system

Abstract

We provide the system. [Solution] Methods for collecting data from past case databases, A means for preprocessing the aforementioned data using natural language processing technology, A means of generating multiple solutions in real time using a trained generative AI model, A means for presenting the generated solution via a user interface, A means of collecting and analyzing user feedback, Means to protect data privacy, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventional dispute resolution has problems that it requires a great deal of time and cost until an agreement is formed among the parties involved, and furthermore, the knowledge obtained from past cases cannot be effectively utilized. In such a situation, means for quickly and efficiently resolving disputes are required. In particular, extracting appropriate solutions from a large amount of data and proposing them in real time is important for reducing time and cost.

Means for Solving the Problems

[0005] This invention trains a generative AI model by collecting relevant data from a database of past cases and preprocessing it using natural language processing technology. This generative AI model is then used to generate multiple solutions in real time and present them through a user interface. Furthermore, it provides a system for collecting user feedback and protecting data privacy. This system aims to expedite and streamline dispute resolution, making it easier for users to find satisfactory solutions.

[0006] A "case database" is a collection of data that has accumulated information on past dispute resolutions and legal precedents.

[0007] "Natural language processing technology" is a technology used to process human language using computers, and is utilized for data analysis and meaning extraction.

[0008] A "generative AI model" is an artificial intelligence model constructed using machine learning techniques based on collected data, and is used to provide multiple solutions.

[0009] A "user interface" is a design that enables human communication, allowing users to input information into a system and to check the output from the system.

[0010] "Feedback collection" is the process of gathering evaluations and opinions from users to help improve the system and enhance the accuracy of suggestions.

[0011] "Privacy protection" refers to technical measures taken to protect users' personal information and input data from external sources and maintain security. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), etc.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] The dispute resolution support system of the present invention has a system configuration that includes a server connected to a network and terminals used by users. The program processing and specific examples of this system are described below.

[0034] Program Processing Overview

[0035] Data acquisition and preprocessing

[0036] The server periodically collects data from external legal databases and public case databases. The collected data is preprocessed using natural language processing techniques, including noise reduction, tokenization, and stop word removal. This prepares the data in a format suitable for training generative AI models.

[0037] Training and application of generative AI models

[0038] The server trains a generative AI model using a large, pre-processed dataset. This model learns past conflict resolution patterns and improves its ability to generate solutions for new cases. When the user provides detailed conflict information, the server uses this generative AI model to identify similar cases and generate several solutions in real time.

[0039] Suggestion presentation via user interface

[0040] The terminal sends details of the problem entered by the user to the server and presents the user with the solution received from the server in response. The user interface is intuitive and displays multiple solutions in a format that makes it easy to compare them.

[0041] Gathering feedback and protecting privacy

[0042] Users input their evaluations and feedback on the presented solutions into their devices. This feedback data is sent to a server and used to improve the generated AI model. The server stores all data using robust encryption technology, ensuring the utmost protection of user privacy.

[0043] Specific example

[0044] For example, consider a dispute arising from a licensing agreement between companies. In this case, the user inputs the contract details, points of disagreement, and the opinions of the parties involved into the terminal. The server receives this information, analyzes similar cases in real time from a vast amount of collected past case data, and proposes solutions such as the following.

[0045] Proposal for phased payment of license fees

[0046] Arbitration proposal by a third party

[0047] Creation of new contract terms

[0048] By having users consider these options, select the most appropriate solution, and provide feedback, the system continuously improves its accuracy.

[0049] The following describes the processing flow.

[0050] Step 1:

[0051] The server periodically accesses external legal and case databases and automatically collects relevant data. This collection includes information retrieval using APIs and web scraping.

[0052] Step 2:

[0053] The server applies natural language processing techniques to cleanse the collected data and format the text. This process involves denoising, tokenizing, and removing stop words from the data.

[0054] Step 3:

[0055] The server trains a generative AI model using pre-processed data. This allows the AI ​​model to learn patterns and useful features from past cases and acquire the ability to generate solutions applicable to new conflicts.

[0056] Step 4:

[0057] The device provides users with an intuitive interface, allowing them to input detailed information about the conflict they are facing.

[0058] Step 5:

[0059] Users enter information about their issue into the terminal. This information includes the nature of the dispute, the parties involved, and the points of disagreement.

[0060] Step 6:

[0061] The terminal sends the information entered by the user to the server. This transmission allows the server to receive data for analyzing the user's situation.

[0062] Step 7:

[0063] The server uses a generative AI model to generate multiple solutions in real time based on the input data. In this process, it refers to similar past cases to create optimized solutions.

[0064] Step 8:

[0065] The server sends the generated solutions to the terminal. Multiple options are presented, with their respective advantages and disadvantages explained.

[0066] Step 9:

[0067] The terminal displays the solutions received from the server to the user. The user can then review these solutions and select the one they deem best.

[0068] Step 10:

[0069] Users input feedback on the presented solutions into their devices and share their evaluations and reasons for their choices.

[0070] Step 11:

[0071] The device sends feedback to the server, recording the user's opinions. This information is used to improve the system and further enhance the accuracy of the generated AI model.

[0072] Step 12:

[0073] The server protects user privacy by encrypting all data and storing it in secure storage.

[0074] (Example 1)

[0075] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0076] The objective of this invention is to provide an effective means for dispute resolution and to efficiently generate multiple proposals. Conventional systems often struggle to effectively utilize past cases, resulting in a heavy burden on users. To address this issue, there is a need for a system that processes data quickly and accurately, providing users with the most suitable solution.

[0077] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0078] In this invention, the server includes means for acquiring information from a historical database, means for preprocessing the information using processing technology, and means for generating multiple proposals in real time using a trained generative machine learning model. This enables the efficient and accurate generation of proposals for dispute resolution.

[0079] "Means of acquiring information" refers to the function that allows a server to collect necessary data from external databases and recording systems.

[0080] "Means of pre-processing using processing technology" refers to the process of removing noise from data acquired by the server and preparing it into an analyzable format, and involves using techniques such as natural language processing.

[0081] A "generative machine learning model" is an algorithm that learns from past data and can generate patterns and suggestions based on new data.

[0082] "Means for generating multiple proposals" refers to a function that utilizes generative machine learning models to create multiple solutions to present to the user.

[0083] "Means of presentation via terminal" refers to the procedure for displaying suggestions generated by the server on the screen of the device used by the user.

[0084] "Means for collecting and analyzing evaluation information" refers to the process of gathering feedback and opinions from users, analyzing them, and using that information to improve the system.

[0085] "Means of protecting the confidentiality of information" refers to security technologies that encrypt data stored on a server to protect it from unauthorized access by third parties.

[0086] The dispute resolution support system of the present invention consists of a server and terminals used by users. This system contributes to efficient and effective dispute resolution using various means described below.

[0087] The server automatically retrieves necessary information from external databases. These databases provide access to a wide range of past cases, including legal information. The server then preprocesses the collected data using natural language processing techniques. This processing may involve using libraries such as NLTK or spaCy, which are implemented in Python. By performing denoising, tokenization, and stop word removal, the server prepares the information into a format that is easy to analyze.

[0088] Next, the server learns from historical data using a generative AI model. This model is implemented using machine learning frameworks such as TENSORFLOW® and PyTorch. The model has the ability to analyze new conflict cases sent to the server and generate diverse solutions.

[0089] Users can input information about their disputes through their terminal and send it to the server. The server analyzes the input information and generates multiple solutions in real time based on similar cases. The generated solutions are presented to the terminal via the user interface, allowing the user to review them and select the most suitable solution.

[0090] User feedback is sent to the server via the device and used to improve the generated AI model. Feedback and personal information are protected using encryption technologies such as AES to maintain confidentiality.

[0091] For example, if a dispute arises between companies regarding a license agreement, the user can input information such as the contract details, disagreements, and a prompt in Japanese stating, "I want to resolve a dispute regarding a license agreement between companies." The server receives this information and uses its model to suggest solutions such as "a proposal for tiered payment of license fees," "a proposal for third-party arbitration," or "the creation of new contract terms." The user can then consider these suggestions and select the next step.

[0092] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0093] Step 1:

[0094] The server connects to an external database via the network to retrieve data, including legal information and past cases. The input consists of keywords related to a specific legal area or case. The database responds with a relevant dataset, which is then stored in the server's data storage.

[0095] Step 2:

[0096] The server preprocesses the acquired data by applying natural language processing. The stored raw data is used as input. Specific processing includes noise reduction, text tokenization, and stop word removal. This results in processed data that is ready for analysis. Natural language processing libraries such as NLTK and spaCy are used in this process.

[0097] Step 3:

[0098] The server trains a generative AI model using preprocessed data. An analyzable dataset is provided as input. The AI ​​model learns past conflict resolution patterns from this data, improving its predictive ability for new cases. The output of this step is the trained model. Deep learning frameworks such as TensorFlow and PyTorch are used for training.

[0099] Step 4:

[0100] The user inputs information about a specific dispute case through their device. This input includes details of the dispute, the opinions of those involved, and past interactions. The device sends the input data to a server. The server receives this information and uses a generative AI model to identify similar cases. As output, a list of candidate solutions is generated.

[0101] Step 5:

[0102] The server organizes the solutions generated by the AI ​​model into a presentable format. The organized solutions are sent to the terminal and displayed to the user through an intuitive user interface. The user can easily compare multiple proposed solutions. The output provides a list of solutions that the user can select.

[0103] Step 6:

[0104] The user inputs information to provide feedback on the presented solution and sends it to the server via their device. This feedback input includes evaluations and suggestions for improvement of the selected solution. The server receives this feedback and analyzes the data to improve the accuracy of the model. As output, an improved AI model is generated. This feedback data is securely stored using encryption technology.

[0105] (Application Example 1)

[0106] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0107] In the realm of electronic transactions, fee disputes and contractual discrepancies frequently occur, requiring prompt and fair solutions. However, current methods have made it difficult to provide solutions based on past cases, forcing users to expend considerable time and effort to find solutions themselves. Therefore, there is a need for a user support system that can efficiently resolve problems in electronic transactions.

[0108] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0109] In this invention, the server includes means for collecting data from a database of past cases, means for preprocessing the data using natural language processing technology, means for generating multiple solutions in real time using a trained generative AI model, and means for identifying past trouble cases related to payment services and presenting solutions in order to support problem solving in electronic transactions. This enables users to quickly and easily obtain appropriate solutions based on past cases.

[0110] A "database of past cases" is a collection of data that compiles information on disputes and troubles that have occurred in the past.

[0111] "Natural language processing technology" refers to techniques that enable computers to understand and process human language, and involves methods for analyzing and preprocessing text data.

[0112] A "generative AI model" is an artificial intelligence model that has the ability to learn from data and generate new solutions and suggestions.

[0113] A "user interface" is an interface with an intuitive design that allows users to operate a system and input and output information.

[0114] "User feedback" refers to information that users use to provide evaluations and opinions on system solutions.

[0115] "Data privacy protection" refers to security measures taken to prevent users' personal information and data from being illegally obtained.

[0116] "Electronic transactions" refer to a form of transaction in which goods and services are bought and sold via the internet.

[0117] A "payment service" is a service used to process payments in electronic transactions.

[0118] The system for realizing this invention involves a server and terminal working in conjunction. The server collects data from a database of past cases and preprocesses it using natural language processing techniques. During this process, it denoises and tokenizes the data to prepare a dataset for training a generative AI model. The software used includes NLTK (Natural Language Toolkit).

[0119] The server uses generative AI models such as OpenAI's GPT to learn patterns from pre-processed data. Based on the information input by the user, it generates multiple solutions in real time. The generated solutions are sent to the terminal in JSON format.

[0120] The device presents the user with solutions received from the server through its user interface. The interface on the device is developed using React Native and features an intuitive design. This allows users to easily input information and compare the presented solutions.

[0121] When a user provides feedback on a solution via their device, that information is sent to the server and used to further improve the generated AI model. This feedback is encrypted and stored to protect the user's privacy.

[0122] As a concrete example, consider a case where a refund issue occurs in an electronic transaction. The user enters details of the problem into their terminal, and the server generates a solution based on similar cases. For example, solutions such as "a proposal to compensate for the next transaction free of charge" or "use chat support for a quicker resolution" might be offered. In this case, an example of the prompt message used would be, "I'm having trouble because my refund hasn't been processed. Please provide suggestions based on past refund problem resolution cases."

[0123] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0124] Step 1:

[0125] The server periodically collects data from external case databases. This data includes details about past transaction troubles and disputes. Inputs are information from legal databases and public case databases, and output is a collection of raw data.

[0126] Step 2:

[0127] The server preprocesses the collected data using natural language processing. This includes denoising, tokenization, and stop word removal. The input is the raw data obtained in step 1, and the output is clean text data.

[0128] Step 3:

[0129] The server trains a generative AI model using preprocessed data. The model used here includes OpenAI's GPT. The input is the clean text data obtained in step 2, and the output is a generative AI model with problem-solving capabilities.

[0130] Step 4:

[0131] When a user enters details of a problem from their device, the device sends that information to the server. The input is the detailed problem information entered by the user, and the output is request data containing that information.

[0132] Step 5:

[0133] The server uses a generative AI model to generate optimal solutions in real time based on the information received from the user. The input is the request data received in step 4, and the output is multiple solutions.

[0134] Step 6:

[0135] The server sends the solution in JSON format to the terminal, and the terminal presents the solution to the user through the user interface. The input is the solution generated in step 5, and the output is the list of solutions presented to the user.

[0136] Step 7:

[0137] The user considers the proposed solutions and submits feedback to the server via their device. The input is user feedback information, and the output is data containing that feedback.

[0138] Step 8:

[0139] The server analyzes the received feedback and uses it to improve the generative AI model. The input is the feedback data received in step 7, and the output is the improved generative AI model.

[0140] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0141] The conflict resolution support system incorporating the emotion engine of the present invention consists of a data analysis server, a user input terminal, and an emotion analysis module. This system enables the generation of conflict resolutions that take into account the user's emotions, providing a more user-friendly solution.

[0142] Program Processing Overview

[0143] Data acquisition and preprocessing

[0144] The server continuously collects historical case data from an external database. The collected data is preprocessed using natural language processing techniques and used for analysis in generative AI models.

[0145] Operation of the emotion analysis module

[0146] When a user inputs information about a conflict through their device, an emotion analysis module analyzes the text and audio data to identify the user's emotional state. This analysis determines what the user's current emotions are (e.g., stressed, confused, calm, etc.).

[0147] Solution generation using generative AI models

[0148] The server generates multiple solutions using a generative AI model based on the data entered by the user and the output of the sentiment analysis module. The sentiment analysis results are used to provide more personalized solutions and to prioritize the selection of proposals.

[0149] Suggestion presentation via user interface

[0150] The device presents the user with solutions generated through the user interface. Based on sentiment analysis results, the interface display is adjusted to ensure that information is conveyed in the most easily understandable way for the user.

[0151] Feedback collection and privacy protection

[0152] Users provide feedback on suggestions executed via their devices. This feedback information is sent to the server and used to improve system performance and the accuracy of the AI ​​model. All data is encrypted using security technology and stored securely, thus preserving privacy.

[0153] Specific example

[0154] For example, if a dispute arises regarding a specific contract clause, the user inputs the issue along with their emotional state (anger, anxiety, etc.) into the terminal. The emotion analysis module identifies the user's current emotions from the input information. The server uses this information to generate suggestions that alleviate the user's emotions and emphasize reasonable solutions in the situation.

[0155] This system allows users to receive emotionally-driven solutions and helps them engage in more constructive negotiations.

[0156] The following describes the processing flow.

[0157] Step 1:

[0158] The server accesses legal databases and databases of publicly available dispute cases, automatically collecting relevant data. This is done by periodically utilizing APIs or web scraping.

[0159] Step 2:

[0160] The server preprocesses the collected data using natural language processing techniques. Specifically, it tokenizes the data, denoises it, and extracts the necessary information.

[0161] Step 3:

[0162] As part of training the generative AI model, the server uses pre-processed data to learn patterns and relationships, enabling it to generate solutions for new conflicts in the future.

[0163] Step 4:

[0164] Users use their devices to enter detailed information about the conflict they are facing (e.g., background of the conflict, parties involved, disagreements, etc.).

[0165] Step 5:

[0166] An emotion analysis module installed in the device analyzes text or voice data entered by the user in real time to identify the user's emotional state.

[0167] Step 6:

[0168] The device sends collected sentiment data and detailed user-generated problem information to the server. This enables the generation of context-based solutions.

[0169] Step 7:

[0170] The server generates multiple solutions in real time using a generative AI model based on the transmitted information. During this process, it considers the sentiment analysis results and prioritizes solutions that are appropriate to the user's emotional state.

[0171] Step 8:

[0172] The server sends the generated solution to the terminal. This is provided in an appropriately tailored format, taking into consideration the user's feelings.

[0173] Step 9:

[0174] The device presents solutions to the user. The user interface is designed to be intuitively easy for the user to understand, and displays are based on sentiment analysis.

[0175] Step 10:

[0176] The user selects the solution they deem most appropriate from the presented options and inputs feedback and opinions about that selection into the device.

[0177] Step 11:

[0178] The device sends collected user feedback to the server. This allows for further improvement of the generative AI model and the system.

[0179] Step 12:

[0180] The server ensures user privacy by protecting all data with encryption technology and storing it securely.

[0181] (Example 2)

[0182] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0183] In today's information society, it is crucial to present solutions that take into account the user's emotions and state of mind. However, existing systems do not adequately detect and reflect user emotions in their solutions, making it difficult to present optimal solutions to users and achieve effective problem-solving.

[0184] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0185] In this invention, the server includes means for collecting information from past case and event information sources, means for pre-processing the information using language data processing technology, and means for receiving information about a problem input by the user through an information device. This enables the generation and presentation of flexible and effective solutions based on the user's emotions and state.

[0186] "Past case and event information sources" refer to sources of information that contain records of past events and cases, and provide basic data that can be used for new analyses and judgments based on this information.

[0187] "Information equipment" refers to devices used by users to input or receive information, and includes computers, smartphones, tablets, and other similar devices.

[0188] "Language data processing technology" refers to the technology of analyzing and processing natural language using computers, enabling text preprocessing and semantic analysis.

[0189] An "information analysis module" is a software or system component that analyzes information received from a user to identify their emotional state and other characteristics.

[0190] An "information processing AI system" is a system that utilizes artificial intelligence technology designed to process large amounts of data and automatically generate solutions tailored to specific purposes.

[0191] A "user information device" refers to a device used by a user to input information or receive solutions, and functions as an interface.

[0192] This invention provides a system that supports problem-solving while taking user emotions into consideration, and its details are described below.

[0193] The server collects information from past case and event sources. Specifically, it retrieves past case data using SQL queries through access to a large-scale database. This data is preprocessed using language data processing techniques. For example, NLTK and SpaCy are used to clean and tokenize the data.

[0194] Users input information about their problems and emotions through their information devices. The device receives this information and sends it to an emotion analysis module. This module uses online language analysis services via APIs and identifies the user's emotions through emotion analysis technologies from Azure® and Google®.

[0195] The server uses an information processing AI system to generate solutions based on information received from the user and the results of sentiment analysis. Specifically, it uses a generative AI model to create concrete suggestions for addressing the obtained information. An example of a prompt used in this process is, "Propose a way to resolve the contractual conflict and generate a suitable solution for a user whose current emotion is anger."

[0196] The terminal displays the generated solution via the user information device. The interface is adjusted according to the user's emotional state. For example, a calm user is presented with detailed information, while an emotionally charged user receives a gentler explanation.

[0197] As a concrete example, if a user is dissatisfied with a business contract, the user inputs the problem and their feelings into the terminal. An emotion analysis module identifies the user's anger, and the server generates suggestions that emphasize solutions appropriate to the situation. In this way, the user receives appropriate solutions that take their feelings into account, enabling more effective communication and problem-solving.

[0198] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0199] Step 1:

[0200] The server collects data from past case and event information sources. Specifically, it performs SQL queries against the database to extract similar past cases. The input is raw data from the database, and the output is a set of cases. The server uses this as an information infrastructure for the next steps.

[0201] Step 2:

[0202] The server preprocesses the collected historical data using language data processing techniques. Specifically, it performs tokenization, stop word removal, and stemming using NLTK. The input is the example data obtained in step 1, and the output is preprocessed data in a format suitable for analysis.

[0203] Step 3:

[0204] The user inputs information about their problem through the device. Specifically, this involves using text forms or voice input to enter a descriptive statement describing their current situation and emotions (e.g., stress, anger). This input is received as raw data.

[0205] Step 4:

[0206] The terminal sends user input data to an emotion analysis module. The emotion analysis module performs data analysis to identify the user's emotional state. The input here is text or voice data from the user, and the output is a label for the identified emotional state (e.g., anger, anxiety).

[0207] Step 5:

[0208] The server integrates the data entered by the user with the output of the sentiment analysis module and inputs it as a prompt to the generative AI model. The input here consists of the pre-processed data obtained in step 2 and the sentiment analysis data obtained in step 4. The generative AI model generates multiple solutions for the input and provides them as output.

[0209] Step 6:

[0210] The terminal receives output from the generated AI model and presents solutions via user information devices. This step involves adjusting the user interface to take emotional states into account. Specifically, it presents detailed information to calm users and in a considerate tone to emotional users. The input is the model's generation, and the output is user-customized suggested information.

[0211] Step 7:

[0212] The user provides feedback on the presented solution. The terminal receives this feedback and sends it to the server as data. This input consists of user ratings and comments, and the output is data that helps improve the system's performance. The server analyzes the feedback to improve the accuracy of the model and the system.

[0213] (Application Example 2)

[0214] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0215] In caregiving settings, there is a need to reduce troubles and stress caused by a lack of understanding of the emotions of users and their families, as well as inappropriate responses during communication. In particular, a challenge is the lack of technical means to accurately grasp the emotional state of users and to provide appropriate countermeasures quickly.

[0216] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0217] In this invention, the server includes means for collecting data from past case data storage, means for preprocessing the data using natural language processing technology, means for generating multiple solutions in real time using a trained generative AI model, means for analyzing the emotional state in interactions with users, and means for proposing appropriate countermeasures in the care environment that correspond to the user's emotions. This enables care staff to quickly obtain optimal countermeasures that take into account the user's emotions.

[0218] A "past case data storage" is a data storage device that saves case information from past caregiving settings and stores it in an accessible format.

[0219] "Natural language processing technology" refers to information technology methods that analyze text data to understand and generate human language.

[0220] A "generative AI model" is an algorithm trained using artificial intelligence technology to generate multiple solutions from input information.

[0221] A "user interface" is a means of display and input for a user to interact with a system.

[0222] "Means for analyzing emotional states" refer to algorithms and technologies for identifying a user's emotions from text and audio data.

[0223] "Means of proposing appropriate countermeasures" refers to methods and processes for presenting the optimal actions for care staff based on analyzed emotional data.

[0224] "User feedback" refers to response information provided by system users regarding the effectiveness and satisfaction level of proposed solutions.

[0225] "Means of protecting data privacy" refer to security technologies and measures to prevent unauthorized access to personal and confidential information.

[0226] To realize this invention, the system is configured as follows: The server collects data from past case data storage and preprocesses that data using natural language processing technology. Specifically, it preprocesses the data using the Python NLTK library to prepare for training an AI model utilizing Hugging Face's Transformers. The emotion analysis module allows the server to analyze text and voice data input from the user and identify the emotional state. At this stage, the Google Cloud Natural Language API is used to identify emotions in real time.

[0227] Once the user's emotional state is identified, the server generates multiple solutions using a generative AI model. This generation process utilizes a model based on the TensorFlow library to present the resulting solutions to care staff appropriately and quickly.

[0228] The user interface on the device is built using React Native and visually presents appropriate solutions tailored to the user's emotions. Users can review the displayed solutions and make their own selections. It also includes a feedback function to collect evaluations and opinions from care staff, which are securely stored and managed using AWS® S3.

[0229] As a concrete example, in a nursing home, if a resident shows signs of anxiety during communication, the system analyzes the cause and quickly provides guidance to staff on how to respond. Examples of prompts include, "The family seems anxious. Please identify the reason and suggest reassuring words," and "We have noticed that the resident is experiencing stress. How should we communicate with them?" In this way, the system supports smooth communication and rapid problem-solving in nursing care settings.

[0230] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0231] Step 1:

[0232] The server collects data from a storage of past case data. The input is case data, which is preprocessed using the Python NLTK library. The output is data in a parseable format. Specifically, the data is cleaned and tokenized, and the text data is converted into a format suitable for generating AI models.

[0233] Step 2:

[0234] Users input information via their devices in voice or text format. This input includes specific situations and emotional expressions related to interactions with the user. The device then transmits the input data to the server.

[0235] Step 3:

[0236] The server uses the Google Cloud Natural Language API to analyze the emotional state of the input information. The input is text data, and the output is the emotional state extracted through the analysis. This analysis identifies emotional states such as stress, anxiety, and relief.

[0237] Step 4:

[0238] The server uses a generative AI model to generate multiple solutions based on the sentiment analysis results. The input is the sentiment analysis result, and the generative AI model generates candidate solutions. Specifically, the model is executed using the TensorFlow library to create appropriate responses based on the sentiment.

[0239] Step 5:

[0240] The device presents solutions to the user through a user interface built with React Native. Input is solution information from the server, displayed in a clear and intuitive format. Output is a visual presentation of information.

[0241] Step 6:

[0242] Users can provide feedback on the proposed solutions. This feedback is sent to the server via the terminal.

[0243] Step 7:

[0244] The server sends the collected feedback to AWS S3 for secure storage. The input is feedback data, and the output is data stored in an appropriately encrypted state. This allows the feedback to be regularly incorporated into improving the accuracy of the AI ​​model.

[0245] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0246] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0247] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0248] [Second Embodiment]

[0249] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0250] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0251] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0252] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0253] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0254] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0255] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0256] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0257] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0258] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0259] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0260] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0261] The dispute resolution support system of the present invention has a system configuration that includes a server connected to a network and terminals used by users. The program processing and specific examples of this system are described below.

[0262] Program Processing Overview

[0263] Data acquisition and preprocessing

[0264] The server periodically collects data from external legal databases and public case databases. The collected data is preprocessed using natural language processing techniques, including noise reduction, tokenization, and stop word removal. This prepares the data in a format suitable for training generative AI models.

[0265] Training and application of generative AI models

[0266] The server trains a generative AI model using a large, pre-processed dataset. This model learns past conflict resolution patterns and improves its ability to generate solutions for new cases. When the user provides detailed conflict information, the server uses this generative AI model to identify similar cases and generate several solutions in real time.

[0267] Suggestion presentation via user interface

[0268] The terminal sends details of the problem entered by the user to the server and presents the user with the solution received from the server in response. The user interface is intuitive and displays multiple solutions in a format that makes it easy to compare them.

[0269] Gathering feedback and protecting privacy

[0270] Users input their evaluations and feedback on the presented solutions into their devices. This feedback data is sent to a server and used to improve the generated AI model. The server stores all data using robust encryption technology, ensuring the utmost protection of user privacy.

[0271] Specific example

[0272] For example, consider a dispute arising from a licensing agreement between companies. In this case, the user inputs the contract details, points of disagreement, and the opinions of the parties involved into the terminal. The server receives this information, analyzes similar cases in real time from a vast amount of collected past case data, and proposes solutions such as the following.

[0273] Proposal for phased payment of license fees

[0274] Arbitration proposal by a third party

[0275] Creation of new contract terms

[0276] By having users consider these options, select the most appropriate solution, and provide feedback, the system continuously improves its accuracy.

[0277] The following describes the processing flow.

[0278] Step 1:

[0279] The server periodically accesses external legal and case databases and automatically collects relevant data. This collection includes information retrieval using APIs and web scraping.

[0280] Step 2:

[0281] The server applies natural language processing techniques to cleanse the collected data and format the text. This process involves denoising, tokenizing, and removing stop words from the data.

[0282] Step 3:

[0283] The server trains a generative AI model using pre-processed data. This allows the AI ​​model to learn patterns and useful features from past cases and acquire the ability to generate solutions applicable to new conflicts.

[0284] Step 4:

[0285] The terminal provides an intuitive interface for the user and enables the user to input detailed information about the disputes they are facing.

[0286] Step 5:

[0287] The user inputs information about their problem into the terminal. This information includes the content of the dispute, the parties involved, differences in opinions, etc.

[0288] Step 6:

[0289] The terminal sends the information input by the user to the server. Through this information transmission, the server receives data for analyzing the user's situation.

[0290] Step 7:

[0291] The server uses the generative AI model to generate multiple solutions in real time based on the input data. In this process, it refers to past similar cases to create optimized solutions.

[0292] Step 8:

[0293] The server sends the generated solutions to the terminal. They are presented as multiple options, and the merits and demerits of each are explained.

[0294] Step 9:

[0295] The terminal displays the solutions received from the server to the user. The user can refer to these and select the solution that they feel is optimal.

[0296] Step 10:

[0297] The user inputs feedback on the presented solutions into the terminal, sharing the reasons for their evaluation and selection.

[0298] Step 11:

[0299] The device sends feedback to the server, recording the user's opinions. This information is used to improve the system and further enhance the accuracy of the generated AI model.

[0300] Step 12:

[0301] The server protects user privacy by encrypting all data and storing it in secure storage.

[0302] (Example 1)

[0303] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0304] The objective of this invention is to provide an effective means for dispute resolution and to efficiently generate multiple proposals. Conventional systems often struggle to effectively utilize past cases, resulting in a heavy burden on users. To address this issue, there is a need for a system that processes data quickly and accurately, providing users with the most suitable solution.

[0305] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0306] In this invention, the server includes means for acquiring information from a historical database, means for preprocessing the information using processing technology, and means for generating multiple proposals in real time using a trained generative machine learning model. This enables the efficient and accurate generation of proposals for dispute resolution.

[0307] "Means of acquiring information" refers to the function that allows a server to collect necessary data from external databases and recording systems.

[0308] The means of preprocessing using processing technology is a process of removing noise from the data acquired by the server and arranging it in an analyzable format, which involves using natural language processing technology and the like.

[0309] The "generative machine learning model" is an algorithm that learns based on past data and can generate patterns and proposals based on new data.

[0310] The means of generating multiple proposals is a function that utilizes the generative machine learning model to create multiple solutions for presenting to the user.

[0311] The means of presenting via the terminal is a procedure for displaying the proposals generated by the server on the screen of the device used by the user.

[0312] The means of collecting and analyzing evaluation information is a process of collecting feedback and opinions obtained from the user, analyzing them, and using them to improve the system.

[0313] The means of protecting the confidentiality of information is a security technology for encrypting the data stored by the server and protecting it from unauthorized access by third parties.

[0314] The dispute resolution support system of the present invention is composed of a server and a terminal used by the user. This system contributes to dispute resolution efficiently and effectively using various means described below.

[0315] The server automatically acquires necessary information from external databases. These databases can reference a wide range of past cases including legal information. Subsequently, the server preprocesses the collected data using natural language processing technology. For this processing, libraries implemented in Python such as NLTK and spaCy may be used. By performing noise removal, tokenization, and exclusion of stop words, the server arranges the information in a format that is easy to analyze.

[0316] Next, the server learns from historical data using a generative AI model. This model is implemented using machine learning frameworks such as TensorFlow and PyTorch. The model has the ability to analyze new conflict cases sent to the server and generate diverse solutions.

[0317] Users can input information about their disputes through their terminal and send it to the server. The server analyzes the input information and generates multiple solutions in real time based on similar cases. The generated solutions are presented to the terminal via the user interface, allowing the user to review them and select the most suitable solution.

[0318] User feedback is sent to the server via the device and used to improve the generated AI model. Feedback and personal information are protected using encryption technologies such as AES to maintain confidentiality.

[0319] For example, if a dispute arises between companies regarding a license agreement, the user can input information such as the contract details, disagreements, and a prompt in Japanese stating, "I want to resolve a dispute regarding a license agreement between companies." The server receives this information and uses its model to suggest solutions such as "a proposal for tiered payment of license fees," "a proposal for third-party arbitration," or "the creation of new contract terms." The user can then consider these suggestions and select the next step.

[0320] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0321] Step 1:

[0322] The server connects to an external database via the network to retrieve data, including legal information and past cases. The input consists of keywords related to a specific legal area or case. The database responds with a relevant dataset, which is then stored in the server's data storage.

[0323] Step 2:

[0324] The server preprocesses the acquired data by applying natural language processing. The stored raw data is used as input. Specific processing includes noise reduction, text tokenization, and stop word removal. This results in processed data that is ready for analysis. Natural language processing libraries such as NLTK and spaCy are used in this process.

[0325] Step 3:

[0326] The server trains a generative AI model using preprocessed data. An analyzable dataset is provided as input. The AI ​​model learns past conflict resolution patterns from this data, improving its predictive ability for new cases. The output of this step is the trained model. Deep learning frameworks such as TensorFlow and PyTorch are used for training.

[0327] Step 4:

[0328] The user inputs information about a specific dispute case through their device. This input includes details of the dispute, the opinions of those involved, and past interactions. The device sends the input data to a server. The server receives this information and uses a generative AI model to identify similar cases. As output, a list of candidate solutions is generated.

[0329] Step 5:

[0330] The server organizes the solutions generated by the AI ​​model into a presentable format. The organized solutions are sent to the terminal and displayed to the user through an intuitive user interface. The user can easily compare multiple proposed solutions. The output provides a list of solutions that the user can select.

[0331] Step 6:

[0332] The user inputs information to provide feedback on the presented solution and sends it to the server via their device. This feedback input includes evaluations and suggestions for improvement of the selected solution. The server receives this feedback and analyzes the data to improve the accuracy of the model. As output, an improved AI model is generated. This feedback data is securely stored using encryption technology.

[0333] (Application Example 1)

[0334] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0335] In the realm of electronic transactions, fee disputes and contractual discrepancies frequently occur, requiring prompt and fair solutions. However, current methods have made it difficult to provide solutions based on past cases, forcing users to expend considerable time and effort to find solutions themselves. Therefore, there is a need for a user support system that can efficiently resolve problems in electronic transactions.

[0336] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0337] In this invention, the server includes means for collecting data from a database of past cases, means for preprocessing the data using natural language processing technology, means for generating multiple solutions in real time using a trained generative AI model, and means for identifying past trouble cases related to payment services and presenting solutions in order to support problem solving in electronic transactions. This enables users to quickly and easily obtain appropriate solutions based on past cases.

[0338] A "database of past cases" is a collection of data that compiles information on disputes and troubles that have occurred in the past.

[0339] "Natural language processing technology" refers to techniques that enable computers to understand and process human language, and involves methods for analyzing and preprocessing text data.

[0340] A "generative AI model" is an artificial intelligence model that has the ability to learn from data and generate new solutions and suggestions.

[0341] A "user interface" is an interface with an intuitive design that allows users to operate a system and input and output information.

[0342] "User feedback" refers to information that users use to provide evaluations and opinions on system solutions.

[0343] "Data privacy protection" refers to security measures taken to prevent users' personal information and data from being illegally obtained.

[0344] "Electronic transactions" refer to a form of transaction in which goods and services are bought and sold via the internet.

[0345] A "payment service" is a service used to process payments in electronic transactions.

[0346] The system for realizing this invention involves a server and terminal working in conjunction. The server collects data from a database of past cases and preprocesses it using natural language processing techniques. During this process, it denoises and tokenizes the data to prepare a dataset for training a generative AI model. The software used includes NLTK (Natural Language Toolkit).

[0347] The server uses generative AI models such as OpenAI's GPT to learn patterns from pre-processed data. Then, based on information input from the user, it generates multiple solutions in real time. The generated solutions are sent to the terminal in JSON format.

[0348] The device presents the user with solutions received from the server through its user interface. The interface on the device is developed using React Native and features an intuitive design. This allows users to easily input information and compare the presented solutions.

[0349] When a user provides feedback on a solution via their device, that information is sent to the server and used to further improve the generated AI model. This feedback is encrypted and stored to protect the user's privacy.

[0350] As a concrete example, consider a case where a refund issue occurs in an electronic transaction. The user enters details of the problem into their terminal, and the server generates a solution based on similar cases. For example, solutions such as "a proposal to compensate for the next transaction free of charge" or "use chat support for a quicker resolution" might be offered. In this case, an example of the prompt message used would be, "I'm having trouble because my refund hasn't been processed. Please provide suggestions based on past refund problem resolution cases."

[0351] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0352] Step 1:

[0353] The server periodically collects data from external case databases. This data includes details about past transaction troubles and disputes. Inputs are information from legal databases and public case databases, and output is a collection of raw data.

[0354] Step 2:

[0355] The server preprocesses the collected data using natural language processing. This includes denoising, tokenization, and stop word removal. The input is the raw data obtained in step 1, and the output is clean text data.

[0356] Step 3:

[0357] The server trains a generative AI model using preprocessed data. The model used here includes OpenAI's GPT. The input is the clean text data obtained in step 2, and the output is a generative AI model with problem-solving capabilities.

[0358] Step 4:

[0359] When a user enters details of a problem from their device, the device sends that information to the server. The input is the detailed problem information entered by the user, and the output is request data containing that information.

[0360] Step 5:

[0361] The server uses a generative AI model to generate optimal solutions in real time based on the information received from the user. The input is the request data received in step 4, and the output is multiple solutions.

[0362] Step 6:

[0363] The server sends the solution in JSON format to the terminal, and the terminal presents the solution to the user through the user interface. The input is the solution generated in step 5, and the output is the list of solutions presented to the user.

[0364] Step 7:

[0365] The user considers the proposed solutions and submits feedback to the server via their device. The input is user feedback information, and the output is data containing that feedback.

[0366] Step 8:

[0367] The server analyzes the received feedback and uses it to improve the generative AI model. The input is the feedback data received in step 7, and the output is the improved generative AI model.

[0368] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0369] The conflict resolution support system incorporating the emotion engine of the present invention consists of a data analysis server, a user input terminal, and an emotion analysis module. This system enables the generation of conflict resolutions that take into account the user's emotions, providing a more user-friendly solution.

[0370] Program Processing Overview

[0371] Data acquisition and preprocessing

[0372] The server continuously collects historical case data from an external database. The collected data is preprocessed using natural language processing techniques and used for analysis in generative AI models.

[0373] Operation of the emotion analysis module

[0374] When a user inputs information about a conflict through their device, an emotion analysis module analyzes the text and audio data to identify the user's emotional state. This analysis determines what the user's current emotions are (e.g., stressed, confused, calm, etc.).

[0375] Solution generation using generative AI models

[0376] The server generates multiple solutions using a generative AI model based on the data entered by the user and the output of the sentiment analysis module. The sentiment analysis results are used to provide more personalized solutions and to prioritize the selection of proposals.

[0377] Suggestion presentation via user interface

[0378] The device presents the user with solutions generated through the user interface. Based on sentiment analysis results, the interface display is adjusted to ensure that information is conveyed in the most easily understandable way for the user.

[0379] Feedback collection and privacy protection

[0380] Users provide feedback on suggestions executed via their devices. This feedback information is sent to the server and used to improve system performance and the accuracy of the AI ​​model. All data is encrypted using security technology and stored securely, thus preserving privacy.

[0381] Specific example

[0382] For example, if a dispute arises regarding a specific contract clause, the user inputs the issue along with their emotional state (anger, anxiety, etc.) into the terminal. The emotion analysis module identifies the user's current emotions from the input information. The server uses this information to generate suggestions that alleviate the user's emotions and emphasize reasonable solutions in the situation.

[0383] This system allows users to receive emotionally-driven solutions and helps them engage in more constructive negotiations.

[0384] The following describes the processing flow.

[0385] Step 1:

[0386] The server accesses legal databases and databases of publicly available dispute cases, automatically collecting relevant data. This is done by periodically utilizing APIs or web scraping.

[0387] Step 2:

[0388] The server preprocesses the collected data using natural language processing techniques. Specifically, it tokenizes the data, denoises it, and extracts the necessary information.

[0389] Step 3:

[0390] As part of training the generative AI model, the server uses pre-processed data to learn patterns and relationships, enabling it to generate solutions for new conflicts in the future.

[0391] Step 4:

[0392] Users use their devices to enter detailed information about the conflict they are facing (e.g., background of the conflict, parties involved, disagreements, etc.).

[0393] Step 5:

[0394] An emotion analysis module installed in the device analyzes text or voice data entered by the user in real time to identify the user's emotional state.

[0395] Step 6:

[0396] The device sends collected sentiment data and detailed user-generated problem information to the server. This enables the generation of context-based solutions.

[0397] Step 7:

[0398] The server generates multiple solutions in real time using a generative AI model based on the transmitted information. During this process, it considers the sentiment analysis results and prioritizes solutions that are appropriate to the user's emotional state.

[0399] Step 8:

[0400] The server sends the generated solution to the terminal. This is provided in an appropriately tailored format, taking into consideration the user's feelings.

[0401] Step 9:

[0402] The device presents solutions to the user. The user interface is designed to be intuitively easy for the user to understand, and displays are based on sentiment analysis.

[0403] Step 10:

[0404] The user selects the solution they deem most appropriate from the presented options and inputs feedback and opinions about that selection into the device.

[0405] Step 11:

[0406] The device sends collected user feedback to the server. This allows for further improvement of the generative AI model and the system.

[0407] Step 12:

[0408] The server ensures user privacy by protecting all data with encryption technology and storing it securely.

[0409] (Example 2)

[0410] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0411] In today's information society, it is crucial to present solutions that take into account the user's emotions and state of mind. However, existing systems do not adequately detect and reflect user emotions in their solutions, making it difficult to present optimal solutions to users and achieve effective problem-solving.

[0412] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0413] In this invention, the server includes means for collecting information from past case and event information sources, means for pre-processing the information using language data processing technology, and means for receiving information about a problem input by the user through an information device. This enables the generation and presentation of flexible and effective solutions based on the user's emotions and state.

[0414] "Past case and event information sources" refer to sources of information that contain records of past events and cases, and provide basic data that can be used for new analyses and judgments based on this information.

[0415] "Information equipment" refers to devices used by users to input or receive information, and includes computers, smartphones, tablets, and other similar devices.

[0416] "Language data processing technology" refers to the technology of analyzing and processing natural language using computers, enabling text preprocessing and semantic analysis.

[0417] An "information analysis module" is a software or system component that analyzes information received from a user to identify their emotional state and other characteristics.

[0418] An "information processing AI system" is a system that utilizes artificial intelligence technology designed to process large amounts of data and automatically generate solutions tailored to specific purposes.

[0419] A "user information device" refers to a device used by a user to input information or receive solutions, and functions as an interface.

[0420] This invention provides a system that supports problem-solving while taking user emotions into consideration, and its details are described below.

[0421] The server collects information from past case and event sources. Specifically, it retrieves past case data using SQL queries through access to a large-scale database. This data is preprocessed using language data processing techniques. For example, NLTK and SpaCy are used to clean and tokenize the data.

[0422] Users input information about their problems and emotions through their information devices. The device receives this information and sends it to an emotion analysis module. This module uses online language analysis services via APIs and identifies the user's emotions through emotion analysis technologies from Azure and Google.

[0423] The server uses an information processing AI system to generate solutions based on information received from the user and the results of sentiment analysis. Specifically, it uses a generative AI model to create concrete suggestions for addressing the obtained information. An example of a prompt used in this process is, "Propose a way to resolve the contractual conflict and generate a suitable solution for a user whose current emotion is anger."

[0424] The terminal displays the generated solution via the user information device. The interface is adjusted according to the user's emotional state. For example, a calm user is presented with detailed information, while an emotionally charged user receives a gentler explanation.

[0425] As a concrete example, if a user is dissatisfied with a business contract, the user inputs the problem and their feelings into the terminal. An emotion analysis module identifies the user's anger, and the server generates suggestions that emphasize solutions appropriate to the situation. In this way, the user receives appropriate solutions that take their feelings into account, enabling more effective communication and problem-solving.

[0426] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0427] Step 1:

[0428] The server collects data from past case and event information sources. Specifically, it performs SQL queries against the database to extract similar past cases. The input is raw data from the database, and the output is a set of cases. The server uses this as an information infrastructure for the next steps.

[0429] Step 2:

[0430] The server preprocesses the collected historical data using language data processing techniques. Specifically, it performs tokenization, stop word removal, and stemming using NLTK. The input is the example data obtained in step 1, and the output is preprocessed data in a format suitable for analysis.

[0431] Step 3:

[0432] The user inputs information about their problem through the device. Specifically, this involves using text forms or voice input to enter a descriptive statement describing their current situation and emotions (e.g., stress, anger). This input is received as raw data.

[0433] Step 4:

[0434] The terminal sends user input data to an emotion analysis module. The emotion analysis module performs data analysis to identify the user's emotional state. The input here is text or voice data from the user, and the output is a label for the identified emotional state (e.g., anger, anxiety).

[0435] Step 5:

[0436] The server integrates the data entered by the user with the output of the sentiment analysis module and inputs it as a prompt to the generative AI model. The input here consists of the pre-processed data obtained in step 2 and the sentiment analysis data obtained in step 4. The generative AI model generates multiple solutions for the input and provides them as output.

[0437] Step 6:

[0438] The terminal receives output from the generated AI model and presents solutions via user information devices. This step involves adjusting the user interface to take emotional states into account. Specifically, it presents detailed information to calm users and in a considerate tone to emotional users. The input is the model's generation, and the output is user-customized suggested information.

[0439] Step 7:

[0440] The user provides feedback on the presented solution. The terminal receives this feedback and sends it to the server as data. This input consists of user ratings and comments, and the output is data that helps improve the system's performance. The server analyzes the feedback to improve the accuracy of the model and the system.

[0441] (Application Example 2)

[0442] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0443] In caregiving settings, there is a need to reduce troubles and stress caused by a lack of understanding of the emotions of users and their families, as well as inappropriate responses during communication. In particular, a challenge is the lack of technical means to accurately grasp the emotional state of users and to provide appropriate countermeasures quickly.

[0444] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0445] In this invention, the server includes means for collecting data from past case data storage, means for preprocessing the data using natural language processing technology, means for generating multiple solutions in real time using a trained generative AI model, means for analyzing the emotional state in interactions with users, and means for proposing appropriate countermeasures in the care environment that correspond to the user's emotions. This enables care staff to quickly obtain optimal countermeasures that take into account the user's emotions.

[0446] A "past case data storage" is a data storage device that saves case information from past caregiving settings and stores it in an accessible format.

[0447] "Natural language processing technology" refers to information technology methods that analyze text data to understand and generate human language.

[0448] A "generative AI model" is an algorithm trained using artificial intelligence technology to generate multiple solutions from input information.

[0449] A "user interface" is a means of display and input for a user to interact with a system.

[0450] "Means for analyzing emotional states" refer to algorithms and technologies for identifying a user's emotions from text and audio data.

[0451] "Means of proposing appropriate countermeasures" refers to methods and processes for presenting the optimal actions for care staff based on analyzed emotional data.

[0452] "User feedback" refers to response information provided by system users regarding the effectiveness and satisfaction level of proposed solutions.

[0453] "Means of protecting data privacy" refer to security technologies and measures to prevent unauthorized access to personal and confidential information.

[0454] To realize this invention, the system is configured as follows: The server collects data from past case data storage and preprocesses that data using natural language processing technology. Specifically, it preprocesses the data using the Python NLTK library to prepare for training an AI model utilizing Hugging Face's Transformers. The emotion analysis module allows the server to analyze text and voice data input from the user and identify the emotional state. At this stage, the Google Cloud Natural Language API is used to identify emotions in real time.

[0455] Once the user's emotional state is identified, the server generates multiple solutions using a generative AI model. This generation process utilizes a model based on the TensorFlow library to present the resulting solutions to care staff appropriately and quickly.

[0456] The user interface on the device is built using React Native and visually presents appropriate solutions tailored to the user's emotions in an easy-to-understand manner. Users can review the displayed solutions and make their own selections. It also includes a feedback function to collect evaluations and opinions from care staff, which are securely stored and managed using AWS S3.

[0457] As a concrete example, in a nursing home, if a resident shows signs of anxiety during communication, the system analyzes the cause and quickly provides guidance to staff on how to respond. Examples of prompts include, "The family seems anxious. Please identify the reason and suggest reassuring words," and "We have noticed that the resident is experiencing stress. How should we communicate with them?" In this way, the system supports smooth communication and rapid problem-solving in nursing care settings.

[0458] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0459] Step 1:

[0460] The server collects data from a storage of past case data. The input is case data, which is preprocessed using the Python NLTK library. The output is data in a parseable format. Specifically, the data is cleaned and tokenized, and the text data is converted into a format suitable for generating AI models.

[0461] Step 2:

[0462] Users input information via their devices in voice or text format. This input includes specific situations and emotional expressions related to interactions with the user. The device then transmits the input data to the server.

[0463] Step 3:

[0464] The server uses the Google Cloud Natural Language API to analyze the emotional state of the input information. The input is text data, and the output is the emotional state extracted through the analysis. This analysis identifies emotional states such as stress, anxiety, and relief.

[0465] Step 4:

[0466] The server uses a generative AI model to generate multiple solutions based on the sentiment analysis results. The input is the sentiment analysis result, and the generative AI model generates candidate solutions. Specifically, the model is executed using the TensorFlow library to create appropriate responses based on the sentiment.

[0467] Step 5:

[0468] The device presents solutions to the user through a user interface built with React Native. Input is solution information from the server, displayed in a clear and intuitive format. Output is a visual presentation of information.

[0469] Step 6:

[0470] Users can provide feedback on the proposed solutions. This feedback is sent to the server via the terminal.

[0471] Step 7:

[0472] The server sends the collected feedback to AWS S3 for secure storage. The input is feedback data, and the output is data stored in an appropriately encrypted state. This allows the feedback to be regularly incorporated into improving the accuracy of the AI ​​model.

[0473] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0474] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0475] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0476] [Third Embodiment]

[0477] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0478] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0479] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0480] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0481] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0482] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0483] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0484] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0485] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0486] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0487] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0488] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0489] The dispute resolution support system of the present invention has a system configuration that includes a server connected to a network and terminals used by users. The program processing and specific examples of this system are described below.

[0490] Program Processing Overview

[0491] Data acquisition and preprocessing

[0492] The server periodically collects data from external legal databases and public case databases. The collected data is preprocessed using natural language processing techniques, including noise reduction, tokenization, and stop word removal. This prepares the data in a format suitable for training generative AI models.

[0493] Training and application of generative AI models

[0494] The server trains a generative AI model using a large, pre-processed dataset. This model learns past conflict resolution patterns and improves its ability to generate solutions for new cases. When the user provides detailed conflict information, the server uses this generative AI model to identify similar cases and generate several solutions in real time.

[0495] Suggestion presentation via user interface

[0496] The terminal sends details of the problem entered by the user to the server and presents the user with the solution received from the server in response. The user interface is intuitive and displays multiple solutions in a format that makes it easy to compare them.

[0497] Gathering feedback and protecting privacy

[0498] Users input their evaluations and feedback on the presented solutions into their devices. This feedback data is sent to a server and used to improve the generated AI model. The server stores all data using robust encryption technology, ensuring the utmost protection of user privacy.

[0499] Specific example

[0500] For example, consider a dispute arising from a licensing agreement between companies. In this case, the user inputs the contract details, points of disagreement, and the opinions of the parties involved into the terminal. The server receives this information, analyzes similar cases in real time from a vast amount of collected past case data, and proposes solutions such as the following.

[0501] Proposal for phased payment of license fees

[0502] Arbitration proposal by a third party

[0503] Creation of new contract terms

[0504] By having users consider these options, select the most appropriate solution, and provide feedback, the system continuously improves its accuracy.

[0505] The following describes the processing flow.

[0506] Step 1:

[0507] The server periodically accesses external legal and case databases and automatically collects relevant data. This collection includes information retrieval using APIs and web scraping.

[0508] Step 2:

[0509] The server applies natural language processing techniques to cleanse the collected data and format the text. This process involves denoising, tokenizing, and removing stop words from the data.

[0510] Step 3:

[0511] The server trains a generative AI model using pre-processed data. This allows the AI ​​model to learn patterns and useful features from past cases and acquire the ability to generate solutions applicable to new conflicts.

[0512] Step 4:

[0513] The device provides users with an intuitive interface, allowing them to input detailed information about the conflict they are facing.

[0514] Step 5:

[0515] Users enter information about their issue into the terminal. This information includes the nature of the dispute, the parties involved, and the points of disagreement.

[0516] Step 6:

[0517] The terminal sends the information entered by the user to the server. This transmission allows the server to receive data for analyzing the user's situation.

[0518] Step 7:

[0519] The server uses a generative AI model to generate multiple solutions in real time based on the input data. In this process, it refers to similar past cases to create optimized solutions.

[0520] Step 8:

[0521] The server sends the generated solutions to the terminal. Multiple options are presented, with their respective advantages and disadvantages explained.

[0522] Step 9:

[0523] The terminal displays the solutions received from the server to the user. The user can then review these solutions and select the one they deem best.

[0524] Step 10:

[0525] Users input feedback on the presented solutions into their devices and share their evaluations and reasons for their choices.

[0526] Step 11:

[0527] The device sends feedback to the server, recording the user's opinions. This information is used to improve the system and further enhance the accuracy of the generated AI model.

[0528] Step 12:

[0529] The server protects user privacy by encrypting all data and storing it in secure storage.

[0530] (Example 1)

[0531] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0532] The objective of this invention is to provide an effective means for dispute resolution and to efficiently generate multiple proposals. Conventional systems often struggle to effectively utilize past cases, resulting in a heavy burden on users. To address this issue, there is a need for a system that processes data quickly and accurately, providing users with the most suitable solution.

[0533] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0534] In this invention, the server includes means for acquiring information from a historical database, means for preprocessing the information using processing technology, and means for generating multiple proposals in real time using a trained generative machine learning model. This enables the efficient and accurate generation of proposals for dispute resolution.

[0535] "Means of acquiring information" refers to the function that allows a server to collect necessary data from external databases and recording systems.

[0536] "Means of pre-processing using processing technology" refers to the process of removing noise from data acquired by the server and preparing it into an analyzable format, and involves using techniques such as natural language processing.

[0537] A "generative machine learning model" is an algorithm that learns from past data and can generate patterns and suggestions based on new data.

[0538] "Means for generating multiple proposals" refers to a function that utilizes generative machine learning models to create multiple solutions to present to the user.

[0539] "Means of presentation via terminal" refers to the procedure for displaying suggestions generated by the server on the screen of the device used by the user.

[0540] "Means for collecting and analyzing evaluation information" refers to the process of gathering feedback and opinions from users, analyzing them, and using that information to improve the system.

[0541] "Means of protecting the confidentiality of information" refers to security technologies that encrypt data stored on a server to protect it from unauthorized access by third parties.

[0542] The dispute resolution support system of the present invention consists of a server and terminals used by users. This system contributes to efficient and effective dispute resolution using various means described below.

[0543] The server automatically retrieves necessary information from external databases. These databases provide access to a wide range of past cases, including legal information. The server then preprocesses the collected data using natural language processing techniques. This processing may involve using libraries such as NLTK or spaCy, which are implemented in Python. By performing denoising, tokenization, and stop word removal, the server prepares the information into a format that is easy to analyze.

[0544] Next, the server learns from historical data using a generative AI model. This model is implemented using machine learning frameworks such as TensorFlow and PyTorch. The model has the ability to analyze new conflict cases sent to the server and generate diverse solutions.

[0545] Users can input information about their disputes through their terminal and send it to the server. The server analyzes the input information and generates multiple solutions in real time based on similar cases. The generated solutions are presented to the terminal via the user interface, allowing the user to review them and select the most suitable solution.

[0546] User feedback is sent to the server via the device and used to improve the generated AI model. Feedback and personal information are protected using encryption technologies such as AES to maintain confidentiality.

[0547] For example, if a dispute arises between companies regarding a license agreement, the user can input information such as the contract details, disagreements, and a prompt in Japanese stating, "I want to resolve a dispute regarding a license agreement between companies." The server receives this information and uses its model to suggest solutions such as "a proposal for tiered payment of license fees," "a proposal for third-party arbitration," or "the creation of new contract terms." The user can then consider these suggestions and select the next step.

[0548] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0549] Step 1:

[0550] The server connects to an external database via the network to retrieve data, including legal information and past cases. The input consists of keywords related to a specific legal area or case. The database responds with a relevant dataset, which is then stored in the server's data storage.

[0551] Step 2:

[0552] The server preprocesses the acquired data by applying natural language processing. The stored raw data is used as input. Specific processing includes noise reduction, text tokenization, and stop word removal. This results in processed data that is ready for analysis. Natural language processing libraries such as NLTK and spaCy are used in this process.

[0553] Step 3:

[0554] The server trains a generative AI model using preprocessed data. An analyzable dataset is provided as input. The AI ​​model learns past conflict resolution patterns from this data, improving its predictive ability for new cases. The output of this step is the trained model. Deep learning frameworks such as TensorFlow and PyTorch are used for training.

[0555] Step 4:

[0556] The user inputs information about a specific dispute case through their device. This input includes details of the dispute, the opinions of those involved, and past interactions. The device sends the input data to a server. The server receives this information and uses a generative AI model to identify similar cases. As output, a list of candidate solutions is generated.

[0557] Step 5:

[0558] The server organizes the solutions generated by the AI ​​model into a presentable format. The organized solutions are sent to the terminal and displayed to the user through an intuitive user interface. The user can easily compare multiple proposed solutions. The output provides a list of solutions that the user can select.

[0559] Step 6:

[0560] The user inputs information to provide feedback on the presented solution and sends it to the server via their device. This feedback input includes evaluations and suggestions for improvement of the selected solution. The server receives this feedback and analyzes the data to improve the accuracy of the model. As output, an improved AI model is generated. This feedback data is securely stored using encryption technology.

[0561] (Application Example 1)

[0562] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0563] In the realm of electronic transactions, fee disputes and contractual discrepancies frequently occur, requiring prompt and fair solutions. However, current methods have made it difficult to provide solutions based on past cases, forcing users to expend considerable time and effort to find solutions themselves. Therefore, there is a need for a user support system that can efficiently resolve problems in electronic transactions.

[0564] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0565] In this invention, the server includes means for collecting data from a database of past cases, means for preprocessing the data using natural language processing technology, means for generating multiple solutions in real time using a trained generative AI model, and means for identifying past trouble cases related to payment services and presenting solutions in order to support problem solving in electronic transactions. This enables users to quickly and easily obtain appropriate solutions based on past cases.

[0566] A "database of past cases" is a collection of data that compiles information on disputes and troubles that have occurred in the past.

[0567] "Natural language processing technology" refers to techniques that enable computers to understand and process human language, and involves methods for analyzing and preprocessing text data.

[0568] A "generative AI model" is an artificial intelligence model that has the ability to learn from data and generate new solutions and suggestions.

[0569] A "user interface" is an interface with an intuitive design that allows users to operate a system and input and output information.

[0570] "User feedback" refers to information that users use to provide evaluations and opinions on system solutions.

[0571] "Data privacy protection" refers to security measures taken to prevent users' personal information and data from being illegally obtained.

[0572] "Electronic transactions" refer to a form of transaction in which goods and services are bought and sold via the internet.

[0573] A "payment service" is a service used to process payments in electronic transactions.

[0574] The system for realizing this invention involves a server and terminal working in conjunction. The server collects data from a database of past cases and preprocesses it using natural language processing techniques. During this process, it denoises and tokenizes the data to prepare a dataset for training a generative AI model. The software used includes NLTK (Natural Language Toolkit).

[0575] The server uses generative AI models such as OpenAI's GPT to learn patterns from pre-processed data. Then, based on information input from the user, it generates multiple solutions in real time. The generated solutions are sent to the terminal in JSON format.

[0576] The device presents the user with solutions received from the server through its user interface. The interface on the device is developed using React Native and features an intuitive design. This allows users to easily input information and compare the presented solutions.

[0577] When a user provides feedback on a solution via their device, that information is sent to the server and used to further improve the generated AI model. This feedback is encrypted and stored to protect the user's privacy.

[0578] As a concrete example, consider a case where a refund issue occurs in an electronic transaction. The user enters details of the problem into their terminal, and the server generates a solution based on similar cases. For example, solutions such as "a proposal to compensate for the next transaction free of charge" or "use chat support for a quicker resolution" might be offered. In this case, an example of the prompt message used would be, "I'm having trouble because my refund hasn't been processed. Please provide suggestions based on past refund problem resolution cases."

[0579] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0580] Step 1:

[0581] The server periodically collects data from external case databases. This data includes details about past transaction troubles and disputes. Inputs are information from legal databases and public case databases, and output is a collection of raw data.

[0582] Step 2:

[0583] The server preprocesses the collected data using natural language processing. This includes denoising, tokenization, and stop word removal. The input is the raw data obtained in step 1, and the output is clean text data.

[0584] Step 3:

[0585] The server trains a generative AI model using preprocessed data. The model used here includes OpenAI's GPT. The input is the clean text data obtained in step 2, and the output is a generative AI model with problem-solving capabilities.

[0586] Step 4:

[0587] When a user enters details of a problem from their device, the device sends that information to the server. The input is the detailed problem information entered by the user, and the output is request data containing that information.

[0588] Step 5:

[0589] The server uses a generative AI model to generate optimal solutions in real time based on the information received from the user. The input is the request data received in step 4, and the output is multiple solutions.

[0590] Step 6:

[0591] The server sends the solution in JSON format to the terminal, and the terminal presents the solution to the user through the user interface. The input is the solution generated in step 5, and the output is the list of solutions presented to the user.

[0592] Step 7:

[0593] The user considers the proposed solutions and submits feedback to the server via their device. The input is user feedback information, and the output is data containing that feedback.

[0594] Step 8:

[0595] The server analyzes the received feedback and uses it to improve the generative AI model. The input is the feedback data received in step 7, and the output is the improved generative AI model.

[0596] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0597] The conflict resolution support system incorporating the emotion engine of the present invention consists of a data analysis server, a user input terminal, and an emotion analysis module. This system enables the generation of conflict resolutions that take into account the user's emotions, providing a more user-friendly solution.

[0598] Program Processing Overview

[0599] Data acquisition and preprocessing

[0600] The server continuously collects historical case data from an external database. The collected data is preprocessed using natural language processing techniques and used for analysis in generative AI models.

[0601] Operation of the emotion analysis module

[0602] When a user inputs information about a conflict through their device, an emotion analysis module analyzes the text and audio data to identify the user's emotional state. This analysis determines what the user's current emotions are (e.g., stressed, confused, calm, etc.).

[0603] Solution generation using generative AI models

[0604] The server generates multiple solutions using a generative AI model based on the data entered by the user and the output of the sentiment analysis module. The sentiment analysis results are used to provide more personalized solutions and to prioritize the selection of proposals.

[0605] Suggestion presentation via user interface

[0606] The device presents the user with solutions generated through the user interface. Based on sentiment analysis results, the interface display is adjusted to ensure that information is conveyed in the most easily understandable way for the user.

[0607] Feedback collection and privacy protection

[0608] Users provide feedback on suggestions executed via their devices. This feedback information is sent to the server and used to improve system performance and the accuracy of the AI ​​model. All data is encrypted using security technology and stored securely, thus preserving privacy.

[0609] Specific example

[0610] For example, if a dispute arises regarding a specific contract clause, the user inputs the issue along with their emotional state (anger, anxiety, etc.) into the terminal. The emotion analysis module identifies the user's current emotions from the input information. The server uses this information to generate suggestions that alleviate the user's emotions and emphasize reasonable solutions in the situation.

[0611] This system allows users to receive emotionally-driven solutions and helps them engage in more constructive negotiations.

[0612] The following describes the processing flow.

[0613] Step 1:

[0614] The server accesses legal databases and databases of publicly available dispute cases, automatically collecting relevant data. This is done by periodically utilizing APIs or web scraping.

[0615] Step 2:

[0616] The server preprocesses the collected data using natural language processing techniques. Specifically, it tokenizes the data, denoises it, and extracts the necessary information.

[0617] Step 3:

[0618] As part of training the generative AI model, the server uses pre-processed data to learn patterns and relationships, enabling it to generate solutions for new conflicts in the future.

[0619] Step 4:

[0620] Users use their devices to enter detailed information about the conflict they are facing (e.g., background of the conflict, parties involved, disagreements, etc.).

[0621] Step 5:

[0622] An emotion analysis module installed in the device analyzes text or voice data entered by the user in real time to identify the user's emotional state.

[0623] Step 6:

[0624] The device sends collected sentiment data and detailed user-generated problem information to the server. This enables the generation of context-based solutions.

[0625] Step 7:

[0626] The server generates multiple solutions in real time using a generative AI model based on the transmitted information. During this process, it considers the sentiment analysis results and prioritizes solutions that are appropriate to the user's emotional state.

[0627] Step 8:

[0628] The server sends the generated solution to the terminal. This is provided in an appropriately tailored format, taking into consideration the user's feelings.

[0629] Step 9:

[0630] The device presents solutions to the user. The user interface is designed to be intuitively easy for the user to understand, and displays are based on sentiment analysis.

[0631] Step 10:

[0632] The user selects the solution they deem most appropriate from the presented options and inputs feedback and opinions about that selection into the device.

[0633] Step 11:

[0634] The device sends collected user feedback to the server. This allows for further improvement of the generative AI model and the system.

[0635] Step 12:

[0636] The server ensures user privacy by protecting all data with encryption technology and storing it securely.

[0637] (Example 2)

[0638] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0639] In today's information society, it is crucial to present solutions that take into account the user's emotions and state of mind. However, existing systems do not adequately detect and reflect user emotions in their solutions, making it difficult to present optimal solutions to users and achieve effective problem-solving.

[0640] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0641] In this invention, the server includes means for collecting information from past case and event information sources, means for pre-processing the information using language data processing technology, and means for receiving information about a problem input by the user through an information device. This enables the generation and presentation of flexible and effective solutions based on the user's emotions and state.

[0642] "Past case and event information sources" refer to sources of information that contain records of past events and cases, and provide basic data that can be used for new analyses and judgments based on this information.

[0643] "Information equipment" refers to devices used by users to input or receive information, and includes computers, smartphones, tablets, and other similar devices.

[0644] "Language data processing technology" refers to the technology of analyzing and processing natural language using computers, enabling text preprocessing and semantic analysis.

[0645] An "information analysis module" is a software or system component that analyzes information received from a user to identify their emotional state and other characteristics.

[0646] An "information processing AI system" is a system that utilizes artificial intelligence technology designed to process large amounts of data and automatically generate solutions tailored to specific purposes.

[0647] A "user information device" refers to a device used by a user to input information or receive solutions, and functions as an interface.

[0648] This invention provides a system that supports problem-solving while taking user emotions into consideration, and its details are described below.

[0649] The server collects information from past case and event sources. Specifically, it retrieves past case data using SQL queries through access to a large-scale database. This data is preprocessed using language data processing techniques. For example, NLTK and SpaCy are used to clean and tokenize the data.

[0650] Users input information about their problems and emotions through their information devices. The device receives this information and sends it to an emotion analysis module. This module uses online language analysis services via APIs and identifies the user's emotions through emotion analysis technologies from Azure and Google.

[0651] The server uses an information processing AI system to generate solutions based on information received from the user and the results of sentiment analysis. Specifically, it uses a generative AI model to create concrete suggestions for addressing the obtained information. An example of a prompt used in this process is, "Propose a way to resolve the contractual conflict and generate a suitable solution for a user whose current emotion is anger."

[0652] The terminal displays the generated solution via the user information device. The interface is adjusted according to the user's emotional state. For example, a calm user is presented with detailed information, while an emotionally charged user receives a gentler explanation.

[0653] As a concrete example, if a user is dissatisfied with a business contract, the user inputs the problem and their feelings into the terminal. An emotion analysis module identifies the user's anger, and the server generates suggestions that emphasize solutions appropriate to the situation. In this way, the user receives appropriate solutions that take their feelings into account, enabling more effective communication and problem-solving.

[0654] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0655] Step 1:

[0656] The server collects data from past case and event information sources. Specifically, it performs SQL queries against the database to extract similar past cases. The input is raw data from the database, and the output is a set of cases. The server uses this as an information infrastructure for the next steps.

[0657] Step 2:

[0658] The server preprocesses the collected historical data using language data processing techniques. Specifically, it performs tokenization, stop word removal, and stemming using NLTK. The input is the example data obtained in step 1, and the output is preprocessed data in a format suitable for analysis.

[0659] Step 3:

[0660] The user inputs information about their problem through the device. Specifically, this involves using text forms or voice input to enter a descriptive statement describing their current situation and emotions (e.g., stress, anger). This input is received as raw data.

[0661] Step 4:

[0662] The terminal sends user input data to an emotion analysis module. The emotion analysis module performs data analysis to identify the user's emotional state. The input here is text or voice data from the user, and the output is a label for the identified emotional state (e.g., anger, anxiety).

[0663] Step 5:

[0664] The server integrates the data entered by the user with the output of the sentiment analysis module and inputs it as a prompt to the generative AI model. The input here consists of the pre-processed data obtained in step 2 and the sentiment analysis data obtained in step 4. The generative AI model generates multiple solutions for the input and provides them as output.

[0665] Step 6:

[0666] The terminal receives output from the generated AI model and presents solutions via user information devices. This step involves adjusting the user interface to take emotional states into account. Specifically, it presents detailed information to calm users and in a considerate tone to emotional users. The input is the model's generation, and the output is user-customized suggested information.

[0667] Step 7:

[0668] The user provides feedback on the presented solution. The terminal receives this feedback and sends it to the server as data. This input consists of user ratings and comments, and the output is data that helps improve the system's performance. The server analyzes the feedback to improve the accuracy of the model and the system.

[0669] (Application Example 2)

[0670] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0671] In caregiving settings, there is a need to reduce troubles and stress caused by a lack of understanding of the emotions of users and their families, as well as inappropriate responses during communication. In particular, a challenge is the lack of technical means to accurately grasp the emotional state of users and to provide appropriate countermeasures quickly.

[0672] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0673] In this invention, the server includes means for collecting data from past case data storage, means for preprocessing the data using natural language processing technology, means for generating multiple solutions in real time using a trained generative AI model, means for analyzing the emotional state in interactions with users, and means for proposing appropriate countermeasures in the care environment that correspond to the user's emotions. This enables care staff to quickly obtain optimal countermeasures that take into account the user's emotions.

[0674] A "past case data storage" is a data storage device that saves case information from past caregiving settings and stores it in an accessible format.

[0675] "Natural language processing technology" refers to information technology methods that analyze text data to understand and generate human language.

[0676] A "generative AI model" is an algorithm trained using artificial intelligence technology to generate multiple solutions from input information.

[0677] A "user interface" is a means of display and input for a user to interact with a system.

[0678] "Means for analyzing emotional states" refer to algorithms and technologies for identifying a user's emotions from text and audio data.

[0679] "Means of proposing appropriate countermeasures" refers to methods and processes for presenting the optimal actions for care staff based on analyzed emotional data.

[0680] "User feedback" refers to response information provided by system users regarding the effectiveness and satisfaction level of proposed solutions.

[0681] "Means of protecting data privacy" refer to security technologies and measures to prevent unauthorized access to personal and confidential information.

[0682] To realize this invention, the system is configured as follows: The server collects data from past case data storage and preprocesses that data using natural language processing technology. Specifically, it preprocesses the data using the Python NLTK library to prepare for training an AI model utilizing Hugging Face's Transformers. The emotion analysis module allows the server to analyze text and voice data input from the user and identify the emotional state. At this stage, the Google Cloud Natural Language API is used to identify emotions in real time.

[0683] Once the user's emotional state is identified, the server generates multiple solutions using a generative AI model. This generation process utilizes a model based on the TensorFlow library to present the resulting solutions to care staff appropriately and quickly.

[0684] The user interface on the device is built using React Native and visually presents appropriate solutions tailored to the user's emotions in an easy-to-understand manner. Users can review the displayed solutions and make their own selections. It also includes a feedback function to collect evaluations and opinions from care staff, which are securely stored and managed using AWS S3.

[0685] As a concrete example, in a nursing home, if a resident shows signs of anxiety during communication, the system analyzes the cause and quickly provides guidance to staff on how to respond. Examples of prompts include, "The family seems anxious. Please identify the reason and suggest reassuring words," and "We have noticed that the resident is experiencing stress. How should we communicate with them?" In this way, the system supports smooth communication and rapid problem-solving in nursing care settings.

[0686] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0687] Step 1:

[0688] The server collects data from a storage of past case data. The input is case data, which is preprocessed using the Python NLTK library. The output is data in a parseable format. Specifically, the data is cleaned and tokenized, and the text data is converted into a format suitable for generating AI models.

[0689] Step 2:

[0690] Users input information via their devices in voice or text format. This input includes specific situations and emotional expressions related to interactions with the user. The device then transmits the input data to the server.

[0691] Step 3:

[0692] The server uses the Google Cloud Natural Language API to analyze the emotional state of the input information. The input is text data, and the output is the emotional state extracted through the analysis. This analysis identifies emotional states such as stress, anxiety, and relief.

[0693] Step 4:

[0694] The server uses a generative AI model to generate multiple solutions based on the sentiment analysis results. The input is the sentiment analysis result, and the generative AI model generates candidate solutions. Specifically, the model is executed using the TensorFlow library to create appropriate responses based on the sentiment.

[0695] Step 5:

[0696] The device presents solutions to the user through a user interface built with React Native. Input is solution information from the server, displayed in a clear and intuitive format. Output is a visual presentation of information.

[0697] Step 6:

[0698] Users can provide feedback on the proposed solutions. This feedback is sent to the server via the terminal.

[0699] Step 7:

[0700] The server sends the collected feedback to AWS S3 for secure storage. The input is feedback data, and the output is data stored in an appropriately encrypted state. This allows the feedback to be regularly incorporated into improving the accuracy of the AI ​​model.

[0701] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0702] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0703] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0704] [Fourth Embodiment]

[0705] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0706] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0707] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0708] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0709] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0710] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0711] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0712] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0713] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0714] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0715] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0716] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0717] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0718] The dispute resolution support system of the present invention has a system configuration that includes a server connected to a network and terminals used by users. The program processing and specific examples of this system are described below.

[0719] Program Processing Overview

[0720] Data acquisition and preprocessing

[0721] The server periodically collects data from external legal databases and public case databases. The collected data is preprocessed using natural language processing techniques, including noise reduction, tokenization, and stop word removal. This prepares the data in a format suitable for training generative AI models.

[0722] Training and application of generative AI models

[0723] The server trains a generative AI model using a large, pre-processed dataset. This model learns past conflict resolution patterns and improves its ability to generate solutions for new cases. When the user provides detailed conflict information, the server uses this generative AI model to identify similar cases and generate several solutions in real time.

[0724] Suggestion presentation via user interface

[0725] The terminal sends details of the problem entered by the user to the server and presents the user with the solution received from the server in response. The user interface is intuitive and displays multiple solutions in a format that makes it easy to compare them.

[0726] Gathering feedback and protecting privacy

[0727] Users input their evaluations and feedback on the presented solutions into their devices. This feedback data is sent to a server and used to improve the generated AI model. The server stores all data using robust encryption technology, ensuring the utmost protection of user privacy.

[0728] Specific example

[0729] For example, consider a dispute arising from a licensing agreement between companies. In this case, the user inputs the contract details, points of disagreement, and the opinions of the parties involved into the terminal. The server receives this information, analyzes similar cases in real time from a vast amount of collected past case data, and proposes solutions such as the following.

[0730] Proposal for phased payment of license fees

[0731] Arbitration proposal by a third party

[0732] Creation of new contract terms

[0733] By having users consider these options, select the most appropriate solution, and provide feedback, the system continuously improves its accuracy.

[0734] The following describes the processing flow.

[0735] Step 1:

[0736] The server periodically accesses external legal and case databases and automatically collects relevant data. This collection includes information retrieval using APIs and web scraping.

[0737] Step 2:

[0738] The server applies natural language processing techniques to cleanse the collected data and format the text. This process involves denoising, tokenizing, and removing stop words from the data.

[0739] Step 3:

[0740] The server trains a generative AI model using pre-processed data. This allows the AI ​​model to learn patterns and useful features from past cases and acquire the ability to generate solutions applicable to new conflicts.

[0741] Step 4:

[0742] The device provides users with an intuitive interface, allowing them to input detailed information about the conflict they are facing.

[0743] Step 5:

[0744] Users enter information about their issue into the terminal. This information includes the nature of the dispute, the parties involved, and the points of disagreement.

[0745] Step 6:

[0746] The terminal sends the information entered by the user to the server. This transmission allows the server to receive data for analyzing the user's situation.

[0747] Step 7:

[0748] The server uses a generative AI model to generate multiple solutions in real time based on the input data. In this process, it refers to similar past cases to create optimized solutions.

[0749] Step 8:

[0750] The server sends the generated solutions to the terminal. Multiple options are presented, with their respective advantages and disadvantages explained.

[0751] Step 9:

[0752] The terminal displays the solutions received from the server to the user. The user can then review these solutions and select the one they deem best.

[0753] Step 10:

[0754] Users input feedback on the presented solutions into their devices and share their evaluations and reasons for their choices.

[0755] Step 11:

[0756] The device sends feedback to the server, recording the user's opinions. This information is used to improve the system and further enhance the accuracy of the generated AI model.

[0757] Step 12:

[0758] The server protects user privacy by encrypting all data and storing it in secure storage.

[0759] (Example 1)

[0760] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0761] The objective of this invention is to provide an effective means for dispute resolution and to efficiently generate multiple proposals. Conventional systems often struggle to effectively utilize past cases, resulting in a heavy burden on users. To address this issue, there is a need for a system that processes data quickly and accurately, providing users with the most suitable solution.

[0762] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0763] In this invention, the server includes means for acquiring information from a historical database, means for preprocessing the information using processing technology, and means for generating multiple proposals in real time using a trained generative machine learning model. This enables the efficient and accurate generation of proposals for dispute resolution.

[0764] "Means of acquiring information" refers to the function that allows a server to collect necessary data from external databases and recording systems.

[0765] "Means of pre-processing using processing technology" refers to the process of removing noise from data acquired by the server and preparing it into an analyzable format, and involves using techniques such as natural language processing.

[0766] A "generative machine learning model" is an algorithm that learns from past data and can generate patterns and suggestions based on new data.

[0767] "Means for generating multiple proposals" refers to a function that utilizes generative machine learning models to create multiple solutions to present to the user.

[0768] "Means of presentation via terminal" refers to the procedure for displaying suggestions generated by the server on the screen of the device used by the user.

[0769] "Means for collecting and analyzing evaluation information" refers to the process of gathering feedback and opinions from users, analyzing them, and using that information to improve the system.

[0770] "Means of protecting the confidentiality of information" refers to security technologies that encrypt data stored on a server to protect it from unauthorized access by third parties.

[0771] The dispute resolution support system of the present invention consists of a server and terminals used by users. This system contributes to efficient and effective dispute resolution using various means described below.

[0772] The server automatically retrieves necessary information from external databases. These databases provide access to a wide range of past cases, including legal information. The server then preprocesses the collected data using natural language processing techniques. This processing may involve using libraries such as NLTK or spaCy, which are implemented in Python. By performing denoising, tokenization, and stop word removal, the server prepares the information into a format that is easy to analyze.

[0773] Next, the server learns from historical data using a generative AI model. This model is implemented using machine learning frameworks such as TensorFlow and PyTorch. The model has the ability to analyze new conflict cases sent to the server and generate diverse solutions.

[0774] Users can input information about their disputes through their terminal and send it to the server. The server analyzes the input information and generates multiple solutions in real time based on similar cases. The generated solutions are presented to the terminal via the user interface, allowing the user to review them and select the most suitable solution.

[0775] User feedback is sent to the server via the device and used to improve the generated AI model. Feedback and personal information are protected using encryption technologies such as AES to maintain confidentiality.

[0776] For example, if a dispute arises between companies regarding a license agreement, the user can input information such as the contract details, disagreements, and a prompt in Japanese stating, "I want to resolve a dispute regarding a license agreement between companies." The server receives this information and uses its model to suggest solutions such as "a proposal for tiered payment of license fees," "a proposal for third-party arbitration," or "the creation of new contract terms." The user can then consider these suggestions and select the next step.

[0777] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0778] Step 1:

[0779] The server connects to an external database via the network to retrieve data, including legal information and past cases. The input consists of keywords related to a specific legal area or case. The database responds with a relevant dataset, which is then stored in the server's data storage.

[0780] Step 2:

[0781] The server preprocesses the acquired data by applying natural language processing. The stored raw data is used as input. Specific processing includes noise reduction, text tokenization, and stop word removal. This results in processed data that is ready for analysis. Natural language processing libraries such as NLTK and spaCy are used in this process.

[0782] Step 3:

[0783] The server trains a generative AI model using preprocessed data. An analyzable dataset is provided as input. The AI ​​model learns past conflict resolution patterns from this data, improving its predictive ability for new cases. The output of this step is the trained model. Deep learning frameworks such as TensorFlow and PyTorch are used for training.

[0784] Step 4:

[0785] The user inputs information about a specific dispute case through their device. This input includes details of the dispute, the opinions of those involved, and past interactions. The device sends the input data to a server. The server receives this information and uses a generative AI model to identify similar cases. As output, a list of candidate solutions is generated.

[0786] Step 5:

[0787] The server organizes the solutions generated by the AI ​​model into a presentable format. The organized solutions are sent to the terminal and displayed to the user through an intuitive user interface. The user can easily compare multiple proposed solutions. The output provides a list of solutions that the user can select.

[0788] Step 6:

[0789] The user inputs information to provide feedback on the presented solution and sends it to the server via their device. This feedback input includes evaluations and suggestions for improvement of the selected solution. The server receives this feedback and analyzes the data to improve the accuracy of the model. As output, an improved AI model is generated. This feedback data is securely stored using encryption technology.

[0790] (Application Example 1)

[0791] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0792] In the realm of electronic transactions, fee disputes and contractual discrepancies frequently occur, requiring prompt and fair solutions. However, current methods have made it difficult to provide solutions based on past cases, forcing users to expend considerable time and effort to find solutions themselves. Therefore, there is a need for a user support system that can efficiently resolve problems in electronic transactions.

[0793] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0794] In this invention, the server includes means for collecting data from a database of past cases, means for preprocessing the data using natural language processing technology, means for generating multiple solutions in real time using a trained generative AI model, and means for identifying past trouble cases related to payment services and presenting solutions in order to support problem solving in electronic transactions. This enables users to quickly and easily obtain appropriate solutions based on past cases.

[0795] A "database of past cases" is a collection of data that compiles information on disputes and troubles that have occurred in the past.

[0796] "Natural language processing technology" refers to techniques that enable computers to understand and process human language, and involves methods for analyzing and preprocessing text data.

[0797] A "generative AI model" is an artificial intelligence model that has the ability to learn from data and generate new solutions and suggestions.

[0798] A "user interface" is an interface with an intuitive design that allows users to operate a system and input and output information.

[0799] "User feedback" refers to information that users use to provide evaluations and opinions on system solutions.

[0800] "Data privacy protection" refers to security measures taken to prevent users' personal information and data from being illegally obtained.

[0801] "Electronic transactions" refer to a form of transaction in which goods and services are bought and sold via the internet.

[0802] A "payment service" is a service used to process payments in electronic transactions.

[0803] The system for realizing this invention involves a server and terminal working in conjunction. The server collects data from a database of past cases and preprocesses it using natural language processing techniques. During this process, it denoises and tokenizes the data to prepare a dataset for training a generative AI model. The software used includes NLTK (Natural Language Toolkit).

[0804] The server uses generative AI models such as OpenAI's GPT to learn patterns from pre-processed data. Then, based on information input from the user, it generates multiple solutions in real time. The generated solutions are sent to the terminal in JSON format.

[0805] The device presents the user with solutions received from the server through its user interface. The interface on the device is developed using React Native and features an intuitive design. This allows users to easily input information and compare the presented solutions.

[0806] When a user provides feedback on a solution via their device, that information is sent to the server and used to further improve the generated AI model. This feedback is encrypted and stored to protect the user's privacy.

[0807] As a concrete example, consider a case where a refund issue occurs in an electronic transaction. The user enters details of the problem into their terminal, and the server generates a solution based on similar cases. For example, solutions such as "a proposal to compensate for the next transaction free of charge" or "use chat support for a quicker resolution" might be offered. In this case, an example of the prompt message used would be, "I'm having trouble because my refund hasn't been processed. Please provide suggestions based on past refund problem resolution cases."

[0808] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0809] Step 1:

[0810] The server periodically collects data from external case databases. This data includes details about past transaction troubles and disputes. Inputs are information from legal databases and public case databases, and output is a collection of raw data.

[0811] Step 2:

[0812] The server preprocesses the collected data using natural language processing. This includes denoising, tokenization, and stop word removal. The input is the raw data obtained in step 1, and the output is clean text data.

[0813] Step 3:

[0814] The server trains a generative AI model using preprocessed data. The model used here includes OpenAI's GPT. The input is the clean text data obtained in step 2, and the output is a generative AI model with problem-solving capabilities.

[0815] Step 4:

[0816] When a user enters details of a problem from their device, the device sends that information to the server. The input is the detailed problem information entered by the user, and the output is request data containing that information.

[0817] Step 5:

[0818] The server uses a generative AI model to generate optimal solutions in real time based on the information received from the user. The input is the request data received in step 4, and the output is multiple solutions.

[0819] Step 6:

[0820] The server sends the solution in JSON format to the terminal, and the terminal presents the solution to the user through the user interface. The input is the solution generated in step 5, and the output is the list of solutions presented to the user.

[0821] Step 7:

[0822] The user considers the proposed solutions and submits feedback to the server via their device. The input is user feedback information, and the output is data containing that feedback.

[0823] Step 8:

[0824] The server analyzes the received feedback and uses it to improve the generative AI model. The input is the feedback data received in step 7, and the output is the improved generative AI model.

[0825] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0826] The conflict resolution support system incorporating the emotion engine of the present invention consists of a data analysis server, a user input terminal, and an emotion analysis module. This system enables the generation of conflict resolutions that take into account the user's emotions, providing a more user-friendly solution.

[0827] Program Processing Overview

[0828] Data acquisition and preprocessing

[0829] The server continuously collects historical case data from an external database. The collected data is preprocessed using natural language processing techniques and used for analysis in generative AI models.

[0830] Operation of the emotion analysis module

[0831] When a user inputs information about a conflict through their device, an emotion analysis module analyzes the text and audio data to identify the user's emotional state. This analysis determines what the user's current emotions are (e.g., stressed, confused, calm, etc.).

[0832] Solution generation using generative AI models

[0833] The server generates multiple solutions using a generative AI model based on the data entered by the user and the output of the sentiment analysis module. The sentiment analysis results are used to provide more personalized solutions and to prioritize the selection of proposals.

[0834] Suggestion presentation via user interface

[0835] The device presents the user with solutions generated through the user interface. Based on sentiment analysis results, the interface display is adjusted to ensure that information is conveyed in the most easily understandable way for the user.

[0836] Feedback collection and privacy protection

[0837] Users provide feedback on suggestions executed via their devices. This feedback information is sent to the server and used to improve system performance and the accuracy of the AI ​​model. All data is encrypted using security technology and stored securely, thus preserving privacy.

[0838] Specific example

[0839] For example, if a dispute arises regarding a specific contract clause, the user inputs the issue along with their emotional state (anger, anxiety, etc.) into the terminal. The emotion analysis module identifies the user's current emotions from the input information. The server uses this information to generate suggestions that alleviate the user's emotions and emphasize reasonable solutions in the situation.

[0840] This system allows users to receive emotionally-driven solutions and helps them engage in more constructive negotiations.

[0841] The following describes the processing flow.

[0842] Step 1:

[0843] The server accesses legal databases and databases of publicly available dispute cases, automatically collecting relevant data. This is done by periodically utilizing APIs or web scraping.

[0844] Step 2:

[0845] The server preprocesses the collected data using natural language processing techniques. Specifically, it tokenizes the data, denoises it, and extracts the necessary information.

[0846] Step 3:

[0847] As part of training the generative AI model, the server uses pre-processed data to learn patterns and relationships, enabling it to generate solutions for new conflicts in the future.

[0848] Step 4:

[0849] Users use their devices to enter detailed information about the conflict they are facing (e.g., background of the conflict, parties involved, disagreements, etc.).

[0850] Step 5:

[0851] An emotion analysis module installed in the device analyzes text or voice data entered by the user in real time to identify the user's emotional state.

[0852] Step 6:

[0853] The device sends collected sentiment data and detailed user-generated problem information to the server. This enables the generation of context-based solutions.

[0854] Step 7:

[0855] The server generates multiple solutions in real time using a generative AI model based on the transmitted information. During this process, it considers the sentiment analysis results and prioritizes solutions that are appropriate to the user's emotional state.

[0856] Step 8:

[0857] The server sends the generated solution to the terminal. This is provided in an appropriately tailored format, taking into consideration the user's feelings.

[0858] Step 9:

[0859] The device presents solutions to the user. The user interface is designed to be intuitively easy for the user to understand, and displays are based on sentiment analysis.

[0860] Step 10:

[0861] The user selects the solution they deem most appropriate from the presented options and inputs feedback and opinions about that selection into the device.

[0862] Step 11:

[0863] The device sends collected user feedback to the server. This allows for further improvement of the generative AI model and the system.

[0864] Step 12:

[0865] The server ensures user privacy by protecting all data with encryption technology and storing it securely.

[0866] (Example 2)

[0867] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0868] In today's information society, it is crucial to present solutions that take into account the user's emotions and state of mind. However, existing systems do not adequately detect and reflect user emotions in their solutions, making it difficult to present optimal solutions to users and achieve effective problem-solving.

[0869] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0870] In this invention, the server includes means for collecting information from past case and event information sources, means for pre-processing the information using language data processing technology, and means for receiving information about a problem input by the user through an information device. This enables the generation and presentation of flexible and effective solutions based on the user's emotions and state.

[0871] "Past case and event information sources" refer to sources of information that contain records of past events and cases, and provide basic data that can be used for new analyses and judgments based on this information.

[0872] "Information equipment" refers to devices used by users to input or receive information, and includes computers, smartphones, tablets, and other similar devices.

[0873] "Language data processing technology" refers to the technology of analyzing and processing natural language using computers, enabling text preprocessing and semantic analysis.

[0874] An "information analysis module" is a software or system component that analyzes information received from a user to identify their emotional state and other characteristics.

[0875] An "information processing AI system" is a system that utilizes artificial intelligence technology designed to process large amounts of data and automatically generate solutions tailored to specific purposes.

[0876] A "user information device" refers to a device used by a user to input information or receive solutions, and functions as an interface.

[0877] This invention provides a system that supports problem-solving while taking user emotions into consideration, and its details are described below.

[0878] The server collects information from past case and event sources. Specifically, it retrieves past case data using SQL queries through access to a large-scale database. This data is preprocessed using language data processing techniques. For example, NLTK and SpaCy are used to clean and tokenize the data.

[0879] Users input information about their problems and emotions through their information devices. The device receives this information and sends it to an emotion analysis module. This module uses online language analysis services via APIs and identifies the user's emotions through emotion analysis technologies from Azure and Google.

[0880] The server uses an information processing AI system to generate solutions based on information received from the user and the results of sentiment analysis. Specifically, it uses a generative AI model to create concrete suggestions for addressing the obtained information. An example of a prompt used in this process is, "Propose a way to resolve the contractual conflict and generate a suitable solution for a user whose current emotion is anger."

[0881] The terminal displays the generated solution via the user information device. The interface is adjusted according to the user's emotional state. For example, a calm user is presented with detailed information, while an emotionally charged user receives a gentler explanation.

[0882] As a concrete example, if a user is dissatisfied with a business contract, the user inputs the problem and their feelings into the terminal. An emotion analysis module identifies the user's anger, and the server generates suggestions that emphasize solutions appropriate to the situation. In this way, the user receives appropriate solutions that take their feelings into account, enabling more effective communication and problem-solving.

[0883] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0884] Step 1:

[0885] The server collects data from past case and event information sources. Specifically, it performs SQL queries against the database to extract similar past cases. The input is raw data from the database, and the output is a set of cases. The server uses this as an information infrastructure for the next steps.

[0886] Step 2:

[0887] The server preprocesses the collected historical data using language data processing techniques. Specifically, it performs tokenization, stop word removal, and stemming using NLTK. The input is the example data obtained in step 1, and the output is preprocessed data in a format suitable for analysis.

[0888] Step 3:

[0889] The user inputs information about their problem through the device. Specifically, this involves using text forms or voice input to enter a descriptive statement describing their current situation and emotions (e.g., stress, anger). This input is received as raw data.

[0890] Step 4:

[0891] The terminal sends user input data to an emotion analysis module. The emotion analysis module performs data analysis to identify the user's emotional state. The input here is text or voice data from the user, and the output is a label for the identified emotional state (e.g., anger, anxiety).

[0892] Step 5:

[0893] The server integrates the data entered by the user with the output of the sentiment analysis module and inputs it as a prompt to the generative AI model. The input here consists of the pre-processed data obtained in step 2 and the sentiment analysis data obtained in step 4. The generative AI model generates multiple solutions for the input and provides them as output.

[0894] Step 6:

[0895] The terminal receives output from the generated AI model and presents solutions via user information devices. This step involves adjusting the user interface to take emotional states into account. Specifically, it presents detailed information to calm users and in a considerate tone to emotional users. The input is the model's generation, and the output is user-customized suggested information.

[0896] Step 7:

[0897] The user provides feedback on the presented solution. The terminal receives this feedback and sends it to the server as data. This input consists of user ratings and comments, and the output is data that helps improve the system's performance. The server analyzes the feedback to improve the accuracy of the model and the system.

[0898] (Application Example 2)

[0899] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0900] In caregiving settings, there is a need to reduce troubles and stress caused by a lack of understanding of the emotions of users and their families, as well as inappropriate responses during communication. In particular, a challenge is the lack of technical means to accurately grasp the emotional state of users and to provide appropriate countermeasures quickly.

[0901] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0902] In this invention, the server includes means for collecting data from past case data storage, means for preprocessing the data using natural language processing technology, means for generating multiple solutions in real time using a trained generative AI model, means for analyzing the emotional state in interactions with users, and means for proposing appropriate countermeasures in the care environment that correspond to the user's emotions. This enables care staff to quickly obtain optimal countermeasures that take into account the user's emotions.

[0903] A "past case data storage" is a data storage device that saves case information from past caregiving settings and stores it in an accessible format.

[0904] "Natural language processing technology" refers to information technology methods that analyze text data to understand and generate human language.

[0905] A "generative AI model" is an algorithm trained using artificial intelligence technology to generate multiple solutions from input information.

[0906] A "user interface" is a means of display and input for a user to interact with a system.

[0907] "Means for analyzing emotional states" refer to algorithms and technologies for identifying a user's emotions from text and audio data.

[0908] "Means of proposing appropriate countermeasures" refers to methods and processes for presenting the optimal actions for care staff based on analyzed emotional data.

[0909] "User feedback" refers to response information provided by system users regarding the effectiveness and satisfaction level of proposed solutions.

[0910] "Means of protecting data privacy" refer to security technologies and measures to prevent unauthorized access to personal and confidential information.

[0911] To realize this invention, the system is configured as follows: The server collects data from past case data storage and preprocesses that data using natural language processing technology. Specifically, it preprocesses the data using the Python NLTK library to prepare for training an AI model utilizing Hugging Face's Transformers. The emotion analysis module allows the server to analyze text and voice data input from the user and identify the emotional state. At this stage, the Google Cloud Natural Language API is used to identify emotions in real time.

[0912] Once the user's emotional state is identified, the server generates multiple solutions using a generative AI model. This generation process utilizes a model based on the TensorFlow library to present the resulting solutions to care staff appropriately and quickly.

[0913] The user interface on the device is built using React Native and visually presents appropriate solutions tailored to the user's emotions in an easy-to-understand manner. Users can review the displayed solutions and make their own selections. It also includes a feedback function to collect evaluations and opinions from care staff, which are securely stored and managed using AWS S3.

[0914] As a concrete example, in a nursing home, if a resident shows signs of anxiety during communication, the system analyzes the cause and quickly provides guidance to staff on how to respond. Examples of prompts include, "The family seems anxious. Please identify the reason and suggest reassuring words," and "We have noticed that the resident is experiencing stress. How should we communicate with them?" In this way, the system supports smooth communication and rapid problem-solving in nursing care settings.

[0915] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0916] Step 1:

[0917] The server collects data from a storage of past case data. The input is case data, which is preprocessed using the Python NLTK library. The output is data in a parseable format. Specifically, the data is cleaned and tokenized, and the text data is converted into a format suitable for generating AI models.

[0918] Step 2:

[0919] Users input information via their devices in voice or text format. This input includes specific situations and emotional expressions related to interactions with the user. The device then transmits the input data to the server.

[0920] Step 3:

[0921] The server uses the Google Cloud Natural Language API to analyze the emotional state of the input information. The input is text data, and the output is the emotional state extracted through the analysis. This analysis identifies emotional states such as stress, anxiety, and relief.

[0922] Step 4:

[0923] The server uses a generative AI model to generate multiple solutions based on the sentiment analysis results. The input is the sentiment analysis result, and the generative AI model generates candidate solutions. Specifically, the model is executed using the TensorFlow library to create appropriate responses based on the sentiment.

[0924] Step 5:

[0925] The device presents solutions to the user through a user interface built with React Native. Input is solution information from the server, displayed in a clear and intuitive format. Output is a visual presentation of information.

[0926] Step 6:

[0927] Users can provide feedback on the proposed solutions. This feedback is sent to the server via the terminal.

[0928] Step 7:

[0929] The server sends the collected feedback to AWS S3 for secure storage. The input is feedback data, and the output is data stored in an appropriately encrypted state. This allows the feedback to be regularly incorporated into improving the accuracy of the AI ​​model.

[0930] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0931] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0932] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0933] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0934] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0935] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0936] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0937] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0938] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0939] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0940] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0941] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0942] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0943] 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.

[0944] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0945] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0946] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0947] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0948] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0949] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0950] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0951] The following is further disclosed regarding the embodiments described above.

[0952] (Claim 1)

[0953] Methods for collecting data from past case databases,

[0954] A means for preprocessing the aforementioned data using natural language processing technology,

[0955] A means of generating multiple solutions in real time using a trained generative AI model,

[0956] A means for presenting the generated solution via a user interface,

[0957] A means of collecting and analyzing user feedback,

[0958] Means to protect data privacy,

[0959] A system that includes this.

[0960] (Claim 2)

[0961] The system according to claim 1, wherein the generating AI model is configured to learn conflict patterns based on a database of past cases.

[0962] (Claim 3)

[0963] The system according to claim 1, wherein the user interface is designed to provide intuitive operation, allowing the user to easily input information and select a solution.

[0964] "Example 1"

[0965] (Claim 1)

[0966] Means of retrieving information from past databases,

[0967] Means for preprocessing the aforementioned information using processing technology,

[0968] A means of generating multiple proposals in real time using a trained generative machine learning model,

[0969] A means for presenting the generated proposal via a terminal,

[0970] A means of collecting and analyzing evaluation information from users,

[0971] Means to protect the confidentiality of information,

[0972] A system that includes this.

[0973] (Claim 2)

[0974] The system according to claim 1, wherein the generative machine learning model is configured to learn resolution patterns based on a historical database.

[0975] (Claim 3)

[0976] The system according to claim 1, wherein the terminal is designed to provide intuitive operation, allowing the user to easily input information and select suggestions.

[0977] "Application Example 1"

[0978] (Claim 1)

[0979] Methods for collecting data from past case databases,

[0980] A means for preprocessing the aforementioned data using natural language processing technology,

[0981] A means of generating multiple solutions in real time using a trained generative AI model,

[0982] A means for presenting the generated solution via a user interface,

[0983] Means for collecting and analyzing user feedback,

[0984] Means to protect data privacy,

[0985] To support problem-solving in electronic transactions, we have identified past trouble cases related to payment services and provided solutions.

[0986] A system that includes this.

[0987] (Claim 2)

[0988] The system according to claim 1, wherein the generating AI model is configured to learn dispute patterns based on a database of past cases and to identify patterns related to a particular category of electronic transactions.

[0989] (Claim 3)

[0990] The system according to claim 1, wherein the user interface is designed to provide intuitive operation, allowing the user to easily input information and select a solution, and presenting information particularly suitable for troubleshooting in trade using electronic terminals.

[0991] "Example 2 of combining an emotion engine"

[0992] (Claim 1)

[0993] Means of collecting information from past case and event sources,

[0994] Means for preprocessing the aforementioned information using language data processing technology,

[0995] A means for receiving information about a problem that a user inputs through an information device,

[0996] A means of using an information analysis module to analyze and identify emotional states,

[0997] A means of generating multiple solutions in real time using a trained information processing AI system,

[0998] A means for presenting the generated solution via a user information device,

[0999] Means for collecting and analyzing user information,

[1000] Means of protecting data,

[1001] A system that includes this.

[1002] (Claim 2)

[1003] The system according to claim 1, wherein the information processing AI system is configured to learn problem-solving patterns based on past case and event information sources.

[1004] (Claim 3)

[1005] The system according to claim 1, wherein the user information device is designed to provide intuitive operation, allowing the user to easily input information and select a solution.

[1006] "Application example 2 when combining with an emotional engine"

[1007] (Claim 1)

[1008] A means of collecting data from past case data storage,

[1009] A means for preprocessing the aforementioned data using natural language processing technology,

[1010] A means of generating multiple solutions in real time using a trained generative AI model,

[1011] A means for presenting the generated solution via a user interface,

[1012] A means of analyzing emotional states in interactions with users,

[1013] A means of proposing appropriate countermeasures that respond to the emotions of users in a care environment,

[1014] A means of collecting and analyzing user feedback,

[1015] Means to protect data privacy,

[1016] A system that includes this.

[1017] (Claim 2)

[1018] The system according to claim 1, wherein the generating AI model is configured to learn conflict patterns based on past case data storage.

[1019] (Claim 3)

[1020] The system according to claim 1, wherein the user interface is designed to provide intuitive operation, allowing the user to easily input information and select a solution. [Explanation of Symbols]

[1021] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Methods for collecting data from past case databases, A means for preprocessing the aforementioned data using natural language processing technology, A means of generating multiple solutions in real time using a trained generative AI model, A means for presenting the generated solution via a user interface, A means of collecting and analyzing user feedback, Means to protect data privacy, A system that includes this.

2. The system according to claim 1, wherein the generating AI model is configured to learn conflict patterns based on a database of past cases.

3. The system according to claim 1, wherein the user interface is designed to provide intuitive operation, allowing the user to easily input information and select a solution.

Images