their devices to scan or upload documents related to the case (e.g., invoices and construction records) in electronic format, which are then sent to the server and stored in the appropriate folders.

[0418] Example: A user uploads "Lawsuit Invoice.pdf" from their device. The server receives it and saves it in a specified folder.

[0419] OCR processing

[0420] The server passes the stored data to an OCR device (using optical character recognition technology), which extracts the text from the image data and converts it into character data.

[0421] Example: The OCR tool scans "Litigation Invoice.pdf" and extracts text data such as "Company A, Construction Cost, 500,000 yen." The server acquires this text data and saves it linked to the original file.

[0422] Analysis of data

[0423] The server passes the text data to the analysis means, which analyzes the content based on the criteria for litigation materials. The analysis means determines whether there is any possibility of fraudulent activity and returns the results to the server.

[0424] Example: The analysis means analyzes the text data "Company A, construction cost, 500,000 yen" and compares it with the market price. This determines that the billing amount may be fraudulent, and sends the result to the server. The server stores this in a database.

[0425] Document Generation

[0426] When a user requests the creation of litigation documents from a terminal, the server activates the document generation means based on the analysis results, which automatically generates the necessary litigation documents quickly and efficiently.

[0427] Example: A user makes a request from the litigation document creation screen. The server uses the generation means to create litigation documents based on the analysis results and source materials, and provides them to the user in a downloadable format.

[0428] effect

[0429] This system automates the collection, analysis, and document generation of materials required for litigation, significantly reducing the time and effort required for litigation preparation. It also enables the rapid detection of fraudulent activity and appropriate responses, thereby providing support to the socially vulnerable in particular in effectively filing lawsuits.

[0430] The processing flow will be explained below.

[0431] Step 1:

[0432] The user prepares documents related to the lawsuit (such as invoices and construction records) in electronic format or scans them using the terminal, then clicks the "Upload" button on the terminal, selects the documents from the file selection dialog, and uploads them.

[0433] Step 2:

[0434] The server receives the data sent from the device, stores it in the appropriate format (e.g., PDF or image file), and records the data's metadata (upload date and time, original file name, etc.) in a database.

[0435] Step 3:

[0436] The server passes the stored data to the AI-OCR module, which extracts text from the image data and converts it into character data. During the OCR process, image preprocessing (such as noise reduction and contrast adjustment) is performed to improve the accuracy of character recognition.

[0437] Step 4:

[0438] The AI-OCR module extracts text data such as "Company A, construction cost, 500,000 yen" from the image data and returns this text data to the server.

[0439] Step 5:

[0440] The server links the acquired text data to the original material and stores it in a database, allowing the necessary data to be quickly retrieved for subsequent processing.

[0441] Step 6:

[0442] The server passes the saved text data to an analysis tool that incorporates pre-trained criteria for judging litigation documents, and analyzes the contents of the documents based on these criteria to determine whether or not there is any fraud.

[0443] Step 7:

[0444] The analysis tool evaluates the text data and determines whether each document is likely to contain fraud. For example, it may determine that "Company A, construction cost, 500,000 yen" is higher than the market price and evaluate it as likely to contain fraud.

[0445] Step 8:

[0446] The server stores the analysis results in a database and links them to the original documents, allowing for centralized management of all the information needed for litigation.

[0447] Step 9:

[0448] The user requests the creation of litigation documents from their terminal. On the litigation document creation screen, they enter the necessary information and click the "Generate" button.

[0449] Step 10:

[0450] The server retrieves the relevant materials and analysis results from the database and activates the document generation means, which automatically generates the necessary documents (litigation documents, evidence lists, analysis result reports, etc.) in template format.

[0451] Step 11:

[0452] The server provides the generated litigation materials in a format that can be downloaded by the user. The user can check the generated documents on their device and download them as needed to use them in litigation preparations.

[0453] This processing flow automates the process from collecting materials required for litigation to analyzing them and generating documents, enabling litigation preparation to be carried out quickly and efficiently.

[0454] Example 1

[0455] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0456] In conventional litigation document collection and analysis systems, the process of digitizing and analyzing documents was often done manually, which was time-consuming and labor-intensive. It was also difficult to quickly and accurately detect any misconduct in documents, placing a significant burden on litigation preparation. As a result, it was difficult for vulnerable groups, especially those in society, to file lawsuits effectively.

[0457] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0458] In this invention, the server includes a data collection means for collecting and storing litigation-related materials, an optical character recognition means for scanning the collected materials and converting them into text data, an analysis means for analyzing the text data and determining whether or not there is any fraud, and a document generation means for generating litigation documents based on the analysis results upon request from the user. This makes it possible to automate the entire process from collecting litigation materials to analyzing them and generating documents.

[0459] A "data collection instrument" is a device or system for collecting and storing materials relevant to a litigation.

[0460] An "optical character recognition means" is a device or system that uses technology to extract text from scanned image data and convert it into digital character data.

[0461] The "analysis means" is a device or system that analyzes the extracted text data and evaluates the content of the material based on the presence or absence of fraud or other specific criteria.

[0462] The "document generation means" is a device or system that quickly and automatically generates litigation documents based on the analysis results.

[0463] A "server" is a device or system that includes a data collection means, an optical character recognition means, an analysis means, and a document generation means, and that integrates and manages these functions.

[0464] "User" means any person or entity that utilizes the System to manage, analyze, and request document generation related to litigation.

[0465] "Documents" refers to documents, records, and electronic data containing information relevant to the litigation.

[0466] A "folder" is a virtual storage location within a server where data is systematically organized and saved.

[0467] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[0468] System Configuration

[0469] The present invention comprises a system including a user terminal, a server, a data collection means, an optical character recognition means, an analysis means, and a document generation means, and is intended to digitize litigation-related materials and rapidly analyze and generate documents.

[0470] Program processing overview

[0471] Data collection

[0472] Users use their devices to scan or upload documents related to the case (e.g., invoices and construction records) in electronic format, which are then sent to the server and stored in the appropriate folders.

[0473] Example: A user uploads "Lawsuit Invoice.pdf" from their device. The server receives it and saves it in a specified folder.

[0474] Optical Character Recognition Processing

[0475] The server passes the stored data to an optical character recognition (OCR) tool, which extracts the text in the image data and converts it into character data.

[0476] Example: The OCR tool scans "Litigation Invoice.pdf" and extracts text data such as "Company A, Construction Cost, 500,000 yen." The server acquires this text data and saves it linked to the original file.

[0477] Analysis of data

[0478] The server passes the text data to the analysis means, which analyzes the content based on the criteria for litigation materials. The analysis means determines whether there is any possibility of fraudulent activity and returns the results to the server.

[0479] Example: The analysis means analyzes the text data "Company A, construction cost, 500,000 yen" and compares it with the market price. This determines that the billing amount may be fraudulent, and sends the result to the server. The server stores this in a database.

[0480] Document Generation

[0481] When a user requests the creation of litigation documents from a terminal, the server activates the document generation means based on the analysis results, which automatically generates the necessary litigation documents quickly and efficiently.

[0482] Example: A user makes a request from the litigation document creation screen. The server uses the generation means to create litigation documents based on the analysis results and source materials, and provides them to the user in a downloadable format.

[0483] effect

[0484] This system automates the collection, analysis, and document generation of materials required for litigation, significantly reducing the time and effort required for litigation preparation. It also enables the rapid detection of fraudulent activity and appropriate responses, thereby providing support to the socially vulnerable in particular in effectively filing lawsuits.

[0485] Prompt Sentence Examples

[0486] "Please tell me the specific steps to upload a litigation claim form to the system, run OCR and analysis, and ultimately generate the litigation document."

[0487] Hardware and software used

[0488] A scanner or camera is connected to the user's device, and relevant documents are scanned as electronic data. The server is equipped with a powerful processor and large-capacity storage, and is installed with data collection means, optical character recognition means, analysis means, and document generation means. OCR technologies such as Tesseract and Google Cloud Vision are used. Natural language processing models and generative AI models are used for analysis means.

[0489] Based on the above system configuration and processing overview, litigation-related materials are automatically digitized, analyzed, and litigation documents are quickly generated.

[0490] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0491] Step 1:

[0492] A user uses the device to upload materials related to the case.

[0493] Specific behavior:

[0494] The user opens the file selection screen on the terminal and selects the electronic file of the litigation materials (e.g., "Litigation Invoice.pdf").

[0495] The user clicks the "Upload" button.

[0496] Input: Electronic format document files

[0497] Output: Sending a file from the terminal to the server

[0498] Step 2:

[0499] The server stores the received materials.

[0500] Specific behavior:

[0501] The server receives the file sent from the terminal.

[0502] The server stores the received file in the "New Litigation Documents" folder.

[0503] Input: Data file sent from the terminal

[0504] Output: Document files saved in the "New Litigation Documents" folder

[0505] Step 3:

[0506] The server passes the stored material to an optical character recognition (OCR) facility.

[0507] Specific behavior:

[0508] The server scans the "New Case Files" folder for new files.

[0509] The server passes the scanned file to the OCR means.

[0510] Input: Saved document file

[0511] Output: Image data passed to the OCR tool

[0512] Step 4:

[0513] An OCR means extracts text from the image data.

[0514] Specific behavior:

[0515] The OCR means processes the scanned image data and converts it into text data (e.g., "Company A, construction cost, 500,000 yen").

[0516] The extracted character data is converted into a text file.

[0517] Input: Image data passed to the OCR tool

[0518] Output: Extracted text data file

[0519] Step 5:

[0520] The server stores the text data file and links it to the original file.

[0521] Specific behavior:

[0522] The server receives the text data obtained from the OCR means.

[0523] Save the text data file and link it to the original scan file.

[0524] Input: Text data file from OCR tool

[0525] Output: Linked text data files and scan files

[0526] Step 6:

[0527] The server passes the text data to the analysis means.

[0528] Specific behavior:

[0529] The server passes the linked text data file to the analysis means.

[0530] Input: Linked text data file

[0531] Output: Text data passed to the analysis tool

[0532] Step 7:

[0533] The analysis means analyzes the text data and determines whether or not there is any fraud.

[0534] Specific behavior:

[0535] The analysis means compares the text data with standards such as market prices.

[0536] Determines the possibility of fraud and generates a result (e.g., "Company A, construction cost, 500,000 yen" is compared with the market price and determined to be a possible indication of fraud).

[0537] Input: Text data passed to the analysis tool

[0538] Output: Analysis results including whether or not there was fraud

[0539] Step 8:

[0540] The server stores the analysis results and activates the document generation means when requested by the user.

[0541] Specific behavior:

[0542] The server stores the analysis results obtained from the analysis means in a database.

[0543] When a user requests document generation from a terminal, the server activates document generation means based on the analysis results.

[0544] Input: Analysis results, document generation request from user

[0545] Output: Invokes the document generation method

[0546] Step 9:

[0547] A document generation means automatically generates a litigation document.

[0548] Specific behavior:

[0549] The document generation means creates litigation documents based on the analysis results and the original materials.

[0550] The generated documentation is made available to users in a downloadable format.

[0551] Input: Analysis results, source data

[0552] Output: Generated legal document

[0553] Step 10:

[0554] The user downloads the generated litigation document.

[0555] Specific behavior:

[0556] The server provides the user with a download link or button.

[0557] The user clicks on the download link or button to obtain the generated litigation document.

[0558] Input: Generated legal documents

[0559] Output: The case documents downloaded by the user

[0560] (Application example 1)

[0561] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0562] Modern logistics centers handle a wide variety of documents, and manual management and input errors reduce operational efficiency while requiring a great deal of time and effort. There are also many challenges in early detection of fraudulent activity and appropriate response. Therefore, there is a need for a method to efficiently digitize, analyze, and automatically generate documents, thereby reducing errors and improving operational efficiency.

[0563] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0564] In this invention, the server includes a data collection means for collecting and storing documents, an OCR means for scanning the collected documents and converting them into text data, an analysis means for analyzing the text data and determining whether or not there is fraud, a document generation means for quickly generating business documents based on the analysis results, and a classification means for automatically classifying input documents and generating business documents accordingly. This enables complete automation and optimization of document management in a logistics center.

[0565] "Data collection means" means means for collecting and storing data.

[0566] "OCR Method" means a method that uses optical character recognition technology to scan collected materials and convert them into text data.

[0567] The "analysis means" is a means for analyzing text data and determining whether or not there is fraud.

[0568] The "document generation means" is a means for quickly generating business documents based on the analysis results.

[0569] The "classification means" is a means for automatically classifying input materials and generating business documents accordingly.

[0570] System Configuration

[0571] This invention aims to improve the efficiency of document management in logistics centers by providing a system for digitizing, analyzing, and automatically generating documents. This system consists of a user terminal, a server, data collection means, OCR means, analysis means, document generation means, and classification means.

[0572] Program processing overview

[0573] Data collection

[0574] Users use their smartphones or robots to scan or electronically submit documents such as delivery notes and shipping instructions, which are then sent to the server and stored in the appropriate folders.

[0575] OCR processing

[0576] The server passes the saved documents to the OCR tool, which extracts the text from the image data. The OCR tool uses the Google Vision API or similar to convert the images of delivery notes and shipping instructions into text data.

[0577] Analysis of data

[0578] The server analyzes the extracted text data using analytical tools to determine whether there is any fraud and to extract information necessary for business purposes. This analysis is performed using the Python pandas library, etc.

[0579] Document Generation

[0580] When a user requests the creation of a business document from a terminal, the server activates the document generation means based on the analysis results. The document generation means uses LaTeX, Word API, etc. to quickly and automatically generate the required document.

[0581] Data classification

[0582] The server automatically classifies the input materials using a classification means and generates documents according to specific business processes. For example, it automatically extracts data necessary for inventory management or purchase order generation and generates corresponding documents.

[0583] Hardware and software used

[0584] Hardware: Smartphones (e.g., iPhone), robots (e.g., autonomous driving carriers in logistics centers), servers (e.g., Amazon Web Services, Google Cloud)

[0585] Software: OCR tools (e.g., Google Vision API), data analysis tools (e.g., Python's pandas library), document generation tools (e.g., LaTeX, Word API)

[0586] Specific examples

[0587] Take a delivery note as an example. A user scans the delivery note using their smartphone camera and uploads it as an image to the server. The server receives the image and extracts text data using the Google Vision API. This text data is then parsed using Python's pandas library to obtain the necessary information for inventory management and purchase order generation. Finally, the inventory list and purchase order are automatically generated using LaTeX or Word APIs and made available for download by the user.

[0588] Prompt Sentence Examples

[0589] For example, give the generative AI model the following prompt:

[0590] Design an inventory management system for use in a distribution center. This system will digitize paper delivery notes and shipping instructions using a camera, extract text data using OCR technology, and then use analysis technology to update inventory lists and automatically generate purchase orders based on product information. The generated digital documents will be made available to users in a downloadable format.

[0591] In this way, the present invention can improve the efficiency of document management in a logistics center, and can also improve the speed and accuracy of operations.

[0592] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0593] Step 1:

[0594] Users use smartphones or robots to scan or send documents such as delivery notes and shipping instructions in electronic format. The input data is the paper delivery note or shipping instruction, and the output is the scanned image data or a file in electronic format.

[0595] Step 2:

[0596] The server stores the received image data and electronic format files. The input data is the scanned image or electronic format file in step 1, and the output is the file saved in an appropriate folder on the server.

[0597] Step 3:

[0598] The server passes the stored documents to an OCR tool and extracts the text from the image data. Specifically, it uses an OCR tool (for example, Google Vision API) to convert images of delivery notes and shipping instructions into text data. The input data is the stored image data, and the output is the extracted text data.

[0599] Step 4:

[0600] The server uses analysis tools to analyze the extracted text data and extract information necessary for business purposes, such as whether there is any fraud. Specifically, it uses the Python pandas library to analyze the contents of delivery notes and shipping instructions and extract the necessary data. The input data is text data generated by OCR tools, and the output is the analyzed information necessary for business purposes.

[0601] Step 5:

[0602] The server automatically classifies the input materials using the classification means. Based on the data obtained by the analysis means, it generates documents corresponding to specific business processes (e.g., inventory management or purchase order generation). The input data is the analyzed information required for the business, and the output is the classified data and documents corresponding to the specific business process.

[0603] Step 6:

[0604] When a user requests the creation of a business document from a terminal, the server activates the document generation means and automatically generates the required document. Specifically, it uses LaTeX and Word APIs to generate inventory lists, purchase orders, etc. The input data are the analysis and classification results, and the output is the automatically generated business document.

[0605] Step 7:

[0606] The server provides the generated business document in a format that can be downloaded by the user. The input data is the automatically generated business document, and the output is a download link to the user's terminal.

[0607] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0608] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[0609] System Configuration

[0610] The present invention is composed of a system including a user terminal, a server, data collection means, OCR means, analysis means, document generation means, and an emotion engine that recognizes the user's emotions. This system digitizes and analyzes documents related to litigation, and further supports litigation preparation by taking into account the user's emotional state.

[0611] Program processing overview

[0612] Data collection

[0613] The user scans or electronically prepares documents related to the lawsuit (such as invoices and construction records) using a terminal. Then, they click the "Upload" button on the terminal, select the target documents from the file selection dialog, and upload them. The server receives the documents sent from the terminal, saves them in the appropriate folder, and records the metadata in the database.

[0614] Example: A user uploads "Lawsuit Invoice.pdf" from their device. The server receives it and saves it in a specified folder.

[0615] OCR processing

[0616] The server passes the stored data to an OCR tool (using optical character recognition technology), which extracts the text from the image data and converts it into character data. During this process, image preprocessing (noise removal, contrast adjustment, etc.) is performed to improve the accuracy of character recognition.

[0617] Example: The OCR tool scans "Litigation Invoice.pdf" and extracts text data such as "Company A, Construction Cost, 500,000 yen." The server acquires this text data and saves it linked to the original file.

[0618] Analysis of data

[0619] The server passes the text data to the analysis means, which analyzes the content based on the criteria for legal documents. The analysis means determines whether there is any possibility of fraud and returns the results to the server. In addition, feedback from the emotion engine is also taken into account.

[0620] Example: The analysis means analyzes the text data "Company A, construction cost, 500,000 yen" and compares it with the market price. This determines that the billing amount may be fraudulent, and sends the result to the server. The server stores this in a database.

[0621] Emotion engine processing

[0622] The emotion engine evaluates the inputs and actions of the user when operating the device (e.g., click speed, text entry speed, etc.). The emotion engine then feeds back the user's emotional state (stress, anxiety, relief, etc.) to the analysis means. The analysis means can incorporate this emotional data into the analysis results of the litigation materials.

[0623] Example: If the emotion engine determines that anxiety is increasing based on the user's input data, the server will provide feedback to the analysis means.

[0624] Document Generation

[0625] When a user requests the creation of litigation documents from a terminal, the server activates the document generation means based on the analysis results. The document generation means automatically generates the necessary litigation documents quickly and efficiently. The display method and document structure may be adjusted based on the user's emotional state.

[0626] Example: A user makes a request from the litigation document creation screen. The server uses generation means to create litigation documents based on the analysis results and source materials, and provides them in a format that the user can download. If the user's anxiety is increasing, kind language and concise explanations are used.

[0627] effect

[0628] This system automates the collection, analysis, and document generation of materials necessary for litigation, significantly reducing the time and effort required for litigation preparation. It also enables the rapid detection of fraudulent activity and appropriate responses, helping particularly vulnerable people to file lawsuits effectively. The introduction of an emotion engine allows for litigation preparation that takes into account the user's emotional state, providing more effective support.

[0629] The processing flow will be explained below.

[0630] Step 1:

[0631] The user prepares documents related to the lawsuit (such as invoices and construction records) in electronic format or scans them using the terminal, then clicks the "Upload" button on the terminal, selects the documents from the file selection dialog, and uploads them.

[0632] Step 2:

[0633] The server receives the data sent from the device, saves it in the appropriate folder, and records the data's metadata (upload date and time, original file name, etc.) in a database.

[0634] Step 3:

[0635] The server passes the stored data to the OCR tool, which uses optical character recognition technology to extract text from the image data and convert it into character data. During this process, preprocessing such as noise removal and contrast adjustment is performed to improve the accuracy of character recognition.

[0636] Step 4:

[0637] The OCR means extracts text data such as "Company A, construction cost, 500,000 yen" from the image data and returns this text data to the server.

[0638] Step 5:

[0639] The server links the acquired text data to the original material and stores it in a database.

[0640] Step 6:

[0641] The server passes the saved text data to the analysis means, which analyzes the content of the documents based on pre-trained criteria for litigation documents and determines whether or not there is any fraud.

[0642] Step 7:

[0643] The analysis means evaluates the text data and determines that "Company A, construction cost, 500,000 yen" may be fraudulent when compared to the market price. Based on this, the analysis results are sent to the server.

[0644] Step 8:

[0645] The server stores the analysis results in a database and links them to the original materials.

[0646] Step 9:

[0647] While the user is operating the device, the emotion engine evaluates the user's inputs and actions (e.g., click speed, text entry speed, mouse movements, etc.).

[0648] Step 10:

[0649] The emotion engine analyzes the user's emotional state (e.g., stress, anxiety, impatience, etc.) and feeds the results back to the server.

[0650] Step 11:

[0651] When a user requests the creation of a lawsuit document from a terminal, the server receives this request. The user enters the necessary information on the lawsuit document creation screen and clicks the "Generate" button.

[0652] Step 12:

[0653] The server retrieves the relevant materials and analysis results from the database and activates the document generation means, which automatically generates the necessary litigation documents (such as a complaint, a list of evidence, and a report on the analysis results) based on the analysis results and feedback from the emotion engine.

[0654] Step 13:

[0655] The server provides the generated litigation materials to the user in a format that can be downloaded. The user can review the generated documents on their device and download them as needed to use them in litigation preparations. The way the content is displayed may be adjusted based on the user's emotional state (for example, if the user is feeling anxious, explanations may be displayed in simple, gentle language).

[0656] This process automates the collection, analysis, emotional feedback, and document generation of materials necessary for litigation, allowing for fast and efficient litigation preparation. Furthermore, the introduction of an emotion engine enables support that takes into account the user's emotional state, resulting in more effective litigation preparation.

[0657] Example 2

[0658] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0659] In recent years, the digitization and analysis of litigation-related materials has become an important issue, but it is often extremely time-consuming and labor-intensive. Furthermore, detecting fraud requires advanced analysis, and support that takes into account the user's emotional state is also required. However, conventional systems cannot effectively meet these requirements, making litigation preparation particularly difficult for vulnerable members of society. Therefore, there is a need for a system that can efficiently perform data collection, analysis, and document generation, while also taking into account the user's emotional state.

[0660] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0661] In this invention, the server includes a data collection means for collecting and storing litigation-related records, an optical character recognition means for scanning the collected records and converting them into text data, an analysis means for analyzing the text data and determining whether or not there is any fraud, a document generation means for quickly generating litigation documents based on the analysis results, and an emotion engine means for analyzing the user's emotional state and providing feedback to the analysis means. This automates the process from digitizing materials to analyzing them, enabling fast and efficient document generation. Furthermore, the emotion engine analyzes the user's emotional state and provides support based on that analysis, thereby providing support for litigation preparation, particularly for the socially vulnerable.

[0662] "Litigation-related records" are document information such as invoices, contracts, and construction records collected in connection with litigation.

[0663] A "data collection tool" is a function or interface that allows a user to submit records related to a lawsuit to a server.

[0664] "Optical character recognition" refers to techniques and processes for extracting characters from image data and converting them into text data.

[0665] "Analysis means" refers to algorithms or systems that analyze the content of text data and determine whether or not there is fraudulent activity.

[0666] "Document generation means" refers to a function or system that automatically generates litigation documents quickly and efficiently based on the analysis results.

[0667] The "emotion engine means" is a system that analyzes the emotional state based on the user's input data and actions, and provides feedback to the analysis means.

[0668] "Emotional state" refers to the psychological state such as stress, anxiety, or relief that a user feels when operating a system.

[0669] "Feedback" refers to emotion analysis data provided by emotion engine means to analysis means.

[0670] "Litigation documents" are documents that contain information necessary for litigation and are required for legal proceedings.

[0671] System Configuration

[0672] The present invention comprises a system including a user terminal, a server, a data collection means, an optical character recognition means (OCR), an analysis means, a document generation means, and an emotion engine that recognizes the user's emotions. The system digitizes and analyzes records related to litigation, and further supports litigation preparation by taking into account the user's emotional state.

[0673] Program processing

[0674] The system of the present invention operates through the following main processing steps: Specific hardware and software names are also specified.

[0675] Data collection

[0676] The user prepares records related to the lawsuit (invoices, construction records, etc.) and scans them, or saves records already in electronic format to the device. The user uses the device's browser or a dedicated app to click the "Upload" button. Then, the user selects the target records from the file selection dialog and clicks the "Send File" button to send the documents to the server. As a concrete example, the user uploads "Lawsuit Invoice.pdf" from the device.

[0677] The server receives the records sent from the device and saves them in a designated folder. The server also records the metadata of the document in a database. For example, the server receives "Lawsuit Invoice.pdf" and saves it in the folder " / uploaded_documents / ", and records the file name "Lawsuit Invoice.pdf", upload date and time "2023-10-05 14:30", and user ID "user123" as metadata in the database.

[0678] OCR processing

[0679] The server passes the saved documents to the OCR means. The OCR means extracts text from the image data in the documents and converts it into character data. At this time, noise removal and contrast adjustment are performed as pre-processing of the image. As a concrete example, the OCR means processes "Litigation Invoice.pdf" and extracts text data such as "Company A, Construction Cost, 500,000 yen."

[0680] The server receives the text data sent from the OCR means, links it to the original record file, and saves it in the database. For example, the server receives the text data "Company A, construction cost, 500,000 yen," links it to "Litigation invoice.pdf," and saves it in the database.

[0681] Analysis of data

[0682] The server passes the acquired text data to the analysis means, which analyzes the content using criteria based on the litigation materials. The analysis means evaluates it by comparing it with market rates, legal standards, and patterns of fraudulent activity. As a specific example, the server passes the text data "Company A, construction cost, 500,000 yen" to the analysis means and determines whether this is higher than the market rate or whether there is a possibility of fraud. The analysis means compares it with market rates and returns a result stating that there is a "high possibility of fraud."

[0683] The server receives the analysis results from the analysis means and stores them in a database, incorporating feedback from the emotion engine. For example, the server receives a result from the analysis means that "high probability of fraud" and associates it with "Lawsuit Invoice.pdf" and stores it in the database.

[0684] Emotion engine processing

[0685] The emotion engine collects input data and behavioral information (click speed, text input speed, etc.) in real time when the user operates the device. The emotion engine analyzes the user's emotional state based on this data and feeds the results back to the analysis means. In concrete terms, if a user clicks quickly when uploading documents, the emotion engine collects this information and determines that the user is in a hurry.

[0686] Document Generation

[0687] When a user requests the creation of documents from the litigation document creation screen on the terminal, the server activates the document generation means based on the analysis results and feedback from the emotion engine, and automatically generates the necessary litigation documents.As a specific example, when a user requests the creation of documents from the litigation document creation screen, the server uses the document generation means to create litigation documents using gentle language based on the analysis result "Possibility of fraud" and the emotion engine's feedback "The user is feeling anxious."

[0688] effect

[0689] This system automates the process from digitizing materials to analyzing them, enabling fast and efficient document generation. Furthermore, an emotion engine analyzes the user's emotional state and provides support based on that analysis, thereby supporting litigation preparation, particularly for vulnerable members of society. It also enables early detection of fraudulent activity and appropriate responses, significantly reducing the overall time and effort required for litigation preparation.

[0690] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0691] Step 1:

[0692] The user scans records relevant to the lawsuit (e.g., invoices or construction records) or prepares records already in electronic format and saves them on the device. Next, the user clicks the "Upload" button using the device's browser or a dedicated app. A file selection dialog appears, and the user selects the target record file and clicks the "Send File" button to send the document to the server.

[0693] Input: Record file saved on the device (e.g., litigation claim form.pdf)

[0694] Output: Record file sent to server

[0695] Specific operation: The user selects "Litigation Invoice.pdf" from the terminal and clicks the upload button to send the file to the server.

[0696] Step 2:

[0697] The server receives the records sent from the terminal and saves them in a designated folder. In addition, the server records the metadata of the uploaded records (e.g., file name, upload date and time, user ID, etc.) in a database.

[0698] Input: The submitted record file

[0699] Output: Saved recording files and recording metadata

[0700] Specific operation: The server receives "Lawsuit Invoice.pdf" and saves it in the folder " / uploaded_documents / ". It also records the file name "Lawsuit Invoice.pdf", the upload date and time "2023-10-05 14:30", and the user ID "user123" in the database.

[0701] Step 3:

[0702] The server passes the stored records to an optical character recognition (OCR) tool, which detects text from the image data in the records and converts it into character data. Image preprocessing such as noise reduction and contrast adjustment improves the accuracy of character recognition.

[0703] Input: Saved recording file

[0704] Output: Text converted to character data

[0705] Specific operation: The OCR tool processes "Litigation Invoice.pdf", removes noise and adjusts contrast, and then extracts text data such as "Company A, construction cost, 500,000 yen."

[0706] Step 4:

[0707] The server receives the text data sent from the OCR means, links it to the original recording file, and stores it in a database.

[0708] Input: Text data sent from the OCR tool

[0709] Output: Saved text data and link information

[0710] Specific operation: The server receives the text data "Company A, construction cost, 500,000 yen" from the OCR means, links it to "Litigation invoice.pdf" and saves it in the database.

[0711] Step 5:

[0712] The server passes the acquired text data to an analysis means, which performs a content analysis based on the text data. The analysis means evaluates the data by comparing it with market rates, legal standards, patterns of fraudulent activity, etc.

[0713] Input: Received text data

[0714] Output: Analyzed data and evaluation results

[0715] Specific operation: The server passes the text data "Company A, construction cost, 500,000 yen" to the analysis means, compares it with the market price, and receives an evaluation result such as "high possibility of fraud."

[0716] Step 6:

[0717] The server receives the evaluation results from the analysis means and stores them in a database, while also incorporating feedback from the emotion engine.

[0718] Input: Evaluation results from the analysis means and feedback from the emotion engine

[0719] Output: Evaluation results stored in a database

[0720] Specific operation: The server receives the evaluation result of "high possibility of fraud," associates it with "Lawsuit Invoice.pdf," and stores it in the database. It also records the feedback information from the emotion engine.

[0721] Step 7:

[0722] The emotion engine collects input data and behavioral information (e.g., click speed, text input speed, etc.) when the user operates the device. Based on this data, it analyzes the user's emotional state and feeds the results back to the analysis means.

[0723] Input: User operation data

[0724] Output: Parsed emotion data

[0725] Specific operation: If a user clicks quickly when uploading documents, the emotion engine analyzes the data and determines that the user is in a hurry.

[0726] Step 8:

[0727] The user performs an operation to request the creation of documents from the litigation document creation screen on the terminal.

[0728] Input: Request for document creation

[0729] Output: The server that received the create request

[0730] Specific operation: The user opens the litigation document creation screen on the terminal and clicks the "Create Document" button.

[0731] Step 9:

[0732] The server activates the document generation means based on the analysis results and feedback from the emotion engine, and automatically generates the necessary litigation documents. The generated documents are then provided to users in a downloadable format.

[0733] Input: Analysis results, emotional feedback, document creation request

[0734] Output: Generated case documents

[0735] Specific operation: Based on the analysis result that "there is a possibility of fraud" and the emotional feedback that "the user is feeling anxious," the server uses a document generation means to create a gently worded lawsuit document and makes it available for the user to download.

[0736] (Application example 2)

[0737] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0738] While conventional litigation preparation systems automate the digitization and analysis of documents, they lack support that takes into account the user's emotional state. Furthermore, they have difficulty responding to situations where security risks must be identified in addition to fraud detection. This makes it difficult to provide appropriate risk avoidance measures when users feel anxious, resulting in the problem of being unable to provide optimal support.

[0739] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0740] In this invention, the server includes a data collection means for collecting and storing litigation-related materials, an OCR means for scanning the collected materials and converting them into text data, an analysis means for analyzing the text data to determine whether or not there is fraud and the risk level, a document generation means for quickly generating litigation documents based on the analysis results and adjusting the display method based on the user's emotional state, and an emotion engine for analyzing the user's emotional state from input and behavior. This makes it possible to automate litigation preparation and security risk identification, and also to provide risk avoidance measures that take the user's emotional state into consideration.

[0741] "Data collection instrument" means any device or software capable of collecting and storing materials relevant to a litigation.

[0742] "OCR tool" means a device or software that uses optical character recognition technology to scan collected materials and convert image data into text data.

[0743] "Analysis means" refers to a device or software that has the function of analyzing text data and determining whether or not there is fraud and the risk level.

[0744] "Document generation means" refers to a device or software that generates rapid legal documents based on the analysis results and adjusts the presentation based on the user's emotional state.

[0745] An "emotion engine" is a device or software that has the function of analyzing a user's emotional state from their input and actions.

[0746] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[0747] System Configuration

[0748] The present invention comprises a system including a data collection means, an OCR means, an analysis means, a document generation means, and an emotion engine, which digitizes and analyzes materials related to litigation and security risks, and further supports litigation preparation and risk management by taking into account the user's emotional state.

[0749] Program processing overview

[0750] Data collection methods

[0751] The user scans or electronically prepares documents related to litigation or security risks (e.g., reports, invoices, etc.) using a terminal. Then, the user clicks the "Upload" button on the terminal, selects the target documents from the file selection dialog, and uploads them. The server receives the documents sent from the terminal, saves them in the appropriate folder, and records the metadata in a database.

[0752] OCR means

[0753] The server passes the stored data to an OCR tool (using optical character recognition technology), which extracts the text from the image data and converts it into character data. During this process, image preprocessing (noise removal, contrast adjustment, etc.) is performed to improve the accuracy of character recognition.

[0754] Analysis means

[0755] The server passes the text data to the analysis means, which analyzes the content based on the legal documents and security risk criteria. The analysis means determines the possibility of fraud and the risk level, and returns the results to the server.

[0756] Emotion Engine

[0757] The emotion engine evaluates the inputs and actions of users when operating their devices (e.g., click speed, text entry speed, etc.). The emotion engine then feeds back the user's emotional state (e.g., stress, anxiety, relief) to the analysis means. The analysis means can incorporate this emotional data into litigation documents and risk analysis results.

[0758] Document Generation Method

[0759] When a user requests the creation of litigation materials and risk avoidance measures from a terminal, the server activates a document generation means based on the analysis results. The document generation means automatically generates the necessary documents quickly and efficiently. The display method and document structure may be adjusted based on the user's emotional state.

[0760] Specific examples

[0761] For example, if a user submits a scanned image of a report about unauthorized access and comments, "I'm very worried about the current situation. I need help," the system will process the scanned image with OCR and analyze the extracted text data to determine the risk level. At the same time, the emotion engine will detect the user's anxiety and, based on the analysis results, determine that the risk is high and provide advice to stay calm.

[0762] Example of a generative AI model prompt:

[0763] Input: "I'm really worried about my current situation. I need help."

[0764] Output: "We understand your concerns. The risks are high, so take appropriate measures immediately."

[0765] The system enables users to receive appropriate support that is efficient and takes into account their emotional state.

[0766] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0767] Step 1:

[0768] The user uses a terminal to prepare documents related to litigation or security risks in scanned or electronic format. When the user clicks the document upload button, a file selection dialog appears, allowing the user to select and upload the desired documents. The server receives the documents sent from the terminal and stores them in the appropriate folder. The metadata is recorded in a database. The input is the documents uploaded by the user, and the output is the digital documents stored on the server.

[0769] Step 2:

[0770] The server passes the stored material to the OCR means. The OCR means extracts the text in the image data and converts it into character data. During this process, image preprocessing such as noise removal and contrast adjustment is performed to improve the accuracy of character recognition. The input is the stored image data, and the output is text data. Specifically, the OCR means analyzes the image and extracts the text.

[0771] Step 3:

[0772] The server passes the text data to the analysis means, which analyzes the content based on litigation materials and security risk criteria. The analysis means determines the possibility of fraud and the risk level, and returns the results to the server. The input is text data, and the output is the analysis result. Specifically, the analysis means analyzes the text and evaluates it against the criteria.

[0773] Step 4:

[0774] The emotion engine evaluates the inputs and actions (e.g., click speed, text input speed, etc.) made by the user when operating the device. The emotion engine then feeds back the user's emotional state (stress, anxiety, relief, etc.) to the analysis means. The input is the user's behavioral data, and the output is emotional state data. Specifically, the emotion engine analyzes the behavioral data in real time and estimates emotions.

[0775] Step 5:

[0776] When a user requests the creation of litigation materials and risk avoidance measures from a terminal, the server activates the document generation means based on the analysis results. The document generation means automatically generates the required documents quickly and efficiently. The display method and document structure may be adjusted based on the user's emotional state. The input is the user's request and the analysis results, and the output is the generated document. In concrete terms, the document generation means creates a document based on the result data and provides it to the user.

[0777] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0778] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0779] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0780] [Third embodiment]

[0781] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0782] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0783] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0784] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0785] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0786] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0787] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0788] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0789] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0790] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0791] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0792] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0793] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[0794] System Configuration

[0795] The present invention is comprised of a system including a user terminal, a server, data collection means, OCR means, analysis means, and document generation means. This system is designed to digitize litigation-related materials and rapidly analyze and generate documents.

[0796] Program processing overview

[0797] Data collection

[0798] Users use their devices to scan or upload documents related to the case (e.g., invoices and construction records) in electronic format, which are then sent to the server and stored in the appropriate folders.

[0799] Example: A user uploads "Lawsuit Invoice.pdf" from their device. The server receives it and saves it in a specified folder.

[0800] OCR processing

[0801] The server passes the stored data to an OCR device (using optical character recognition technology), which extracts the text from the image data and converts it into character data.

[0802] Example: The OCR tool scans "Litigation Invoice.pdf" and extracts text data such as "Company A, Construction Cost, 500,000 yen." The server acquires this text data and saves it linked to the original file.

[0803] Analysis of data

[0804] The server passes the text data to the analysis means, which analyzes the content based on the criteria for litigation materials. The analysis means determines whether there is any possibility of fraudulent activity and returns the results to the server.

[0805] Example: The analysis means analyzes the text data "Company A, construction cost, 500,000 yen" and compares it with the market price. This determines that the billing amount may be fraudulent, and sends the result to the server. The server stores this in a database.

[0806] Document Generation

[0807] When a user requests the creation of litigation documents from a terminal, the server activates the document generation means based on the analysis results, which automatically generates the necessary litigation documents quickly and efficiently.

[0808] Example: A user makes a request from the litigation document creation screen. The server uses the generation means to create litigation documents based on the analysis results and source materials, and provides them to the user in a downloadable format.

[0809] effect

[0810] This system automates the collection, analysis, and document generation of materials required for litigation, significantly reducing the time and effort required for litigation preparation. It also enables the rapid detection of fraudulent activity and appropriate responses, thereby providing support to the socially vulnerable in particular in effectively filing lawsuits.

[0811] The processing flow will be explained below.

[0812] Step 1:

[0813] The user prepares documents related to the lawsuit (such as invoices and construction records) in electronic format or scans them using the terminal, then clicks the "Upload" button on the terminal, selects the documents from the file selection dialog, and uploads them.

[0814] Step 2:

[0815] The server receives the data sent from the device, stores it in the appropriate format (e.g., PDF or image file), and records the data's metadata (upload date and time, original file name, etc.) in a database.

[0816] Step 3:

[0817] The server passes the stored data to the AI-OCR module, which extracts text from the image data and converts it into character data. During the OCR process, image preprocessing (such as noise reduction and contrast adjustment) is performed to improve the accuracy of character recognition.

[0818] Step 4:

[0819] The AI-OCR module extracts text data such as "Company A, construction cost, 500,000 yen" from the image data and returns this text data to the server.

[0820] Step 5:

[0821] The server links the acquired text data to the original material and stores it in a database, allowing the necessary data to be quickly retrieved for subsequent processing.

[0822] Step 6:

[0823] The server passes the saved text data to an analysis tool that incorporates pre-trained criteria for judging litigation documents, and analyzes the contents of the documents based on these criteria to determine whether or not there is any fraud.

[0824] Step 7:

[0825] The analysis tool evaluates the text data and determines whether each document is likely to contain fraud. For example, it may determine that "Company A, construction cost, 500,000 yen" is higher than the market price and evaluate it as likely to contain fraud.

[0826] Step 8:

[0827] The server stores the analysis results in a database and links them to the original documents, allowing for centralized management of all the information needed for litigation.

[0828] Step 9:

[0829] The user requests the creation of litigation documents from their terminal. On the litigation document creation screen, they enter the necessary information and click the "Generate" button.

[0830] Step 10:

[0831] The server retrieves the relevant materials and analysis results from the database and activates the document generation means, which automatically generates the necessary documents (litigation documents, evidence lists, analysis result reports, etc.) in template format.

[0832] Step 11:

[0833] The server provides the generated litigation materials in a format that can be downloaded by the user. The user can check the generated documents on their device and download them as needed to use them in litigation preparations.

[0834] This processing flow automates the process from collecting materials required for litigation to analyzing them and generating documents, enabling litigation preparation to be carried out quickly and efficiently.

[0835] Example 1

[0836] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0837] In conventional litigation document collection and analysis systems, the process of digitizing and analyzing documents was often done manually, which was time-consuming and labor-intensive. It was also difficult to quickly and accurately detect any misconduct in documents, placing a significant burden on litigation preparation. As a result, it was difficult for vulnerable groups, especially those in society, to file lawsuits effectively.

[0838] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0839] In this invention, the server includes a data collection means for collecting and storing litigation-related materials, an optical character recognition means for scanning the collected materials and converting them into text data, an analysis means for analyzing the text data and determining whether or not there is any fraud, and a document generation means for generating litigation documents based on the analysis results upon request from the user. This makes it possible to automate the entire process from collecting litigation materials to analyzing them and generating documents.

[0840] A "data collection instrument" is a device or system for collecting and storing materials relevant to a litigation.

[0841] An "optical character recognition means" is a device or system that uses technology to extract text from scanned image data and convert it into digital character data.

[0842] The "analysis means" is a device or system that analyzes the extracted text data and evaluates the content of the material based on the presence or absence of fraud or other specific criteria.

[0843] The "document generation means" is a device or system that quickly and automatically generates litigation documents based on the analysis results.

[0844] A "server" is a device or system that includes a data collection means, an optical character recognition means, an analysis means, and a document generation means, and that integrates and manages these functions.

[0845] "User" means any person or entity that utilizes the System to manage, analyze, and request document generation related to litigation.

[0846] "Documents" refers to documents, records, and electronic data containing information relevant to the litigation.

[0847] A "folder" is a virtual storage location within a server where data is systematically organized and saved.

[0848] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[0849] System Configuration

[0850] The present invention comprises a system including a user terminal, a server, a data collection means, an optical character recognition means, an analysis means, and a document generation means, and is intended to digitize litigation-related materials and rapidly analyze and generate documents.

[0851] Program processing overview

[0852] Data collection

[0853] Users use their devices to scan or upload documents related to the case (e.g., invoices and construction records) in electronic format, which are then sent to the server and stored in the appropriate folders.

[0854] Example: A user uploads "Lawsuit Invoice.pdf" from their device. The server receives it and saves it in a specified folder.

[0855] Optical Character Recognition Processing

[0856] The server passes the stored data to an optical character recognition (OCR) tool, which extracts the text in the image data and converts it into character data.

[0857] Example: The OCR tool scans "Litigation Invoice.pdf" and extracts text data such as "Company A, Construction Cost, 500,000 yen." The server acquires this text data and saves it linked to the original file.

[0858] Analysis of data

[0859] The server passes the text data to the analysis means, which analyzes the content based on the criteria for litigation materials. The analysis means determines whether there is any possibility of fraudulent activity and returns the results to the server.

[0860] Example: The analysis means analyzes the text data "Company A, construction cost, 500,000 yen" and compares it with the market price. This determines that the billing amount may be fraudulent, and sends the result to the server. The server stores this in a database.

[0861] Document Generation

[0862] When a user requests the creation of litigation documents from a terminal, the server activates the document generation means based on the analysis results, which automatically generates the necessary litigation documents quickly and efficiently.

[0863] Example: A user makes a request from the litigation document creation screen. The server uses the generation means to create litigation documents based on the analysis results and source materials, and provides them to the user in a downloadable format.

[0864] effect

[0865] This system automates the collection, analysis, and document generation of materials required for litigation, significantly reducing the time and effort required for litigation preparation. It also enables the rapid detection of fraudulent activity and appropriate responses, thereby providing support to the socially vulnerable in particular in effectively filing lawsuits.

[0866] Prompt Sentence Examples

[0867] "Please tell me the specific steps to upload a litigation claim form to the system, run OCR and analysis, and ultimately generate the litigation document."

[0868] Hardware and software used

[0869] A scanner or camera is connected to the user's device, and relevant documents are scanned as electronic data. The server is equipped with a powerful processor and large-capacity storage, and is installed with data collection means, optical character recognition means, analysis means, and document generation means. OCR technologies such as Tesseract and Google Cloud Vision are used. Natural language processing models and generative AI models are used for analysis means.

[0870] Based on the above system configuration and processing overview, litigation-related materials are automatically digitized, analyzed, and litigation documents are quickly generated.

[0871] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0872] Step 1:

[0873] A user uses the device to upload materials related to the case.

[0874] Specific behavior:

[0875] The user opens the file selection screen on the terminal and selects the electronic file of the litigation materials (e.g., "Litigation Invoice.pdf").

[0876] The user clicks the "Upload" button.

[0877] Input: Electronic format document files

[0878] Output: Sending a file from the terminal to the server

[0879] Step 2:

[0880] The server stores the received materials.

[0881] Specific behavior:

[0882] The server receives the file sent from the terminal.

[0883] The server stores the received file in the "New Litigation Documents" folder.

[0884] Input: Data file sent from the terminal

[0885] Output: Document files saved in the "New Litigation Documents" folder

[0886] Step 3:

[0887] The server passes the stored material to an optical character recognition (OCR) facility.

[0888] Specific behavior:

[0889] The server scans the "New Case Files" folder for new files.

[0890] The server passes the scanned file to the OCR means.

[0891] Input: Saved document file

[0892] Output: Image data passed to the OCR tool

[0893] Step 4:

[0894] An OCR means extracts text from the image data.

[0895] Specific behavior:

[0896] The OCR means processes the scanned image data and converts it into text data (e.g., "Company A, construction cost, 500,000 yen").

[0897] The extracted character data is converted into a text file.

[0898] Input: Image data passed to the OCR tool

[0899] Output: Extracted text data file

[0900] Step 5:

[0901] The server stores the text data file and links it to the original file.

[0902] Specific behavior:

[0903] The server receives the text data obtained from the OCR means.

[0904] Save the text data file and link it to the original scan file.

[0905] Input: Text data file from OCR tool

[0906] Output: Linked text data files and scan files

[0907] Step 6:

[0908] The server passes the text data to the analysis means.

[0909] Specific behavior:

[0910] The server passes the linked text data file to the analysis means.

[0911] Input: Linked text data file

[0912] Output: Text data passed to the analysis tool

[0913] Step 7:

[0914] The analysis means analyzes the text data and determines whether or not there is any fraud.

[0915] Specific behavior:

[0916] The analysis means compares the text data with standards such as market prices.

[0917] Determines the possibility of fraud and generates a result (e.g., "Company A, construction cost, 500,000 yen" is compared with the market price and determined to be a possible indication of fraud).

[0918] Input: Text data passed to the analysis tool

[0919] Output: Analysis results including whether or not there was fraud

[0920] Step 8:

[0921] The server stores the analysis results and activates the document generation means when requested by the user.

[0922] Specific behavior:

[0923] The server stores the analysis results obtained from the analysis means in a database.

[0924] When a user requests document generation from a terminal, the server activates document generation means based on the analysis results.

[0925] Input: Analysis results, document generation request from user

[0926] Output: Invokes the document generation method

[0927] Step 9:

[0928] A document generation means automatically generates a litigation document.

[0929] Specific behavior:

[0930] The document generation means creates litigation documents based on the analysis results and the original materials.

[0931] The generated documentation is made available to users in a downloadable format.

[0932] Input: Analysis results, source data

[0933] Output: Generated legal document

[0934] Step 10:

[0935] The user downloads the generated litigation document.

[0936] Specific behavior:

[0937] The server provides the user with a download link or button.

[0938] The user clicks on the download link or button to obtain the generated litigation document.

[0939] Input: Generated legal documents

[0940] Output: The case documents downloaded by the user

[0941] (Application example 1)

[0942] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0943] Modern logistics centers handle a wide variety of documents, and manual management and input errors reduce operational efficiency while requiring a great deal of time and effort. There are also many challenges in early detection of fraudulent activity and appropriate response. Therefore, there is a need for a method to efficiently digitize, analyze, and automatically generate documents, thereby reducing errors and improving operational efficiency.

[0944] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0945] In this invention, the server includes a data collection means for collecting and storing documents, an OCR means for scanning the collected documents and converting them into text data, an analysis means for analyzing the text data and determining whether or not there is fraud, a document generation means for quickly generating business documents based on the analysis results, and a classification means for automatically classifying input documents and generating business documents accordingly. This enables complete automation and optimization of document management in a logistics center.

[0946] "Data collection means" means means for collecting and storing data.

[0947] "OCR Method" means a method that uses optical character recognition technology to scan collected materials and convert them into text data.

[0948] The "analysis means" is a means for analyzing text data and determining whether or not there is fraud.

[0949] The "document generation means" is a means for quickly generating business documents based on the analysis results.

[0950] The "classification means" is a means for automatically classifying input materials and generating business documents accordingly.

[0951] System Configuration

[0952] This invention aims to improve the efficiency of document management in logistics centers by providing a system for digitizing, analyzing, and automatically generating documents. This system consists of a user terminal, a server, data collection means, OCR means, analysis means, document generation means, and classification means.

[0953] Program processing overview

[0954] Data collection

[0955] Users use their smartphones or robots to scan or electronically submit documents such as delivery notes and shipping instructions, which are then sent to the server and stored in the appropriate folders.

[0956] OCR processing

[0957] The server passes the saved documents to the OCR tool, which extracts the text from the image data. The OCR tool uses the Google Vision API or similar to convert the images of delivery notes and shipping instructions into text data.

[0958] Analysis of data

[0959] The server analyzes the extracted text data using analytical tools to determine whether there is any fraud and to extract information necessary for business purposes. This analysis is performed using the Python pandas library, etc.

[0960] Document Generation

[0961] When a user requests the creation of a business document from a terminal, the server activates the document generation means based on the analysis results. The document generation means uses LaTeX, Word API, etc. to quickly and automatically generate the required document.

[0962] Data classification

[0963] The server automatically classifies the input materials using a classification means and generates documents according to specific business processes. For example, it automatically extracts data necessary for inventory management or purchase order generation and generates corresponding documents.

[0964] Hardware and software used

[0965] Hardware: Smartphones (e.g., iPhone), robots (e.g., autonomous driving carriers in logistics centers), servers (e.g., Amazon Web Services, Google Cloud)

[0966] Software: OCR tools (e.g., Google Vision API), data analysis tools (e.g., Python's pandas library), document generation tools (e.g., LaTeX, Word API)

[0967] Specific examples

[0968] Take a delivery note as an example. A user scans the delivery note using their smartphone camera and uploads it as an image to the server. The server receives the image and extracts text data using the Google Vision API. This text data is then parsed using Python's pandas library to obtain the necessary information for inventory management and purchase order generation. Finally, the inventory list and purchase order are automatically generated using LaTeX or Word APIs and made available for download by the user.

[0969] Prompt Sentence Examples

[0970] For example, give the generative AI model the following prompt:

[0971] Design an inventory management system for use in a distribution center. This system will digitize paper delivery notes and shipping instructions using a camera, extract text data using OCR technology, and then use analysis technology to update inventory lists and automatically generate purchase orders based on product information. The generated digital documents will be made available to users in a downloadable format.

[0972] In this way, the present invention can improve the efficiency of document management in a logistics center, and can also improve the speed and accuracy of operations.

[0973] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0974] Step 1:

[0975] Users use smartphones or robots to scan or send documents such as delivery notes and shipping instructions in electronic format. The input data is the paper delivery note or shipping instruction, and the output is the scanned image data or a file in electronic format.

[0976] Step 2:

[0977] The server stores the received image data and electronic format files. The input data is the scanned image or electronic format file in step 1, and the output is the file saved in an appropriate folder on the server.

[0978] Step 3:

[0979] The server passes the stored documents to an OCR tool and extracts the text from the image data. Specifically, it uses an OCR tool (for example, Google Vision API) to convert images of delivery notes and shipping instructions into text data. The input data is the stored image data, and the output is the extracted text data.

[0980] Step 4:

[0981] The server uses analysis tools to analyze the extracted text data and extract information necessary for business purposes, such as whether there is any fraud. Specifically, it uses the Python pandas library to analyze the contents of delivery notes and shipping instructions and extract the necessary data. The input data is text data generated by OCR tools, and the output is the analyzed information necessary for business purposes.

[0982] Step 5:

[0983] The server automatically classifies the input materials using the classification means. Based on the data obtained by the analysis means, it generates documents corresponding to specific business processes (e.g., inventory management or purchase order generation). The input data is the analyzed information required for the business, and the output is the classified data and documents corresponding to the specific business process.

[0984] Step 6:

[0985] When a user requests the creation of a business document from a terminal, the server activates the document generation means and automatically generates the required document. Specifically, it uses LaTeX and Word APIs to generate inventory lists, purchase orders, etc. The input data are the analysis and classification results, and the output is the automatically generated business document.

[0986] Step 7:

[0987] The server provides the generated business document in a format that can be downloaded by the user. The input data is the automatically generated business document, and the output is a download link to the user's terminal.

[0988] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0989] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[0990] System Configuration

[0991] The present invention is composed of a system including a user terminal, a server, data collection means, OCR means, analysis means, document generation means, and an emotion engine that recognizes the user's emotions. This system digitizes and analyzes documents related to litigation, and further supports litigation preparation by taking into account the user's emotional state.

[0992] Program processing overview

[0993] Data collection

[0994] The user scans or electronically prepares documents related to the lawsuit (such as invoices and construction records) using a terminal. Then, they click the "Upload" button on the terminal, select the target documents from the file selection dialog, and upload them. The server receives the documents sent from the terminal, saves them in the appropriate folder, and records the metadata in the database.

[0995] Example: A user uploads "Lawsuit Invoice.pdf" from their device. The server receives it and saves it in a specified folder.

[0996] OCR processing

[0997] The server passes the stored data to an OCR tool (using optical character recognition technology), which extracts the text from the image data and converts it into character data. During this process, image preprocessing (noise removal, contrast adjustment, etc.) is performed to improve the accuracy of character recognition.

[0998] Example: The OCR tool scans "Litigation Invoice.pdf" and extracts text data such as "Company A, Construction Cost, 500,000 yen." The server acquires this text data and saves it linked to the original file.

[0999] Analysis of data

[1000] The server passes the text data to the analysis means, which analyzes the content based on the criteria for legal documents. The analysis means determines whether there is any possibility of fraud and returns the results to the server. In addition, feedback from the emotion engine is also taken into account.

[1001] Example: The analysis means analyzes the text data "Company A, construction cost, 500,000 yen" and compares it with the market price. This determines that the billing amount may be fraudulent, and sends the result to the server. The server stores this in a database.

[1002] Emotion engine processing

[1003] The emotion engine evaluates the inputs and actions of the user when operating the device (e.g., click speed, text entry speed, etc.). The emotion engine then feeds back the user's emotional state (stress, anxiety, relief, etc.) to the analysis means. The analysis means can incorporate this emotional data into the analysis results of the litigation materials.

[1004] Example: If the emotion engine determines that anxiety is increasing based on the user's input data, the server will provide feedback to the analysis means.

[1005] Document Generation

[1006] When a user requests the creation of litigation documents from a terminal, the server activates the document generation means based on the analysis results. The document generation means automatically generates the necessary litigation documents quickly and efficiently. The display method and document structure may be adjusted based on the user's emotional state.

[1007] Example: A user makes a request from the litigation document creation screen. The server uses generation means to create litigation documents based on the analysis results and source materials, and provides them in a format that the user can download. If the user's anxiety is increasing, kind language and concise explanations are used.

[1008] effect

[1009] This system automates the collection, analysis, and document generation of materials necessary for litigation, significantly reducing the time and effort required for litigation preparation. It also enables the rapid detection of fraudulent activity and appropriate responses, helping particularly vulnerable people to file lawsuits effectively. The introduction of an emotion engine allows for litigation preparation that takes into account the user's emotional state, providing more effective support.

[1010] The processing flow will be explained below.

[1011] Step 1:

[1012] The user prepares documents related to the lawsuit (such as invoices and construction records) in electronic format or scans them using the terminal, then clicks the "Upload" button on the terminal, selects the documents from the file selection dialog, and uploads them.

[1013] Step 2:

[1014] The server receives the data sent from the device, saves it in the appropriate folder, and records the data's metadata (upload date and time, original file name, etc.) in a database.

[1015] Step 3:

[1016] The server passes the stored data to the OCR tool, which uses optical character recognition technology to extract text from the image data and convert it into character data. During this process, preprocessing such as noise removal and contrast adjustment is performed to improve the accuracy of character recognition.

[1017] Step 4:

[1018] The OCR means extracts text data such as "Company A, construction cost, 500,000 yen" from the image data and returns this text data to the server.

[1019] Step 5:

[1020] The server links the acquired text data to the original material and stores it in a database.

[1021] Step 6:

[1022] The server passes the saved text data to the analysis means, which analyzes the content of the documents based on pre-trained criteria for litigation documents and determines whether or not there is any fraud.

[1023] Step 7:

[1024] The analysis means evaluates the text data and determines that "Company A, construction cost, 500,000 yen" may be fraudulent when compared to the market price. Based on this, the analysis results are sent to the server.

[1025] Step 8:

[1026] The server stores the analysis results in a database and links them to the original materials.

[1027] Step 9:

[1028] While the user is operating the device, the emotion engine evaluates the user's inputs and actions (e.g., click speed, text entry speed, mouse movements, etc.).

[1029] Step 10:

[1030] The emotion engine analyzes the user's emotional state (e.g., stress, anxiety, impatience, etc.) and feeds the results back to the server.

[1031] Step 11:

[1032] When a user requests the creation of a lawsuit document from a terminal, the server receives this request. The user enters the necessary information on the lawsuit document creation screen and clicks the "Generate" button.

[1033] Step 12:

[1034] The server retrieves the relevant materials and analysis results from the database and activates the document generation means, which automatically generates the necessary litigation documents (such as a complaint, a list of evidence, and a report on the analysis results) based on the analysis results and feedback from the emotion engine.

[1035] Step 13:

[1036] The server provides the generated litigation materials to the user in a format that can be downloaded. The user can review the generated documents on their device and download them as needed to use them in litigation preparations. The way the content is displayed may be adjusted based on the user's emotional state (for example, if the user is feeling anxious, explanations may be displayed in simple, gentle language).

[1037] This process automates the collection, analysis, emotional feedback, and document generation of materials necessary for litigation, allowing for fast and efficient litigation preparation. Furthermore, the introduction of an emotion engine enables support that takes into account the user's emotional state, resulting in more effective litigation preparation.

[1038] Example 2

[1039] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1040] In recent years, the digitization and analysis of litigation-related materials has become an important issue, but it is often extremely time-consuming and labor-intensive. Furthermore, detecting fraud requires advanced analysis, and support that takes into account the user's emotional state is also required. However, conventional systems cannot effectively meet these requirements, making litigation preparation particularly difficult for vulnerable members of society. Therefore, there is a need for a system that can efficiently perform data collection, analysis, and document generation, while also taking into account the user's emotional state.

[1041] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1042] In this invention, the server includes a data collection means for collecting and storing litigation-related records, an optical character recognition means for scanning the collected records and converting them into text data, an analysis means for analyzing the text data and determining whether or not there is any fraud, a document generation means for quickly generating litigation documents based on the analysis results, and an emotion engine means for analyzing the user's emotional state and providing feedback to the analysis means. This automates the process from digitizing materials to analyzing them, enabling fast and efficient document generation. Furthermore, the emotion engine analyzes the user's emotional state and provides support based on that analysis, thereby providing support for litigation preparation, particularly for the socially vulnerable.

[1043] "Litigation-related records" are document information such as invoices, contracts, and construction records collected in connection with litigation.

[1044] A "data collection tool" is a function or interface that allows a user to submit records related to a lawsuit to a server.

[1045] "Optical character recognition" refers to techniques and processes for extracting characters from image data and converting them into text data.

[1046] "Analysis means" refers to algorithms or systems that analyze the content of text data and determine whether or not there is fraudulent activity.

[1047] "Document generation means" refers to a function or system that automatically generates litigation documents quickly and efficiently based on the analysis results.

[1048] The "emotion engine means" is a system that analyzes the emotional state based on the user's input data and actions, and provides feedback to the analysis means.

[1049] "Emotional state" refers to the psychological state such as stress, anxiety, or relief that a user feels when operating a system.

[1050] "Feedback" refers to emotion analysis data provided by emotion engine means to analysis means.

[1051] "Litigation documents" are documents that contain information necessary for litigation and are required for legal proceedings.

[1052] System Configuration

[1053] The present invention comprises a system including a user terminal, a server, a data collection means, an optical character recognition means (OCR), an analysis means, a document generation means, and an emotion engine that recognizes the user's emotions. The system digitizes and analyzes records related to litigation, and further supports litigation preparation by taking into account the user's emotional state.

[1054] Program processing

[1055] The system of the present invention operates through the following main processing steps: Specific hardware and software names are also specified.

[1056] Data collection

[1057] The user prepares records related to the lawsuit (invoices, construction records, etc.) and scans them, or saves records already in electronic format to the device. The user uses the device's browser or a dedicated app to click the "Upload" button. Then, the user selects the target records from the file selection dialog and clicks the "Send File" button to send the documents to the server. As a concrete example, the user uploads "Lawsuit Invoice.pdf" from the device.

[1058] The server receives the records sent from the device and saves them in a designated folder. The server also records the metadata of the document in a database. For example, the server receives "Lawsuit Invoice.pdf" and saves it in the folder " / uploaded_documents / ", and records the file name "Lawsuit Invoice.pdf", upload date and time "2023-10-05 14:30", and user ID "user123" as metadata in the database.

[1059] OCR processing

[1060] The server passes the saved documents to the OCR means. The OCR means extracts text from the image data in the documents and converts it into character data. At this time, noise removal and contrast adjustment are performed as pre-processing of the image. As a concrete example, the OCR means processes "Litigation Invoice.pdf" and extracts text data such as "Company A, Construction Cost, 500,000 yen."

[1061] The server receives the text data sent from the OCR means, links it to the original record file, and saves it in the database. For example, the server receives the text data "Company A, construction cost, 500,000 yen," links it to "Litigation invoice.pdf," and saves it in the database.

[1062] Analysis of data

[1063] The server passes the acquired text data to the analysis means, which analyzes the content using criteria based on the litigation materials. The analysis means evaluates it by comparing it with market rates, legal standards, and patterns of fraudulent activity. As a specific example, the server passes the text data "Company A, construction cost, 500,000 yen" to the analysis means and determines whether this is higher than the market rate or whether there is a possibility of fraud. The analysis means compares it with market rates and returns a result stating that there is a "high possibility of fraud."

[1064] The server receives the analysis results from the analysis means and stores them in a database, incorporating feedback from the emotion engine. For example, the server receives a result from the analysis means that "high probability of fraud" and associates it with "Lawsuit Invoice.pdf" and stores it in the database.

[1065] Emotion engine processing

[1066] The emotion engine collects input data and behavioral information (click speed, text input speed, etc.) in real time when the user operates the device. The emotion engine analyzes the user's emotional state based on this data and feeds the results back to the analysis means. In concrete terms, if a user clicks quickly when uploading documents, the emotion engine collects this information and determines that the user is in a hurry.

[1067] Document Generation

[1068] When a user requests the creation of documents from the litigation document creation screen on the terminal, the server activates the document generation means based on the analysis results and feedback from the emotion engine, and automatically generates the necessary litigation documents.As a specific example, when a user requests the creation of documents from the litigation document creation screen, the server uses the document generation means to create litigation documents using gentle language based on the analysis result "Possibility of fraud" and the emotion engine's feedback "The user is feeling anxious."

[1069] effect

[1070] This system automates the process from digitizing materials to analyzing them, enabling fast and efficient document generation. Furthermore, an emotion engine analyzes the user's emotional state and provides support based on that analysis, thereby supporting litigation preparation, particularly for vulnerable members of society. It also enables early detection of fraudulent activity and appropriate responses, significantly reducing the overall time and effort required for litigation preparation.

[1071] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1072] Step 1:

[1073] The user scans records relevant to the lawsuit (e.g., invoices or construction records) or prepares records already in electronic format and saves them on the device. Next, the user clicks the "Upload" button using the device's browser or a dedicated app. A file selection dialog appears, and the user selects the target record file and clicks the "Send File" button to send the document to the server.

[1074] Input: Record file saved on the device (e.g., litigation claim form.pdf)

[1075] Output: Record file sent to server

[1076] Specific operation: The user selects "Litigation Invoice.pdf" from the terminal and clicks the upload button to send the file to the server.

[1077] Step 2:

[1078] The server receives the records sent from the terminal and saves them in a designated folder. In addition, the server records the metadata of the uploaded records (e.g., file name, upload date and time, user ID, etc.) in a database.

[1079] Input: The submitted record file

[1080] Output: Saved recording files and recording metadata

[1081] Specific operation: The server receives "Lawsuit Invoice.pdf" and saves it in the folder " / uploaded_documents / ". It also records the file name "Lawsuit Invoice.pdf", the upload date and time "2023-10-05 14:30", and the user ID "user123" in the database.

[1082] Step 3:

[1083] The server passes the stored records to an optical character recognition (OCR) tool, which detects text from the image data in the records and converts it into character data. Image preprocessing such as noise reduction and contrast adjustment improves the accuracy of character recognition.

[1084] Input: Saved recording file

[1085] Output: Text converted to character data

[1086] Specific operation: The OCR tool processes "Litigation Invoice.pdf", removes noise and adjusts contrast, and then extracts text data such as "Company A, construction cost, 500,000 yen."

[1087] Step 4:

[1088] The server receives the text data sent from the OCR means, links it to the original recording file, and stores it in a database.

[1089] Input: Text data sent from the OCR tool

[1090] Output: Saved text data and link information

[1091] Specific operation: The server receives the text data "Company A, construction cost, 500,000 yen" from the OCR means, links it to "Litigation invoice.pdf" and saves it in the database.

[1092] Step 5:

[1093] The server passes the acquired text data to an analysis means, which performs a content analysis based on the text data. The analysis means evaluates the data by comparing it with market rates, legal standards, patterns of fraudulent activity, etc.

[1094] Input: Received text data

[1095] Output: Analyzed data and evaluation results

[1096] Specific operation: The server passes the text data "Company A, construction cost, 500,000 yen" to the analysis means, compares it with the market price, and receives an evaluation result such as "high possibility of fraud."

[1097] Step 6:

[1098] The server receives the evaluation results from the analysis means and stores them in a database, while also incorporating feedback from the emotion engine.

[1099] Input: Evaluation results from the analysis means and feedback from the emotion engine

[1100] Output: Evaluation results stored in a database

[1101] Specific operation: The server receives the evaluation result of "high possibility of fraud," associates it with "Lawsuit Invoice.pdf," and stores it in the database. It also records the feedback information from the emotion engine.

[1102] Step 7:

[1103] The emotion engine collects input data and behavioral information (e.g., click speed, text input speed, etc.) when the user operates the device. Based on this data, it analyzes the user's emotional state and feeds the results back to the analysis means.

[1104] Input: User operation data

[1105] Output: Parsed emotion data

[1106] Specific operation: If a user clicks quickly when uploading documents, the emotion engine analyzes the data and determines that the user is in a hurry.

[1107] Step 8:

[1108] The user performs an operation to request the creation of documents from the litigation document creation screen on the terminal.

[1109] Input: Request for document creation

[1110] Output: The server that received the create request

[1111] Specific operation: The user opens the litigation document creation screen on the terminal and clicks the "Create Document" button.

[1112] Step 9:

[1113] The server activates the document generation means based on the analysis results and feedback from the emotion engine, and automatically generates the necessary litigation documents. The generated documents are then provided to users in a downloadable format.

[1114] Input: Analysis results, emotional feedback, document creation request

[1115] Output: Generated case documents

[1116] Specific operation: Based on the analysis result that "there is a possibility of fraud" and the emotional feedback that "the user is feeling anxious," the server uses a document generation means to create a gently worded lawsuit document and makes it available for the user to download.

[1117] (Application example 2)

[1118] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1119] While conventional litigation preparation systems automate the digitization and analysis of documents, they lack support that takes into account the user's emotional state. Furthermore, they have difficulty responding to situations where security risks must be identified in addition to fraud detection. This makes it difficult to provide appropriate risk avoidance measures when users feel anxious, resulting in the problem of being unable to provide optimal support.

[1120] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1121] In this invention, the server includes a data collection means for collecting and storing litigation-related materials, an OCR means for scanning the collected materials and converting them into text data, an analysis means for analyzing the text data to determine whether or not there is fraud and the risk level, a document generation means for quickly generating litigation documents based on the analysis results and adjusting the display method based on the user's emotional state, and an emotion engine for analyzing the user's emotional state from input and behavior. This makes it possible to automate litigation preparation and security risk identification, and also to provide risk avoidance measures that take the user's emotional state into consideration.

[1122] "Data collection instrument" means any device or software capable of collecting and storing materials relevant to a litigation.

[1123] "OCR tool" means a device or software that uses optical character recognition technology to scan collected materials and convert image data into text data.

[1124] "Analysis means" refers to a device or software that has the function of analyzing text data and determining whether or not there is fraud and the risk level.

[1125] "Document generation means" refers to a device or software that generates rapid legal documents based on the analysis results and adjusts the presentation based on the user's emotional state.

[1126] An "emotion engine" is a device or software that has the function of analyzing a user's emotional state from their input and actions.

[1127] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[1128] System Configuration

[1129] The present invention comprises a system including a data collection means, an OCR means, an analysis means, a document generation means, and an emotion engine, which digitizes and analyzes materials related to litigation and security risks, and further supports litigation preparation and risk management by taking into account the user's emotional state.

[1130] Program processing overview

[1131] Data collection methods

[1132] The user scans or electronically prepares documents related to litigation or security risks (e.g., reports, invoices, etc.) using a terminal. Then, the user clicks the "Upload" button on the terminal, selects the target documents from the file selection dialog, and uploads them. The server receives the documents sent from the terminal, saves them in the appropriate folder, and records the metadata in a database.

[1133] OCR means

[1134] The server passes the stored data to an OCR tool (using optical character recognition technology), which extracts the text from the image data and converts it into character data. During this process, image preprocessing (noise removal, contrast adjustment, etc.) is performed to improve the accuracy of character recognition.

[1135] Analysis means

[1136] The server passes the text data to the analysis means, which analyzes the content based on the legal documents and security risk criteria. The analysis means determines the possibility of fraud and the risk level, and returns the results to the server.

[1137] Emotion Engine

[1138] The emotion engine evaluates the inputs and actions of users when operating their devices (e.g., click speed, text entry speed, etc.). The emotion engine then feeds back the user's emotional state (e.g., stress, anxiety, relief) to the analysis means. The analysis means can incorporate this emotional data into litigation documents and risk analysis results.

[1139] Document Generation Method

[1140] When a user requests the creation of litigation materials and risk avoidance measures from a terminal, the server activates a document generation means based on the analysis results. The document generation means automatically generates the necessary documents quickly and efficiently. The display method and document structure may be adjusted based on the user's emotional state.

[1141] Specific examples

[1142] For example, if a user submits a scanned image of a report about unauthorized access and comments, "I'm very worried about the current situation. I need help," the system will process the scanned image with OCR and analyze the extracted text data to determine the risk level. At the same time, the emotion engine will detect the user's anxiety and, based on the analysis results, determine that the risk is high and provide advice to stay calm.

[1143] Example of a generative AI model prompt:

[1144] Input: "I'm really worried about my current situation. I need help."

[1145] Output: "We understand your concerns. The risks are high, so take appropriate measures immediately."

[1146] The system enables users to receive appropriate support that is efficient and takes into account their emotional state.

[1147] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1148] Step 1:

[1149] The user uses a terminal to prepare documents related to litigation or security risks in scanned or electronic format. When the user clicks the document upload button, a file selection dialog appears, allowing the user to select and upload the desired documents. The server receives the documents sent from the terminal and stores them in the appropriate folder. The metadata is recorded in a database. The input is the documents uploaded by the user, and the output is the digital documents stored on the server.

[1150] Step 2:

[1151] The server passes the stored material to the OCR means. The OCR means extracts the text in the image data and converts it into character data. During this process, image preprocessing such as noise removal and contrast adjustment is performed to improve the accuracy of character recognition. The input is the stored image data, and the output is text data. Specifically, the OCR means analyzes the image and extracts the text.

[1152] Step 3:

[1153] The server passes the text data to the analysis means, which analyzes the content based on litigation materials and security risk criteria. The analysis means determines the possibility of fraud and the risk level, and returns the results to the server. The input is text data, and the output is the analysis result. Specifically, the analysis means analyzes the text and evaluates it against the criteria.

[1154] Step 4:

[1155] The emotion engine evaluates the inputs and actions (e.g., click speed, text input speed, etc.) made by the user when operating the device. The emotion engine then feeds back the user's emotional state (stress, anxiety, relief, etc.) to the analysis means. The input is the user's behavioral data, and the output is emotional state data. Specifically, the emotion engine analyzes the behavioral data in real time and estimates emotions.

[1156] Step 5:

[1157] When a user requests the creation of litigation materials and risk avoidance measures from a terminal, the server activates the document generation means based on the analysis results. The document generation means automatically generates the required documents quickly and efficiently. The display method and document structure may be adjusted based on the user's emotional state. The input is the user's request and the analysis results, and the output is the generated document. In concrete terms, the document generation means creates a document based on the result data and provides it to the user.

[1158] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1159] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1160] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1161] [Fourth embodiment]

[1162] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1163] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1164] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1165] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1166] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1167] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1168] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1169] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1170] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1171] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1172] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1173] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1174] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1175] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[1176] System Configuration

[1177] The present invention is comprised of a system including a user terminal, a server, data collection means, OCR means, analysis means, and document generation means. This system is designed to digitize litigation-related materials and rapidly analyze and generate documents.

[1178] Program processing overview

[1179] Data collection

[1180] Users use their devices to scan or upload documents related to the case (e.g., invoices and construction records) in electronic format, which are then sent to the server and stored in the appropriate folders.

[1181] Example: A user uploads "Lawsuit Invoice.pdf" from their device. The server receives it and saves it in a specified folder.

[1182] OCR processing

[1183] The server passes the stored data to an OCR device (using optical character recognition technology), which extracts the text from the image data and converts it into character data.

[1184] Example: The OCR tool scans "Litigation Invoice.pdf" and extracts text data such as "Company A, Construction Cost, 500,000 yen." The server acquires this text data and saves it linked to the original file.

[1185] Analysis of data

[1186] The server passes the text data to the analysis means, which analyzes the content based on the criteria for litigation materials. The analysis means determines whether there is any possibility of fraudulent activity and returns the results to the server.

[1187] Example: The analysis means analyzes the text data "Company A, construction cost, 500,000 yen" and compares it with the market price. This determines that the billing amount may be fraudulent, and sends the result to the server. The server stores this in a database.

[1188] Document Generation

[1189] When a user requests the creation of litigation documents from a terminal, the server activates the document generation means based on the analysis results, which automatically generates the necessary litigation documents quickly and efficiently.

[1190] Example: A user makes a request from the litigation document creation screen. The server uses the generation means to create litigation documents based on the analysis results and source materials, and provides them to the user in a downloadable format.

[1191] effect

[1192] This system automates the collection, analysis, and document generation of materials required for litigation, significantly reducing the time and effort required for litigation preparation. It also enables the rapid detection of fraudulent activity and appropriate responses, thereby providing support to the socially vulnerable in particular in effectively filing lawsuits.

[1193] The processing flow will be explained below.

[1194] Step 1:

[1195] The user prepares documents related to the lawsuit (such as invoices and construction records) in electronic format or scans them using the terminal, then clicks the "Upload" button on the terminal, selects the documents from the file selection dialog, and uploads them.

[1196] Step 2:

[1197] The server receives the data sent from the device, stores it in the appropriate format (e.g., PDF or image file), and records the data's metadata (upload date and time, original file name, etc.) in a database.

[1198] Step 3:

[1199] The server passes the stored data to the AI-OCR module, which extracts text from the image data and converts it into character data. During the OCR process, image preprocessing (such as noise reduction and contrast adjustment) is performed to improve the accuracy of character recognition.

[1200] Step 4:

[1201] The AI-OCR module extracts text data such as "Company A, construction cost, 500,000 yen" from the image data and returns this text data to the server.

[1202] Step 5:

[1203] The server links the acquired text data to the original material and stores it in a database, allowing the necessary data to be quickly retrieved for subsequent processing.

[1204] Step 6:

[1205] The server passes the saved text data to an analysis tool that incorporates pre-trained criteria for judging litigation documents, and analyzes the contents of the documents based on these criteria to determine whether or not there is any fraud.

[1206] Step 7:

[1207] The analysis tool evaluates the text data and determines whether each document is likely to contain fraud. For example, it may determine that "Company A, construction cost, 500,000 yen" is higher than the market price and evaluate it as likely to contain fraud.

[1208] Step 8:

[1209] The server stores the analysis results in a database and links them to the original documents, allowing for centralized management of all the information needed for litigation.

[1210] Step 9:

[1211] The user requests the creation of litigation documents from their terminal. On the litigation document creation screen, they enter the necessary information and click the "Generate" button.

[1212] Step 10:

[1213] The server retrieves the relevant materials and analysis results from the database and activates the document generation means, which automatically generates the necessary documents (litigation documents, evidence lists, analysis result reports, etc.) in template format.

[1214] Step 11:

[1215] The server provides the generated litigation materials in a format that can be downloaded by the user. The user can check the generated documents on their device and download them as needed to use them in litigation preparations.

[1216] This processing flow automates the process from collecting materials required for litigation to analyzing them and generating documents, enabling litigation preparation to be carried out quickly and efficiently.

[1217] Example 1

[1218] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1219] In conventional litigation document collection and analysis systems, the process of digitizing and analyzing documents was often done manually, which was time-consuming and labor-intensive. It was also difficult to quickly and accurately detect any misconduct in documents, placing a significant burden on litigation preparation. As a result, it was difficult for vulnerable groups, especially those in society, to file lawsuits effectively.

[1220] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1221] In this invention, the server includes a data collection means for collecting and storing litigation-related materials, an optical character recognition means for scanning the collected materials and converting them into text data, an analysis means for analyzing the text data and determining whether or not there is any fraud, and a document generation means for generating litigation documents based on the analysis results upon request from the user. This makes it possible to automate the entire process from collecting litigation materials to analyzing them and generating documents.

[1222] A "data collection instrument" is a device or system for collecting and storing materials relevant to a litigation.

[1223] An "optical character recognition means" is a device or system that uses technology to extract text from scanned image data and convert it into digital character data.

[1224] The "analysis means" is a device or system that analyzes the extracted text data and evaluates the content of the material based on the presence or absence of fraud or other specific criteria.

[1225] The "document generation means" is a device or system that quickly and automatically generates litigation documents based on the analysis results.

[1226] A "server" is a device or system that includes a data collection means, an optical character recognition means, an analysis means, and a document generation means, and that integrates and manages these functions.

[1227] "User" means any person or entity that utilizes the System to manage, analyze, and request document generation related to litigation.

[1228] "Documents" refers to documents, records, and electronic data containing information relevant to the litigation.

[1229] A "folder" is a virtual storage location within a server where data is systematically organized and saved.

[1230] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[1231] System Configuration

[1232] The present invention comprises a system including a user terminal, a server, a data collection means, an optical character recognition means, an analysis means, and a document generation means, and is intended to digitize litigation-related materials and rapidly analyze and generate documents.

[1233] Program processing overview

[1234] Data collection

[1235] Users use their devices to scan or upload documents related to the case (e.g., invoices and construction records) in electronic format, which are then sent to the server and stored in the appropriate folders.

[1236] Example: A user uploads "Lawsuit Invoice.pdf" from their device. The server receives it and saves it in a specified folder.

[1237] Optical Character Recognition Processing

[1238] The server passes the stored data to an optical character recognition (OCR) tool, which extracts the text in the image data and converts it into character data.

[1239] Example: The OCR tool scans "Litigation Invoice.pdf" and extracts text data such as "Company A, Construction Cost, 500,000 yen." The server acquires this text data and saves it linked to the original file.

[1240] Analysis of data

[1241] The server passes the text data to the analysis means, which analyzes the content based on the criteria for litigation materials. The analysis means determines whether there is any possibility of fraudulent activity and returns the results to the server.

[1242] Example: The analysis means analyzes the text data "Company A, construction cost, 500,000 yen" and compares it with the market price. This determines that the billing amount may be fraudulent, and sends the result to the server. The server stores this in a database.

[1243] Document Generation

[1244] When a user requests the creation of litigation documents from a terminal, the server activates the document generation means based on the analysis results, which automatically generates the necessary litigation documents quickly and efficiently.

[1245] Example: A user makes a request from the litigation document creation screen. The server uses the generation means to create litigation documents based on the analysis results and source materials, and provides them to the user in a downloadable format.

[1246] effect

[1247] This system automates the collection, analysis, and document generation of materials required for litigation, significantly reducing the time and effort required for litigation preparation. It also enables the rapid detection of fraudulent activity and appropriate responses, thereby providing support to the socially vulnerable in particular in effectively filing lawsuits.

[1248] Prompt Sentence Examples

[1249] "Please tell me the specific steps to upload a litigation claim form to the system, run OCR and analysis, and ultimately generate the litigation document."

[1250] Hardware and software used

[1251] A scanner or camera is connected to the user's device, and relevant documents are scanned as electronic data. The server is equipped with a powerful processor and large-capacity storage, and is installed with data collection means, optical character recognition means, analysis means, and document generation means. OCR technologies such as Tesseract and Google Cloud Vision are used. Natural language processing models and generative AI models are used for analysis means.

[1252] Based on the above system configuration and processing overview, litigation-related materials are automatically digitized, analyzed, and litigation documents are quickly generated.

[1253] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1254] Step 1:

[1255] A user uses the device to upload materials related to the case.

[1256] Specific behavior:

[1257] The user opens the file selection screen on the terminal and selects the electronic file of the litigation materials (e.g., "Litigation Invoice.pdf").

[1258] The user clicks the "Upload" button.

[1259] Input: Electronic format document files

[1260] Output: Sending a file from the terminal to the server

[1261] Step 2:

[1262] The server stores the received materials.

[1263] Specific behavior:

[1264] The server receives the file sent from the terminal.

[1265] The server stores the received file in the "New Litigation Documents" folder.

[1266] Input: Data file sent from the terminal

[1267] Output: Document files saved in the "New Litigation Documents" folder

[1268] Step 3:

[1269] The server passes the stored material to an optical character recognition (OCR) facility.

[1270] Specific behavior:

[1271] The server scans the "New Case Files" folder for new files.

[1272] The server passes the scanned file to the OCR means.

[1273] Input: Saved document file

[1274] Output: Image data passed to the OCR tool

[1275] Step 4:

[1276] An OCR means extracts text from the image data.

[1277] Specific behavior:

[1278] The OCR means processes the scanned image data and converts it into text data (e.g., "Company A, construction cost, 500,000 yen").

[1279] The extracted character data is converted into a text file.

[1280] Input: Image data passed to the OCR tool

[1281] Output: Extracted text data file

[1282] Step 5:

[1283] The server stores the text data file and links it to the original file.

[1284] Specific behavior:

[1285] The server receives the text data obtained from the OCR means.

[1286] Save the text data file and link it to the original scan file.

[1287] Input: Text data file from OCR tool

[1288] Output: Linked text data files and scan files

[1289] Step 6:

[1290] The server passes the text data to the analysis means.

[1291] Specific behavior:

[1292] The server passes the linked text data file to the analysis means.

[1293] Input: Linked text data file

[1294] Output: Text data passed to the analysis tool

[1295] Step 7:

[1296] The analysis means analyzes the text data and determines whether or not there is any fraud.

[1297] Specific behavior:

[1298] The analysis means compares the text data with standards such as market prices.

[1299] Determines the possibility of fraud and generates a result (e.g., "Company A, construction cost, 500,000 yen" is compared with the market price and determined to be a possible indication of fraud).

[1300] Input: Text data passed to the analysis tool

[1301] Output: Analysis results including whether or not there was fraud

[1302] Step 8:

[1303] The server stores the analysis results and activates the document generation means when requested by the user.

[1304] Specific behavior:

[1305] The server stores the analysis results obtained from the analysis means in a database.

[1306] When a user requests document generation from a terminal, the server activates document generation means based on the analysis results.

[1307] Input: Analysis results, document generation request from user

[1308] Output: Invokes the document generation method

[1309] Step 9:

[1310] A document generation means automatically generates a litigation document.

[1311] Specific behavior:

[1312] The document generation means creates litigation documents based on the analysis results and the original materials.

[1313] The generated documentation is made available to users in a downloadable format.

[1314] Input: Analysis results, source data

[1315] Output: Generated legal document

[1316] Step 10:

[1317] The user downloads the generated litigation document.

[1318] Specific behavior:

[1319] The server provides the user with a download link or button.

[1320] The user clicks on the download link or button to obtain the generated litigation document.

[1321] Input: Generated legal documents

[1322] Output: The case documents downloaded by the user

[1323] (Application example 1)

[1324] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1325] Modern logistics centers handle a wide variety of documents, and manual management and input errors reduce operational efficiency while requiring a great deal of time and effort. There are also many challenges in early detection of fraudulent activity and appropriate response. Therefore, there is a need for a method to efficiently digitize, analyze, and automatically generate documents, thereby reducing errors and improving operational efficiency.

[1326] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1327] In this invention, the server includes a data collection means for collecting and storing documents, an OCR means for scanning the collected documents and converting them into text data, an analysis means for analyzing the text data and determining whether or not there is fraud, a document generation means for quickly generating business documents based on the analysis results, and a classification means for automatically classifying input documents and generating business documents accordingly. This enables complete automation and optimization of document management in a logistics center.

[1328] "Data collection means" means means for collecting and storing data.

[1329] "OCR Method" means a method that uses optical character recognition technology to scan collected materials and convert them into text data.

[1330] The "analysis means" is a means for analyzing text data and determining whether or not there is fraud.

[1331] The "document generation means" is a means for quickly generating business documents based on the analysis results.

[1332] The "classification means" is a means for automatically classifying input materials and generating business documents accordingly.

[1333] System Configuration

[1334] This invention aims to improve the efficiency of document management in logistics centers by providing a system for digitizing, analyzing, and automatically generating documents. This system consists of a user terminal, a server, data collection means, OCR means, analysis means, document generation means, and classification means.

[1335] Program processing overview

[1336] Data collection

[1337] Users use their smartphones or robots to scan or electronically submit documents such as delivery notes and shipping instructions, which are then sent to the server and stored in the appropriate folders.

[1338] OCR processing

[1339] The server passes the saved documents to the OCR tool, which extracts the text from the image data. The OCR tool uses the Google Vision API or similar to convert the images of delivery notes and shipping instructions into text data.

[1340] Analysis of data

[1341] The server analyzes the extracted text data using analytical tools to determine whether there is any fraud and to extract information necessary for business purposes. This analysis is performed using the Python pandas library, etc.

[1342] Document Generation

[1343] When a user requests the creation of a business document from a terminal, the server activates the document generation means based on the analysis results. The document generation means uses LaTeX, Word API, etc. to quickly and automatically generate the required document.

[1344] Data classification

[1345] The server automatically classifies the input materials using a classification means and generates documents according to specific business processes. For example, it automatically extracts data necessary for inventory management or purchase order generation and generates corresponding documents.

[1346] Hardware and software used

[1347] Hardware: Smartphones (e.g., iPhone), robots (e.g., autonomous driving carriers in logistics centers), servers (e.g., Amazon Web Services, Google Cloud)

[1348] Software: OCR tools (e.g., Google Vision API), data analysis tools (e.g., Python's pandas library), document generation tools (e.g., LaTeX, Word API)

[1349] Specific examples

[1350] Take a delivery note as an example. A user scans the delivery note using their smartphone camera and uploads it as an image to the server. The server receives the image and extracts text data using the Google Vision API. This text data is then parsed using Python's pandas library to obtain the necessary information for inventory management and purchase order generation. Finally, the inventory list and purchase order are automatically generated using LaTeX or Word APIs and made available for download by the user.

[1351] Prompt Sentence Examples

[1352] For example, give the generative AI model the following prompt:

[1353] Design an inventory management system for use in a distribution center. This system will digitize paper delivery notes and shipping instructions using a camera, extract text data using OCR technology, and then use analysis technology to update inventory lists and automatically generate purchase orders based on product information. The generated digital documents will be made available to users in a downloadable format.

[1354] In this way, the present invention can improve the efficiency of document management in a logistics center, and can also improve the speed and accuracy of operations.

[1355] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1356] Step 1:

[1357] Users use smartphones or robots to scan or send documents such as delivery notes and shipping instructions in electronic format. The input data is the paper delivery note or shipping instruction, and the output is the scanned image data or a file in electronic format.

[1358] Step 2:

[1359] The server stores the received image data and electronic format files. The input data is the scanned image or electronic format file in step 1, and the output is the file saved in an appropriate folder on the server.

[1360] Step 3:

[1361] The server passes the stored documents to an OCR tool and extracts the text from the image data. Specifically, it uses an OCR tool (for example, Google Vision API) to convert images of delivery notes and shipping instructions into text data. The input data is the stored image data, and the output is the extracted text data.

[1362] Step 4:

[1363] The server uses analysis tools to analyze the extracted text data and extract information necessary for business purposes, such as whether there is any fraud. Specifically, it uses the Python pandas library to analyze the contents of delivery notes and shipping instructions and extract the necessary data. The input data is text data generated by OCR tools, and the output is the analyzed information necessary for business purposes.

[1364] Step 5:

[1365] The server automatically classifies the input materials using the classification means. Based on the data obtained by the analysis means, it generates documents corresponding to specific business processes (e.g., inventory management or purchase order generation). The input data is the analyzed information required for the business, and the output is the classified data and documents corresponding to the specific business process.

[1366] Step 6:

[1367] When a user requests the creation of a business document from a terminal, the server activates the document generation means and automatically generates the required document. Specifically, it uses LaTeX and Word APIs to generate inventory lists, purchase orders, etc. The input data are the analysis and classification results, and the output is the automatically generated business document.

[1368] Step 7:

[1369] The server provides the generated business document in a format that can be downloaded by the user. The input data is the automatically generated business document, and the output is a download link to the user's terminal.

[1370] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1371] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[1372] System Configuration

[1373] The present invention is composed of a system including a user terminal, a server, data collection means, OCR means, analysis means, document generation means, and an emotion engine that recognizes the user's emotions. This system digitizes and analyzes documents related to litigation, and further supports litigation preparation by taking into account the user's emotional state.

[1374] Program processing overview

[1375] Data collection

[1376] The user scans or electronically prepares documents related to the lawsuit (such as invoices and construction records) using a terminal. Then, they click the "Upload" button on the terminal, select the target documents from the file selection dialog, and upload them. The server receives the documents sent from the terminal, saves them in the appropriate folder, and records the metadata in the database.

[1377] Example: A user uploads "Lawsuit Invoice.pdf" from their device. The server receives it and saves it in a specified folder.

[1378] OCR processing

[1379] The server passes the stored data to an OCR tool (using optical character recognition technology), which extracts the text from the image data and converts it into character data. During this process, image preprocessing (noise removal, contrast adjustment, etc.) is performed to improve the accuracy of character recognition.

[1380] Example: The OCR tool scans "Litigation Invoice.pdf" and extracts text data such as "Company A, Construction Cost, 500,000 yen." The server acquires this text data and saves it linked to the original file.

[1381] Analysis of data

[1382] The server passes the text data to the analysis means, which analyzes the content based on the criteria for legal documents. The analysis means determines whether there is any possibility of fraud and returns the results to the server. In addition, feedback from the emotion engine is also taken into account.

[1383] Example: The analysis means analyzes the text data "Company A, construction cost, 500,000 yen" and compares it with the market price. This determines that the billing amount may be fraudulent, and sends the result to the server. The server stores this in a database.

[1384] Emotion engine processing

[1385] The emotion engine evaluates the inputs and actions of the user when operating the device (e.g., click speed, text entry speed, etc.). The emotion engine then feeds back the user's emotional state (stress, anxiety, relief, etc.) to the analysis means. The analysis means can incorporate this emotional data into the analysis results of the litigation materials.

[1386] Example: If the emotion engine determines that anxiety is increasing based on the user's input data, the server will provide feedback to the analysis means.

[1387] Document Generation

[1388] When a user requests the creation of litigation documents from a terminal, the server activates the document generation means based on the analysis results. The document generation means automatically generates the necessary litigation documents quickly and efficiently. The display method and document structure may be adjusted based on the user's emotional state.

[1389] Example: A user makes a request from the litigation document creation screen. The server uses generation means to create litigation documents based on the analysis results and source materials, and provides them in a format that the user can download. If the user's anxiety is increasing, kind language and concise explanations are used.

[1390] effect

[1391] This system automates the collection, analysis, and document generation of materials necessary for litigation, significantly reducing the time and effort required for litigation preparation. It also enables the rapid detection of fraudulent activity and appropriate responses, helping particularly vulnerable people to file lawsuits effectively. The introduction of an emotion engine allows for litigation preparation that takes into account the user's emotional state, providing more effective support.

[1392] The processing flow will be explained below.

[1393] Step 1:

[1394] The user prepares documents related to the lawsuit (such as invoices and construction records) in electronic format or scans them using the terminal, then clicks the "Upload" button on the terminal, selects the documents from the file selection dialog, and uploads them.

[1395] Step 2:

[1396] The server receives the data sent from the device, saves it in the appropriate folder, and records the data's metadata (upload date and time, original file name, etc.) in a database.

[1397] Step 3:

[1398] The server passes the stored data to the OCR tool, which uses optical character recognition technology to extract text from the image data and convert it into character data. During this process, preprocessing such as noise removal and contrast adjustment is performed to improve the accuracy of character recognition.

[1399] Step 4:

[1400] The OCR means extracts text data such as "Company A, construction cost, 500,000 yen" from the image data and returns this text data to the server.

[1401] Step 5:

[1402] The server links the acquired text data to the original material and stores it in a database.

[1403] Step 6:

[1404] The server passes the saved text data to the analysis means, which analyzes the content of the documents based on pre-trained criteria for litigation documents and determines whether or not there is any fraud.

[1405] Step 7:

[1406] The analysis means evaluates the text data and determines that "Company A, construction cost, 500,000 yen" may be fraudulent when compared to the market price. Based on this, the analysis results are sent to the server.

[1407] Step 8:

[1408] The server stores the analysis results in a database and links them to the original materials.

[1409] Step 9:

[1410] While the user is operating the device, the emotion engine evaluates the user's inputs and actions (e.g., click speed, text entry speed, mouse movements, etc.).

[1411] Step 10:

[1412] The emotion engine analyzes the user's emotional state (e.g., stress, anxiety, impatience, etc.) and feeds the results back to the server.

[1413] Step 11:

[1414] When a user requests the creation of a lawsuit document from a terminal, the server receives this request. The user enters the necessary information on the lawsuit document creation screen and clicks the "Generate" button.

[1415] Step 12:

[1416] The server retrieves the relevant materials and analysis results from the database and activates the document generation means, which automatically generates the necessary litigation documents (such as a complaint, a list of evidence, and a report on the analysis results) based on the analysis results and feedback from the emotion engine.

[1417] Step 13:

[1418] The server provides the generated litigation materials to the user in a format that can be downloaded. The user can review the generated documents on their device and download them as needed to use them in litigation preparations. The way the content is displayed may be adjusted based on the user's emotional state (for example, if the user is feeling anxious, explanations may be displayed in simple, gentle language).

[1419] This process automates the collection, analysis, emotional feedback, and document generation of materials necessary for litigation, allowing for fast and efficient litigation preparation. Furthermore, the introduction of an emotion engine enables support that takes into account the user's emotional state, resulting in more effective litigation preparation.

[1420] Example 2

[1421] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1422] In recent years, the digitization and analysis of litigation-related materials has become an important issue, but it is often extremely time-consuming and labor-intensive. Furthermore, detecting fraud requires advanced analysis, and support that takes into account the user's emotional state is also required. However, conventional systems cannot effectively meet these requirements, making litigation preparation particularly difficult for vulnerable members of society. Therefore, there is a need for a system that can efficiently perform data collection, analysis, and document generation, while also taking into account the user's emotional state.

[1423] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1424] In this invention, the server includes a data collection means for collecting and storing litigation-related records, an optical character recognition means for scanning the collected records and converting them into text data, an analysis means for analyzing the text data and determining whether or not there is any fraud, a document generation means for quickly generating litigation documents based on the analysis results, and an emotion engine means for analyzing the user's emotional state and providing feedback to the analysis means. This automates the process from digitizing materials to analyzing them, enabling fast and efficient document generation. Furthermore, the emotion engine analyzes the user's emotional state and provides support based on that analysis, thereby providing support for litigation preparation, particularly for the socially vulnerable.

[1425] "Litigation-related records" are document information such as invoices, contracts, and construction records collected in connection with litigation.

[1426] A "data collection tool" is a function or interface that allows a user to submit records related to a lawsuit to a server.

[1427] "Optical character recognition" refers to techniques and processes for extracting characters from image data and converting them into text data.

[1428] "Analysis means" refers to algorithms or systems that analyze the content of text data and determine whether or not there is fraudulent activity.

[1429] "Document generation means" refers to a function or system that automatically generates litigation documents quickly and efficiently based on the analysis results.

[1430] The "emotion engine means" is a system that analyzes the emotional state based on the user's input data and actions, and provides feedback to the analysis means.

[1431] "Emotional state" refers to the psychological state such as stress, anxiety, or relief that a user feels when operating a system.

[1432] "Feedback" refers to emotion analysis data provided by emotion engine means to analysis means.

[1433] "Litigation documents" are documents that contain information necessary for litigation and are required for legal proceedings.

[1434] System Configuration

[1435] The present invention comprises a system including a user terminal, a server, a data collection means, an optical character recognition means (OCR), an analysis means, a document generation means, and an emotion engine that recognizes the user's emotions. The system digitizes and analyzes records related to litigation, and further supports litigation preparation by taking into account the user's emotional state.

[1436] Program processing

[1437] The system of the present invention operates through the following main processing steps: Specific hardware and software names are also specified.

[1438] Data collection

[1439] The user prepares records related to the lawsuit (invoices, construction records, etc.) and scans them, or saves records already in electronic format to the device. The user uses the device's browser or a dedicated app to click the "Upload" button. Then, the user selects the target records from the file selection dialog and clicks the "Send File" button to send the documents to the server. As a concrete example, the user uploads "Lawsuit Invoice.pdf" from the device.

[1440] The server receives the records sent from the device and saves them in a designated folder. The server also records the metadata of the document in a database. For example, the server receives "Lawsuit Invoice.pdf" and saves it in the folder " / uploaded_documents / ", and records the file name "Lawsuit Invoice.pdf", upload date and time "2023-10-05 14:30", and user ID "user123" as metadata in the database.

[1441] OCR processing

[1442] The server passes the saved documents to the OCR means. The OCR means extracts text from the image data in the documents and converts it into character data. At this time, noise removal and contrast adjustment are performed as pre-processing of the image. As a concrete example, the OCR means processes "Litigation Invoice.pdf" and extracts text data such as "Company A, Construction Cost, 500,000 yen."

[1443] The server receives the text data sent from the OCR means, links it to the original record file, and saves it in the database. For example, the server receives the text data "Company A, construction cost, 500,000 yen," links it to "Litigation invoice.pdf," and saves it in the database.

[1444] Analysis of data

[1445] The server passes the acquired text data to the analysis means, which analyzes the content using criteria based on the litigation materials. The analysis means evaluates it by comparing it with market rates, legal standards, and patterns of fraudulent activity. As a specific example, the server passes the text data "Company A, construction cost, 500,000 yen" to the analysis means and determines whether this is higher than the market rate or whether there is a possibility of fraud. The analysis means compares it with market rates and returns a result stating that there is a "high possibility of fraud."

[1446] The server receives the analysis results from the analysis means and stores them in a database, incorporating feedback from the emotion engine. For example, the server receives a result from the analysis means that "high probability of fraud" and associates it with "Lawsuit Invoice.pdf" and stores it in the database.

[1447] Emotion engine processing

[1448] The emotion engine collects input data and behavioral information (click speed, text input speed, etc.) in real time when the user operates the device. The emotion engine analyzes the user's emotional state based on this data and feeds the results back to the analysis means. In concrete terms, if a user clicks quickly when uploading documents, the emotion engine collects this information and determines that the user is in a hurry.

[1449] Document Generation

[1450] When a user requests the creation of documents from the litigation document creation screen on the terminal, the server activates the document generation means based on the analysis results and feedback from the emotion engine, and automatically generates the necessary litigation documents.As a specific example, when a user requests the creation of documents from the litigation document creation screen, the server uses the document generation means to create litigation documents using gentle language based on the analysis result "Possibility of fraud" and the emotion engine's feedback "The user is feeling anxious."

[1451] effect

[1452] This system automates the process from digitizing materials to analyzing them, enabling fast and efficient document generation. Furthermore, an emotion engine analyzes the user's emotional state and provides support based on that analysis, thereby supporting litigation preparation, particularly for vulnerable members of society. It also enables early detection of fraudulent activity and appropriate responses, significantly reducing the overall time and effort required for litigation preparation.

[1453] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1454] Step 1:

[1455] The user scans records relevant to the lawsuit (e.g., invoices or construction records) or prepares records already in electronic format and saves them on the device. Next, the user clicks the "Upload" button using the device's browser or a dedicated app. A file selection dialog appears, and the user selects the target record file and clicks the "Send File" button to send the document to the server.

[1456] Input: Record file saved on the device (e.g., litigation claim form.pdf)

[1457] Output: Record file sent to server

[1458] Specific operation: The user selects "Litigation Invoice.pdf" from the terminal and clicks the upload button to send the file to the server.

[1459] Step 2:

[1460] The server receives the records sent from the terminal and saves them in a designated folder. In addition, the server records the metadata of the uploaded records (e.g., file name, upload date and time, user ID, etc.) in a database.

[1461] Input: The submitted record file

[1462] Output: Saved recording files and recording metadata

[1463] Specific operation: The server receives "Lawsuit Invoice.pdf" and saves it in the folder " / uploaded_documents / ". It also records the file name "Lawsuit Invoice.pdf", the upload date and time "2023-10-05 14:30", and the user ID "user123" in the database.

[1464] Step 3:

[1465] The server passes the stored records to an optical character recognition (OCR) tool, which detects text from the image data in the records and converts it into character data. Image preprocessing such as noise reduction and contrast adjustment improves the accuracy of character recognition.

[1466] Input: Saved recording file

[1467] Output: Text converted to character data

[1468] Specific operation: The OCR tool processes "Litigation Invoice.pdf", removes noise and adjusts contrast, and then extracts text data such as "Company A, construction cost, 500,000 yen."

[1469] Step 4:

[1470] The server receives the text data sent from the OCR means, links it to the original recording file, and stores it in a database.

[1471] Input: Text data sent from the OCR tool

[1472] Output: Saved text data and link information

[1473] Specific operation: The server receives the text data "Company A, construction cost, 500,000 yen" from the OCR means, links it to "Litigation invoice.pdf" and saves it in the database.

[1474] Step 5:

[1475] The server passes the acquired text data to an analysis means, which performs a content analysis based on the text data. The analysis means evaluates the data by comparing it with market rates, legal standards, patterns of fraudulent activity, etc.

[1476] Input: Received text data

[1477] Output: Analyzed data and evaluation results

[1478] Specific operation: The server passes the text data "Company A, construction cost, 500,000 yen" to the analysis means, compares it with the market price, and receives an evaluation result such as "high possibility of fraud."

[1479] Step 6:

[1480] The server receives the evaluation results from the analysis means and stores them in a database, while also incorporating feedback from the emotion engine.

[1481] Input: Evaluation results from the analysis means and feedback from the emotion engine

[1482] Output: Evaluation results stored in a database

[1483] Specific operation: The server receives the evaluation result of "high possibility of fraud," associates it with "Lawsuit Invoice.pdf," and stores it in the database. It also records the feedback information from the emotion engine.

[1484] Step 7:

[1485] The emotion engine collects input data and behavioral information (e.g., click speed, text input speed, etc.) when the user operates the device. Based on this data, it analyzes the user's emotional state and feeds the results back to the analysis means.

[1486] Input: User operation data

[1487] Output: Parsed emotion data

[1488] Specific operation: If a user clicks quickly when uploading documents, the emotion engine analyzes the data and determines that the user is in a hurry.

[1489] Step 8:

[1490] The user performs an operation to request the creation of documents from the litigation document creation screen on the terminal.

[1491] Input: Request for document creation

[1492] Output: The server that received the create request

[1493] Specific operation: The user opens the litigation document creation screen on the terminal and clicks the "Create Document" button.

[1494] Step 9:

[1495] The server activates the document generation means based on the analysis results and feedback from the emotion engine, and automatically generates the necessary litigation documents. The generated documents are then provided to users in a downloadable format.

[1496] Input: Analysis results, emotional feedback, document creation request

[1497] Output: Generated case documents

[1498] Specific operation: Based on the analysis result that "there is a possibility of fraud" and the emotional feedback that "the user is feeling anxious," the server uses a document generation means to create a gently worded lawsuit document and makes it available for the user to download.

[1499] (Application example 2)

[1500] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1501] While conventional litigation preparation systems automate the digitization and analysis of documents, they lack support that takes into account the user's emotional state. Furthermore, they have difficulty responding to situations where security risks must be identified in addition to fraud detection. This makes it difficult to provide appropriate risk avoidance measures when users feel anxious, resulting in the problem of being unable to provide optimal support.

[1502] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1503] In this invention, the server includes a data collection means for collecting and storing litigation-related materials, an OCR means for scanning the collected materials and converting them into text data, an analysis means for analyzing the text data to determine whether or not there is fraud and the risk level, a document generation means for quickly generating litigation documents based on the analysis results and adjusting the display method based on the user's emotional state, and an emotion engine for analyzing the user's emotional state from input and behavior. This makes it possible to automate litigation preparation and security risk identification, and also to provide risk avoidance measures that take the user's emotional state into consideration.

[1504] "Data collection instrument" means any device or software capable of collecting and storing materials relevant to a litigation.

[1505] "OCR tool" means a device or software that uses optical character recognition technology to scan collected materials and convert image data into text data.

[1506] "Analysis means" refers to a device or software that has the function of analyzing text data and determining whether or not there is fraud and the risk level.

[1507] "Document generation means" refers to a device or software that generates rapid legal documents based on the analysis results and adjusts the presentation based on the user's emotional state.

[1508] An "emotion engine" is a device or software that has the function of analyzing a user's emotional state from their input and actions.

[1509] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[1510] System Configuration

[1511] The present invention comprises a system including a data collection means, an OCR means, an analysis means, a document generation means, and an emotion engine, which digitizes and analyzes materials related to litigation and security risks, and further supports litigation preparation and risk management by taking into account the user's emotional state.

[1512] Program processing overview

[1513] Data collection methods

[1514] The user scans or electronically prepares documents related to litigation or security risks (e.g., reports, invoices, etc.) using a terminal. Then, the user clicks the "Upload" button on the terminal, selects the target documents from the file selection dialog, and uploads them. The server receives the documents sent from the terminal, saves them in the appropriate folder, and records the metadata in a database.

[1515] OCR means

[1516] The server passes the stored data to an OCR tool (using optical character recognition technology), which extracts the text from the image data and converts it into character data. During this process, image preprocessing (noise removal, contrast adjustment, etc.) is performed to improve the accuracy of character recognition.

[1517] Analysis means

[1518] The server passes the text data to the analysis means, which analyzes the content based on the legal documents and security risk criteria. The analysis means determines the possibility of fraud and the risk level, and returns the results to the server.

[1519] Emotion Engine

[1520] The emotion engine evaluates the inputs and actions of users when operating their devices (e.g., click speed, text entry speed, etc.). The emotion engine then feeds back the user's emotional state (e.g., stress, anxiety, relief) to the analysis means. The analysis means can incorporate this emotional data into litigation documents and risk analysis results.

[1521] Document Generation Method

[1522] When a user requests the creation of litigation materials and risk avoidance measures from a terminal, the server activates a document generation means based on the analysis results. The document generation means automatically generates the necessary documents quickly and efficiently. The display method and document structure may be adjusted based on the user's emotional state.

[1523] Specific examples

[1524] For example, if a user submits a scanned image of a report about unauthorized access and comments, "I'm very worried about the current situation. I need help," the system will process the scanned image with OCR and analyze the extracted text data to determine the risk level. At the same time, the emotion engine will detect the user's anxiety and, based on the analysis results, determine that the risk is high and provide advice to stay calm.

[1525] Example of a generative AI model prompt:

[1526] Input: "I'm really worried about my current situation. I need help."

[1527] Output: "We understand your concerns. The risks are high, so take appropriate measures immediately."

[1528] The system enables users to receive appropriate support that is efficient and takes into account their emotional state.

[1529] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1530] Step 1:

[1531] The user uses a terminal to prepare documents related to litigation or security risks in scanned or electronic format. When the user clicks the document upload button, a file selection dialog appears, allowing the user to select and upload the desired documents. The server receives the documents sent from the terminal and stores them in the appropriate folder. The metadata is recorded in a database. The input is the documents uploaded by the user, and the output is the digital documents stored on the server.

[1532] Step 2:

[1533] The server passes the stored material to the OCR means. The OCR means extracts the text in the image data and converts it into character data. During this process, image preprocessing such as noise removal and contrast adjustment is performed to improve the accuracy of character recognition. The input is the stored image data, and the output is text data. Specifically, the OCR means analyzes the image and extracts the text.

[1534] Step 3:

[1535] The server passes the text data to the analysis means, which analyzes the content based on litigation materials and security risk criteria. The analysis means determines the possibility of fraud and the risk level, and returns the results to the server. The input is text data, and the output is the analysis result. Specifically, the analysis means analyzes the text and evaluates it against the criteria.

[1536] Step 4:

[1537] The emotion engine evaluates the inputs and actions (e.g., click speed, text input speed, etc.) made by the user when operating the device. The emotion engine then feeds back the user's emotional state (stress, anxiety, relief, etc.) to the analysis means. The input is the user's behavioral data, and the output is emotional state data. Specifically, the emotion engine analyzes the behavioral data in real time and estimates emotions.

[1538] Step 5:

[1539] When a user requests the creation of litigation materials and risk avoidance measures from a terminal, the server activates the document generation means based on the analysis results. The document generation means automatically generates the required documents quickly and efficiently. The display method and document structure may be adjusted based on the user's emotional state. The input is the user's request and the analysis results, and the output is the generated document. In concrete terms, the document generation means creates a document based on the result data and provides it to the user.

[1540] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1541] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1542] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1543] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1544] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1545] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1546] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1547] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1548] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1549] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1550] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1551] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1552] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1553] 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.

[1554] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1555] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1556] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1557] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1558] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1559] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1560] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1561] The following is further disclosed regarding the above embodiment.

[1562] (Claim 1)

[1563] data collection instruments to collect and store materials relevant to the litigation;

[1564] An OCR method to scan collected materials and convert them into text data;

[1565] an analysis means for analyzing the text data and determining whether or not there is fraud;

[1566] a document generation means for quickly generating litigation documents based on the analysis results;

[1567] A system including:

[1568] (Claim 2)

[1569] 2. The system according to claim 1, wherein the analysis means learns criteria for judging litigation materials and evaluates the content of the materials based on those criteria.

[1570] (Claim 3)

[1571] 10. The system of claim 1, wherein the OCR means pre-processes the image to improve accuracy of character recognition.

[1572] "Example 1"

[1573] (Claim 1)

[1574] data collection instruments to collect and store materials relevant to the litigation;

[1575] Optical character recognition means for scanning the collected materials and converting them into text data;

[1576] an analysis means for analyzing the text data and determining whether or not there is fraud;

[1577] a document generation means for generating a litigation document based on the analysis result when requested by a user;

[1578] A system including:

[1579] (Claim 2)

[1580] 2. The system according to claim 1, wherein the analysis means learns criteria for judging litigation materials and evaluates the content of the materials based on those criteria.

[1581] (Claim 3)

[1582] 10. The system of claim 1, wherein the optical character recognition means pre-processes the image to improve accuracy of character recognition.

[1583] "Application Example 1"

[1584] (Claim 1)

[1585] data collection instruments to collect and store materials relevant to the litigation;

[1586] An OCR method to scan collected materials and convert them into text data;

[1587] an analysis means for analyzing the text data and determining whether or not there is fraud;

[1588] a document generation means for quickly generating litigation documents based on the analysis results;

[1589] a classification means for automatically classifying input materials and generating business documents accordingly;

[1590] A system including:

[1591] (Claim 2)

[1592] 2. The system according to claim 1, wherein the analysis means learns criteria for judging litigation materials and evaluates the content of the materials based on those criteria.

[1593] (Claim 3)

[1594] 10. The system of claim 1, wherein the OCR means pre-processes the image to improve accuracy of character recognition.

[1595] (Claim 4)

[1596] 2. The system according to claim 1, wherein the classification means automatically performs specific business processes such as inventory management and purchase order generation based on the text data extracted by the analysis means.

[1597] "Example 2: Combining Emotion Engines"

[1598] (Claim 1)

[1599] data collection measures to collect and preserve records relevant to the litigation;

[1600] Optical character recognition means for scanning and converting the collected records into text data;

[1601] an analysis means for analyzing the text data and determining whether or not there is fraud;

[1602] a document generation means for quickly generating litigation documents based on the analysis results;

[1603] emotion engine means for analyzing the user's emotional state and feeding it back to the analysis means;

[1604] A system including:

[1605] (Claim 2)

[1606] 2. The system of claim 1, wherein the analysis means learns criteria for judging litigation records and evaluates the contents of the records based on those criteria.

[1607] (Claim 3)

[1608] 10. The system of claim 1, wherein the optical character recognition means pre-processes the image to improve accuracy of character recognition.

[1609] (Claim 4)

[1610] 10. The system of claim 1, utilizing an emotion engine that collects user input data (e.g., click speed, text entry speed, etc.) and analyzes the user's emotional state.

[1611] (Claim 5)

[1612] 2. The system according to claim 1, wherein the document generation means adjusts the display method and structure of the litigation document based on the analysis results of the emotion engine.

[1613] "Application example 2 when combining emotion engines"

[1614] (Claim 1)

[1615] data collection instruments to collect and store materials relevant to the litigation;

[1616] An OCR method to scan collected materials and convert them into text data;

[1617] an analysis means for analyzing the text data and determining whether or not there is fraud and the risk level;

[1618] a document generation means for generating a quick litigation document based on the analysis results and adjusting the display method based on the user's emotional state;

[1619] An emotion engine that analyzes the user's emotional state from their input and behavior;

[1620] A system including:

[1621] (Claim 2)

[1622] 2. The system according to claim 1, wherein the analysis means learns criteria for judging litigation materials and security risks, and evaluates the materials and risk content based on those criteria.

[1623] (Claim 3)

[1624] 10. The system of claim 1, wherein the OCR means pre-processes the image to improve accuracy of character recognition. [Explanation of symbols]

[1625] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. data collection instruments to collect and store materials relevant to the litigation; An OCR method to scan collected materials and convert them into text data; an analysis means for analyzing the text data and determining whether or not there is fraud; a document generation means for quickly generating litigation documents based on the analysis results; A system including:

2. 2. The system according to claim 1, wherein the analysis means learns criteria for judging litigation materials and evaluates the contents of the materials based on the criteria.

3. 10. The system of claim 1, wherein the OCR means pre-processes the image to improve accuracy of character recognition.

Images