system

Abstract

Provide a system. The method includes: means for automatically collecting information from a data source; a means of analyzing the collected information to extract key players, sources of conflict, and sentiment; a means for generating neutral recommendations based on the analysis results; a means for providing suggestions and collecting feedback from users through a user interface; A means to incorporate collected feedback into analysis and improvement of recommendations; A system including:

Description

[Technical Field]

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

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

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

[0004] In traditional dispute resolution processes, information gathering and analysis is often done manually, requiring time and effort. Furthermore, illogical proposals based on emotion or bias toward specific stakeholders can be made, complicating negotiations and prolonging disputes. These issues make it difficult to propose efficient and neutral solutions. [Means for solving the problem]

[0005] The present invention includes a means for automatically collecting information from data sources and a means for analyzing the collected information to extract key stakeholders, causes of conflict, and emotions, thereby eliminating the need for manual information collection and enabling rapid analysis results. The present invention also includes a means for generating neutral proposals based on the analysis results, and further includes a means for providing proposals through a user interface and collecting feedback from users, thereby enabling fair and logical proposals to be provided quickly. Additionally, by using a means for reflecting the collected feedback in improving the analysis and proposals, the accuracy of the proposals can be improved while reflecting user opinions.

[0006] A "data source" is the source from which information is collected, and can range from news sites, official reports from international organizations, government statements, social media, and more.

[0007] "Collection tools" refers to software or programs used to automatically obtain information from data sources.

[0008] "Analysis tools" refer to algorithms and tools used to process collected information and extract key actors, sources of conflict, and sentiment.

[0009] "Proposal generation means" refers to a function for automatically creating neutral and logical proposals based on the analysis results.

[0010] "User Interface" refers to the interactive screens and dashboards that allow users to view suggestions and provide feedback.

[0011] "Feedback collection method" refers to a form or system for collecting user opinions and suggested revisions.

[0012] "Feedback analysis means" refers to a method for analyzing feedback collected from users and improving the content of suggestions.

[0013] "Natural language processing algorithms" refer to computer programs and technologies that analyze text data and extract meaning and emotion.

[0014] "Graphs and charts" refers to diagrams that visually display the results of data analysis and provide information in a form that is easy for users to understand. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram illustrating a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] The present invention provides a system for supporting dispute resolution through data collection, proposal generation, feedback collection and analysis via a user interface. Specific embodiments of this system will be described below.

[0037] System Overview

[0038] Data collection

[0039] The server automatically collects information from trusted data sources (news sites, official reports from international organizations, government statements, social media, etc.) using API calls and web scraping techniques, and stores the collected data in a cloud-based database.

[0040] Data analysis

[0041] The server uses natural language processing (NLP) algorithms to analyze the collected data, extracting key stakeholders, sources of conflict, and sentiment from the text data, and employs sentiment analysis tools to determine sentiment within the text and generate graphs and charts to visualize trends in the data.

[0042] Proposal generation

[0043] The server generates neutral and logical proposals based on the analysis results, including specific action plans and recommended strategies. The proposal documents are automatically generated and provided through a user interface.

[0044] User Interface

[0045] The device displays an interactive dashboard for users to view the proposals and provide feedback. The user interface includes graphs and charts that visually represent the analysis results and proposals. Users can also provide comments and corrections to the proposals using a feedback form.

[0046] Feedback Processing and Integration

[0047] The server analyzes the collected feedback and updates the recommendations, a process that results in better, more effective recommendations that reflect user input.

[0048] Specific examples

[0049] For example, suppose there are two groups in conflict over the distribution of resources in a conflict area. In this system, the process proceeds as follows:

[0050] 1. Data collection: The server automatically collects the latest conflict-related news from the news API, along with official government statements and reports from international organizations.

[0051] 2. Data analysis: The server uses NLP algorithms to analyze the collected text data and extract information such as "The main cause of the conflict between Group A and Group B is resource allocation." It also performs sentiment analysis and obtains results such as "Group A feels strong anger."

[0052] 3. Proposal Generation: Based on the analysis results, the server proposes the establishment of a third-party organization to ensure fair resource distribution. The proposal document also includes a specific operating scheme and funding plan.

[0053] 4. User interface: The device displays the proposals on a dashboard, along with graphs and charts. Users (representatives of international organizations) can view the proposals and provide feedback, such as "international experts should be included in the third-party organization."

[0054] 5. Feedback processing and integration: The server receives the feedback and updates the proposal document, reflecting the suggested change: "The third-party body should include international experts."

[0055] In this way, the system generates efficient and neutral proposals and supports conflict resolution by incorporating user feedback.

[0056] The processing flow will be explained below.

[0057] Step 1: Start collecting data

[0058] The server sends requests to API endpoints of authoritative data sources to retrieve the latest conflict-related data, collating data from news sites, reports from international organizations, government statements, social media posts, and more.

[0059] Step 2: Save your data

[0060] The server stores the collected data in a cloud-based database in structured formats such as JSON and CSV.

[0061] Step 3: Text analysis

[0062] The server applies natural language processing (NLP) algorithms to the stored data to extract key actors, sources of conflict, and sentiment from the text data, including extracting key events and important keywords.

[0063] Step 4: Sentiment analysis

[0064] Based on the text analysis results, the server uses a sentiment analysis tool to classify and assess the emotions of each participant, using algorithms to identify emotional expressions in the text and distinguish between anger, frustration, hope, etc.

[0065] Step 5: Trend analysis and visualization

[0066] The server performs trend analysis on the analyzed data and generates graphs and charts that visualize changes and patterns over time, allowing users to understand the development and trends of the conflict at a glance.

[0067] Step 6: Proposal Generation

[0068] The server automatically generates neutral and logical proposals based on the results of text and sentiment analysis, including concrete action plans and strategies.

[0069] Step 7: Providing a User Interface

[0070] The device displays a user-accessible dashboard that displays analysis results, recommendations, trend graphs, and more.

[0071] Step 8: Gather feedback

[0072] Users can provide reviews and feedback on the suggestions provided through a feedback form on the dashboard, including suggested modifications and opinions.

[0073] Step 9: Feedback analysis

[0074] The server analyzes the feedback collected from users, understands the intent of the feedback and the suggestions, and identifies which parts of the suggestions need to be revised.

[0075] Step 10: Update your proposal

[0076] The server updates the proposal document based on the feedback, and the revised proposal is again presented through the user interface and displayed for the user to review and evaluate.

[0077] Step 11: Final confirmation of feedback

[0078] Users review the updated proposal and provide further feedback if necessary, and this process continues until a final consensus is reached.

[0079] Through this series of processes, the system has the ability to effectively support dialogue and negotiation and promote conflict resolution.

[0080] Example 1

[0081] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0082] Current dispute resolution support systems often lack efficient data collection, analysis, proposal generation, and feedback processing, making it difficult to provide fast and accurate dispute resolution solutions. Furthermore, they lack the ability to properly analyze collected information and generate neutral proposals, which can lead to biased solutions. Furthermore, systems for collecting and incorporating user feedback through a user interface are inadequate. The objective of the present invention is to solve these problems.

[0083] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0084] In this invention, the server includes means for automatically collecting information from data sources, means for storing the collected information in a cloud-based database, means for analyzing the collected information to extract key stakeholders, causes of conflicts, and emotions, means for generating neutral proposals based on the analysis results, means for providing the proposals through a user interface and collecting feedback from users, and means for reflecting the collected feedback in improving the analysis and proposals, thereby enabling efficient generation of neutral proposals and rapid reflection of user feedback.

[0085] "Data Source" means an external information source that provides information in a variety of formats.

[0086] An "automated collection means" is a mechanism for obtaining data without requiring manual input from a user.

[0087] A "cloud-based database" is a data management system that operates over the internet and stores data on a remote server.

[0088] "Means for analyzing collected information" are methods and algorithms used to understand, classify, and extract meaning from collected data.

[0089] "Key Stakeholders" refers to individuals or organizations that play a significant role in a particular event or issue.

[0090] "Causes of conflict" refers to the underlying factors or reasons that cause conflict or disputes.

[0091] "Means for extracting emotions" are algorithms and tools for identifying and analyzing emotions and sentiments from text data.

[0092] A "neutral proposal" is one that does not favor any particular position and presents a solution that is fair to all parties involved.

[0093] "User interface" refers to the graphical screen or dashboard that allows users to interact with the system and manipulate and view information.

[0094] "Feedback" refers to response information such as opinions, evaluations, and suggested revisions provided by users.

[0095] A "means for improving recommendations" is a process or algorithm for modifying or updating initial recommendations based on collected feedback.

[0096] The present invention provides a system for supporting dispute resolution through data collection, proposal generation, feedback collection via a user interface, and analysis. Specific embodiments of this system will be described below.

[0097] System Overview

[0098] The system consists of the following main components:

[0099] Data collection

[0100] The server automatically collects information from data sources such as news sites, reports from international organizations, government statements, and social media. This process involves calling APIs and web scraping techniques. The collected data is then stored in a cloud-based database. For example, the requests library is used to call the API and BeautifulSoup is used for web scraping.

[0101] Data analysis

[0102] The server uses natural language processing (NLP) algorithms to analyze the collected data. This extracts key stakeholders, sources of conflict, and sentiment from the text data. It also uses sentiment analysis tools to determine sentiment within the text and generate graphs and charts to visualize data trends. Specifically, it uses NLP libraries (e.g., NLTK, spaCy) and sentiment analysis tools such as VADER and TextBlob.

[0103] Proposal generation

[0104] The server generates neutral and logical proposals based on the analysis results, including specific action plans and recommended strategies. The proposal documents are automatically generated and provided through a user interface. This process uses generative AI models, such as OpenAI's GPT model.

[0105] User Interface

[0106] The terminal displays an interactive dashboard for users to view the proposals and provide feedback. The user interface includes graphs and charts that visually display the analysis results and proposals. Users can also provide opinions and corrections to the proposals using a feedback form. Front-end frameworks such as React.js are used.

[0107] Feedback Processing and Integration

[0108] The server analyzes the collected feedback and updates the recommendations. This process results in more relevant and actionable recommendations that reflect user input. The generated AI model is then used again, and the updates are displayed in the user interface using a front-end framework.

[0109] Specific examples

[0110] For example, if there are two groups in conflict over the distribution of resources in a conflict area, the process would proceed as follows:

[0111] 1. Data Collection:

[0112] The server automatically collects the latest conflict-related news from a news API, simultaneously retrieving official government statements and reports from international organizations.

[0113] 2. Data Analysis:

[0114] The server uses an NLP algorithm to analyze the text data, extracting information such as "The main cause of the conflict between Group A and Group B is resource allocation," and performs sentiment analysis to obtain results such as "Group A feels strong anger."

[0115] 3. Proposal generation:

[0116] Based on the analysis results, the server will propose the establishment of a third-party organization to ensure fair distribution of resources, and will include a specific operating scheme and funding plan.

[0117] 4. User Interface:

[0118] The device displays the recommendations on a dashboard, complete with graphs and charts, and users can view the recommendations and provide feedback, such as "The third-party organization should include international experts."

[0119] 5. Feedback processing and integration:

[0120] The server receives the feedback and uses the generative AI model to update the proposal document, including the suggested change that the third-party body should include international experts.

[0121] Prompt Sentence Examples

[0122] The following prompt sentences can be input into the generative AI model to analyze and generate suggestions:

[0123] Get the latest news data, extract the key causes of conflict for a particular dispute, analyze the sentiment behind the conflict, and recommend solutions.

[0124] Data sources: news sites, official reports from international organizations, government statements

[0125] In this way, the system generates efficient and neutral proposals and supports conflict resolution by incorporating user feedback.

[0126] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0127] Step 1: Automated data collection

[0128] What it does: The server collects the latest information from reliable data sources such as news sites, official reports from international organizations, government statements, and social media. For example, it uses the requests library to call news APIs and BeautifulSoup to scrape data from official reporting sites. The input to this process is the URL and API key of the data source, and the output is the collected raw data.

[0129] Step 2: Save your data

[0130] Specific operation: The server stores the collected data in a cloud-based database, for example, using AWS® RDS or Google® Cloud's BigQuery, and executes SQL queries to insert the data. The input to this process is the raw data obtained in step 1, and the output is structured data stored in the database.

[0131] Step 3: Data analysis

[0132] What it does: The server analyzes the collected data using NLP algorithms. Specifically, it uses NLP libraries (e.g., NLTK, spaCy) to extract key players, conflict causes, and sentiment from the text data. For sentiment analysis, it uses VADER and TextBlob. The input to this process is the structured data saved in step 2, and the output is the analysis results, such as conflict causes and sentiment.

[0133] Step 4: Generate graphs and charts

[0134] Specific operation: The server generates graphs and charts to visualize data trends based on the analysis results. Specifically, it visualizes the data using Python's matplotlib and seaborn. The input to this process is the analysis results obtained in step 3, and the output is the generated graphs and charts.

[0135] Step 5: Proposal Generation

[0136] Specific operation: The server generates neutral and logical proposals based on the analysis results. Using a generative AI model (e.g., OpenAI's GPT model), it automatically generates a proposal document containing a specific action plan and recommended strategies. The input to this process is the analysis results obtained in Step 3, and the output is the generated proposal document.

[0137] Step 6: Displaying the User Interface

[0138] Specific operation: The terminal displays an interactive dashboard for users to view the proposals and provide feedback. A front-end framework such as React.js is used to visually display the analysis results and proposals. Users can also enter their opinions and corrections using a feedback form. The input of this process is the proposal document and visualized graphs and charts generated in step 5, and the output is the user's feedback.

[0139] Step 7: Collect and analyze feedback

[0140] What happens: The server analyzes the feedback collected from the user and updates the proposal. It uses the generative AI model again to generate more appropriate and actionable proposals. The input to this process is the user feedback obtained in step 6, and the output is the updated proposal document.

[0141] Step 8: Redistribute the updated proposal

[0142] Specific operation: The server delivers the updated proposal document back to the user interface, allowing the user to view the latest proposal content. Using React.js, the updated proposal document is displayed on a dashboard. The input of this process is the updated proposal document generated in step 7, and the output is a dashboard containing the updated proposal content.

[0143] (Application example 1)

[0144] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0145] Modern society requires real-time conflict monitoring and rapid resolution support. Conflicts and disputes at event venues and other public spaces must be resolved as quickly as possible, but conventional systems have struggled to respond quickly and appropriately. There was also a need for a system that could efficiently analyze data collected in real time, generate appropriate proposals based on the results, and improve those proposals by incorporating feedback.

[0146] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0147] In this invention, the server includes means for automatically collecting information from data sources, means for analyzing the collected information to extract key stakeholders, causes of conflict, and emotions, means for generating neutral proposals based on the analysis results, means for providing the proposals through a user interface and collecting feedback from users, means for reflecting the collected feedback in improving the analysis and proposals, means for recording the surrounding situation and converting it into text using a voice recognition function, and means for displaying the analysis results and proposals on a display in real time, thereby enabling the system to instantly grasp the local situation, generate and provide appropriate countermeasures in real time, and quickly reflect user feedback.

[0148] "Data sources" refers to reliable sources for gathering information, such as news sites, official reports, government statements, and social media.

[0149] "Means of automatically collecting information" refers to technologies for automatically obtaining information from data sources, such as by calling APIs or using web scraping techniques.

[0150] "Key actors" refer to important people or groups in a conflict or conflict situation.

[0151] "Causes of conflict" refers to the main reasons or factors behind conflict or confrontation.

[0152] "Means of extracting emotions" refers to technology that uses natural language processing algorithms and emotion analysis tools to determine emotions from text data and audio data.

[0153] A "neutral proposal" refers to a specific action plan or recommended strategy that aims to solve a problem in an impartial and logical manner, without favoring any particular position.

[0154] "User interface" refers to the interactive screen or operating environment that allows a user to interact with a system.

[0155] "Feedback" refers to users' opinions and requests for corrections regarding the proposal.

[0156] "Recording and voice recognition function" refers to technology that uses a camera and microphone to record the surrounding situation and converts the voice data into text data.

[0157] "Display" means a screen or display device for visually presenting information or offers.

[0158] This invention is a system that supports real-time dispute resolution through data collection, proposal generation, feedback collection and analysis via a user interface. A specific embodiment for realizing this system will be described below.

[0159] Overall structure

[0160] The server automatically collects information from data sources, analyzes the collected information to extract key stakeholders, sources of conflict, and sentiment, then generates neutral proposals based on the analysis results and provides them through a user interface. Users provide feedback on the proposals through the user interface, and the server analyzes this feedback and updates the proposals.

[0161] Data collection

[0162] The servers automatically collect information from trusted data sources such as news sites, official reports, government statements, social media, etc. The data is retrieved using API calls and web scraping techniques and stored in a cloud-based database.

[0163] Data analysis

[0164] The collected data is analyzed using a server-based natural language processing (NLP) algorithm to extract key stakeholders, sources of conflict, and sentiment. Sentiment analysis tools are also used to identify sentiment within the text and generate graphs and charts to visualize trends in the data. Specifically, Google NLP APIs and sentiment analysis tools are used.

[0165] Proposal generation

[0166] Based on the analysis results, the server generates neutral and logical proposals, including specific action plans and recommended strategies, and automatically generates proposal documents using a generative AI model.

[0167] User Interface

[0168] The device displays an interactive dashboard where users can view the recommendations and provide feedback. The dashboard includes graphs and charts visually illustrating the analysis results and recommendations. When using smart glasses, this information is displayed in real time on the display. Using voice recognition, the device converts the user's speech into text, allowing feedback to be provided via the operation panel.

[0169] Feedback Processing and Integration

[0170] The server analyzes the collected feedback and updates the suggestions. This process results in more appropriate and effective suggestions that reflect user opinions. For example, the feedback is managed using the Firebase database.

[0171] Specific examples

[0172] For example, a system for resolving conflict situations in real time at an event venue works as follows: A security officer wearing smart glasses records the conflict and converts the conversation into text using a voice recognition API. The server analyzes the video using an NLP algorithm and identifies "insufficient visitor number control" as the cause of the conflict. Based on the analysis results, the server generates a recommendation to "set up a counter and assign additional staff" and displays it on the smart glasses' display. The security officer provides feedback, and the server updates the recommendation accordingly.

[0173] Prompt Sentence Examples

[0174] Event A and Event B are in conflict. The main cause is a lack of coordination on the number of attendees. Please suggest a solution.

[0175] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0176] Step 1: Data collection

[0177] The server automatically collects information from data sources, such as news sites, official reports, government statements, and social media, using API calls and web scraping techniques. This data is then stored in a cloud-based database. The input for the collected data is the API calls and web scraping, and the output is the data stored in the cloud database.

[0178] Step 2: Surroundings recording and voice recognition

[0179] The smart glasses, which serve as the device, record the surrounding situation and collect audio using a microphone. The collected audio data is converted into text using a speech recognition API. The input is camera footage and audio data, and the output is text-formatted conversation data. This makes it possible to grasp the situation in real time.

[0180] Step 3: Data analysis

[0181] The server uses natural language processing (NLP) algorithms to analyze the collected data, extracting key players, causes of conflict, and sentiment from the text data. The input is text data, and the output is information on key players, causes of conflict, and sentiment. Specifically, it uses Google NLP API and sentiment analysis tools.

[0182] Step 4: Proposal Generation

[0183] The server generates neutral and logical proposals based on the analysis results. These are automatically generated as proposal documents using a generative AI model. The input is the analysis results, and the output is the proposal document. For example, from the analysis result of "insufficient visitor number adjustment," the server generates a specific proposal such as "install a counter and assign additional staff."

[0184] Step 5: Display the user interface

[0185] The smart glasses, which are the terminals, display the proposals in real time. The analysis results and proposals are visualized as graphs and charts. The inputs are the proposal documents and analysis results, and the output is the information displayed on the screen. The user can provide feedback using the operation panel on the glasses.

[0186] Step 6: Feedback collection and analysis

[0187] The server collects and analyzes feedback provided by users. The input of the feedback is text data from the user, and the output is the analyzed feedback information. Specifically, the feedback is managed via the Firebase database.

[0188] Step 7: Improve and update your proposal

[0189] The server updates the proposal document based on the analyzed feedback, resulting in a more appropriate proposal that reflects user input. The input is the feedback information, and the output is an updated proposal document. For example, a new proposal reflecting "allocation of additional staff" is generated.

[0190] This processing step allows the system to efficiently execute a series of processes: grasping the situation in real time, making appropriate suggestions, providing them to the user, and incorporating the feedback.

[0191] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0192] This invention is a system that supports conflict resolution by recognizing user emotions through data collection, proposal generation, feedback collection and analysis via a user interface, and a combination of an emotion engine. Specific embodiments of this system are described below.

[0193] System Overview

[0194] Data collection

[0195] The server automatically collects information from trusted data sources (news sites, official reports from international organizations, government statements, social media, etc.) using API calls and web scraping techniques, and stores the collected data in a cloud-based database.

[0196] Data analysis

[0197] The server uses natural language processing (NLP) algorithms to analyze the collected data, extracting key stakeholders, sources of conflict, and sentiment from the text data, and employs sentiment analysis tools to determine sentiment within the text and generate graphs and charts to visualize trends in the data.

[0198] Proposal generation

[0199] The server generates neutral and logical proposals based on the analysis results, including specific action plans and recommended strategies. The proposal documents are automatically generated and provided through a user interface.

[0200] User Interface

[0201] The device displays an interactive dashboard for users to view the proposals and provide feedback. The user interface includes graphs and charts that visually represent the analysis results and proposals. Users can also provide comments and corrections to the proposals using a feedback form.

[0202] Feedback Processing and Integration

[0203] The server analyzes the collected feedback and updates the recommendations, a process that results in better, more effective recommendations that reflect user input.

[0204] Emotion Engine Functions

[0205] The server uses an emotion engine to perform emotion analysis on the feedback provided by the user, allowing the server to recognize the user's emotional state in real time and display it on a dashboard. The emotion engine uses natural language processing techniques to identify, classify, and rate emotional expressions in the text.

[0206] Specific examples

[0207] For example, the following is a series of processes that may be applied to a conflict zone where two groups are in conflict over the allocation of resources.

[0208] 1. Data Collection:

[0209] The server automatically collects the latest conflict-related news from a news API, along with official government statements and reports from international organizations.

[0210] 2. Data Analysis:

[0211] The server uses an NLP algorithm to analyze the collected text data and extract information such as "The main cause of the conflict between Group A and Group B is resource allocation." It also performs sentiment analysis and obtains results such as "Group A feels strong anger."

[0212] 3. Proposal generation:

[0213] Based on the analysis results, the server will propose the establishment of a third-party organization to ensure the fair distribution of resources. The proposal document will also include a specific operating scheme and funding plan.

[0214] 4. User Interface:

[0215] The device displays the proposals on a dashboard, along with graphs and charts. Users (representatives of international organizations) can view the proposals and provide feedback, such as "The third-party organization should also include international experts."

[0216] 5. Feedback processing and integration:

[0217] The server receives the feedback and updates the proposal document, reflecting the revised suggestion that "the third-party body should include international experts."

[0218] 6. Use of Emotion Engine:

[0219] The server uses an emotion engine to analyze the emotions of the feedback provided by the user. For example, if emotions such as "anger" or "dissatisfaction" are detected, this is reflected in the dashboard, visually displaying the emotions with which the user is providing feedback.

[0220] In this way, a system incorporating an emotion engine can generate efficient and neutral suggestions, reflect user feedback, and more effectively support conflict resolution by recognizing and displaying user emotions in real time.

[0221] The processing flow will be explained below.

[0222] Step 1:

[0223] The server uses API calls and web scraping techniques to automatically collect information from reliable data sources (news sites, official reports from international organizations, government statements, social media, etc.) and stores the collected data in a cloud-based database.

[0224] Step 2:

[0225] The server applies natural language processing (NLP) algorithms to the stored data to extract key stakeholders, sources of conflict, and sentiment from the text data. Specifically, it extracts key events and important keywords from the collected text data.

[0226] Step 3:

[0227] The server uses a sentiment analysis tool based on the text analysis results to classify and evaluate the emotional expressions in the text, identifying emotions such as anger, frustration, and hope, and storing the emotional state as data.

[0228] Step 4:

[0229] The server performs trend analysis on the analyzed data and generates graphs and charts that visualize changes and patterns over time, allowing users to understand the development and trends of the conflict at a glance.

[0230] Step 5:

[0231] The server automatically generates neutral and logical proposals based on the results of text and sentiment analysis, including the establishment of a third-party organization to ensure fair resource distribution, a specific operating scheme, and a funding plan.

[0232] Step 6:

[0233] The terminal displays a user-accessible dashboard that displays the analysis results, recommendations, trend graphs and charts generated by the server.

[0234] Step 7:

[0235] The terminal provides a feedback form for the user to view the proposal and to enter their opinions and suggestions for corrections to the proposal.

[0236] Step 8:

[0237] The server analyzes the feedback collected from users through the feedback form, and again uses NLP algorithms to analyze the text data in the feedback to identify which parts of the suggestion should be revised.

[0238] Step 9:

[0239] The server uses an emotion engine to analyze the emotion contained in the user's feedback in real time. The emotion engine performs emotion analysis on the user's feedback to determine the user's emotional state, such as anger or frustration.

[0240] Step 10:

[0241] The device displays the results of the emotion engine's analysis on a dashboard, which visually displays the emotional state of the feedback provided by the user.

[0242] Step 11:

[0243] The server updates the proposal document based on the analysis results and the emotion engine's evaluation results. The revised proposal is again presented through the user interface and displayed for the user to review and evaluate.

[0244] Step 12:

[0245] Users review the updated proposal and provide further feedback if necessary, repeating the process until a final consensus is reached.

[0246] In this way, a system incorporating an emotion engine can recognize users' emotions in real time, provide efficient and neutral suggestions, and support optimal conflict resolution.

[0247] Example 2

[0248] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0249] While conventional data collection and analysis systems can efficiently collect and analyze data, they lack the functionality to automatically generate specific and neutral proposals for conflict resolution, and to collect and incorporate user feedback. Furthermore, there is no mechanism for analyzing and incorporating the user's emotional state in real time, which means the quality and effectiveness of the proposals cannot be fully guaranteed.

[0250] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for automatically collecting information from data sources, means for analyzing the collected information to extract key stakeholders, causes of conflict, and emotions, means for generating neutral proposals based on the analysis results, means for providing proposals through a user interface and collecting feedback from users, means for reflecting the collected feedback in improving the analysis and proposals, and means for analyzing emotional expressions included in the feedback in real time and displaying them on a dashboard. This makes it possible to perform processes from data collection to analysis, proposal generation, feedback reflection, and real-time emotion analysis in a centralized and integrated manner.

[0251] "Data sources" refers to various media that provide information, such as news sites, official reports from international organizations, government statements, social media, etc.

[0252] "Means of collection" refers to technical devices or software for automatically obtaining information from data sources, such as by calling APIs or using web scraping techniques.

[0253] "Analyzing means" refers to technical devices or algorithms, in particular natural language processing (NLP) algorithms, used to process the collected data and extract the required information.

[0254] A "neutral proposal" refers to an action plan or strategy that is fair and objective, not influenced by any particular interest or bias.

[0255] "User interface" refers to the interface through which a user interacts with a machine, particularly the dashboard for displaying suggestions and collecting feedback.

[0256] "Feedback collection means" refers to any technological device or form for receiving comments or corrections to a proposal from users.

[0257] "Emotional expressions" refer to the emotional states that appear in text, specifically expressions that classify emotions such as "anger," "sadness," and "joy."

[0258] "Means for analyzing in real time and displaying on a dashboard" refers to a technological device or software that uses an emotion engine to instantly evaluate the emotion in the feedback and display it visually.

[0259] This invention is a system that supports conflict resolution by recognizing user emotions through data collection, proposal generation, feedback collection and analysis via a user interface, and a combination of an emotion engine. Specific embodiments of this system are described below.

[0260] Data collection

[0261] The server automatically collects information from reliable data sources (news sites, official reports from international organizations, government statements, social media, etc.) using API calls and web scraping techniques. Specifically, it uses a news API to retrieve data by calling the API, such as "https: / / newsapi.org / v2 / top-headlines?country=us&apiKey=YOUR_API_KEY." The retrieved data is then stored in a cloud-based database, such as Google Cloud Firestore or Amazon DynamoDB.

[0262] Data analysis

[0263] The server uses natural language processing (NLP) algorithms to analyze the collected data. Specifically, it preprocesses the text data using toolkits such as NLTK and SpaCy. It then applies NLP algorithms to extract key stakeholders and conflict sources. It also uses sentiment analysis tools (e.g., Sentiment Analysis API and TextBlob) to determine the sentiment within the text. The analysis results are visualized as graphs and charts using visualization libraries such as matplotlib and plotly.

[0264] As a concrete example, the server collects the latest conflict-related news via a news API and uses an NLP algorithm to extract information such as "The main cause of the conflict between Group A and Group B is resource allocation." It also performs sentiment analysis to obtain the result that "Group A feels strong anger."

[0265] Proposal generation

[0266] The server generates neutral and logical proposals based on the analysis results. For example, a generative AI model can be used to automatically generate a proposal document for "establishing a third-party organization to ensure the fair distribution of resources." The generated proposal document includes a specific operating scheme and funding plan. The proposal document is generated in HTML or PDF format and sent to the user interface.

[0267] As a specific example, the server proposes "the establishment of a third-party organization to ensure fair distribution of resources" based on the analysis results, and generates a document that includes the specific operating scheme and funding plan.

[0268] User Interface

[0269] The device displays an interactive dashboard for users to view and provide feedback on the proposals. The dashboard includes graphs and charts that visually represent the analysis results and proposals. Users can provide comments and corrections to the proposals using a feedback form.

[0270] For example, a user (representative of an international organization) can view the proposal through the dashboard and provide feedback such as, "The third-party organization should also include international experts."

[0271] Feedback Processing and Integration

[0272] The server analyzes the feedback collected from users and updates the proposals, generating more specific and effective proposals that reflect the user's opinions.

[0273] As a concrete example, the server analyzes the user's feedback "The third party should include international experts" and generates an updated document that reflects this.

[0274] Emotion Engine Functions

[0275] The server uses an emotion engine to perform emotion analysis on the feedback provided by the user. It identifies the user's emotional state in real time and displays it on a dashboard. The emotion engine uses natural language processing techniques to identify, classify, and rate emotional expressions in the text.

[0276] As a specific example, the server performs an emotional analysis of the feedback content, and if emotions such as "anger" or "dissatisfaction" are detected, they are displayed on the dashboard.

[0277] Example prompt for a generative AI model:

[0278] "The representative of international organization A has provided feedback on a proposal regarding resource allocation. Please analyze the representative's feedback using the sentiment engine and display it in real time on a dashboard."

[0279] The present invention is a system that more effectively supports conflict resolution by centrally performing data collection, analysis, proposal generation, feedback reflection, and sentiment analysis.

[0280] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0281] Program processing procedure and specific operations

[0282] Step 1: Data collection

[0283] 1. Input: URL and authentication information for news API or official report API

[0284] The server sets the URL and authentication information to call the API of a trusted data source (e.g., news site, official report from an international organization, government statement, social media).

[0285] 2. Operation: API calls and data retrieval

[0286] The server retrieves the latest information from the data source by making an API call, such as for the News API, using the URL "https: / / newsapi.org / v2 / top-headlines?country=us&apiKey=YOUR_API_KEY".

[0287] 3. Output: Acquired data

[0288] The acquired data is, for example, in JSON format.

[0289] 4. Operation: Data storage

[0290] The server stores the retrieved data in a cloud-based database such as Google Cloud Firestore or Amazon DynamoDB.

[0291] Step 2: Data analysis

[0292] 1. Input: Collected data (e.g., JSON format)

[0293] The server prepares the collected data for the NLP algorithms.

[0294] 2. Operation: Preprocessing text data

[0295] The server uses toolkits like NLTK or SpaCy to pre-process the data, removing unnecessary parts like advertisements and HTML tags.

[0296] 3. Action: Identifying key stakeholders and conflict sources

[0297] The server applies natural language processing algorithms to extract key players and sources of conflict from the text, e.g., "Group A and Group B are in conflict over resource allocation."

[0298] 4. Behavior: Sentiment analysis

[0299] The server uses sentiment analysis tools to identify emotional expressions in the text. For example, it uses the Sentiment Analysis API or TextBlob to analyze emotional data such as "Group A feels very angry."

[0300] 5. Output: Analysis results

[0301] Analysis results including information on extracted parties, conflict causes, emotional expressions, etc.

[0302] 6. Action: Visualizing data trends

[0303] The server visualizes the analysis results as graphs and charts using visualization libraries such as matplotlib and plotly.

[0304] Step 3: Proposal Generation

[0305] 1. Input: Analysis results

[0306] The server inputs the analysis results into a generative AI model.

[0307] 2. Action: Creating a proposal document

[0308] The server uses a generative AI model to automatically generate neutral and logical proposal documents, such as proposing the establishment of a third-party organization to ensure the fair distribution of resources.

[0309] 3. Output: Proposal document

[0310] The generated proposal document is in HTML or PDF format.

[0311] 4. Action: Proposal document distribution

[0312] The server sends the generated proposal document to the user interface.

[0313] Step 4: Display the user interface

[0314] 1. Input: Proposal document and analysis results

[0315] The terminal receives the proposed document and the analysis results.

[0316] 2. Action: Rendering a dashboard

[0317] The terminal displays an interactive dashboard as a user interface, which is implemented using frameworks such as Django or Flask.

[0318] 3. Action: Data Visualization

[0319] The terminal displays the data visualization results (graphs and charts) on a dashboard.

[0320] 4. Action: Providing a feedback form

[0321] The terminal displays a feedback form in which the user can provide comments and corrections to the proposal.

[0322] Step 5: Feedback processing and integration

[0323] 1. Input: User feedback

[0324] The server receives feedback from the user.

[0325] 2. Action: Feedback Analysis

[0326] The server analyzes the feedback and extracts specific opinions and suggested modifications.

[0327] 3. Action: Proposal document update

[0328] The server updates the proposal document based on the analysis, for example, to reflect the suggested revision that "the third-party body should include international experts."

[0329] 4. Output: Updated proposal document

[0330] The updated proposal document is again sent to the user interface and displayed.

[0331] Step 6: Functioning of the Emotion Engine

[0332] 1. Input: User feedback

[0333] The server inputs the user's feedback into the emotion engine.

[0334] 2. Action: Feedback sentiment analysis

[0335] The server uses an emotion engine to analyze the emotional state of the feedback, identifying emotions such as "anger" or "frustration."

[0336] 3. Output: Emotion analysis results

[0337] If sentiment analysis shows that the feedback is "angry," that information will be displayed on the dashboard.

[0338] 4. Action: Displaying Emotional State

[0339] The device displays the user's emotional state in real time on a dashboard, analyzed by the emotion engine. For example, if anger is detected, it is highlighted in red.

[0340] (Application example 2)

[0341] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0342] Frequent traffic congestion and accidents are increasing the stress and burden on drivers. Furthermore, there is a problem that drivers are unable to respond quickly to changes in traffic conditions, making it difficult to select the optimal route. Furthermore, there is a lack of systems that can grasp the driver's emotional state and make appropriate suggestions, preventing improvements in driving safety.

[0343] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0344] In this invention, the server includes: means for automatically collecting information from data sources; means for analyzing the collected information to extract key stakeholders, causes of conflict, and emotions; means for generating neutral proposals based on the analysis results; means for providing proposals through a user interface and collecting user feedback; means for reflecting the collected feedback in improving the analysis and proposals; means for analyzing traffic conditions in real time and proposing optimal routes; and means for analyzing the driver's emotional state and displaying the results. This makes it possible to quickly respond to traffic conditions in real time and propose optimal routes while reducing the driver's burden. Furthermore, making proposals based on the driver's emotional state can improve safety.

[0345] "Data Source" is a trusted source used to gather information (e.g., news sites, traffic APIs, social media, etc.).

[0346] "Means of automatically collecting information" refers to the process of asynchronously obtaining the necessary information from data sources using API calls or web scraping techniques.

[0347] "Means for analyzing collected information" refers to the process of using natural language processing algorithms and data mining techniques to extract key stakeholders, sources of conflict, and sentiment from the collected text data.

[0348] A "means for generating neutral proposals" is a process that automatically creates logical and effective proposals based on the results of data analysis, without any particular position or bias.

[0349] A "user interface" is an interactive interface through which a user can view information, receive suggestions, and provide feedback.

[0350] A "feedback collection method" is a form or interactive digital tool used to systematically collect user opinions and comments.

[0351] "Means for reflecting feedback in analysis and improvement of proposals" refers to the process of re-analyzing the data based on the feedback collected from users and updating the proposal content to make it more appropriate.

[0352] "Means of analyzing traffic conditions in real time" refers to the process of analyzing real-time data obtained from vehicle sensors and traffic information APIs to understand the current traffic situation.

[0353] "Means for proposing optimal routes" refers to the process of presenting optimal travel routes to drivers based on real-time data and analysis results.

[0354] "Means for analyzing the emotional state of a driver" refers to the process of using an emotion analysis tool to identify and evaluate the emotional state of a driver from the feedback and behaviors provided by the driver.

[0355] The "means for displaying the results" is a display or dashboard that visually shows the analyzed emotional state information to the driver in real time.

[0356] This invention is a system for autonomous vehicles that analyzes traffic conditions in real time and makes suggestions based on the driver's emotional state. The system has the functions of data collection, data analysis, suggestion generation, user interface, feedback processing and integration, and an emotion engine.

[0357] Data collection

[0358] The server collects data from vehicle sensors (cameras, LiDAR, GPS, etc.) and traffic information APIs (e.g., popular traffic information providers) in real time, using API calls and data streaming techniques.

[0359] Data analysis

[0360] Data collected from vehicle sensors and traffic information APIs is sent to a server where it is analyzed using natural language processing (NLP) algorithms and data mining techniques, such as extracting key stakeholders, sources of conflict, and sentiment from text data. For sentiment analysis, TextBlob and other AI-based sentiment analysis tools are used.

[0361] Proposal generation

[0362] The server generates neutral and effective suggestions based on the analysis results. These include optimal routes, workarounds, and break suggestions. During this process, a generative AI model (e.g., GPT-3 (registered trademark)) is used to automatically generate the suggestions. A specific example is the optimal route suggestion.

[0363] User Interface

[0364] The device displays information on the vehicle's dashboard or head-up display. Recommendations and analysis results are presented visually, and the driver can provide feedback using the touch panel or voice commands. This feedback is used to improve the recommendations.

[0365] Feedback Processing and Integration

[0366] The server analyzes the collected feedback and generates more appropriate and effective suggestions through a process of updating the suggestions, using natural language processing algorithms to analyze the feedback text.

[0367] Emotion Engine Functions

[0368] The server uses an emotion engine to determine the driver's emotional state in real time from feedback and behavioral data, and displays the results on a dashboard. If the driver is tired, the server suggests taking a break. This process is important for improving driving safety.

[0369] Specific examples

[0370] For example, to generate optimal route suggestions to avoid traffic jams, the following prompt sentences are input into the generative AI model:

[0371] Example prompt sentence:

[0372] "Please suggest the best route based on the latest traffic data. Use the following information: Sensor data: [data], Traffic information from API: [data]"

[0373] This allows the system to utilize generative AI models to suggest appropriate routes, reducing the burden on the driver.

[0374] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0375] Step 1:

[0376] Data collection

[0377] The server collects real-time sensor data and traffic information data from vehicle sensors (cameras, LiDAR, GPS, etc.) and traffic information APIs, periodically obtains the latest traffic information using API calls and data streaming technology, and integrates this data.

[0378] Input: Data from vehicle sensors, data from traffic information API

[0379] Output: Integrated real-time traffic data

[0380] Step 2:

[0381] Data analysis

[0382] The server analyzes the collected traffic data using natural language processing (NLP) algorithms and data mining techniques. The analysis of the data extracts key stakeholders, sources of conflict, and sentiment. Sentiment analysis tools (e.g., TextBlob) are used to detect emotional states within the data.

[0383] Input: Integrated real-time traffic data

[0384] Output: Analysis results (key players, causes of conflict, emotional state)

[0385] Step 3:

[0386] Proposal Generation

[0387] The server generates optimal routes and solutions to avoid traffic problems based on the results of data analysis. During this process, a generative AI model (e.g., GPT-3) is used to automatically generate suggested text. For example, the prompt "Please suggest the optimal route" is input into the generative AI model, and the optimal route is output as a suggested output.

[0388] Input: Analysis results

[0389] Output: Auto-generated suggestion

[0390] Step 4:

[0391] User Interface Display

[0392] The device visually displays the suggestions and analysis results on the vehicle's dashboard or head-up display, and the driver receives the suggestions via touch panel or voice command and provides feedback as needed, which is also collected.

[0393] Input: Auto-generated proposal, analysis results

[0394] Output: Display on dashboard or heads-up display, collected feedback

[0395] Step 5:

[0396] Handling feedback and improving suggestions

[0397] The server analyzes the feedback collected from the driver and reflects it in the next suggestion. It uses a natural language processing algorithm to analyze the feedback text and update the suggestion to make it more appropriate.

[0398] Input: Collected feedback

[0399] Output: Improved suggestion

[0400] Step 6:

[0401] Sentiment engine analysis and display

[0402] The server uses an emotion engine to determine the driver's emotional state in real time from their feedback and behavioral data, and the results are displayed on the dashboard or HUD, suggesting a break if the driver is tired, for example.

[0403] Input: Feedback and behavioral data

[0404] Output: Emotional state analysis results, displayed on dashboard or heads-up display

[0405] In this way, each step works together to create a system that optimizes traffic conditions in real time and makes suggestions that take into account the driver's emotional state.

[0406] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0407] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0408] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0409] [Second embodiment]

[0410] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0411] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0412] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0413] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0414] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0415] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0416] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0417] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0418] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0419] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0420] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0421] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0422] The present invention provides a system for supporting dispute resolution through data collection, proposal generation, feedback collection and analysis via a user interface. Specific embodiments of this system will be described below.

[0423] System Overview

[0424] Data collection

[0425] The server automatically collects information from trusted data sources (news sites, official reports from international organizations, government statements, social media, etc.) using API calls and web scraping techniques, and stores the collected data in a cloud-based database.

[0426] Data analysis

[0427] The server uses natural language processing (NLP) algorithms to analyze the collected data, extracting key stakeholders, sources of conflict, and sentiment from the text data, and employs sentiment analysis tools to determine sentiment within the text and generate graphs and charts to visualize trends in the data.

[0428] Proposal generation

[0429] The server generates neutral and logical proposals based on the analysis results, including specific action plans and recommended strategies. The proposal documents are automatically generated and provided through a user interface.

[0430] User Interface

[0431] The device displays an interactive dashboard for users to view the proposals and provide feedback. The user interface includes graphs and charts that visually represent the analysis results and proposals. Users can also provide comments and corrections to the proposals using a feedback form.

[0432] Feedback Processing and Integration

[0433] The server analyzes the collected feedback and updates the recommendations, a process that results in better, more effective recommendations that reflect user input.

[0434] Specific examples

[0435] For example, suppose there are two groups in conflict over the distribution of resources in a conflict area. In this system, the process proceeds as follows:

[0436] 1. Data collection: The server automatically collects the latest conflict-related news from the news API, along with official government statements and reports from international organizations.

[0437] 2. Data analysis: The server uses NLP algorithms to analyze the collected text data and extract information such as "The main cause of the conflict between Group A and Group B is resource allocation." It also performs sentiment analysis and obtains results such as "Group A feels strong anger."

[0438] 3. Proposal Generation: Based on the analysis results, the server proposes the establishment of a third-party organization to ensure fair resource distribution. The proposal document also includes a specific operating scheme and funding plan.

[0439] 4. User interface: The device displays the proposals on a dashboard, along with graphs and charts. Users (representatives of international organizations) can view the proposals and provide feedback, such as "international experts should be included in the third-party organization."

[0440] 5. Feedback processing and integration: The server receives the feedback and updates the proposal document, reflecting the suggested change: "The third-party body should include international experts."

[0441] In this way, the system generates efficient and neutral proposals and supports conflict resolution by incorporating user feedback.

[0442] The processing flow will be explained below.

[0443] Step 1: Start collecting data

[0444] The server sends requests to API endpoints of authoritative data sources to retrieve the latest conflict-related data, collating data from news sites, reports from international organizations, government statements, social media posts, and more.

[0445] Step 2: Save your data

[0446] The server stores the collected data in a cloud-based database in structured formats such as JSON and CSV.

[0447] Step 3: Text analysis

[0448] The server applies natural language processing (NLP) algorithms to the stored data to extract key actors, sources of conflict, and sentiment from the text data, including extracting key events and important keywords.

[0449] Step 4: Sentiment analysis

[0450] Based on the text analysis results, the server uses a sentiment analysis tool to classify and assess the emotions of each participant, using algorithms to identify emotional expressions in the text and distinguish between anger, frustration, hope, etc.

[0451] Step 5: Trend analysis and visualization

[0452] The server performs trend analysis on the analyzed data and generates graphs and charts that visualize changes and patterns over time, allowing users to understand the development and trends of the conflict at a glance.

[0453] Step 6: Proposal Generation

[0454] The server automatically generates neutral and logical proposals based on the results of text and sentiment analysis, including concrete action plans and strategies.

[0455] Step 7: Providing a User Interface

[0456] The device displays a user-accessible dashboard that displays analysis results, recommendations, trend graphs, and more.

[0457] Step 8: Gather feedback

[0458] Users can provide reviews and feedback on the suggestions provided through a feedback form on the dashboard, including suggested modifications and opinions.

[0459] Step 9: Feedback analysis

[0460] The server analyzes the feedback collected from users, understands the intent of the feedback and the suggestions, and identifies which parts of the suggestions need to be revised.

[0461] Step 10: Update your proposal

[0462] The server updates the proposal document based on the feedback, and the revised proposal is again presented through the user interface and displayed for the user to review and evaluate.

[0463] Step 11: Final confirmation of feedback

[0464] Users review the updated proposal and provide further feedback if necessary, and this process continues until a final consensus is reached.

[0465] Through this series of processes, the system has the ability to effectively support dialogue and negotiation and promote conflict resolution.

[0466] Example 1

[0467] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0468] Current dispute resolution support systems often lack efficient data collection, analysis, proposal generation, and feedback processing, making it difficult to provide fast and accurate dispute resolution solutions. Furthermore, they lack the ability to properly analyze collected information and generate neutral proposals, which can lead to biased solutions. Furthermore, systems for collecting and incorporating user feedback through a user interface are inadequate. The objective of the present invention is to solve these problems.

[0469] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0470] In this invention, the server includes means for automatically collecting information from data sources, means for storing the collected information in a cloud-based database, means for analyzing the collected information to extract key stakeholders, causes of conflicts, and emotions, means for generating neutral proposals based on the analysis results, means for providing the proposals through a user interface and collecting feedback from users, and means for reflecting the collected feedback in improving the analysis and proposals, thereby enabling efficient generation of neutral proposals and rapid reflection of user feedback.

[0471] "Data Source" means an external information source that provides information in a variety of formats.

[0472] An "automated collection means" is a mechanism for obtaining data without requiring manual input from a user.

[0473] A "cloud-based database" is a data management system that operates over the internet and stores data on a remote server.

[0474] "Means for analyzing collected information" are methods and algorithms used to understand, classify, and extract meaning from collected data.

[0475] "Key Stakeholders" refers to individuals or organizations that play a significant role in a particular event or issue.

[0476] "Causes of conflict" refers to the underlying factors or reasons that cause conflict or disputes.

[0477] "Means for extracting emotions" are algorithms and tools for identifying and analyzing emotions and sentiments from text data.

[0478] A "neutral proposal" is one that does not favor any particular position and presents a solution that is fair to all parties involved.

[0479] "User interface" refers to the graphical screen or dashboard that allows users to interact with the system and manipulate and view information.

[0480] "Feedback" refers to response information such as opinions, evaluations, and suggested revisions provided by users.

[0481] A "means for improving recommendations" is a process or algorithm for modifying or updating initial recommendations based on collected feedback.

[0482] The present invention provides a system for supporting dispute resolution through data collection, proposal generation, feedback collection via a user interface, and analysis. Specific embodiments of this system will be described below.

[0483] System Overview

[0484] The system consists of the following main components:

[0485] Data collection

[0486] The server automatically collects information from data sources such as news sites, reports from international organizations, government statements, and social media. This process involves calling APIs and web scraping techniques. The collected data is then stored in a cloud-based database. For example, the requests library is used to call the API and BeautifulSoup is used for web scraping.

[0487] Data analysis

[0488] The server uses natural language processing (NLP) algorithms to analyze the collected data. This extracts key stakeholders, sources of conflict, and sentiment from the text data. It also uses sentiment analysis tools to determine sentiment within the text and generate graphs and charts to visualize data trends. Specifically, it uses NLP libraries (e.g., NLTK, spaCy) and sentiment analysis tools such as VADER and TextBlob.

[0489] Proposal generation

[0490] The server generates neutral and logical proposals based on the analysis results, including specific action plans and recommended strategies. The proposal documents are automatically generated and provided through a user interface. This process uses generative AI models, such as OpenAI's GPT model.

[0491] User Interface

[0492] The terminal displays an interactive dashboard for users to view the proposals and provide feedback. The user interface includes graphs and charts that visually display the analysis results and proposals. Users can also provide opinions and corrections to the proposals using a feedback form. Front-end frameworks such as React.js are used.

[0493] Feedback Processing and Integration

[0494] The server analyzes the collected feedback and updates the recommendations. This process results in more relevant and actionable recommendations that reflect user input. The generated AI model is then used again, and the updates are displayed in the user interface using a front-end framework.

[0495] Specific examples

[0496] For example, if there are two groups in conflict over the distribution of resources in a conflict area, the process would proceed as follows:

[0497] 1. Data Collection:

[0498] The server automatically collects the latest conflict-related news from a news API, simultaneously retrieving official government statements and reports from international organizations.

[0499] 2. Data Analysis:

[0500] The server uses an NLP algorithm to analyze the text data, extracting information such as "The main cause of the conflict between Group A and Group B is resource allocation," and performs sentiment analysis to obtain results such as "Group A feels strong anger."

[0501] 3. Proposal generation:

[0502] Based on the analysis results, the server will propose the establishment of a third-party organization to ensure fair distribution of resources, and will include a specific operating scheme and funding plan.

[0503] 4. User Interface:

[0504] The device displays the recommendations on a dashboard, complete with graphs and charts, and users can view the recommendations and provide feedback, such as "The third-party organization should include international experts."

[0505] 5. Feedback processing and integration:

[0506] The server receives the feedback and uses the generative AI model to update the proposal document, including the suggested change that the third-party body should include international experts.

[0507] Prompt Sentence Examples

[0508] The following prompt sentences can be input into the generative AI model to analyze and generate suggestions:

[0509] Get the latest news data, extract the key causes of conflict for a particular dispute, analyze the sentiment behind the conflict, and recommend solutions.

[0510] Data sources: news sites, official reports from international organizations, government statements

[0511] In this way, the system generates efficient and neutral proposals and supports conflict resolution by incorporating user feedback.

[0512] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0513] Step 1: Automated data collection

[0514] What it does: The server collects the latest information from reliable data sources such as news sites, official reports from international organizations, government statements, and social media. For example, it uses the requests library to call news APIs and BeautifulSoup to scrape data from official reporting sites. The input to this process is the URL and API key of the data source, and the output is the collected raw data.

[0515] Step 2: Save your data

[0516] What happens: The server stores the collected data in a cloud-based database, such as AWS's RDS or Google Cloud's BigQuery, by executing a SQL query to insert the data. The input to this process is the raw data obtained in step 1, and the output is structured data stored in the database.

[0517] Step 3: Data analysis

[0518] What it does: The server analyzes the collected data using NLP algorithms. Specifically, it uses NLP libraries (e.g., NLTK, spaCy) to extract key players, conflict causes, and sentiment from the text data. For sentiment analysis, it uses VADER and TextBlob. The input to this process is the structured data saved in step 2, and the output is the analysis results, such as conflict causes and sentiment.

[0519] Step 4: Generate graphs and charts

[0520] Specific operation: The server generates graphs and charts to visualize data trends based on the analysis results. Specifically, it visualizes the data using Python's matplotlib and seaborn. The input to this process is the analysis results obtained in step 3, and the output is the generated graphs and charts.

[0521] Step 5: Proposal Generation

[0522] Specific operation: The server generates neutral and logical proposals based on the analysis results. Using a generative AI model (e.g., OpenAI's GPT model), it automatically generates a proposal document containing a specific action plan and recommended strategies. The input to this process is the analysis results obtained in Step 3, and the output is the generated proposal document.

[0523] Step 6: Displaying the User Interface

[0524] Specific operation: The terminal displays an interactive dashboard for users to view the proposals and provide feedback. A front-end framework such as React.js is used to visually display the analysis results and proposals. Users can also enter their opinions and corrections using a feedback form. The input of this process is the proposal document and visualized graphs and charts generated in step 5, and the output is the user's feedback.

[0525] Step 7: Collect and analyze feedback

[0526] What happens: The server analyzes the feedback collected from the user and updates the proposal. It uses the generative AI model again to generate more appropriate and actionable proposals. The input to this process is the user feedback obtained in step 6, and the output is the updated proposal document.

[0527] Step 8: Redistribute the updated proposal

[0528] Specific operation: The server delivers the updated proposal document back to the user interface, allowing the user to view the latest proposal content. Using React.js, the updated proposal document is displayed on a dashboard. The input of this process is the updated proposal document generated in step 7, and the output is a dashboard containing the updated proposal content.

[0529] (Application example 1)

[0530] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0531] Modern society requires real-time conflict monitoring and rapid resolution support. Conflicts and disputes at event venues and other public spaces must be resolved as quickly as possible, but conventional systems have struggled to respond quickly and appropriately. There was also a need for a system that could efficiently analyze data collected in real time, generate appropriate proposals based on the results, and improve those proposals by incorporating feedback.

[0532] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0533] In this invention, the server includes means for automatically collecting information from data sources, means for analyzing the collected information to extract key stakeholders, causes of conflict, and emotions, means for generating neutral proposals based on the analysis results, means for providing the proposals through a user interface and collecting feedback from users, means for reflecting the collected feedback in improving the analysis and proposals, means for recording the surrounding situation and converting it into text using a voice recognition function, and means for displaying the analysis results and proposals on a display in real time, thereby enabling the system to instantly grasp the local situation, generate and provide appropriate countermeasures in real time, and quickly reflect user feedback.

[0534] "Data sources" refers to reliable sources for gathering information, such as news sites, official reports, government statements, and social media.

[0535] "Means of automatically collecting information" refers to technologies for automatically obtaining information from data sources, such as by calling APIs or using web scraping techniques.

[0536] "Key actors" refer to important people or groups in a conflict or conflict situation.

[0537] "Causes of conflict" refers to the main reasons or factors behind conflict or confrontation.

[0538] "Means of extracting emotions" refers to technology that uses natural language processing algorithms and emotion analysis tools to determine emotions from text data and audio data.

[0539] A "neutral proposal" refers to a specific action plan or recommended strategy that aims to solve a problem in an impartial and logical manner, without favoring any particular position.

[0540] "User interface" refers to the interactive screen or operating environment that allows a user to interact with a system.

[0541] "Feedback" refers to users' opinions and requests for corrections regarding the proposal.

[0542] "Recording and voice recognition function" refers to technology that uses a camera and microphone to record the surrounding situation and converts the voice data into text data.

[0543] "Display" means a screen or display device for visually presenting information or offers.

[0544] This invention is a system that supports real-time dispute resolution through data collection, proposal generation, feedback collection and analysis via a user interface. A specific embodiment for realizing this system will be described below.

[0545] Overall structure

[0546] The server automatically collects information from data sources, analyzes the collected information to extract key stakeholders, sources of conflict, and sentiment, then generates neutral proposals based on the analysis results and provides them through a user interface. Users provide feedback on the proposals through the user interface, and the server analyzes this feedback and updates the proposals.

[0547] Data collection

[0548] The servers automatically collect information from trusted data sources such as news sites, official reports, government statements, social media, etc. The data is retrieved using API calls and web scraping techniques and stored in a cloud-based database.

[0549] Data analysis

[0550] The collected data is analyzed using a server-based natural language processing (NLP) algorithm to extract key stakeholders, sources of conflict, and sentiment. Sentiment analysis tools are also used to identify sentiment within the text and generate graphs and charts to visualize trends in the data. Specifically, Google NLP APIs and sentiment analysis tools are used.

[0551] Proposal generation

[0552] Based on the analysis results, the server generates neutral and logical proposals, including specific action plans and recommended strategies, and automatically generates proposal documents using a generative AI model.

[0553] User Interface

[0554] The device displays an interactive dashboard where users can view the recommendations and provide feedback. The dashboard includes graphs and charts visually illustrating the analysis results and recommendations. When using smart glasses, this information is displayed in real time on the display. Using voice recognition, the device converts the user's speech into text, allowing feedback to be provided via the operation panel.

[0555] Feedback Processing and Integration

[0556] The server analyzes the collected feedback and updates the suggestions. This process results in more appropriate and effective suggestions that reflect user opinions. For example, the feedback is managed using the Firebase database.

[0557] Specific examples

[0558] For example, a system for resolving conflict situations in real time at an event venue works as follows: A security officer wearing smart glasses records the conflict and converts the conversation into text using a voice recognition API. The server analyzes the video using an NLP algorithm and identifies "insufficient visitor number control" as the cause of the conflict. Based on the analysis results, the server generates a recommendation to "set up a counter and assign additional staff" and displays it on the smart glasses' display. The security officer provides feedback, and the server updates the recommendation accordingly.

[0559] Prompt Sentence Examples

[0560] Event A and Event B are in conflict. The main cause is a lack of coordination on the number of attendees. Please suggest a solution.

[0561] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0562] Step 1: Data collection

[0563] The server automatically collects information from data sources, such as news sites, official reports, government statements, and social media, using API calls and web scraping techniques. This data is then stored in a cloud-based database. The input for the collected data is the API calls and web scraping, and the output is the data stored in the cloud database.

[0564] Step 2: Surroundings recording and voice recognition

[0565] The smart glasses, which serve as the device, record the surrounding situation and collect audio using a microphone. The collected audio data is converted into text using a speech recognition API. The input is camera footage and audio data, and the output is text-formatted conversation data. This makes it possible to grasp the situation in real time.

[0566] Step 3: Data analysis

[0567] The server uses natural language processing (NLP) algorithms to analyze the collected data, extracting key players, causes of conflict, and sentiment from the text data. The input is text data, and the output is information on key players, causes of conflict, and sentiment. Specifically, it uses Google NLP API and sentiment analysis tools.

[0568] Step 4: Proposal Generation

[0569] The server generates neutral and logical proposals based on the analysis results. These are automatically generated as proposal documents using a generative AI model. The input is the analysis results, and the output is the proposal document. For example, from the analysis result of "insufficient visitor number adjustment," the server generates a specific proposal such as "install a counter and assign additional staff."

[0570] Step 5: Display the user interface

[0571] The smart glasses, which are the terminals, display the proposals in real time. The analysis results and proposals are visualized as graphs and charts. The inputs are the proposal documents and analysis results, and the output is the information displayed on the screen. The user can provide feedback using the operation panel on the glasses.

[0572] Step 6: Feedback collection and analysis

[0573] The server collects and analyzes feedback provided by users. The input of the feedback is text data from the user, and the output is the analyzed feedback information. Specifically, the feedback is managed via the Firebase database.

[0574] Step 7: Improve and update your proposal

[0575] The server updates the proposal document based on the analyzed feedback, resulting in a more appropriate proposal that reflects user input. The input is the feedback information, and the output is an updated proposal document. For example, a new proposal reflecting "allocation of additional staff" is generated.

[0576] This processing step allows the system to efficiently execute a series of processes: grasping the situation in real time, making appropriate suggestions, providing them to the user, and incorporating the feedback.

[0577] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0578] This invention is a system that supports conflict resolution by recognizing user emotions through data collection, proposal generation, feedback collection and analysis via a user interface, and a combination of an emotion engine. Specific embodiments of this system are described below.

[0579] System Overview

[0580] Data collection

[0581] The server automatically collects information from trusted data sources (news sites, official reports from international organizations, government statements, social media, etc.) using API calls and web scraping techniques, and stores the collected data in a cloud-based database.

[0582] Data analysis

[0583] The server uses natural language processing (NLP) algorithms to analyze the collected data, extracting key stakeholders, sources of conflict, and sentiment from the text data, and employs sentiment analysis tools to determine sentiment within the text and generate graphs and charts to visualize trends in the data.

[0584] Proposal generation

[0585] The server generates neutral and logical proposals based on the analysis results, including specific action plans and recommended strategies. The proposal documents are automatically generated and provided through a user interface.

[0586] User Interface

[0587] The device displays an interactive dashboard for users to view the proposals and provide feedback. The user interface includes graphs and charts that visually represent the analysis results and proposals. Users can also provide comments and corrections to the proposals using a feedback form.

[0588] Feedback Processing and Integration

[0589] The server analyzes the collected feedback and updates the recommendations, a process that results in better, more effective recommendations that reflect user input.

[0590] Emotion Engine Functions

[0591] The server uses an emotion engine to perform emotion analysis on the feedback provided by the user, allowing the server to recognize the user's emotional state in real time and display it on a dashboard. The emotion engine uses natural language processing techniques to identify, classify, and rate emotional expressions in the text.

[0592] Specific examples

[0593] For example, the following is a series of processes that may be applied to a conflict zone where two groups are in conflict over the allocation of resources.

[0594] 1. Data Collection:

[0595] The server automatically collects the latest conflict-related news from a news API, along with official government statements and reports from international organizations.

[0596] 2. Data Analysis:

[0597] The server uses an NLP algorithm to analyze the collected text data and extract information such as "The main cause of the conflict between Group A and Group B is resource allocation." It also performs sentiment analysis and obtains results such as "Group A feels strong anger."

[0598] 3. Proposal generation:

[0599] Based on the analysis results, the server will propose the establishment of a third-party organization to ensure the fair distribution of resources. The proposal document will also include a specific operating scheme and funding plan.

[0600] 4. User Interface:

[0601] The device displays the proposals on a dashboard, along with graphs and charts. Users (representatives of international organizations) can view the proposals and provide feedback, such as "The third-party organization should also include international experts."

[0602] 5. Feedback processing and integration:

[0603] The server receives the feedback and updates the proposal document, reflecting the revised suggestion that "the third-party body should include international experts."

[0604] 6. Use of Emotion Engine:

[0605] The server uses an emotion engine to analyze the emotions of the feedback provided by the user. For example, if emotions such as "anger" or "dissatisfaction" are detected, this is reflected in the dashboard, visually displaying the emotions with which the user is providing feedback.

[0606] In this way, a system incorporating an emotion engine can generate efficient and neutral suggestions, reflect user feedback, and more effectively support conflict resolution by recognizing and displaying user emotions in real time.

[0607] The processing flow will be explained below.

[0608] Step 1:

[0609] The server uses API calls and web scraping techniques to automatically collect information from reliable data sources (news sites, official reports from international organizations, government statements, social media, etc.) and stores the collected data in a cloud-based database.

[0610] Step 2:

[0611] The server applies natural language processing (NLP) algorithms to the stored data to extract key stakeholders, sources of conflict, and sentiment from the text data. Specifically, it extracts key events and important keywords from the collected text data.

[0612] Step 3:

[0613] The server uses a sentiment analysis tool based on the text analysis results to classify and evaluate the emotional expressions in the text, identifying emotions such as anger, frustration, and hope, and storing the emotional state as data.

[0614] Step 4:

[0615] The server performs trend analysis on the analyzed data and generates graphs and charts that visualize changes and patterns over time, allowing users to understand the development and trends of the conflict at a glance.

[0616] Step 5:

[0617] The server automatically generates neutral and logical proposals based on the results of text and sentiment analysis, including the establishment of a third-party organization to ensure fair resource distribution, a specific operating scheme, and a funding plan.

[0618] Step 6:

[0619] The terminal displays a user-accessible dashboard that displays the analysis results, recommendations, trend graphs and charts generated by the server.

[0620] Step 7:

[0621] The terminal provides a feedback form for the user to view the proposal and to enter their opinions and suggestions for corrections to the proposal.

[0622] Step 8:

[0623] The server analyzes the feedback collected from users through the feedback form, and again uses NLP algorithms to analyze the text data in the feedback to identify which parts of the suggestion should be revised.

[0624] Step 9:

[0625] The server uses an emotion engine to analyze the emotion contained in the user's feedback in real time. The emotion engine performs emotion analysis on the user's feedback to determine the user's emotional state, such as anger or frustration.

[0626] Step 10:

[0627] The device displays the results of the emotion engine's analysis on a dashboard, which visually displays the emotional state of the feedback provided by the user.

[0628] Step 11:

[0629] The server updates the proposal document based on the analysis results and the emotion engine's evaluation results. The revised proposal is again presented through the user interface and displayed for the user to review and evaluate.

[0630] Step 12:

[0631] Users review the updated proposal and provide further feedback if necessary, repeating the process until a final consensus is reached.

[0632] In this way, a system incorporating an emotion engine can recognize users' emotions in real time, provide efficient and neutral suggestions, and support optimal conflict resolution.

[0633] Example 2

[0634] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0635] While conventional data collection and analysis systems can efficiently collect and analyze data, they lack the functionality to automatically generate specific and neutral proposals for conflict resolution, and to collect and incorporate user feedback. Furthermore, there is no mechanism for analyzing and incorporating the user's emotional state in real time, which means the quality and effectiveness of the proposals cannot be fully guaranteed.

[0636] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for automatically collecting information from data sources, means for analyzing the collected information to extract key stakeholders, causes of conflict, and emotions, means for generating neutral proposals based on the analysis results, means for providing proposals through a user interface and collecting feedback from users, means for reflecting the collected feedback in improving the analysis and proposals, and means for analyzing emotional expressions included in the feedback in real time and displaying them on a dashboard. This makes it possible to perform processes from data collection to analysis, proposal generation, feedback reflection, and real-time emotion analysis in a centralized and integrated manner.

[0637] "Data sources" refers to various media that provide information, such as news sites, official reports from international organizations, government statements, social media, etc.

[0638] "Means of collection" refers to technical devices or software for automatically obtaining information from data sources, such as by calling APIs or using web scraping techniques.

[0639] "Analyzing means" refers to technical devices or algorithms, in particular natural language processing (NLP) algorithms, used to process the collected data and extract the required information.

[0640] A "neutral proposal" refers to an action plan or strategy that is fair and objective, not influenced by any particular interest or bias.

[0641] "User interface" refers to the interface through which a user interacts with a machine, particularly the dashboard for displaying suggestions and collecting feedback.

[0642] "Feedback collection means" refers to any technological device or form for receiving comments or corrections to a proposal from users.

[0643] "Emotional expressions" refer to the emotional states that appear in text, specifically expressions that classify emotions such as "anger," "sadness," and "joy."

[0644] "Means for analyzing in real time and displaying on a dashboard" refers to a technological device or software that uses an emotion engine to instantly evaluate the emotion in the feedback and display it visually.

[0645] This invention is a system that supports conflict resolution by recognizing user emotions through data collection, proposal generation, feedback collection and analysis via a user interface, and a combination of an emotion engine. Specific embodiments of this system are described below.

[0646] Data collection

[0647] The server automatically collects information from reliable data sources (news sites, official reports from international organizations, government statements, social media, etc.) using API calls and web scraping techniques. Specifically, it uses a news API to retrieve data by calling the API, such as "https: / / newsapi.org / v2 / top-headlines?country=us&apiKey=YOUR_API_KEY." The retrieved data is then stored in a cloud-based database, such as Google Cloud Firestore or Amazon DynamoDB.

[0648] Data analysis

[0649] The server uses natural language processing (NLP) algorithms to analyze the collected data. Specifically, it preprocesses the text data using toolkits such as NLTK and SpaCy. It then applies NLP algorithms to extract key stakeholders and conflict sources. It also uses sentiment analysis tools (e.g., Sentiment Analysis API and TextBlob) to determine the sentiment within the text. The analysis results are visualized as graphs and charts using visualization libraries such as matplotlib and plotly.

[0650] As a concrete example, the server collects the latest conflict-related news via a news API and uses an NLP algorithm to extract information such as "The main cause of the conflict between Group A and Group B is resource allocation." It also performs sentiment analysis to obtain the result that "Group A feels strong anger."

[0651] Proposal generation

[0652] The server generates neutral and logical proposals based on the analysis results. For example, a generative AI model can be used to automatically generate a proposal document for "establishing a third-party organization to ensure the fair distribution of resources." The generated proposal document includes a specific operating scheme and funding plan. The proposal document is generated in HTML or PDF format and sent to the user interface.

[0653] As a specific example, the server proposes "the establishment of a third-party organization to ensure fair distribution of resources" based on the analysis results, and generates a document that includes the specific operating scheme and funding plan.

[0654] User Interface

[0655] The device displays an interactive dashboard for users to view and provide feedback on the proposals. The dashboard includes graphs and charts that visually represent the analysis results and proposals. Users can provide comments and corrections to the proposals using a feedback form.

[0656] For example, a user (representative of an international organization) can view the proposal through the dashboard and provide feedback such as, "The third-party organization should also include international experts."

[0657] Feedback Processing and Integration

[0658] The server analyzes the feedback collected from users and updates the proposals, generating more specific and effective proposals that reflect the user's opinions.

[0659] As a concrete example, the server analyzes the user's feedback "The third party should include international experts" and generates an updated document that reflects this.

[0660] Emotion Engine Functions

[0661] The server uses an emotion engine to perform emotion analysis on the feedback provided by the user. It identifies the user's emotional state in real time and displays it on a dashboard. The emotion engine uses natural language processing techniques to identify, classify, and rate emotional expressions in the text.

[0662] As a specific example, the server performs an emotional analysis of the feedback content, and if emotions such as "anger" or "dissatisfaction" are detected, they are displayed on the dashboard.

[0663] Example prompt for a generative AI model:

[0664] "The representative of international organization A has provided feedback on a proposal regarding resource allocation. Please analyze the representative's feedback using the sentiment engine and display it in real time on a dashboard."

[0665] The present invention is a system that more effectively supports conflict resolution by centrally performing data collection, analysis, proposal generation, feedback reflection, and sentiment analysis.

[0666] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0667] Program processing procedure and specific operations

[0668] Step 1: Data collection

[0669] 1. Input: URL and authentication information for news API or official report API

[0670] The server sets the URL and authentication information to call the API of a trusted data source (e.g., news site, official report from an international organization, government statement, social media).

[0671] 2. Operation: API calls and data retrieval

[0672] The server retrieves the latest information from the data source by making an API call, such as for the News API, using the URL "https: / / newsapi.org / v2 / top-headlines?country=us&apiKey=YOUR_API_KEY".

[0673] 3. Output: Acquired data

[0674] The acquired data is, for example, in JSON format.

[0675] 4. Operation: Data storage

[0676] The server stores the retrieved data in a cloud-based database such as Google Cloud Firestore or Amazon DynamoDB.

[0677] Step 2: Data analysis

[0678] 1. Input: Collected data (e.g., JSON format)

[0679] The server prepares the collected data for the NLP algorithms.

[0680] 2. Operation: Preprocessing text data

[0681] The server uses toolkits like NLTK or SpaCy to pre-process the data, removing unnecessary parts like advertisements and HTML tags.

[0682] 3. Action: Identifying key stakeholders and conflict sources

[0683] The server applies natural language processing algorithms to extract key players and sources of conflict from the text, e.g., "Group A and Group B are in conflict over resource allocation."

[0684] 4. Behavior: Sentiment analysis

[0685] The server uses sentiment analysis tools to identify emotional expressions in the text. For example, it uses the Sentiment Analysis API or TextBlob to analyze emotional data such as "Group A feels very angry."

[0686] 5. Output: Analysis results

[0687] Analysis results including information on extracted parties, conflict causes, emotional expressions, etc.

[0688] 6. Action: Visualizing data trends

[0689] The server visualizes the analysis results as graphs and charts using visualization libraries such as matplotlib and plotly.

[0690] Step 3: Proposal Generation

[0691] 1. Input: Analysis results

[0692] The server inputs the analysis results into a generative AI model.

[0693] 2. Action: Creating a proposal document

[0694] The server uses a generative AI model to automatically generate neutral and logical proposal documents, such as proposing the establishment of a third-party organization to ensure the fair distribution of resources.

[0695] 3. Output: Proposal document

[0696] The generated proposal document is in HTML or PDF format.

[0697] 4. Action: Proposal document distribution

[0698] The server sends the generated proposal document to the user interface.

[0699] Step 4: Display the user interface

[0700] 1. Input: Proposal document and analysis results

[0701] The terminal receives the proposed document and the analysis results.

[0702] 2. Action: Rendering a dashboard

[0703] The terminal displays an interactive dashboard as a user interface, which is implemented using frameworks such as Django or Flask.

[0704] 3. Action: Data Visualization

[0705] The terminal displays the data visualization results (graphs and charts) on a dashboard.

[0706] 4. Action: Providing a feedback form

[0707] The terminal displays a feedback form in which the user can provide comments and corrections to the proposal.

[0708] Step 5: Feedback processing and integration

[0709] 1. Input: User feedback

[0710] The server receives feedback from the user.

[0711] 2. Action: Feedback Analysis

[0712] The server analyzes the feedback and extracts specific opinions and suggested modifications.

[0713] 3. Action: Proposal document update

[0714] The server updates the proposal document based on the analysis, for example, to reflect the suggested revision that "the third-party body should include international experts."

[0715] 4. Output: Updated proposal document

[0716] The updated proposal document is again sent to the user interface and displayed.

[0717] Step 6: Functioning of the Emotion Engine

[0718] 1. Input: User feedback

[0719] The server inputs the user's feedback into the emotion engine.

[0720] 2. Action: Feedback sentiment analysis

[0721] The server uses an emotion engine to analyze the emotional state of the feedback, identifying emotions such as "anger" or "frustration."

[0722] 3. Output: Emotion analysis results

[0723] If sentiment analysis shows that the feedback is "angry," that information will be displayed on the dashboard.

[0724] 4. Action: Displaying Emotional State

[0725] The device displays the user's emotional state in real time on a dashboard, analyzed by the emotion engine. For example, if anger is detected, it is highlighted in red.

[0726] (Application example 2)

[0727] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0728] Frequent traffic congestion and accidents are increasing the stress and burden on drivers. Furthermore, there is a problem that drivers are unable to respond quickly to changes in traffic conditions, making it difficult to select the optimal route. Furthermore, there is a lack of systems that can grasp the driver's emotional state and make appropriate suggestions, preventing improvements in driving safety.

[0729] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0730] In this invention, the server includes: means for automatically collecting information from data sources; means for analyzing the collected information to extract key stakeholders, causes of conflict, and emotions; means for generating neutral proposals based on the analysis results; means for providing proposals through a user interface and collecting user feedback; means for reflecting the collected feedback in improving the analysis and proposals; means for analyzing traffic conditions in real time and proposing optimal routes; and means for analyzing the driver's emotional state and displaying the results. This makes it possible to quickly respond to traffic conditions in real time and propose optimal routes while reducing the driver's burden. Furthermore, making proposals based on the driver's emotional state can improve safety.

[0731] "Data Source" is a trusted source used to gather information (e.g., news sites, traffic APIs, social media, etc.).

[0732] "Means of automatically collecting information" refers to the process of asynchronously obtaining the necessary information from data sources using API calls or web scraping techniques.

[0733] "Means for analyzing collected information" refers to the process of using natural language processing algorithms and data mining techniques to extract key stakeholders, sources of conflict, and sentiment from the collected text data.

[0734] A "means for generating neutral proposals" is a process that automatically creates logical and effective proposals based on the results of data analysis, without any particular position or bias.

[0735] A "user interface" is an interactive interface through which a user can view information, receive suggestions, and provide feedback.

[0736] A "feedback collection method" is a form or interactive digital tool used to systematically collect user opinions and comments.

[0737] "Means for reflecting feedback in analysis and improvement of proposals" refers to the process of re-analyzing the data based on the feedback collected from users and updating the proposal content to make it more appropriate.

[0738] "Means of analyzing traffic conditions in real time" refers to the process of analyzing real-time data obtained from vehicle sensors and traffic information APIs to understand the current traffic situation.

[0739] "Means for proposing optimal routes" refers to the process of presenting optimal travel routes to drivers based on real-time data and analysis results.

[0740] "Means for analyzing the emotional state of a driver" refers to the process of using an emotion analysis tool to identify and evaluate the emotional state of a driver from the feedback and behaviors provided by the driver.

[0741] The "means for displaying the results" is a display or dashboard that visually shows the analyzed emotional state information to the driver in real time.

[0742] This invention is a system for autonomous vehicles that analyzes traffic conditions in real time and makes suggestions based on the driver's emotional state. The system has the functions of data collection, data analysis, suggestion generation, user interface, feedback processing and integration, and an emotion engine.

[0743] Data collection

[0744] The server collects data from vehicle sensors (cameras, LiDAR, GPS, etc.) and traffic information APIs (e.g., popular traffic information providers) in real time, using API calls and data streaming techniques.

[0745] Data analysis

[0746] Data collected from vehicle sensors and traffic information APIs is sent to a server where it is analyzed using natural language processing (NLP) algorithms and data mining techniques, such as extracting key stakeholders, sources of conflict, and sentiment from text data. For sentiment analysis, TextBlob and other AI-based sentiment analysis tools are used.

[0747] Proposal generation

[0748] The server generates neutral and effective suggestions based on the analysis results. These include optimal routes, workarounds, and break suggestions. During this process, a generative AI model (e.g., GPT-3) is used to automatically generate the suggestions. A specific example is the optimal route suggestion.

[0749] User Interface

[0750] The device displays information on the vehicle's dashboard or head-up display. Recommendations and analysis results are presented visually, and the driver can provide feedback using the touch panel or voice commands. This feedback is used to improve the recommendations.

[0751] Feedback Processing and Integration

[0752] The server analyzes the collected feedback and generates more appropriate and effective suggestions through a process of updating the suggestions, using natural language processing algorithms to analyze the feedback text.

[0753] Emotion Engine Functions

[0754] The server uses an emotion engine to determine the driver's emotional state in real time from feedback and behavioral data, and displays the results on a dashboard. If the driver is tired, the server suggests taking a break. This process is important for improving driving safety.

[0755] Specific examples

[0756] For example, to generate optimal route suggestions to avoid traffic jams, the following prompt sentences are input into the generative AI model:

[0757] Example prompt sentence:

[0758] "Please suggest the best route based on the latest traffic data. Use the following information: Sensor data: [data], Traffic information from API: [data]"

[0759] This allows the system to utilize generative AI models to suggest appropriate routes, reducing the burden on the driver.

[0760] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0761] Step 1:

[0762] Data collection

[0763] The server collects real-time sensor data and traffic information data from vehicle sensors (cameras, LiDAR, GPS, etc.) and traffic information APIs, periodically obtains the latest traffic information using API calls and data streaming technology, and integrates this data.

[0764] Input: Data from vehicle sensors, data from traffic information API

[0765] Output: Integrated real-time traffic data

[0766] Step 2:

[0767] Data analysis

[0768] The server analyzes the collected traffic data using natural language processing (NLP) algorithms and data mining techniques. The analysis of the data extracts key stakeholders, sources of conflict, and sentiment. Sentiment analysis tools (e.g., TextBlob) are used to detect emotional states within the data.

[0769] Input: Integrated real-time traffic data

[0770] Output: Analysis results (key players, causes of conflict, emotional state)

[0771] Step 3:

[0772] Proposal Generation

[0773] The server generates optimal routes and solutions to avoid traffic problems based on the results of data analysis. During this process, a generative AI model (e.g., GPT-3) is used to automatically generate suggested text. For example, the prompt "Please suggest the optimal route" is input into the generative AI model, and the optimal route is output as a suggested output.

[0774] Input: Analysis results

[0775] Output: Auto-generated suggestion

[0776] Step 4:

[0777] User Interface Display

[0778] The device visually displays the suggestions and analysis results on the vehicle's dashboard or head-up display, and the driver receives the suggestions via touch panel or voice command and provides feedback as needed, which is also collected.

[0779] Input: Auto-generated proposal, analysis results

[0780] Output: Display on dashboard or heads-up display, collected feedback

[0781] Step 5:

[0782] Handling feedback and improving suggestions

[0783] The server analyzes the feedback collected from the driver and reflects it in the next suggestion. It uses a natural language processing algorithm to analyze the feedback text and update the suggestion to make it more appropriate.

[0784] Input: Collected feedback

[0785] Output: Improved suggestion

[0786] Step 6:

[0787] Sentiment engine analysis and display

[0788] The server uses an emotion engine to determine the driver's emotional state in real time from their feedback and behavioral data, and the results are displayed on the dashboard or HUD, suggesting a break if the driver is tired, for example.

[0789] Input: Feedback and behavioral data

[0790] Output: Emotional state analysis results, displayed on dashboard or heads-up display

[0791] In this way, each step works together to create a system that optimizes traffic conditions in real time and makes suggestions that take into account the driver's emotional state.

[0792] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0793] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0794] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0795] [Third embodiment]

[0796] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0797] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0798] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0799] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0800] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0801] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0802] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0803] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0804] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0805] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0806] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0807] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0808] The present invention provides a system for supporting dispute resolution through data collection, proposal generation, feedback collection and analysis via a user interface. Specific embodiments of this system will be described below.

[0809] System Overview

[0810] Data collection

[0811] The server automatically collects information from trusted data sources (news sites, official reports from international organizations, government statements, social media, etc.) using API calls and web scraping techniques, and stores the collected data in a cloud-based database.

[0812] Data analysis

[0813] The server uses natural language processing (NLP) algorithms to analyze the collected data, extracting key stakeholders, sources of conflict, and sentiment from the text data, and employs sentiment analysis tools to determine sentiment within the text and generate graphs and charts to visualize trends in the data.

[0814] Proposal generation

[0815] The server generates neutral and logical proposals based on the analysis results, including specific action plans and recommended strategies. The proposal documents are automatically generated and provided through a user interface.

[0816] User Interface

[0817] The device displays an interactive dashboard for users to view the proposals and provide feedback. The user interface includes graphs and charts that visually represent the analysis results and proposals. Users can also provide comments and corrections to the proposals using a feedback form.

[0818] Feedback Processing and Integration

[0819] The server analyzes the collected feedback and updates the recommendations, a process that results in better, more effective recommendations that reflect user input.

[0820] Specific examples

[0821] For example, suppose there are two groups in conflict over the distribution of resources in a conflict area. In this system, the process proceeds as follows:

[0822] 1. Data collection: The server automatically collects the latest conflict-related news from the news API, along with official government statements and reports from international organizations.

[0823] 2. Data analysis: The server uses NLP algorithms to analyze the collected text data and extract information such as "The main cause of the conflict between Group A and Group B is resource allocation." It also performs sentiment analysis and obtains results such as "Group A feels strong anger."

[0824] 3. Proposal Generation: Based on the analysis results, the server proposes the establishment of a third-party organization to ensure fair resource distribution. The proposal document also includes a specific operating scheme and funding plan.

[0825] 4. User interface: The device displays the proposals on a dashboard, along with graphs and charts. Users (representatives of international organizations) can view the proposals and provide feedback, such as "international experts should be included in the third-party organization."

[0826] 5. Feedback processing and integration: The server receives the feedback and updates the proposal document, reflecting the suggested change: "The third-party body should include international experts."

[0827] In this way, the system generates efficient and neutral proposals and supports conflict resolution by incorporating user feedback.

[0828] The processing flow will be explained below.

[0829] Step 1: Start collecting data

[0830] The server sends requests to API endpoints of authoritative data sources to retrieve the latest conflict-related data, collating data from news sites, reports from international organizations, government statements, social media posts, and more.

[0831] Step 2: Save your data

[0832] The server stores the collected data in a cloud-based database in structured formats such as JSON and CSV.

[0833] Step 3: Text analysis

[0834] The server applies natural language processing (NLP) algorithms to the stored data to extract key actors, sources of conflict, and sentiment from the text data, including extracting key events and important keywords.

[0835] Step 4: Sentiment analysis

[0836] Based on the text analysis results, the server uses a sentiment analysis tool to classify and assess the emotions of each participant, using algorithms to identify emotional expressions in the text and distinguish between anger, frustration, hope, etc.

[0837] Step 5: Trend analysis and visualization

[0838] The server performs trend analysis on the analyzed data and generates graphs and charts that visualize changes and patterns over time, allowing users to understand the development and trends of the conflict at a glance.

[0839] Step 6: Proposal Generation

[0840] The server automatically generates neutral and logical proposals based on the results of text and sentiment analysis, including concrete action plans and strategies.

[0841] Step 7: Providing a User Interface

[0842] The device displays a user-accessible dashboard that displays analysis results, recommendations, trend graphs, and more.

[0843] Step 8: Gather feedback

[0844] Users can provide reviews and feedback on the suggestions provided through a feedback form on the dashboard, including suggested modifications and opinions.

[0845] Step 9: Feedback analysis

[0846] The server analyzes the feedback collected from users, understands the intent of the feedback and the suggestions, and identifies which parts of the suggestions need to be revised.

[0847] Step 10: Update your proposal

[0848] The server updates the proposal document based on the feedback, and the revised proposal is again presented through the user interface and displayed for the user to review and evaluate.

[0849] Step 11: Final confirmation of feedback

[0850] Users review the updated proposal and provide further feedback if necessary, and this process continues until a final consensus is reached.

[0851] Through this series of processes, the system has the ability to effectively support dialogue and negotiation and promote conflict resolution.

[0852] Example 1

[0853] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0854] Current dispute resolution support systems often lack efficient data collection, analysis, proposal generation, and feedback processing, making it difficult to provide fast and accurate dispute resolution solutions. Furthermore, they lack the ability to properly analyze collected information and generate neutral proposals, which can lead to biased solutions. Furthermore, systems for collecting and incorporating user feedback through a user interface are inadequate. The objective of the present invention is to solve these problems.

[0855] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0856] In this invention, the server includes means for automatically collecting information from data sources, means for storing the collected information in a cloud-based database, means for analyzing the collected information to extract key stakeholders, causes of conflicts, and emotions, means for generating neutral proposals based on the analysis results, means for providing the proposals through a user interface and collecting feedback from users, and means for reflecting the collected feedback in improving the analysis and proposals, thereby enabling efficient generation of neutral proposals and rapid reflection of user feedback.

[0857] "Data Source" means an external information source that provides information in a variety of formats.

[0858] An "automated collection means" is a mechanism for obtaining data without requiring manual input from a user.

[0859] A "cloud-based database" is a data management system that operates over the internet and stores data on a remote server.

[0860] "Means for analyzing collected information" are methods and algorithms used to understand, classify, and extract meaning from collected data.

[0861] "Key Stakeholders" refers to individuals or organizations that play a significant role in a particular event or issue.

[0862] "Causes of conflict" refers to the underlying factors or reasons that cause conflict or disputes.

[0863] "Means for extracting emotions" are algorithms and tools for identifying and analyzing emotions and sentiments from text data.

[0864] A "neutral proposal" is one that does not favor any particular position and presents a solution that is fair to all parties involved.

[0865] "User interface" refers to the graphical screen or dashboard that allows users to interact with the system and manipulate and view information.

[0866] "Feedback" refers to response information such as opinions, evaluations, and suggested revisions provided by users.

[0867] A "means for improving recommendations" is a process or algorithm for modifying or updating initial recommendations based on collected feedback.

[0868] The present invention provides a system for supporting dispute resolution through data collection, proposal generation, feedback collection via a user interface, and analysis. Specific embodiments of this system will be described below.

[0869] System Overview

[0870] The system consists of the following main components:

[0871] Data collection

[0872] The server automatically collects information from data sources such as news sites, reports from international organizations, government statements, and social media. This process involves calling APIs and web scraping techniques. The collected data is then stored in a cloud-based database. For example, the requests library is used to call the API and BeautifulSoup is used for web scraping.

[0873] Data analysis

[0874] The server uses natural language processing (NLP) algorithms to analyze the collected data. This extracts key stakeholders, sources of conflict, and sentiment from the text data. It also uses sentiment analysis tools to determine sentiment within the text and generate graphs and charts to visualize data trends. Specifically, it uses NLP libraries (e.g., NLTK, spaCy) and sentiment analysis tools such as VADER and TextBlob.

[0875] Proposal generation

[0876] The server generates neutral and logical proposals based on the analysis results, including specific action plans and recommended strategies. The proposal documents are automatically generated and provided through a user interface. This process uses generative AI models, such as OpenAI's GPT model.

[0877] User Interface

[0878] The terminal displays an interactive dashboard for users to view the proposals and provide feedback. The user interface includes graphs and charts that visually display the analysis results and proposals. Users can also provide opinions and corrections to the proposals using a feedback form. Front-end frameworks such as React.js are used.

[0879] Feedback Processing and Integration

[0880] The server analyzes the collected feedback and updates the recommendations. This process results in more relevant and actionable recommendations that reflect user input. The generated AI model is then used again, and the updates are displayed in the user interface using a front-end framework.

[0881] Specific examples

[0882] For example, if there are two groups in conflict over the distribution of resources in a conflict area, the process would proceed as follows:

[0883] 1. Data Collection:

[0884] The server automatically collects the latest conflict-related news from a news API, simultaneously retrieving official government statements and reports from international organizations.

[0885] 2. Data Analysis:

[0886] The server uses an NLP algorithm to analyze the text data, extracting information such as "The main cause of the conflict between Group A and Group B is resource allocation," and performs sentiment analysis to obtain results such as "Group A feels strong anger."

[0887] 3. Proposal generation:

[0888] Based on the analysis results, the server will propose the establishment of a third-party organization to ensure fair distribution of resources, and will include a specific operating scheme and funding plan.

[0889] 4. User Interface:

[0890] The device displays the recommendations on a dashboard, complete with graphs and charts, and users can view the recommendations and provide feedback, such as "The third-party organization should include international experts."

[0891] 5. Feedback processing and integration:

[0892] The server receives the feedback and uses the generative AI model to update the proposal document, including the suggested change that the third-party body should include international experts.

[0893] Prompt Sentence Examples

[0894] The following prompt sentences can be input into the generative AI model to analyze and generate suggestions:

[0895] Get the latest news data, extract the key causes of conflict for a particular dispute, analyze the sentiment behind the conflict, and recommend solutions.

[0896] Data sources: news sites, official reports from international organizations, government statements

[0897] In this way, the system generates efficient and neutral proposals and supports conflict resolution by incorporating user feedback.

[0898] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0899] Step 1: Automated data collection

[0900] What it does: The server collects the latest information from reliable data sources such as news sites, official reports from international organizations, government statements, and social media. For example, it uses the requests library to call news APIs and BeautifulSoup to scrape data from official reporting sites. The input to this process is the URL and API key of the data source, and the output is the collected raw data.

[0901] Step 2: Save your data

[0902] What happens: The server stores the collected data in a cloud-based database, such as AWS's RDS or Google Cloud's BigQuery, by executing a SQL query to insert the data. The input to this process is the raw data obtained in step 1, and the output is structured data stored in the database.

[0903] Step 3: Data analysis

[0904] What it does: The server analyzes the collected data using NLP algorithms. Specifically, it uses NLP libraries (e.g., NLTK, spaCy) to extract key players, conflict causes, and sentiment from the text data. For sentiment analysis, it uses VADER and TextBlob. The input to this process is the structured data saved in step 2, and the output is the analysis results, such as conflict causes and sentiment.

[0905] Step 4: Generate graphs and charts

[0906] Specific operation: The server generates graphs and charts to visualize data trends based on the analysis results. Specifically, it visualizes the data using Python's matplotlib and seaborn. The input to this process is the analysis results obtained in step 3, and the output is the generated graphs and charts.

[0907] Step 5: Proposal Generation

[0908] Specific operation: The server generates neutral and logical proposals based on the analysis results. Using a generative AI model (e.g., OpenAI's GPT model), it automatically generates a proposal document containing a specific action plan and recommended strategies. The input to this process is the analysis results obtained in Step 3, and the output is the generated proposal document.

[0909] Step 6: Displaying the User Interface

[0910] Specific operation: The terminal displays an interactive dashboard for users to view the proposals and provide feedback. A front-end framework such as React.js is used to visually display the analysis results and proposals. Users can also enter their opinions and corrections using a feedback form. The input of this process is the proposal document and visualized graphs and charts generated in step 5, and the output is the user's feedback.

[0911] Step 7: Collect and analyze feedback

[0912] What happens: The server analyzes the feedback collected from the user and updates the proposal. It uses the generative AI model again to generate more appropriate and actionable proposals. The input to this process is the user feedback obtained in step 6, and the output is the updated proposal document.

[0913] Step 8: Redistribute the updated proposal

[0914] Specific operation: The server delivers the updated proposal document back to the user interface, allowing the user to view the latest proposal content. Using React.js, the updated proposal document is displayed on a dashboard. The input of this process is the updated proposal document generated in step 7, and the output is a dashboard containing the updated proposal content.

[0915] (Application example 1)

[0916] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0917] Modern society requires real-time conflict monitoring and rapid resolution support. Conflicts and disputes at event venues and other public spaces must be resolved as quickly as possible, but conventional systems have struggled to respond quickly and appropriately. There was also a need for a system that could efficiently analyze data collected in real time, generate appropriate proposals based on the results, and improve those proposals by incorporating feedback.

[0918] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0919] In this invention, the server includes means for automatically collecting information from data sources, means for analyzing the collected information to extract key stakeholders, causes of conflict, and emotions, means for generating neutral proposals based on the analysis results, means for providing the proposals through a user interface and collecting feedback from users, means for reflecting the collected feedback in improving the analysis and proposals, means for recording the surrounding situation and converting it into text using a voice recognition function, and means for displaying the analysis results and proposals on a display in real time, thereby enabling the system to instantly grasp the local situation, generate and provide appropriate countermeasures in real time, and quickly reflect user feedback.

[0920] "Data sources" refers to reliable sources for gathering information, such as news sites, official reports, government statements, and social media.

[0921] "Means of automatically collecting information" refers to technologies for automatically obtaining information from data sources, such as by calling APIs or using web scraping techniques.

[0922] "Key actors" refer to important people or groups in a conflict or conflict situation.

[0923] "Causes of conflict" refers to the main reasons or factors behind conflict or confrontation.

[0924] "Means of extracting emotions" refers to technology that uses natural language processing algorithms and emotion analysis tools to determine emotions from text data and audio data.

[0925] A "neutral proposal" refers to a specific action plan or recommended strategy that aims to solve a problem in an impartial and logical manner, without favoring any particular position.

[0926] "User interface" refers to the interactive screen or operating environment that allows a user to interact with a system.

[0927] "Feedback" refers to users' opinions and requests for corrections regarding the proposal.

[0928] "Recording and voice recognition function" refers to technology that uses a camera and microphone to record the surrounding situation and converts the voice data into text data.

[0929] "Display" means a screen or display device for visually presenting information or offers.

[0930] This invention is a system that supports real-time dispute resolution through data collection, proposal generation, feedback collection and analysis via a user interface. A specific embodiment for realizing this system will be described below.

[0931] Overall structure

[0932] The server automatically collects information from data sources, analyzes the collected information to extract key stakeholders, sources of conflict, and sentiment, then generates neutral proposals based on the analysis results and provides them through a user interface. Users provide feedback on the proposals through the user interface, and the server analyzes this feedback and updates the proposals.

[0933] Data collection

[0934] The servers automatically collect information from trusted data sources such as news sites, official reports, government statements, social media, etc. The data is retrieved using API calls and web scraping techniques and stored in a cloud-based database.

[0935] Data analysis

[0936] The collected data is analyzed using a server-based natural language processing (NLP) algorithm to extract key stakeholders, sources of conflict, and sentiment. Sentiment analysis tools are also used to identify sentiment within the text and generate graphs and charts to visualize trends in the data. Specifically, Google NLP APIs and sentiment analysis tools are used.

[0937] Proposal generation

[0938] Based on the analysis results, the server generates neutral and logical proposals, including specific action plans and recommended strategies, and automatically generates proposal documents using a generative AI model.

[0939] User Interface

[0940] The device displays an interactive dashboard where users can view the recommendations and provide feedback. The dashboard includes graphs and charts visually illustrating the analysis results and recommendations. When using smart glasses, this information is displayed in real time on the display. Using voice recognition, the device converts the user's speech into text, allowing feedback to be provided via the operation panel.

[0941] Feedback Processing and Integration

[0942] The server analyzes the collected feedback and updates the suggestions. This process results in more appropriate and effective suggestions that reflect user opinions. For example, the feedback is managed using the Firebase database.

[0943] Specific examples

[0944] For example, a system for resolving conflict situations in real time at an event venue works as follows: A security officer wearing smart glasses records the conflict and converts the conversation into text using a voice recognition API. The server analyzes the video using an NLP algorithm and identifies "insufficient visitor number control" as the cause of the conflict. Based on the analysis results, the server generates a recommendation to "set up a counter and assign additional staff" and displays it on the smart glasses' display. The security officer provides feedback, and the server updates the recommendation accordingly.

[0945] Prompt Sentence Examples

[0946] Event A and Event B are in conflict. The main cause is a lack of coordination on the number of attendees. Please suggest a solution.

[0947] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0948] Step 1: Data collection

[0949] The server automatically collects information from data sources, such as news sites, official reports, government statements, and social media, using API calls and web scraping techniques. This data is then stored in a cloud-based database. The input for the collected data is the API calls and web scraping, and the output is the data stored in the cloud database.

[0950] Step 2: Surroundings recording and voice recognition

[0951] The smart glasses, which serve as the device, record the surrounding situation and collect audio using a microphone. The collected audio data is converted into text using a speech recognition API. The input is camera footage and audio data, and the output is text-formatted conversation data. This makes it possible to grasp the situation in real time.

[0952] Step 3: Data analysis

[0953] The server uses natural language processing (NLP) algorithms to analyze the collected data, extracting key players, causes of conflict, and sentiment from the text data. The input is text data, and the output is information on key players, causes of conflict, and sentiment. Specifically, it uses Google NLP API and sentiment analysis tools.

[0954] Step 4: Proposal Generation

[0955] The server generates neutral and logical proposals based on the analysis results. These are automatically generated as proposal documents using a generative AI model. The input is the analysis results, and the output is the proposal document. For example, from the analysis result of "insufficient visitor number adjustment," the server generates a specific proposal such as "install a counter and assign additional staff."

[0956] Step 5: Display the user interface

[0957] The smart glasses, which are the terminals, display the proposals in real time. The analysis results and proposals are visualized as graphs and charts. The inputs are the proposal documents and analysis results, and the output is the information displayed on the screen. The user can provide feedback using the operation panel on the glasses.

[0958] Step 6: Feedback collection and analysis

[0959] The server collects and analyzes feedback provided by users. The input of the feedback is text data from the user, and the output is the analyzed feedback information. Specifically, the feedback is managed via the Firebase database.

[0960] Step 7: Improve and update your proposal

[0961] The server updates the proposal document based on the analyzed feedback, resulting in a more appropriate proposal that reflects user input. The input is the feedback information, and the output is an updated proposal document. For example, a new proposal reflecting "allocation of additional staff" is generated.

[0962] This processing step allows the system to efficiently execute a series of processes: grasping the situation in real time, making appropriate suggestions, providing them to the user, and incorporating the feedback.

[0963] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0964] This invention is a system that supports conflict resolution by recognizing user emotions through data collection, proposal generation, feedback collection and analysis via a user interface, and a combination of an emotion engine. Specific embodiments of this system are described below.

[0965] System Overview

[0966] Data collection

[0967] The server automatically collects information from trusted data sources (news sites, official reports from international organizations, government statements, social media, etc.) using API calls and web scraping techniques, and stores the collected data in a cloud-based database.

[0968] Data analysis

[0969] The server uses natural language processing (NLP) algorithms to analyze the collected data, extracting key stakeholders, sources of conflict, and sentiment from the text data, and employs sentiment analysis tools to determine sentiment within the text and generate graphs and charts to visualize trends in the data.

[0970] Proposal generation

[0971] The server generates neutral and logical proposals based on the analysis results, including specific action plans and recommended strategies. The proposal documents are automatically generated and provided through a user interface.

[0972] User Interface

[0973] The device displays an interactive dashboard for users to view the proposals and provide feedback. The user interface includes graphs and charts that visually represent the analysis results and proposals. Users can also provide comments and corrections to the proposals using a feedback form.

[0974] Feedback Processing and Integration

[0975] The server analyzes the collected feedback and updates the recommendations, a process that results in better, more effective recommendations that reflect user input.

[0976] Emotion Engine Functions

[0977] The server uses an emotion engine to perform emotion analysis on the feedback provided by the user, allowing the server to recognize the user's emotional state in real time and display it on a dashboard. The emotion engine uses natural language processing techniques to identify, classify, and rate emotional expressions in the text.

[0978] Specific examples

[0979] For example, the following is a series of processes that may be applied to a conflict zone where two groups are in conflict over the allocation of resources.

[0980] 1. Data Collection:

[0981] The server automatically collects the latest conflict-related news from a news API, along with official government statements and reports from international organizations.

[0982] 2. Data Analysis:

[0983] The server uses an NLP algorithm to analyze the collected text data and extract information such as "The main cause of the conflict between Group A and Group B is resource allocation." It also performs sentiment analysis and obtains results such as "Group A feels strong anger."

[0984] 3. Proposal generation:

[0985] Based on the analysis results, the server will propose the establishment of a third-party organization to ensure the fair distribution of resources. The proposal document will also include a specific operating scheme and funding plan.

[0986] 4. User Interface:

[0987] The device displays the proposals on a dashboard, along with graphs and charts. Users (representatives of international organizations) can view the proposals and provide feedback, such as "The third-party organization should also include international experts."

[0988] 5. Feedback processing and integration:

[0989] The server receives the feedback and updates the proposal document, reflecting the revised suggestion that "the third-party body should include international experts."

[0990] 6. Use of Emotion Engine:

[0991] The server uses an emotion engine to analyze the emotions of the feedback provided by the user. For example, if emotions such as "anger" or "dissatisfaction" are detected, this is reflected in the dashboard, visually displaying the emotions with which the user is providing feedback.

[0992] In this way, a system incorporating an emotion engine can generate efficient and neutral suggestions, reflect user feedback, and more effectively support conflict resolution by recognizing and displaying user emotions in real time.

[0993] The processing flow will be explained below.

[0994] Step 1:

[0995] The server uses API calls and web scraping techniques to automatically collect information from reliable data sources (news sites, official reports from international organizations, government statements, social media, etc.) and stores the collected data in a cloud-based database.

[0996] Step 2:

[0997] The server applies natural language processing (NLP) algorithms to the stored data to extract key stakeholders, sources of conflict, and sentiment from the text data. Specifically, it extracts key events and important keywords from the collected text data.

[0998] Step 3:

[0999] The server uses a sentiment analysis tool based on the text analysis results to classify and evaluate the emotional expressions in the text, identifying emotions such as anger, frustration, and hope, and storing the emotional state as data.

[1000] Step 4:

[1001] The server performs trend analysis on the analyzed data and generates graphs and charts that visualize changes and patterns over time, allowing users to understand the development and trends of the conflict at a glance.

[1002] Step 5:

[1003] The server automatically generates neutral and logical proposals based on the results of text and sentiment analysis, including the establishment of a third-party organization to ensure fair resource distribution, a specific operating scheme, and a funding plan.

[1004] Step 6:

[1005] The terminal displays a user-accessible dashboard that displays the analysis results, recommendations, trend graphs and charts generated by the server.

[1006] Step 7:

[1007] The terminal provides a feedback form for the user to view the proposal and to enter their opinions and suggestions for corrections to the proposal.

[1008] Step 8:

[1009] The server analyzes the feedback collected from users through the feedback form, and again uses NLP algorithms to analyze the text data in the feedback to identify which parts of the suggestion should be revised.

[1010] Step 9:

[1011] The server uses an emotion engine to analyze the emotion contained in the user's feedback in real time. The emotion engine performs emotion analysis on the user's feedback to determine the user's emotional state, such as anger or frustration.

[1012] Step 10:

[1013] The device displays the results of the emotion engine's analysis on a dashboard, which visually displays the emotional state of the feedback provided by the user.

[1014] Step 11:

[1015] The server updates the proposal document based on the analysis results and the emotion engine's evaluation results. The revised proposal is again presented through the user interface and displayed for the user to review and evaluate.

[1016] Step 12:

[1017] Users review the updated proposal and provide further feedback if necessary, repeating the process until a final consensus is reached.

[1018] In this way, a system incorporating an emotion engine can recognize users' emotions in real time, provide efficient and neutral suggestions, and support optimal conflict resolution.

[1019] Example 2

[1020] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1021] While conventional data collection and analysis systems can efficiently collect and analyze data, they lack the functionality to automatically generate specific and neutral proposals for conflict resolution, and to collect and incorporate user feedback. Furthermore, there is no mechanism for analyzing and incorporating the user's emotional state in real time, which means the quality and effectiveness of the proposals cannot be fully guaranteed.

[1022] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for automatically collecting information from data sources, means for analyzing the collected information to extract key stakeholders, causes of conflict, and emotions, means for generating neutral proposals based on the analysis results, means for providing proposals through a user interface and collecting feedback from users, means for reflecting the collected feedback in improving the analysis and proposals, and means for analyzing emotional expressions included in the feedback in real time and displaying them on a dashboard. This makes it possible to perform processes from data collection to analysis, proposal generation, feedback reflection, and real-time emotion analysis in a centralized and integrated manner.

[1023] "Data sources" refers to various media that provide information, such as news sites, official reports from international organizations, government statements, social media, etc.

[1024] "Means of collection" refers to technical devices or software for automatically obtaining information from data sources, such as by calling APIs or using web scraping techniques.

[1025] "Analyzing means" refers to technical devices or algorithms, in particular natural language processing (NLP) algorithms, used to process the collected data and extract the required information.

[1026] A "neutral proposal" refers to an action plan or strategy that is fair and objective, not influenced by any particular interest or bias.

[1027] "User interface" refers to the interface through which a user interacts with a machine, particularly the dashboard for displaying suggestions and collecting feedback.

[1028] "Feedback collection means" refers to any technological device or form for receiving comments or corrections to a proposal from users.

[1029] "Emotional expressions" refer to the emotional states that appear in text, specifically expressions that classify emotions such as "anger," "sadness," and "joy."

[1030] "Means for analyzing in real time and displaying on a dashboard" refers to a technological device or software that uses an emotion engine to instantly evaluate the emotion in the feedback and display it visually.

[1031] This invention is a system that supports conflict resolution by recognizing user emotions through data collection, proposal generation, feedback collection and analysis via a user interface, and a combination of an emotion engine. Specific embodiments of this system are described below.

[1032] Data collection

[1033] The server automatically collects information from reliable data sources (news sites, official reports from international organizations, government statements, social media, etc.) using API calls and web scraping techniques. Specifically, it uses a news API to retrieve data by calling the API, such as "https: / / newsapi.org / v2 / top-headlines?country=us&apiKey=YOUR_API_KEY." The retrieved data is then stored in a cloud-based database, such as Google Cloud Firestore or Amazon DynamoDB.

[1034] Data analysis

[1035] The server uses natural language processing (NLP) algorithms to analyze the collected data. Specifically, it preprocesses the text data using toolkits such as NLTK and SpaCy. It then applies NLP algorithms to extract key stakeholders and conflict sources. It also uses sentiment analysis tools (e.g., Sentiment Analysis API and TextBlob) to determine the sentiment within the text. The analysis results are visualized as graphs and charts using visualization libraries such as matplotlib and plotly.

[1036] As a concrete example, the server collects the latest conflict-related news via a news API and uses an NLP algorithm to extract information such as "The main cause of the conflict between Group A and Group B is resource allocation." It also performs sentiment analysis to obtain the result that "Group A feels strong anger."

[1037] Proposal generation

[1038] The server generates neutral and logical proposals based on the analysis results. For example, a generative AI model can be used to automatically generate a proposal document for "establishing a third-party organization to ensure the fair distribution of resources." The generated proposal document includes a specific operating scheme and funding plan. The proposal document is generated in HTML or PDF format and sent to the user interface.

[1039] As a specific example, the server proposes "the establishment of a third-party organization to ensure fair distribution of resources" based on the analysis results, and generates a document that includes the specific operating scheme and funding plan.

[1040] User Interface

[1041] The device displays an interactive dashboard for users to view and provide feedback on the proposals. The dashboard includes graphs and charts that visually represent the analysis results and proposals. Users can provide comments and corrections to the proposals using a feedback form.

[1042] For example, a user (representative of an international organization) can view the proposal through the dashboard and provide feedback such as, "The third-party organization should also include international experts."

[1043] Feedback Processing and Integration

[1044] The server analyzes the feedback collected from users and updates the proposals, generating more specific and effective proposals that reflect the user's opinions.

[1045] As a concrete example, the server analyzes the user's feedback "The third party should include international experts" and generates an updated document that reflects this.

[1046] Emotion Engine Functions

[1047] The server uses an emotion engine to perform emotion analysis on the feedback provided by the user. It identifies the user's emotional state in real time and displays it on a dashboard. The emotion engine uses natural language processing techniques to identify, classify, and rate emotional expressions in the text.

[1048] As a specific example, the server performs an emotional analysis of the feedback content, and if emotions such as "anger" or "dissatisfaction" are detected, they are displayed on the dashboard.

[1049] Example prompt for a generative AI model:

[1050] "The representative of international organization A has provided feedback on a proposal regarding resource allocation. Please analyze the representative's feedback using the sentiment engine and display it in real time on a dashboard."

[1051] The present invention is a system that more effectively supports conflict resolution by centrally performing data collection, analysis, proposal generation, feedback reflection, and sentiment analysis.

[1052] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1053] Program processing procedure and specific operations

[1054] Step 1: Data collection

[1055] 1. Input: URL and authentication information for news API or official report API

[1056] The server sets the URL and authentication information to call the API of a trusted data source (e.g., news site, official report from an international organization, government statement, social media).

[1057] 2. Operation: API calls and data retrieval

[1058] The server retrieves the latest information from the data source by making an API call, such as for the News API, using the URL "https: / / newsapi.org / v2 / top-headlines?country=us&apiKey=YOUR_API_KEY".

[1059] 3. Output: Acquired data

[1060] The acquired data is, for example, in JSON format.

[1061] 4. Operation: Data storage

[1062] The server stores the retrieved data in a cloud-based database such as Google Cloud Firestore or Amazon DynamoDB.

[1063] Step 2: Data analysis

[1064] 1. Input: Collected data (e.g., JSON format)

[1065] The server prepares the collected data for the NLP algorithms.

[1066] 2. Operation: Preprocessing text data

[1067] The server uses toolkits like NLTK or SpaCy to pre-process the data, removing unnecessary parts like advertisements and HTML tags.

[1068] 3. Action: Identifying key stakeholders and conflict sources

[1069] The server applies natural language processing algorithms to extract key players and sources of conflict from the text, e.g., "Group A and Group B are in conflict over resource allocation."

[1070] 4. Behavior: Sentiment analysis

[1071] The server uses sentiment analysis tools to identify emotional expressions in the text. For example, it uses the Sentiment Analysis API or TextBlob to analyze emotional data such as "Group A feels very angry."

[1072] 5. Output: Analysis results

[1073] Analysis results including information on extracted parties, conflict causes, emotional expressions, etc.

[1074] 6. Action: Visualizing data trends

[1075] The server visualizes the analysis results as graphs and charts using visualization libraries such as matplotlib and plotly.

[1076] Step 3: Proposal Generation

[1077] 1. Input: Analysis results

[1078] The server inputs the analysis results into a generative AI model.

[1079] 2. Action: Creating a proposal document

[1080] The server uses a generative AI model to automatically generate neutral and logical proposal documents, such as proposing the establishment of a third-party organization to ensure the fair distribution of resources.

[1081] 3. Output: Proposal document

[1082] The generated proposal document is in HTML or PDF format.

[1083] 4. Action: Proposal document distribution

[1084] The server sends the generated proposal document to the user interface.

[1085] Step 4: Display the user interface

[1086] 1. Input: Proposal document and analysis results

[1087] The terminal receives the proposed document and the analysis results.

[1088] 2. Action: Rendering a dashboard

[1089] The terminal displays an interactive dashboard as a user interface, which is implemented using frameworks such as Django or Flask.

[1090] 3. Action: Data Visualization

[1091] The terminal displays the data visualization results (graphs and charts) on a dashboard.

[1092] 4. Action: Providing a feedback form

[1093] The terminal displays a feedback form in which the user can provide comments and corrections to the proposal.

[1094] Step 5: Feedback processing and integration

[1095] 1. Input: User feedback

[1096] The server receives feedback from the user.

[1097] 2. Action: Feedback Analysis

[1098] The server analyzes the feedback and extracts specific opinions and suggested modifications.

[1099] 3. Action: Proposal document update

[1100] The server updates the proposal document based on the analysis, for example, to reflect the suggested revision that "the third-party body should include international experts."

[1101] 4. Output: Updated proposal document

[1102] The updated proposal document is again sent to the user interface and displayed.

[1103] Step 6: Functioning of the Emotion Engine

[1104] 1. Input: User feedback

[1105] The server inputs the user's feedback into the emotion engine.

[1106] 2. Action: Feedback sentiment analysis

[1107] The server uses an emotion engine to analyze the emotional state of the feedback, identifying emotions such as "anger" or "frustration."

[1108] 3. Output: Emotion analysis results

[1109] If sentiment analysis shows that the feedback is "angry," that information will be displayed on the dashboard.

[1110] 4. Action: Displaying Emotional State

[1111] The device displays the user's emotional state in real time on a dashboard, analyzed by the emotion engine. For example, if anger is detected, it is highlighted in red.

[1112] (Application example 2)

[1113] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1114] Frequent traffic congestion and accidents are increasing the stress and burden on drivers. Furthermore, there is a problem that drivers are unable to respond quickly to changes in traffic conditions, making it difficult to select the optimal route. Furthermore, there is a lack of systems that can grasp the driver's emotional state and make appropriate suggestions, preventing improvements in driving safety.

[1115] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1116] In this invention, the server includes: means for automatically collecting information from data sources; means for analyzing the collected information to extract key stakeholders, causes of conflict, and emotions; means for generating neutral proposals based on the analysis results; means for providing proposals through a user interface and collecting user feedback; means for reflecting the collected feedback in improving the analysis and proposals; means for analyzing traffic conditions in real time and proposing optimal routes; and means for analyzing the driver's emotional state and displaying the results. This makes it possible to quickly respond to traffic conditions in real time and propose optimal routes while reducing the driver's burden. Furthermore, making proposals based on the driver's emotional state can improve safety.

[1117] "Data Source" is a trusted source used to gather information (e.g., news sites, traffic APIs, social media, etc.).

[1118] "Means of automatically collecting information" refers to the process of asynchronously obtaining the necessary information from data sources using API calls or web scraping techniques.

[1119] "Means for analyzing collected information" refers to the process of using natural language processing algorithms and data mining techniques to extract key stakeholders, sources of conflict, and sentiment from the collected text data.

[1120] A "means for generating neutral proposals" is a process that automatically creates logical and effective proposals based on the results of data analysis, without any particular position or bias.

[1121] A "user interface" is an interactive interface through which a user can view information, receive suggestions, and provide feedback.

[1122] A "feedback collection method" is a form or interactive digital tool used to systematically collect user opinions and comments.

[1123] "Means for reflecting feedback in analysis and improvement of proposals" refers to the process of re-analyzing the data based on the feedback collected from users and updating the proposal content to make it more appropriate.

[1124] "Means of analyzing traffic conditions in real time" refers to the process of analyzing real-time data obtained from vehicle sensors and traffic information APIs to understand the current traffic situation.

[1125] "Means for proposing optimal routes" refers to the process of presenting optimal travel routes to drivers based on real-time data and analysis results.

[1126] "Means for analyzing the emotional state of a driver" refers to the process of using an emotion analysis tool to identify and evaluate the emotional state of a driver from the feedback and behaviors provided by the driver.

[1127] The "means for displaying the results" is a display or dashboard that visually shows the analyzed emotional state information to the driver in real time.

[1128] This invention is a system for autonomous vehicles that analyzes traffic conditions in real time and makes suggestions based on the driver's emotional state. The system has the functions of data collection, data analysis, suggestion generation, user interface, feedback processing and integration, and an emotion engine.

[1129] Data collection

[1130] The server collects data from vehicle sensors (cameras, LiDAR, GPS, etc.) and traffic information APIs (e.g., popular traffic information providers) in real time, using API calls and data streaming techniques.

[1131] Data analysis

[1132] Data collected from vehicle sensors and traffic information APIs is sent to a server where it is analyzed using natural language processing (NLP) algorithms and data mining techniques, such as extracting key stakeholders, sources of conflict, and sentiment from text data. For sentiment analysis, TextBlob and other AI-based sentiment analysis tools are used.

[1133] Proposal generation

[1134] The server generates neutral and effective suggestions based on the analysis results. These include optimal routes, workarounds, and break suggestions. During this process, a generative AI model (e.g., GPT-3) is used to automatically generate the suggestions. A specific example is the optimal route suggestion.

[1135] User Interface

[1136] The device displays information on the vehicle's dashboard or head-up display. Recommendations and analysis results are presented visually, and the driver can provide feedback using the touch panel or voice commands. This feedback is used to improve the recommendations.

[1137] Feedback Processing and Integration

[1138] The server analyzes the collected feedback and generates more appropriate and effective suggestions through a process of updating the suggestions, using natural language processing algorithms to analyze the feedback text.

[1139] Emotion Engine Functions

[1140] The server uses an emotion engine to determine the driver's emotional state in real time from feedback and behavioral data, and displays the results on a dashboard. If the driver is tired, the server suggests taking a break. This process is important for improving driving safety.

[1141] Specific examples

[1142] For example, to generate optimal route suggestions to avoid traffic jams, the following prompt sentences are input into the generative AI model:

[1143] Example prompt sentence:

[1144] "Please suggest the best route based on the latest traffic data. Use the following information: Sensor data: [data], Traffic information from API: [data]"

[1145] This allows the system to utilize generative AI models to suggest appropriate routes, reducing the burden on the driver.

[1146] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1147] Step 1:

[1148] Data collection

[1149] The server collects real-time sensor data and traffic information data from vehicle sensors (cameras, LiDAR, GPS, etc.) and traffic information APIs, periodically obtains the latest traffic information using API calls and data streaming technology, and integrates this data.

[1150] Input: Data from vehicle sensors, data from traffic information API

[1151] Output: Integrated real-time traffic data

[1152] Step 2:

[1153] Data analysis

[1154] The server analyzes the collected traffic data using natural language processing (NLP) algorithms and data mining techniques. The analysis of the data extracts key stakeholders, sources of conflict, and sentiment. Sentiment analysis tools (e.g., TextBlob) are used to detect emotional states within the data.

[1155] Input: Integrated real-time traffic data

[1156] Output: Analysis results (key players, causes of conflict, emotional state)

[1157] Step 3:

[1158] Proposal Generation

[1159] The server generates optimal routes and solutions to avoid traffic problems based on the results of data analysis. During this process, a generative AI model (e.g., GPT-3) is used to automatically generate suggested text. For example, the prompt "Please suggest the optimal route" is input into the generative AI model, and the optimal route is output as a suggested output.

[1160] Input: Analysis results

[1161] Output: Auto-generated suggestion

[1162] Step 4:

[1163] User Interface Display

[1164] The device visually displays the suggestions and analysis results on the vehicle's dashboard or head-up display, and the driver receives the suggestions via touch panel or voice command and provides feedback as needed, which is also collected.

[1165] Input: Auto-generated proposal, analysis results

[1166] Output: Display on dashboard or heads-up display, collected feedback

[1167] Step 5:

[1168] Handling feedback and improving suggestions

[1169] The server analyzes the feedback collected from the driver and reflects it in the next suggestion. It uses a natural language processing algorithm to analyze the feedback text and update the suggestion to make it more appropriate.

[1170] Input: Collected feedback

[1171] Output: Improved suggestion

[1172] Step 6:

[1173] Sentiment engine analysis and display

[1174] The server uses an emotion engine to determine the driver's emotional state in real time from their feedback and behavioral data, and the results are displayed on the dashboard or HUD, suggesting a break if the driver is tired, for example.

[1175] Input: Feedback and behavioral data

[1176] Output: Emotional state analysis results, displayed on dashboard or heads-up display

[1177] In this way, each step works together to create a system that optimizes traffic conditions in real time and makes suggestions that take into account the driver's emotional state.

[1178] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1179] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1180] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1181] [Fourth embodiment]

[1182] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1183] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1184] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1185] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1186] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1187] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1188] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1189] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1190] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1191] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1192] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1193] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1194] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1195] The present invention provides a system for supporting dispute resolution through data collection, proposal generation, feedback collection and analysis via a user interface. Specific embodiments of this system will be described below.

[1196] System Overview

[1197] Data collection

[1198] The server automatically collects information from trusted data sources (news sites, official reports from international organizations, government statements, social media, etc.) using API calls and web scraping techniques, and stores the collected data in a cloud-based database.

[1199] Data analysis

[1200] The server uses natural language processing (NLP) algorithms to analyze the collected data, extracting key stakeholders, sources of conflict, and sentiment from the text data, and employs sentiment analysis tools to determine sentiment within the text and generate graphs and charts to visualize trends in the data.

[1201] Proposal generation

[1202] The server generates neutral and logical proposals based on the analysis results, including specific action plans and recommended strategies. The proposal documents are automatically generated and provided through a user interface.

[1203] User Interface

[1204] The device displays an interactive dashboard for users to view the proposals and provide feedback. The user interface includes graphs and charts that visually represent the analysis results and proposals. Users can also provide comments and corrections to the proposals using a feedback form.

[1205] Feedback Processing and Integration

[1206] The server analyzes the collected feedback and updates the recommendations, a process that results in better, more effective recommendations that reflect user input.

[1207] Specific examples

[1208] For example, suppose there are two groups in conflict over the distribution of resources in a conflict area. In this system, the process proceeds as follows:

[1209] 1. Data collection: The server automatically collects the latest conflict-related news from the news API, along with official government statements and reports from international organizations.

[1210] 2. Data analysis: The server uses NLP algorithms to analyze the collected text data and extract information such as "The main cause of the conflict between Group A and Group B is resource allocation." It also performs sentiment analysis and obtains results such as "Group A feels strong anger."

[1211] 3. Proposal Generation: Based on the analysis results, the server proposes the establishment of a third-party organization to ensure fair resource distribution. The proposal document also includes a specific operating scheme and funding plan.

[1212] 4. User interface: The device displays the proposals on a dashboard, along with graphs and charts. Users (representatives of international organizations) can view the proposals and provide feedback, such as "international experts should be included in the third-party organization."

[1213] 5. Feedback processing and integration: The server receives the feedback and updates the proposal document, reflecting the suggested change: "The third-party body should include international experts."

[1214] In this way, the system generates efficient and neutral proposals and supports conflict resolution by incorporating user feedback.

[1215] The processing flow will be explained below.

[1216] Step 1: Start collecting data

[1217] The server sends requests to API endpoints of authoritative data sources to retrieve the latest conflict-related data, collating data from news sites, reports from international organizations, government statements, social media posts, and more.

[1218] Step 2: Save your data

[1219] The server stores the collected data in a cloud-based database in structured formats such as JSON and CSV.

[1220] Step 3: Text analysis

[1221] The server applies natural language processing (NLP) algorithms to the stored data to extract key actors, sources of conflict, and sentiment from the text data, including extracting key events and important keywords.

[1222] Step 4: Sentiment analysis

[1223] Based on the text analysis results, the server uses a sentiment analysis tool to classify and assess the emotions of each participant, using algorithms to identify emotional expressions in the text and distinguish between anger, frustration, hope, etc.

[1224] Step 5: Trend analysis and visualization

[1225] The server performs trend analysis on the analyzed data and generates graphs and charts that visualize changes and patterns over time, allowing users to understand the development and trends of the conflict at a glance.

[1226] Step 6: Proposal Generation

[1227] The server automatically generates neutral and logical proposals based on the results of text and sentiment analysis, including concrete action plans and strategies.

[1228] Step 7: Providing a User Interface

[1229] The device displays a user-accessible dashboard that displays analysis results, recommendations, trend graphs, and more.

[1230] Step 8: Gather feedback

[1231] Users can provide reviews and feedback on the suggestions provided through a feedback form on the dashboard, including suggested modifications and opinions.

[1232] Step 9: Feedback analysis

[1233] The server analyzes the feedback collected from users, understands the intent of the feedback and the suggestions, and identifies which parts of the suggestions need to be revised.

[1234] Step 10: Update your proposal

[1235] The server updates the proposal document based on the feedback, and the revised proposal is again presented through the user interface and displayed for the user to review and evaluate.

[1236] Step 11: Final confirmation of feedback

[1237] Users review the updated proposal and provide further feedback if necessary, and this process continues until a final consensus is reached.

[1238] Through this series of processes, the system has the ability to effectively support dialogue and negotiation and promote conflict resolution.

[1239] Example 1

[1240] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1241] Current dispute resolution support systems often lack efficient data collection, analysis, proposal generation, and feedback processing, making it difficult to provide fast and accurate dispute resolution solutions. Furthermore, they lack the ability to properly analyze collected information and generate neutral proposals, which can lead to biased solutions. Furthermore, systems for collecting and incorporating user feedback through a user interface are inadequate. The objective of the present invention is to solve these problems.

[1242] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1243] In this invention, the server includes means for automatically collecting information from data sources, means for storing the collected information in a cloud-based database, means for analyzing the collected information to extract key stakeholders, causes of conflicts, and emotions, means for generating neutral proposals based on the analysis results, means for providing the proposals through a user interface and collecting feedback from users, and means for reflecting the collected feedback in improving the analysis and proposals, thereby enabling efficient generation of neutral proposals and rapid reflection of user feedback.

[1244] "Data Source" means an external information source that provides information in a variety of formats.

[1245] An "automated collection means" is a mechanism for obtaining data without requiring manual input from a user.

[1246] A "cloud-based database" is a data management system that operates over the internet and stores data on a remote server.

[1247] "Means for analyzing collected information" are methods and algorithms used to understand, classify, and extract meaning from collected data.

[1248] "Key Stakeholders" refers to individuals or organizations that play a significant role in a particular event or issue.

[1249] "Causes of conflict" refers to the underlying factors or reasons that cause conflict or disputes.

[1250] "Means for extracting emotions" are algorithms and tools for identifying and analyzing emotions and sentiments from text data.

[1251] A "neutral proposal" is one that does not favor any particular position and presents a solution that is fair to all parties involved.

[1252] "User interface" refers to the graphical screen or dashboard that allows users to interact with the system and manipulate and view information.

[1253] "Feedback" refers to response information such as opinions, evaluations, and suggested revisions provided by users.

[1254] A "means for improving recommendations" is a process or algorithm for modifying or updating initial recommendations based on collected feedback.

[1255] The present invention provides a system for supporting dispute resolution through data collection, proposal generation, feedback collection via a user interface, and analysis. Specific embodiments of this system will be described below.

[1256] System Overview

[1257] The system consists of the following main components:

[1258] Data collection

[1259] The server automatically collects information from data sources such as news sites, reports from international organizations, government statements, and social media. This process involves calling APIs and web scraping techniques. The collected data is then stored in a cloud-based database. For example, the requests library is used to call the API and BeautifulSoup is used for web scraping.

[1260] Data analysis

[1261] The server uses natural language processing (NLP) algorithms to analyze the collected data. This extracts key stakeholders, sources of conflict, and sentiment from the text data. It also uses sentiment analysis tools to determine sentiment within the text and generate graphs and charts to visualize data trends. Specifically, it uses NLP libraries (e.g., NLTK, spaCy) and sentiment analysis tools such as VADER and TextBlob.

[1262] Proposal generation

[1263] The server generates neutral and logical proposals based on the analysis results, including specific action plans and recommended strategies. The proposal documents are automatically generated and provided through a user interface. This process uses generative AI models, such as OpenAI's GPT model.

[1264] User Interface

[1265] The terminal displays an interactive dashboard for users to view the proposals and provide feedback. The user interface includes graphs and charts that visually display the analysis results and proposals. Users can also provide opinions and corrections to the proposals using a feedback form. Front-end frameworks such as React.js are used.

[1266] Feedback Processing and Integration

[1267] The server analyzes the collected feedback and updates the recommendations. This process results in more relevant and actionable recommendations that reflect user input. The generated AI model is then used again, and the updates are displayed in the user interface using a front-end framework.

[1268] Specific examples

[1269] For example, if there are two groups in conflict over the distribution of resources in a conflict area, the process would proceed as follows:

[1270] 1. Data Collection:

[1271] The server automatically collects the latest conflict-related news from a news API, simultaneously retrieving official government statements and reports from international organizations.

[1272] 2. Data Analysis:

[1273] The server uses an NLP algorithm to analyze the text data, extracting information such as "The main cause of the conflict between Group A and Group B is resource allocation," and performs sentiment analysis to obtain results such as "Group A feels strong anger."

[1274] 3. Proposal generation:

[1275] Based on the analysis results, the server will propose the establishment of a third-party organization to ensure fair distribution of resources, and will include a specific operating scheme and funding plan.

[1276] 4. User Interface:

[1277] The device displays the recommendations on a dashboard, complete with graphs and charts, and users can view the recommendations and provide feedback, such as "The third-party organization should include international experts."

[1278] 5. Feedback processing and integration:

[1279] The server receives the feedback and uses the generative AI model to update the proposal document, including the suggested change that the third-party body should include international experts.

[1280] Prompt Sentence Examples

[1281] The following prompt sentences can be input into the generative AI model to analyze and generate suggestions:

[1282] Get the latest news data, extract the key causes of conflict for a particular dispute, analyze the sentiment behind the conflict, and recommend solutions.

[1283] Data sources: news sites, official reports from international organizations, government statements

[1284] In this way, the system generates efficient and neutral proposals and supports conflict resolution by incorporating user feedback.

[1285] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1286] Step 1: Automated data collection

[1287] What it does: The server collects the latest information from reliable data sources such as news sites, official reports from international organizations, government statements, and social media. For example, it uses the requests library to call news APIs and BeautifulSoup to scrape data from official reporting sites. The input to this process is the URL and API key of the data source, and the output is the collected raw data.

[1288] Step 2: Save your data

[1289] What happens: The server stores the collected data in a cloud-based database, such as AWS's RDS or Google Cloud's BigQuery, by executing a SQL query to insert the data. The input to this process is the raw data obtained in step 1, and the output is structured data stored in the database.

[1290] Step 3: Data analysis

[1291] What it does: The server analyzes the collected data using NLP algorithms. Specifically, it uses NLP libraries (e.g., NLTK, spaCy) to extract key players, conflict causes, and sentiment from the text data. For sentiment analysis, it uses VADER and TextBlob. The input to this process is the structured data saved in step 2, and the output is the analysis results, such as conflict causes and sentiment.

[1292] Step 4: Generate graphs and charts

[1293] Specific operation: The server generates graphs and charts to visualize data trends based on the analysis results. Specifically, it visualizes the data using Python's matplotlib and seaborn. The input to this process is the analysis results obtained in step 3, and the output is the generated graphs and charts.

[1294] Step 5: Proposal Generation

[1295] Specific operation: The server generates neutral and logical proposals based on the analysis results. Using a generative AI model (e.g., OpenAI's GPT model), it automatically generates a proposal document containing a specific action plan and recommended strategies. The input to this process is the analysis results obtained in Step 3, and the output is the generated proposal document.

[1296] Step 6: Displaying the User Interface

[1297] Specific operation: The terminal displays an interactive dashboard for users to view the proposals and provide feedback. A front-end framework such as React.js is used to visually display the analysis results and proposals. Users can also enter their opinions and corrections using a feedback form. The input of this process is the proposal document and visualized graphs and charts generated in step 5, and the output is the user's feedback.

[1298] Step 7: Collect and analyze feedback

[1299] What happens: The server analyzes the feedback collected from the user and updates the proposal. It uses the generative AI model again to generate more appropriate and actionable proposals. The input to this process is the user feedback obtained in step 6, and the output is the updated proposal document.

[1300] Step 8: Redistribute the updated proposal

[1301] Specific operation: The server delivers the updated proposal document back to the user interface, allowing the user to view the latest proposal content. Using React.js, the updated proposal document is displayed on a dashboard. The input of this process is the updated proposal document generated in step 7, and the output is a dashboard containing the updated proposal content.

[1302] (Application example 1)

[1303] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1304] Modern society requires real-time conflict monitoring and rapid resolution support. Conflicts and disputes at event venues and other public spaces must be resolved as quickly as possible, but conventional systems have struggled to respond quickly and appropriately. There was also a need for a system that could efficiently analyze data collected in real time, generate appropriate proposals based on the results, and improve those proposals by incorporating feedback.

[1305] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1306] In this invention, the server includes means for automatically collecting information from data sources, means for analyzing the collected information to extract key stakeholders, causes of conflict, and emotions, means for generating neutral proposals based on the analysis results, means for providing the proposals through a user interface and collecting feedback from users, means for reflecting the collected feedback in improving the analysis and proposals, means for recording the surrounding situation and converting it into text using a voice recognition function, and means for displaying the analysis results and proposals on a display in real time, thereby enabling the system to instantly grasp the local situation, generate and provide appropriate countermeasures in real time, and quickly reflect user feedback.

[1307] "Data sources" refers to reliable sources for gathering information, such as news sites, official reports, government statements, and social media.

[1308] "Means of automatically collecting information" refers to technologies for automatically obtaining information from data sources, such as by calling APIs or using web scraping techniques.

[1309] "Key actors" refer to important people or groups in a conflict or conflict situation.

[1310] "Causes of conflict" refers to the main reasons or factors behind conflict or confrontation.

[1311] "Means of extracting emotions" refers to technology that uses natural language processing algorithms and emotion analysis tools to determine emotions from text data and audio data.

[1312] A "neutral proposal" refers to a specific action plan or recommended strategy that aims to solve a problem in an impartial and logical manner, without favoring any particular position.

[1313] "User interface" refers to the interactive screen or operating environment that allows a user to interact with a system.

[1314] "Feedback" refers to users' opinions and requests for corrections regarding the proposal.

[1315] "Recording and voice recognition function" refers to technology that uses a camera and microphone to record the surrounding situation and converts the voice data into text data.

[1316] "Display" means a screen or display device for visually presenting information or offers.

[1317] This invention is a system that supports real-time dispute resolution through data collection, proposal generation, feedback collection and analysis via a user interface. A specific embodiment for realizing this system will be described below.

[1318] Overall structure

[1319] The server automatically collects information from data sources, analyzes the collected information to extract key stakeholders, sources of conflict, and sentiment, then generates neutral proposals based on the analysis results and provides them through a user interface. Users provide feedback on the proposals through the user interface, and the server analyzes this feedback and updates the proposals.

[1320] Data collection

[1321] The servers automatically collect information from trusted data sources such as news sites, official reports, government statements, social media, etc. The data is retrieved using API calls and web scraping techniques and stored in a cloud-based database.

[1322] Data analysis

[1323] The collected data is analyzed using a server-based natural language processing (NLP) algorithm to extract key stakeholders, sources of conflict, and sentiment. Sentiment analysis tools are also used to identify sentiment within the text and generate graphs and charts to visualize trends in the data. Specifically, Google NLP APIs and sentiment analysis tools are used.

[1324] Proposal generation

[1325] Based on the analysis results, the server generates neutral and logical proposals, including specific action plans and recommended strategies, and automatically generates proposal documents using a generative AI model.

[1326] User Interface

[1327] The device displays an interactive dashboard where users can view the recommendations and provide feedback. The dashboard includes graphs and charts visually illustrating the analysis results and recommendations. When using smart glasses, this information is displayed in real time on the display. Using voice recognition, the device converts the user's speech into text, allowing feedback to be provided via the operation panel.

[1328] Feedback Processing and Integration

[1329] The server analyzes the collected feedback and updates the suggestions. This process results in more appropriate and effective suggestions that reflect user opinions. For example, the feedback is managed using the Firebase database.

[1330] Specific examples

[1331] For example, a system for resolving conflict situations in real time at an event venue works as follows: A security officer wearing smart glasses records the conflict and converts the conversation into text using a voice recognition API. The server analyzes the video using an NLP algorithm and identifies "insufficient visitor number control" as the cause of the conflict. Based on the analysis results, the server generates a recommendation to "set up a counter and assign additional staff" and displays it on the smart glasses' display. The security officer provides feedback, and the server updates the recommendation accordingly.

[1332] Prompt Sentence Examples

[1333] Event A and Event B are in conflict. The main cause is a lack of coordination on the number of attendees. Please suggest a solution.

[1334] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1335] Step 1: Data collection

[1336] The server automatically collects information from data sources, such as news sites, official reports, government statements, and social media, using API calls and web scraping techniques. This data is then stored in a cloud-based database. The input for the collected data is the API calls and web scraping, and the output is the data stored in the cloud database.

[1337] Step 2: Surroundings recording and voice recognition

[1338] The smart glasses, which serve as the device, record the surrounding situation and collect audio using a microphone. The collected audio data is converted into text using a speech recognition API. The input is camera footage and audio data, and the output is text-formatted conversation data. This makes it possible to grasp the situation in real time.

[1339] Step 3: Data analysis

[1340] The server uses natural language processing (NLP) algorithms to analyze the collected data, extracting key players, causes of conflict, and sentiment from the text data. The input is text data, and the output is information on key players, causes of conflict, and sentiment. Specifically, it uses Google NLP API and sentiment analysis tools.

[1341] Step 4: Proposal Generation

[1342] The server generates neutral and logical proposals based on the analysis results. These are automatically generated as proposal documents using a generative AI model. The input is the analysis results, and the output is the proposal document. For example, from the analysis result of "insufficient visitor number adjustment," the server generates a specific proposal such as "install a counter and assign additional staff."

[1343] Step 5: Display the user interface

[1344] The smart glasses, which are the terminals, display the proposals in real time. The analysis results and proposals are visualized as graphs and charts. The inputs are the proposal documents and analysis results, and the output is the information displayed on the screen. The user can provide feedback using the operation panel on the glasses.

[1345] Step 6: Feedback collection and analysis

[1346] The server collects and analyzes feedback provided by users. The input of the feedback is text data from the user, and the output is the analyzed feedback information. Specifically, the feedback is managed via the Firebase database.

[1347] Step 7: Improve and update your proposal

[1348] The server updates the proposal document based on the analyzed feedback, resulting in a more appropriate proposal that reflects user input. The input is the feedback information, and the output is an updated proposal document. For example, a new proposal reflecting "allocation of additional staff" is generated.

[1349] This processing step allows the system to efficiently execute a series of processes: grasping the situation in real time, making appropriate suggestions, providing them to the user, and incorporating the feedback.

[1350] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1351] This invention is a system that supports conflict resolution by recognizing user emotions through data collection, proposal generation, feedback collection and analysis via a user interface, and a combination of an emotion engine. Specific embodiments of this system are described below.

[1352] System Overview

[1353] Data collection

[1354] The server automatically collects information from trusted data sources (news sites, official reports from international organizations, government statements, social media, etc.) using API calls and web scraping techniques, and stores the collected data in a cloud-based database.

[1355] Data analysis

[1356] The server uses natural language processing (NLP) algorithms to analyze the collected data, extracting key stakeholders, sources of conflict, and sentiment from the text data, and employs sentiment analysis tools to determine sentiment within the text and generate graphs and charts to visualize trends in the data.

[1357] Proposal generation

[1358] The server generates neutral and logical proposals based on the analysis results, including specific action plans and recommended strategies. The proposal documents are automatically generated and provided through a user interface.

[1359] User Interface

[1360] The device displays an interactive dashboard for users to view the proposals and provide feedback. The user interface includes graphs and charts that visually represent the analysis results and proposals. Users can also provide comments and corrections to the proposals using a feedback form.

[1361] Feedback Processing and Integration

[1362] The server analyzes the collected feedback and updates the recommendations, a process that results in better, more effective recommendations that reflect user input.

[1363] Emotion Engine Functions

[1364] The server uses an emotion engine to perform emotion analysis on the feedback provided by the user, allowing the server to recognize the user's emotional state in real time and display it on a dashboard. The emotion engine uses natural language processing techniques to identify, classify, and rate emotional expressions in the text.

[1365] Specific examples

[1366] For example, the following is a series of processes that may be applied to a conflict zone where two groups are in conflict over the allocation of resources.

[1367] 1. Data Collection:

[1368] The server automatically collects the latest conflict-related news from a news API, along with official government statements and reports from international organizations.

[1369] 2. Data Analysis:

[1370] The server uses an NLP algorithm to analyze the collected text data and extract information such as "The main cause of the conflict between Group A and Group B is resource allocation." It also performs sentiment analysis and obtains results such as "Group A feels strong anger."

[1371] 3. Proposal generation:

[1372] Based on the analysis results, the server will propose the establishment of a third-party organization to ensure the fair distribution of resources. The proposal document will also include a specific operating scheme and funding plan.

[1373] 4. User Interface:

[1374] The device displays the proposals on a dashboard, along with graphs and charts. Users (representatives of international organizations) can view the proposals and provide feedback, such as "The third-party organization should also include international experts."

[1375] 5. Feedback processing and integration:

[1376] The server receives the feedback and updates the proposal document, reflecting the revised suggestion that "the third-party body should include international experts."

[1377] 6. Use of Emotion Engine:

[1378] The server uses an emotion engine to analyze the emotions of the feedback provided by the user. For example, if emotions such as "anger" or "dissatisfaction" are detected, this is reflected in the dashboard, visually displaying the emotions with which the user is providing feedback.

[1379] In this way, a system incorporating an emotion engine can generate efficient and neutral suggestions, reflect user feedback, and more effectively support conflict resolution by recognizing and displaying user emotions in real time.

[1380] The processing flow will be explained below.

[1381] Step 1:

[1382] The server uses API calls and web scraping techniques to automatically collect information from reliable data sources (news sites, official reports from international organizations, government statements, social media, etc.) and stores the collected data in a cloud-based database.

[1383] Step 2:

[1384] The server applies natural language processing (NLP) algorithms to the stored data to extract key stakeholders, sources of conflict, and sentiment from the text data. Specifically, it extracts key events and important keywords from the collected text data.

[1385] Step 3:

[1386] The server uses a sentiment analysis tool based on the text analysis results to classify and evaluate the emotional expressions in the text, identifying emotions such as anger, frustration, and hope, and storing the emotional state as data.

[1387] Step 4:

[1388] The server performs trend analysis on the analyzed data and generates graphs and charts that visualize changes and patterns over time, allowing users to understand the development and trends of the conflict at a glance.

[1389] Step 5:

[1390] The server automatically generates neutral and logical proposals based on the results of text and sentiment analysis, including the establishment of a third-party organization to ensure fair resource distribution, a specific operating scheme, and a funding plan.

[1391] Step 6:

[1392] The terminal displays a user-accessible dashboard that displays the analysis results, recommendations, trend graphs and charts generated by the server.

[1393] Step 7:

[1394] The terminal provides a feedback form for the user to view the proposal and to enter their opinions and suggestions for corrections to the proposal.

[1395] Step 8:

[1396] The server analyzes the feedback collected from users through the feedback form, and again uses NLP algorithms to analyze the text data in the feedback to identify which parts of the suggestion should be revised.

[1397] Step 9:

[1398] The server uses an emotion engine to analyze the emotion contained in the user's feedback in real time. The emotion engine performs emotion analysis on the user's feedback to determine the user's emotional state, such as anger or frustration.

[1399] Step 10:

[1400] The device displays the results of the emotion engine's analysis on a dashboard, which visually displays the emotional state of the feedback provided by the user.

[1401] Step 11:

[1402] The server updates the proposal document based on the analysis results and the emotion engine's evaluation results. The revised proposal is again presented through the user interface and displayed for the user to review and evaluate.

[1403] Step 12:

[1404] Users review the updated proposal and provide further feedback if necessary, repeating the process until a final consensus is reached.

[1405] In this way, a system incorporating an emotion engine can recognize users' emotions in real time, provide efficient and neutral suggestions, and support optimal conflict resolution.

[1406] Example 2

[1407] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1408] While conventional data collection and analysis systems can efficiently collect and analyze data, they lack the functionality to automatically generate specific and neutral proposals for conflict resolution, and to collect and incorporate user feedback. Furthermore, there is no mechanism for analyzing and incorporating the user's emotional state in real time, which means the quality and effectiveness of the proposals cannot be fully guaranteed.

[1409] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for automatically collecting information from data sources, means for analyzing the collected information to extract key stakeholders, causes of conflict, and emotions, means for generating neutral proposals based on the analysis results, means for providing proposals through a user interface and collecting feedback from users, means for reflecting the collected feedback in improving the analysis and proposals, and means for analyzing emotional expressions included in the feedback in real time and displaying them on a dashboard. This makes it possible to perform processes from data collection to analysis, proposal generation, feedback reflection, and real-time emotion analysis in a centralized and integrated manner.

[1410] "Data sources" refers to various media that provide information, such as news sites, official reports from international organizations, government statements, social media, etc.

[1411] "Means of collection" refers to technical devices or software for automatically obtaining information from data sources, such as by calling APIs or using web scraping techniques.

[1412] "Analyzing means" refers to technical devices or algorithms, in particular natural language processing (NLP) algorithms, used to process the collected data and extract the required information.

[1413] A "neutral proposal" refers to an action plan or strategy that is fair and objective, not influenced by any particular interest or bias.

[1414] "User interface" refers to the interface through which a user interacts with a machine, particularly the dashboard for displaying suggestions and collecting feedback.

[1415] "Feedback collection means" refers to any technological device or form for receiving comments or corrections to a proposal from users.

[1416] "Emotional expressions" refer to the emotional states that appear in text, specifically expressions that classify emotions such as "anger," "sadness," and "joy."

[1417] "Means for analyzing in real time and displaying on a dashboard" refers to a technological device or software that uses an emotion engine to instantly evaluate the emotion in the feedback and display it visually.

[1418] This invention is a system that supports conflict resolution by recognizing user emotions through data collection, proposal generation, feedback collection and analysis via a user interface, and a combination of an emotion engine. Specific embodiments of this system are described below.

[1419] Data collection

[1420] The server automatically collects information from reliable data sources (news sites, official reports from international organizations, government statements, social media, etc.) using API calls and web scraping techniques. Specifically, it uses a news API to retrieve data by calling the API, such as "https: / / newsapi.org / v2 / top-headlines?country=us&apiKey=YOUR_API_KEY." The retrieved data is then stored in a cloud-based database, such as Google Cloud Firestore or Amazon DynamoDB.

[1421] Data analysis

[1422] The server uses natural language processing (NLP) algorithms to analyze the collected data. Specifically, it preprocesses the text data using toolkits such as NLTK and SpaCy. It then applies NLP algorithms to extract key stakeholders and conflict sources. It also uses sentiment analysis tools (e.g., Sentiment Analysis API and TextBlob) to determine the sentiment within the text. The analysis results are visualized as graphs and charts using visualization libraries such as matplotlib and plotly.

[1423] As a concrete example, the server collects the latest conflict-related news via a news API and uses an NLP algorithm to extract information such as "The main cause of the conflict between Group A and Group B is resource allocation." It also performs sentiment analysis to obtain the result that "Group A feels strong anger."

[1424] Proposal generation

[1425] The server generates neutral and logical proposals based on the analysis results. For example, a generative AI model can be used to automatically generate a proposal document for "establishing a third-party organization to ensure the fair distribution of resources." The generated proposal document includes a specific operating scheme and funding plan. The proposal document is generated in HTML or PDF format and sent to the user interface.

[1426] As a specific example, the server proposes "the establishment of a third-party organization to ensure fair distribution of resources" based on the analysis results, and generates a document that includes the specific operating scheme and funding plan.

[1427] User Interface

[1428] The device displays an interactive dashboard for users to view and provide feedback on the proposals. The dashboard includes graphs and charts that visually represent the analysis results and proposals. Users can provide comments and corrections to the proposals using a feedback form.

[1429] For example, a user (representative of an international organization) can view the proposal through the dashboard and provide feedback such as, "The third-party organization should also include international experts."

[1430] Feedback Processing and Integration

[1431] The server analyzes the feedback collected from users and updates the proposals, generating more specific and effective proposals that reflect the user's opinions.

[1432] As a concrete example, the server analyzes the user's feedback "The third party should include international experts" and generates an updated document that reflects this.

[1433] Emotion Engine Functions

[1434] The server uses an emotion engine to perform emotion analysis on the feedback provided by the user. It identifies the user's emotional state in real time and displays it on a dashboard. The emotion engine uses natural language processing techniques to identify, classify, and rate emotional expressions in the text.

[1435] As a specific example, the server performs an emotional analysis of the feedback content, and if emotions such as "anger" or "dissatisfaction" are detected, they are displayed on the dashboard.

[1436] Example prompt for a generative AI model:

[1437] "The representative of international organization A has provided feedback on a proposal regarding resource allocation. Please analyze the representative's feedback using the sentiment engine and display it in real time on a dashboard."

[1438] The present invention is a system that more effectively supports conflict resolution by centrally performing data collection, analysis, proposal generation, feedback reflection, and sentiment analysis.

[1439] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1440] Program processing procedure and specific operations

[1441] Step 1: Data collection

[1442] 1. Input: URL and authentication information for news API or official report API

[1443] The server sets the URL and authentication information to call the API of a trusted data source (e.g., news site, official report from an international organization, government statement, social media).

[1444] 2. Operation: API calls and data retrieval

[1445] The server retrieves the latest information from the data source by making an API call, such as for the News API, using the URL "https: / / newsapi.org / v2 / top-headlines?country=us&apiKey=YOUR_API_KEY".

[1446] 3. Output: Acquired data

[1447] The acquired data is, for example, in JSON format.

[1448] 4. Operation: Data storage

[1449] The server stores the retrieved data in a cloud-based database such as Google Cloud Firestore or Amazon DynamoDB.

[1450] Step 2: Data analysis

[1451] 1. Input: Collected data (e.g., JSON format)

[1452] The server prepares the collected data for the NLP algorithms.

[1453] 2. Operation: Preprocessing text data

[1454] The server uses toolkits like NLTK or SpaCy to pre-process the data, removing unnecessary parts like advertisements and HTML tags.

[1455] 3. Action: Identifying key stakeholders and conflict sources

[1456] The server applies natural language processing algorithms to extract key players and sources of conflict from the text, e.g., "Group A and Group B are in conflict over resource allocation."

[1457] 4. Behavior: Sentiment analysis

[1458] The server uses sentiment analysis tools to identify emotional expressions in the text. For example, it uses the Sentiment Analysis API or TextBlob to analyze emotional data such as "Group A feels very angry."

[1459] 5. Output: Analysis results

[1460] Analysis results including information on extracted parties, conflict causes, emotional expressions, etc.

[1461] 6. Action: Visualizing data trends

[1462] The server visualizes the analysis results as graphs and charts using visualization libraries such as matplotlib and plotly.

[1463] Step 3: Proposal Generation

[1464] 1. Input: Analysis results

[1465] The server inputs the analysis results into a generative AI model.

[1466] 2. Action: Creating a proposal document

[1467] The server uses a generative AI model to automatically generate neutral and logical proposal documents, such as proposing the establishment of a third-party organization to ensure the fair distribution of resources.

[1468] 3. Output: Proposal document

[1469] The generated proposal document is in HTML or PDF format.

[1470] 4. Action: Proposal document distribution

[1471] The server sends the generated proposal document to the user interface.

[1472] Step 4: Display the user interface

[1473] 1. Input: Proposal document and analysis results

[1474] The terminal receives the proposed document and the analysis results.

[1475] 2. Action: Rendering a dashboard

[1476] The terminal displays an interactive dashboard as a user interface, which is implemented using frameworks such as Django or Flask.

[1477] 3. Action: Data Visualization

[1478] The terminal displays the data visualization results (graphs and charts) on a dashboard.

[1479] 4. Action: Providing a feedback form

[1480] The terminal displays a feedback form in which the user can provide comments and corrections to the proposal.

[1481] Step 5: Feedback processing and integration

[1482] 1. Input: User feedback

[1483] The server receives feedback from the user.

[1484] 2. Action: Feedback Analysis

[1485] The server analyzes the feedback and extracts specific opinions and suggested modifications.

[1486] 3. Action: Proposal document update

[1487] The server updates the proposal document based on the analysis, for example, to reflect the suggested revision that "the third-party body should include international experts."

[1488] 4. Output: Updated proposal document

[1489] The updated proposal document is again sent to the user interface and displayed.

[1490] Step 6: Functioning of the Emotion Engine

[1491] 1. Input: User feedback

[1492] The server inputs the user's feedback into the emotion engine.

[1493] 2. Action: Feedback sentiment analysis

[1494] The server uses an emotion engine to analyze the emotional state of the feedback, identifying emotions such as "anger" or "frustration."

[1495] 3. Output: Emotion analysis results

[1496] If sentiment analysis shows that the feedback is "angry," that information will be displayed on the dashboard.

[1497] 4. Action: Displaying Emotional State

[1498] The device displays the user's emotional state in real time on a dashboard, analyzed by the emotion engine. For example, if anger is detected, it is highlighted in red.

[1499] (Application example 2)

[1500] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1501] Frequent traffic congestion and accidents are increasing the stress and burden on drivers. Furthermore, there is a problem that drivers are unable to respond quickly to changes in traffic conditions, making it difficult to select the optimal route. Furthermore, there is a lack of systems that can grasp the driver's emotional state and make appropriate suggestions, preventing improvements in driving safety.

[1502] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1503] In this invention, the server includes: means for automatically collecting information from data sources; means for analyzing the collected information to extract key stakeholders, causes of conflict, and emotions; means for generating neutral proposals based on the analysis results; means for providing proposals through a user interface and collecting user feedback; means for reflecting the collected feedback in improving the analysis and proposals; means for analyzing traffic conditions in real time and proposing optimal routes; and means for analyzing the driver's emotional state and displaying the results. This makes it possible to quickly respond to traffic conditions in real time and propose optimal routes while reducing the driver's burden. Furthermore, making proposals based on the driver's emotional state can improve safety.

[1504] "Data Source" is a trusted source used to gather information (e.g., news sites, traffic APIs, social media, etc.).

[1505] "Means of automatically collecting information" refers to the process of asynchronously obtaining the necessary information from data sources using API calls or web scraping techniques.

[1506] "Means for analyzing collected information" refers to the process of using natural language processing algorithms and data mining techniques to extract key stakeholders, sources of conflict, and sentiment from the collected text data.

[1507] A "means for generating neutral proposals" is a process that automatically creates logical and effective proposals based on the results of data analysis, without any particular position or bias.

[1508] A "user interface" is an interactive interface through which a user can view information, receive suggestions, and provide feedback.

[1509] A "feedback collection method" is a form or interactive digital tool used to systematically collect user opinions and comments.

[1510] "Means for reflecting feedback in analysis and improvement of proposals" refers to the process of re-analyzing the data based on the feedback collected from users and updating the proposal content to make it more appropriate.

[1511] "Means of analyzing traffic conditions in real time" refers to the process of analyzing real-time data obtained from vehicle sensors and traffic information APIs to understand the current traffic situation.

[1512] "Means for proposing optimal routes" refers to the process of presenting optimal travel routes to drivers based on real-time data and analysis results.

[1513] "Means for analyzing the emotional state of a driver" refers to the process of using an emotion analysis tool to identify and evaluate the emotional state of a driver from the feedback and behaviors provided by the driver.

[1514] The "means for displaying the results" is a display or dashboard that visually shows the analyzed emotional state information to the driver in real time.

[1515] This invention is a system for autonomous vehicles that analyzes traffic conditions in real time and makes suggestions based on the driver's emotional state. The system has the functions of data collection, data analysis, suggestion generation, user interface, feedback processing and integration, and an emotion engine.

[1516] Data collection

[1517] The server collects data from vehicle sensors (cameras, LiDAR, GPS, etc.) and traffic information APIs (e.g., popular traffic information providers) in real time, using API calls and data streaming techniques.

[1518] Data analysis

[1519] Data collected from vehicle sensors and traffic information APIs is sent to a server where it is analyzed using natural language processing (NLP) algorithms and data mining techniques, such as extracting key stakeholders, sources of conflict, and sentiment from text data. For sentiment analysis, TextBlob and other AI-based sentiment analysis tools are used.

[1520] Proposal generation

[1521] The server generates neutral and effective suggestions based on the analysis results. These include optimal routes, workarounds, and break suggestions. During this process, a generative AI model (e.g., GPT-3) is used to automatically generate the suggestions. A specific example is the optimal route suggestion.

[1522] User Interface

[1523] The device displays information on the vehicle's dashboard or head-up display. Recommendations and analysis results are presented visually, and the driver can provide feedback using the touch panel or voice commands. This feedback is used to improve the recommendations.

[1524] Feedback Processing and Integration

[1525] The server analyzes the collected feedback and generates more appropriate and effective suggestions through a process of updating the suggestions, using natural language processing algorithms to analyze the feedback text.

[1526] Emotion Engine Functions

[1527] The server uses an emotion engine to determine the driver's emotional state in real time from feedback and behavioral data, and displays the results on a dashboard. If the driver is tired, the server suggests taking a break. This process is important for improving driving safety.

[1528] Specific examples

[1529] For example, to generate optimal route suggestions to avoid traffic jams, the following prompt sentences are input into the generative AI model:

[1530] Example prompt sentence:

[1531] "Please suggest the best route based on the latest traffic data. Use the following information: Sensor data: [data], Traffic information from API: [data]"

[1532] This allows the system to utilize generative AI models to suggest appropriate routes, reducing the burden on the driver.

[1533] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1534] Step 1:

[1535] Data collection

[1536] The server collects real-time sensor data and traffic information data from vehicle sensors (cameras, LiDAR, GPS, etc.) and traffic information APIs, periodically obtains the latest traffic information using API calls and data streaming technology, and integrates this data.

[1537] Input: Data from vehicle sensors, data from traffic information API

[1538] Output: Integrated real-time traffic data

[1539] Step 2:

[1540] Data analysis

[1541] The server analyzes the collected traffic data using natural language processing (NLP) algorithms and data mining techniques. The analysis of the data extracts key stakeholders, sources of conflict, and sentiment. Sentiment analysis tools (e.g., TextBlob) are used to detect emotional states within the data.

[1542] Input: Integrated real-time traffic data

[1543] Output: Analysis results (key players, causes of conflict, emotional state)

[1544] Step 3:

[1545] Proposal Generation

[1546] The server generates optimal routes and solutions to avoid traffic problems based on the results of data analysis. During this process, a generative AI model (e.g., GPT-3) is used to automatically generate suggested text. For example, the prompt "Please suggest the optimal route" is input into the generative AI model, and the optimal route is output as a suggested output.

[1547] Input: Analysis results

[1548] Output: Auto-generated suggestion

[1549] Step 4:

[1550] User Interface Display

[1551] The device visually displays the suggestions and analysis results on the vehicle's dashboard or head-up display, and the driver receives the suggestions via touch panel or voice command and provides feedback as needed, which is also collected.

[1552] Input: Auto-generated proposal, analysis results

[1553] Output: Display on dashboard or heads-up display, collected feedback

[1554] Step 5:

[1555] Handling feedback and improving suggestions

[1556] The server analyzes the feedback collected from the driver and reflects it in the next suggestion. It uses a natural language processing algorithm to analyze the feedback text and update the suggestion to make it more appropriate.

[1557] Input: Collected feedback

[1558] Output: Improved suggestion

[1559] Step 6:

[1560] Sentiment engine analysis and display

[1561] The server uses an emotion engine to determine the driver's emotional state in real time from their feedback and behavioral data, and the results are displayed on the dashboard or HUD, suggesting a break if the driver is tired, for example.

[1562] Input: Feedback and behavioral data

[1563] Output: Emotional state analysis results, displayed on dashboard or heads-up display

[1564] In this way, each step works together to create a system that optimizes traffic conditions in real time and makes suggestions that take into account the driver's emotional state.

[1565] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1566] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1567] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1568] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1569] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1570] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1571] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1572] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1573] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1574] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1575] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1576] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1577] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1578] 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.

[1579] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1580] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1581] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1582] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1583] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1584] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1585] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1586] The following is further disclosed regarding the above embodiment.

[1587] (Claim 1)

[1588] means for automatically collecting information from data sources; and

[1589] a means of analyzing the collected information to extract key players, sources of conflict, and sentiment;

[1590] a means for generating neutral recommendations based on the analysis results;

[1591] a means for providing suggestions and collecting feedback from users through a user interface;

[1592] A means to incorporate collected feedback into analysis and improvement of recommendations;

[1593] A system including:

[1594] (Claim 2)

[1595] 10. The system of claim 1, further comprising: generating graphs and charts for visualizing the suggestions.

[1596] (Claim 3)

[1597] 10. The system of claim 1, wherein the analysis module uses natural language processing algorithms.

[1598] "Example 1"

[1599] (Claim 1)

[1600] means for automatically collecting information from data sources; and

[1601] a means for storing the collected information in a cloud-based database;

[1602] a means of analyzing the collected information to extract key players, sources of conflict, and sentiment;

[1603] a means for generating neutral recommendations based on the analysis results;

[1604] a means for providing suggestions and collecting feedback from users through a user interface;

[1605] A means to incorporate collected feedback into analysis and improvement of recommendations;

[1606] A system including:

[1607] (Claim 2)

[1608] 10. The system of claim 1, further comprising: generating graphs and charts for visualizing the suggestions.

[1609] (Claim 3)

[1610] 10. The system of claim 1, wherein the analysis module uses a natural language processing algorithm and provides a suggested document generated using a generation algorithm.

[1611] "Application Example 1"

[1612] (Claim 1)

[1613] means for automatically collecting information from data sources; and

[1614] a means of analyzing the collected information to extract key players, sources of conflict, and sentiment;

[1615] a means for generating neutral recommendations based on the analysis results;

[1616] a means for providing suggestions and collecting feedback from users through a user interface;

[1617] A means to incorporate collected feedback into analysis and improvement of recommendations;

[1618] A means of recording the surrounding situation and converting it into text using voice recognition;

[1619] a means for displaying the analysis results and suggestions on a display in real time;

[1620] A system including:

[1621] (Claim 2)

[1622] 10. The system of claim 1, further comprising: generating graphs and charts for visualizing the suggestions.

[1623] (Claim 3)

[1624] 10. The system of claim 1, wherein the analysis module uses natural language processing algorithms.

[1625] "Example 2: Combining Emotion Engines"

[1626] (Claim 1)

[1627] means for automatically collecting information from data sources; and

[1628] a means of analyzing the collected information to extract key players, sources of conflict, and sentiment;

[1629] a means for generating neutral recommendations based on the analysis results;

[1630] a means for providing suggestions and collecting feedback from users through a user interface;

[1631] A means to incorporate collected feedback into analysis and improvement of recommendations;

[1632] A means to analyze the emotional expressions contained in the feedback in real time and display them on a dashboard;

[1633] A system including:

[1634] (Claim 2)

[1635] 10. The system of claim 1, further comprising: generating graphs and charts for visualizing the suggestions.

[1636] (Claim 3)

[1637] 10. The system of claim 1, wherein the analysis module uses natural language processing algorithms.

[1638] "Application example 2 when combining emotion engines"

[1639] (Claim 1)

[1640] means for automatically collecting information from data sources; and

[1641] a means of analyzing the collected information to extract key players, sources of conflict, and sentiment;

[1642] a means for generating neutral recommendations based on the analysis results;

[1643] a means for providing suggestions and collecting feedback from users through a user interface;

[1644] A means to incorporate collected feedback into analysis and improvement of recommendations;

[1645] A means of analyzing traffic conditions in real time and proposing optimal routes,

[1646] means for analyzing the emotional state of the driver and displaying the results;

[1647] A system including:

[1648] (Claim 2)

[1649] 10. The system of claim 1, further comprising: generating graphs and charts for visualizing the suggestions.

[1650] (Claim 3)

[1651] 10. The system of claim 1, wherein the analysis module uses natural language processing algorithms. [Explanation of symbols]

[1652] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for automatically collecting information from data sources; and a means of analyzing the collected information to extract key players, sources of conflict, and sentiment; a means for generating neutral recommendations based on the analysis results; a means for providing suggestions and collecting feedback from users through a user interface; A means to incorporate collected feedback into analysis and improvement of recommendations; A system including:

2. The system of claim 1 , which generates graphs and charts for visualizing the suggestions.

3. The system of claim 1 , wherein the analysis module uses natural language processing algorithms.

Images