system

Abstract

We provide the system. [Solution] A means of automatically obtaining data from publicly available information sources on the internet, A means for preprocessing acquired data and extracting relevant information, Means for analyzing anti-social force networks and identifying related individuals or organizations, A means of updating the decision logic using a reinforcement learning algorithm, A system that includes a means to assess risk based on input of business partner information and display the results.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] While companies and local governments need to cut off their relations with antisocial forces, the checks for confirming these relations in conventional methods are inaccurate and require a great deal of labor and time. For this reason, there is a need for means to efficiently and accurately determine the relevance to antisocial forces and support the cut-off of relations.

Means for Solving the Problems

[0005] This invention automatically acquires data from publicly available information sources on the internet, preprocesses the collected data to extract relevant information, and further analyzes the network of anti-social forces, updating the judgment logic using a reinforcement learning algorithm to identify relevant individuals or organizations. By providing a system that instantly determines the risk when business partner information is entered and visually presents the results to the user, these problems are solved.

[0006] "Publicly available information sources on the internet" refer to information sources that are publicly available and accessible, such as news articles, social media, and government and corporate databases.

[0007] "Means of automatically acquiring data" refers to functions that automatically collect information from the internet using web crawlers or APIs.

[0008] "Preprocessing" refers to the process of removing noise and normalizing raw data to prepare it for analysis in a suitable format.

[0009] "Means for extracting relevant information" refers to algorithms or processes that select and obtain information from collected data that is relevant to a specific purpose.

[0010] "Methods for analyzing antisocial force networks" refer to techniques that analyze the relationships between individuals and organizations with antisocial characteristics and reveal their network structure.

[0011] A "reinforcement learning algorithm" is a type of machine learning that learns from past experiences and sequentially improves decision-making.

[0012] "Methods for updating the judgment logic" refers to the process of using reinforcement learning to keep the judgment algorithm constantly up-to-date and improve its accuracy.

[0013] A "means for determining risk" refers to a system that has the function of evaluating the presence and degree of risk based on the input information.

[0014] "Visual display methods" refer to methods of displaying risk assessment results using colors, graphs, etc., so that users can understand them intuitively. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

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

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

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

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

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

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

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

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

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

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

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

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

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

[0036] To implement this invention, a system based on interaction between a server, a terminal, and a user will be constructed. The server will have the function of automatically collecting data from various information sources on the internet. This includes news, social networking services, and publicly available government databases. The data types include text, images, and audio, which will be pre-processed after being taken into the server.

[0037] The pre-processed data is analyzed by a network analysis algorithm running on the server. This analysis algorithm constructs a network of anti-social forces and identifies related individuals and organizations. Furthermore, reinforcement learning is incorporated into this process, updating the judgment logic using historical data to improve accuracy over time.

[0038] The user enters the name of the business partner and related information via a terminal. The terminal sends this information to a server, which immediately determines the risk based on the received information. The result is returned to the terminal and presented to the user. The display visually indicates the risk level, using colors and graphical indicators to present it in a format that is easy for the user to intuitively understand.

[0039] For example, if a user enters a company name, the server uses previously collected data to investigate its connection to that company. Network analysis determines that the company is linked to a specific anti-social group, and a risk score is calculated based on the level of risk. The terminal classifies this score as "high risk," "medium risk," or "low risk" and warns the user with a color-coded signal.

[0040] This system enables companies and local governments to efficiently and accurately detect relevant risks and sever unnecessary relationships early on.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server automatically collects data from publicly available sources on the internet. It retrieves text, images, and audio data from news articles, social media, and government databases, and stores them in storage.

[0044] Step 2:

[0045] The server preprocesses the collected data. Text data undergoes noise reduction and normalization, while image and audio data are subjected to feature extraction. This prepares the data for analysis in a suitable format.

[0046] Step 3:

[0047] The server performs network analysis using pre-processed data. Utilizing natural language processing techniques, it extracts individuals and organizations associated with anti-social forces from text data and constructs a network structure.

[0048] Step 4:

[0049] The server uses a reinforcement learning algorithm to update its decision logic. It references past data and results to make adjustments to improve the accuracy of the decision process.

[0050] Step 5:

[0051] The user enters customer information on their terminal. The terminal sends this information to the server and requests a real-time risk assessment.

[0052] Step 6:

[0053] The server performs a risk assessment based on the received information. It refers to relevant network information and analyzes and generates a risk score for a specific business partner.

[0054] Step 7:

[0055] The server sends the assessment results to the terminal. This includes risk scores and information about related individuals and organizations.

[0056] Step 8:

[0057] The device visually displays the received risk assessment results to the user. It provides color-coded indicators based on score levels and detailed information, allowing the user to intuitively understand the risk.

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] In society and for businesses, it is crucial to detect early on if business partners or related entities are involved with groups considered socially dangerous, and to assess the risks in advance. Traditional methods have been problematic due to the time-consuming nature of information gathering and analysis, as well as the inconsistent accuracy of risk assessments. Therefore, there is a need to provide a system that can quickly and accurately determine risks and present them in a visually easy-to-understand format.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes means for automatically collecting information from public sources, means for preprocessing the collected information and extracting relevant content, means for analyzing networks of socially dangerous groups and identifying relevant entities, means for dynamically improving the judgment logic using a computer learning algorithm, means for evaluating risk by inputting transaction-related information and outputting the evaluation results, means for visually outputting the evaluation results and presenting the risk level to the user using color, and means for displaying a list of important entities and key related information based on the evaluation. This enables rapid and accurate risk assessment and allows users to intuitively understand the degree of risk.

[0063] "Public information sources" generally refer to information sources that are accessible on the internet, such as news sites, social media, and government databases.

[0064] "Preprocessing" refers to the process of removing noise from collected raw data and preparing it in a format suitable for data analysis.

[0065] A "socially dangerous group" refers to an organization or group that has the potential to cause legal or moral harm to society.

[0066] A "computer learning algorithm" refers to a mathematical process by which a computer uses data to learn empirically and make predictions and decisions.

[0067] "Decision logic" refers to a set of criteria used to evaluate risk and relevance based on data.

[0068] "Visual output" refers to displaying results in a way that is easy for users to understand intuitively, typically using colors and shapes.

[0069] "Key actors" refer to influential individuals or organizations identified based on network analysis results.

[0070] To implement this invention, a system based on interaction between a server, a terminal, and a user is constructed. The server plays a central role in information gathering and analysis. Specifically, the server automatically collects information periodically from news sites, social networking services, and government databases on the internet by executing a crawler program. This process often utilizes scraping techniques using scripting languages ​​such as Python and JavaScript (registered trademark).

[0071] The server preprocesses the collected data. This includes formatting the data using data processing libraries such as Python's pandas and numpy, and removing irrelevant elements. For image and audio data, feature extraction and speech recognition technologies using OpenCV and TENSORFLOW® are applied.

[0072] Furthermore, the server utilizes libraries such as scikit-learn and NetworkX to execute network analysis algorithms. This allows it to identify related keywords, individuals, and organizations from the collected data and analyze networks of groups considered socially dangerous. The data obtained from the analysis is further evaluated using computer learning algorithms to improve the accuracy of the results. By introducing a reinforcement learning approach, the model is optimized through a feedback loop based on past results.

[0073] Users can access the system via their terminals. For example, when a user enters information about a trading partner into their terminal, that information is sent to the server, where the risk is quickly assessed. The assessment results are presented to the user in a color-coded graphical interface, allowing them to intuitively understand the risk situation. For instance, if the risk is deemed "high," a warning is displayed in red.

[0074] When utilizing generative AI models, one might consider using prompt statements like the following:

[0075] "Please conduct a risk assessment of the company name. Based on information on relevant social risk groups, calculate a risk score and provide the visualized results."

[0076] This system provides a powerful tool for businesses and local governments to efficiently and accurately identify risks and proactively avoid problematic relationships.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The server automatically collects necessary data from publicly accessible sources. Inputs include news site URLs, social media accounts, and government database APIs. A crawler program visits these sources to retrieve text, images, and audio data. The output is stored as raw data in temporary data storage on the server.

[0080] Step 2:

[0081] The server preprocesses the collected raw data. The input is the raw data obtained in step 1. A data cleansing tool is used to remove HTML tags and unnecessary characters from text data and reduce noise from image data. Audio data is converted to text using speech recognition software. The output is clean data in an organized format, optimized for analysis and training.

[0082] Step 3:

[0083] The server performs network analysis using clean data. The input is the output data from step 2. It runs a network analysis algorithm to identify relevant person names, organization names, and keywords from the text data. A reinforcement learning algorithm is integrated into this, and the analysis model is improved using past results. The output is a relationship map and risk-related data.

[0084] Step 4:

[0085] The user inputs information about their business partners into the system using a terminal. This information is specifically defined, such as company names or individual names. This information is sent from the terminal to the server, which then compares the received information with the analysis results from step 3. The output is the risk assessment result.

[0086] Step 5:

[0087] The server visualizes the risk assessment results and sends them to the terminal. The input is the risk assessment results from step 4. The results are displayed as a warning screen corresponding to the risk level using a color scheme (e.g., red, yellow, green). The output is a warning display in a format that is easy for the user to understand. This visualization enables the user to make quick and appropriate decisions.

[0088] (Application Example 1)

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

[0090] Modern businesses and local governments are required to quickly and accurately assess risks associated with their business partners. However, traditional methods have the problem of being time-consuming and labor-intensive when assessing connections with anti-social forces. Furthermore, the visual and intuitive understanding of risks is difficult, which can lead to misjudgments.

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

[0092] In this invention, the server includes means for automatically acquiring data from publicly available information sources on the Internet, means for preprocessing the acquired data and extracting relevant information, means for analyzing anti-social force networks and identifying relevant individuals or organizations, means for updating the judgment logic using a reinforcement learning algorithm, and means for determining risk when business partner information is input and displaying the risk score as a color-coded graphical indicator based on the analysis results. This makes it possible to quickly and accurately determine the risk of business partners and present it in a format that is easy for users to understand intuitively.

[0093] "Publicly available information sources on the internet" refer to online information media that are accessible to anyone, such as websites, news articles, social media, and government databases.

[0094] "Means of automatically acquiring data" refers to the process of continuously collecting information from the internet using a program.

[0095] "Preprocessing and extracting relevant information" refers to the process of standardizing the format of data to make it easier to analyze and extracting only the necessary information.

[0096] "Methods for analyzing anti-social force networks" refers to data analysis techniques used to identify connections between individuals and organizations involved in criminal acts and illegal activities.

[0097] "A method for updating the judgment logic using a reinforcement learning algorithm" refers to a machine learning technique that improves the accuracy of risk assessment based on past analysis results.

[0098] "A method for determining risk by inputting business partner information" refers to a process that evaluates the risks associated with a business partner based on the information provided by the user.

[0099] "Displaying as a color-coded graphical indicator" refers to using indicators of different colors and shapes to visually represent the level of risk.

[0100] In implementing this invention, a server and a terminal primarily play the roles of the server and terminal. First, the server automatically collects data from publicly available information sources on the internet. The data includes text, images, and audio, which are preprocessed within the server. The hardware used is a general-purpose server, and software such as Python or Scrapy is used for data collection and management. The preprocessed data is then subjected to network analysis using machine learning frameworks such as TensorFlow or PyTorch.

[0101] The server analyzes networks associated with anti-social forces using reinforcement learning algorithms. This process automatically updates the logic based on past judgment results while evaluating the risks of business partners. The analysis is performed in real time, and the results are sent to the terminal.

[0102] On the terminal, the user enters customer information. This information is sent to the server, and the analysis results are returned to the terminal and displayed as a risk score. The risk score is shown with color-coded graphical indicators, and a visually intuitive user interface has been designed using React Native.

[0103] For example, if a company wants to evaluate a potential business partner, this terminal app can be used to identify in advance any business partners who may have been involved in antisocial activities in the past.

[0104] An example of a prompt for a generative AI model would be, "Please provide specific steps on how to implement a reinforcement learning model for conducting risk assessments of business partners using a smartphone app." Based on this prompt, the generative AI can provide support for specific implementation steps.

[0105] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0106] Step 1:

[0107] The user uses a terminal to enter information such as the name of a business partner. The entered data is formatted according to the format specified in the interface. Since this data is sent directly to the server, a check for data accuracy is included.

[0108] Step 2:

[0109] The terminal sends the entered data to the server. HTTPS is used as a secure communication method for this process. The transmitted data is temporarily stored on the server and prepared for analysis. This stored data becomes the input for the next analysis.

[0110] Step 3:

[0111] The server automatically retrieves relevant data from publicly available sources on the internet based on the stored data. Web crawling technology, such as Python or Scrapy, is used for this process. The retrieved data serves as input for preprocessing in the next step.

[0112] Step 4:

[0113] The server preprocesses the acquired data to extract the necessary information. For example, if the data is text, natural language processing techniques are used to remove noise and extract important keywords and sentences. This preprocessing filters out unnecessary information, preparing it as input data for the analysis algorithm.

[0114] Step 5:

[0115] The server uses reinforcement learning algorithms to perform network analysis. It identifies individuals and organizations associated with anti-social forces and assesses the associated risks, improving analysis accuracy by utilizing past analysis results as logic. The output is a risk score for business partners.

[0116] Step 6:

[0117] The server sends the resulting risk score to the terminal, which displays the risk as a color-coded graphical indicator. This allows the user to grasp the risk level of their trading partners at a glance and prepare to make further decisions based on detailed text information.

[0118] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0119] To implement this invention, it is necessary to integrate an emotion engine that recognizes user emotions into a system based on server, terminal, and user interaction. The server has the ability to automatically collect data from various sources on the internet. This collected data is used to evaluate the risks associated with anti-social forces using network analysis and reinforcement learning. This provides real-time risk assessment for business partner information.

[0120] Furthermore, when a user enters business partner information into the terminal, the information is assessed to determine if it poses a risk, and the result is displayed on the terminal. At this point, the emotion engine recognizes the user's current emotional state. This engine analyzes the user's voice, facial expressions, input speed, and interaction patterns to evaluate their emotional state.

[0121] For example, if the emotion engine determines that a user is in a high-stress state, the device will reduce the information burden on the user by providing risk information more gently and gradually. Conversely, if the user is calm, the device will ensure the timeliness of the information by immediately providing the risk score and related detailed information.

[0122] This system will enable companies and local governments to conduct efficient and accurate risk assessments, as well as optimize the user experience by providing information tailored to the user's emotional state.

[0123] The following describes the processing flow.

[0124] Step 1:

[0125] The server collects data from publicly available sources on the internet. It retrieves text, images, and audio data from news articles, social media, and government databases, and stores them on the server.

[0126] Step 2:

[0127] The server preprocesses the collected data. It performs text noise reduction, extracts features from images and audio, and converts the data into a format suitable for analysis.

[0128] Step 3:

[0129] The server performs network analysis based on the pre-processed data. To reveal connections with anti-social forces, it uses natural language processing to identify related individuals and organizations.

[0130] Step 4:

[0131] The server analyzes the processed data using a reinforcement learning algorithm and updates the judgment logic. This is designed to continuously improve accuracy.

[0132] Step 5:

[0133] The user enters the trading partner's information on the terminal. The terminal sends this information to the server, which then requests a risk assessment.

[0134] Step 6:

[0135] The server uses the transmitted customer information to assess risk. It calculates a risk score for a specific customer using relevant network data.

[0136] Step 7:

[0137] The device receives the judgment result sent from the server. Simultaneously, the emotion engine installed in the device analyzes and determines the user's emotional state through voice and facial expression data.

[0138] Step 8:

[0139] The emotion engine recognizes the user's emotions, and based on that, the device displays risk information in a format most appropriate to the user's state. If the user is stressed, information is provided in stages; if they are calm, detailed information is provided immediately.

[0140] Step 9:

[0141] Users review the displayed information and, if necessary, decide whether or not to proceed with the transaction. This allows for risk management while taking emotions into consideration.

[0142] (Example 2)

[0143] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0144] In modern business operations, there is a need to quickly and accurately assess risks related to business partners and stakeholders. However, manually analyzing vast amounts of data on the internet is inefficient and can lead to delays in response. Furthermore, presenting information without considering the emotional state of users may hinder appropriate decision-making. To address these problems, a system is needed that enables efficient data collection and analysis, as well as information provision that takes users' emotions into consideration.

[0145] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0146] In this invention, the server includes means for automatically acquiring information from a data source, means for extracting relevant information using the acquired information, means for analyzing a network of social stakeholders to identify relevant individuals or groups, means for updating the judgment logic using a machine learning algorithm, means including an engine for performing risk assessment and evaluating the emotional state of the user for providing information, and means for visualizing and presenting the information. This enables efficient and accurate risk assessment and the provision of appropriate information according to the user's situation.

[0147] A "data source" refers to the starting point or the information provider from which information is obtained.

[0148] "Means of automatically acquiring information" refers to methods of collecting information using computers and network systems without human intervention.

[0149] "Means of extracting relevant information" refers to the process of selecting useful and necessary information from collected data.

[0150] "Means of analyzing networks of social stakeholders to identify relevant individuals or groups" refers to methods of investigating connections between stakeholders and using that information to identify individuals or organizations with significant relationships.

[0151] "Methods for updating judgment logic using machine learning algorithms" refer to computational methods that learn from empirical data and improve prediction and judgment methods.

[0152] "Means including an engine that evaluates the emotional state of users for risk assessment and information provision" refers to programs or devices that analyze the emotional state of users and present appropriate information based on that analysis.

[0153] "Means of visualizing and presenting information" refers to methods and devices for displaying data and analysis results in a way that is easy for users to understand.

[0154] To implement this invention, a system involving a server, a terminal, and a user is primarily required. The server collects information from various data sources on the internet. This collection process is achieved by using the Python library Requests to automatically send HTTP requests to API endpoints.

[0155] The server further performs risk assessment by analyzing data with Scikit-learn and applying machine learning algorithms using TensorFlow. This makes it possible to assess risks associated with antisocial elements in real time. This information is transmitted to terminals via a dedicated network interface.

[0156] Users enter business partner information on the terminal. This input is done using a standard keyboard or touch panel, and the entered information is immediately transmitted to the server. The terminal is equipped with an engine that evaluates the user's emotional state, using Google® Cloud Speech-to-Text and OpenCV to analyze the user's voice, facial expressions, and input speed to determine their emotions.

[0157] As a concrete example, suppose a user enters information about a new business partner into the system. When this information is sent to the server, the server calculates a risk score for the business partner based on relevant data collected from the internet. In this process, if the data collected by the server indicates past involvement with anti-social forces, the score for that business partner is increased. Once the risk assessment is complete, the results are returned to the terminal and presented to the user visually.

[0158] Furthermore, depending on the user's emotional state, this information can be provided either gradually or immediately in detail. An example of a specific prompt might be, "Describe a system that collects the information necessary for the user to assess the risks of a new business partner and adjusts the information presentation method based on the stress assessment by the emotion engine." In this way, the system can promote appropriate risk management while reducing the burden on the user.

[0159] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0160] Step 1:

[0161] The server automatically retrieves information from publicly available data sources on the internet. Specifically, it uses the Python library Requests to obtain real-time data from news sites, government databases, social media, etc., via APIs. The input to this process is pre-configured keywords and customer names, and the output is a collection of data that matches specific conditions.

[0162] Step 2:

[0163] The server preprocesses the acquired data and extracts relevant information. Here, Scikit-learn is used to analyze the data and perform natural language processing to filter out useful information. The input is the data collected in step 1, and the output is clear information necessary for risk assessment.

[0164] Step 3:

[0165] The server applies a reinforcement learning algorithm to calculate a risk score. Specifically, it uses TensorFlow to build a model that assesses risk based on the past behavior and relevant data of the trading partner. The input is the information obtained in step 2, and the output is a specific risk score.

[0166] Step 4:

[0167] The user enters the business partner's information into the terminal and sends it to the server. The information entered by the user includes the business partner's name, address, and industry, and processing begins once this information is sent to the server.

[0168] Step 5:

[0169] The terminal receives the risk score sent from the server and displays it on the screen. Here, the information is presented to the user in an easy-to-understand way by visually displaying the risk level with different colors. Specifically, a red indicator is displayed on the screen if the risk is high, and a green indicator is displayed if the risk is low. The input is the output of step 3, and the output is the visual information presented to the user.

[0170] Step 6:

[0171] The device's emotion engine detects the user's emotional state and adjusts how information is presented. Using OpenCV and Google Cloud Speech-to-Text, it analyzes the user's facial expressions and tone of voice to assess their emotional state. The input is the user's voice and facial expression data, and the output is a proposal that reflects this in the format of information presentation. Specifically, if a high-stress state is detected, information will be presented in stages.

[0172] (Application Example 2)

[0173] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0174] Risk assessment of business partners is becoming increasingly important in modern business activities. However, current risk assessment systems do not provide information that takes into account the emotional state of users, which can lead to user stress and decision-making errors due to information overload. Furthermore, collecting and analyzing data in real time from numerous sources is difficult. Therefore, there is a need for a system that can consider the emotional state of users and present risk information intuitively and effectively.

[0175] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0176] In this invention, the server includes means for automatically acquiring data from publicly available information sources on the Internet, means for preprocessing the acquired data and extracting relevant information, means for analyzing anti-social groups and identifying relevant individuals or organizations, means for updating the judgment logic using a reinforcement learning algorithm, means for determining risk when business partner information is input and displaying the results, means for sentiment analysis that analyzes the user's voice and facial expressions and evaluates their emotional state, and means for adjusting the presentation of information based on the user's emotional state. This enables efficient and accurate risk assessment by presenting risk information in the most appropriate way according to the user's emotional state.

[0177] "Publicly available information sources on the Internet" refer to a collection of information that exists on the Internet in a form that is generally accessible, such as websites and databases.

[0178] A "function that automatically acquires data" is a mechanism that collects information from the internet according to set criteria without user intervention.

[0179] The "preprocessing and information extraction function" refers to the process of identifying important information from acquired data and converting it into an appropriate format for analysis.

[0180] The "function for analyzing antisocial groups" refers to a mechanism for identifying individuals and groups exhibiting antisocial behavior and analyzing their networks.

[0181] The "emotion analysis function" is a process that evaluates the user's emotional state from their voice and facial expressions, and is used to adjust the information presented.

[0182] A "reinforcement learning algorithm" is a computational method that allows a system to improve its decision-making logic through learning and perform accurate risk assessments.

[0183] A "function to adjust the presentation of information" is a mechanism that optimizes the way information is displayed and its content according to the user's emotional state.

[0184] The "risk assessment and display of results function" is a process that evaluates risk based on input data and visualizes the results for the user.

[0185] To implement this system, the server automatically retrieves data from publicly available sources on the internet. The server preprocesses this data, performing data filtering and analysis to extract relevant information. To identify individuals or groups associated with anti-social forces, the server uses network analysis techniques. Based on the results of this analysis, a reinforcement learning algorithm is employed, and the server continuously improves its judgment logic.

[0186] The device uses emotion analysis to assess the user's emotional state in real time from their voice and facial expressions. This function utilizes services such as the Google Cloud Speech-to-Text API and Microsoft® Azure® Face API. Depending on the user's emotional state, the device adjusts how it presents risk information, communicating the risk level to the user in a gentle manner.

[0187] As a concrete example, consider a scenario where a user enters information about a new business partner into a terminal. The server assesses the risk associated with that information in real time, and the terminal displays the results according to the user's emotional state. If the user is feeling stressed, the risk information is displayed more gently and gradually; if the user is calm, a comprehensive risk assessment is provided quickly.

[0188] An example of a prompt is: "Design an AI system that assesses security risks in real time during meetings with new business partners. This system should have the ability to change how information is presented based on the user's emotional state." Using this example, a generative AI model can build a system that presents information appropriately according to the context.

[0189] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0190] Step 1:

[0191] The server automatically retrieves data from publicly available sources on the internet. It receives configured queries and information filtering conditions as input. Based on this, the server uses APIs and web scraping tools to collect the appropriate information. The output is stored in raw data format.

[0192] Step 2:

[0193] The server preprocesses the acquired raw data and extracts relevant information. The input is the raw data collected in step 1. Data cleaning and transformation processes are performed to convert it into structured data that can be handled by machine learning models. The output is data that has been formatted to be analyzable.

[0194] Step 3:

[0195] The server analyzes antisocial groups and identifies relevant individuals or organizations. The input is the formatted data obtained in step 2. Network analysis algorithms are used to visualize relationships within the data and identify risk factors. The output is a list of high-risk, relevant individuals or organizations.

[0196] Step 4:

[0197] The server updates the decision logic using a reinforcement learning algorithm. The input is the analysis result from step 3. It incorporates feedback data and continues to train the risk assessment model. The output is the updated risk decision logic.

[0198] Step 5:

[0199] The device analyzes the user's voice and facial expressions to assess their emotional state. The input is real-time voice and facial expression data from the user. Facial recognition and speech recognition technologies are used to quantify the user's emotional state. The output is a numerical value or category indicating the emotional state.

[0200] Step 6:

[0201] The device adjusts the information presentation based on the user's emotional state. Inputs are the emotional assessment results from step 5 and risk assessment data from the server. If the user is stressed, an algorithm is applied that presents information gradually and in stages. The output is the method of information presentation tailored to the user's current emotional state.

[0202] Step 7:

[0203] The user inputs customer information via a terminal and assesses the risk. The input consists of detailed customer information provided by the user. The terminal sends the input information to a server, where the risk is assessed in real time. The output is the risk assessment result displayed on the terminal.

[0204] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0205] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0206] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0207] [Second Embodiment]

[0208] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0209] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0210] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0211] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0212] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0213] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0214] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0215] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0216] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0217] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0218] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0219] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0220] To implement this invention, a system based on interaction between a server, a terminal, and a user will be constructed. The server will have the function of automatically collecting data from various information sources on the internet. This includes news, social networking services, and publicly available government databases. The data types include text, images, and audio, which will be pre-processed after being taken into the server.

[0221] The pre-processed data is analyzed by a network analysis algorithm running on the server. This analysis algorithm constructs a network of anti-social forces and identifies related individuals and organizations. Furthermore, reinforcement learning is incorporated into this process, updating the judgment logic using historical data to improve accuracy over time.

[0222] The user enters the name of the business partner and related information via a terminal. The terminal sends this information to a server, which immediately determines the risk based on the received information. The result is returned to the terminal and presented to the user. The display visually indicates the risk level, using colors and graphical indicators to present it in a format that is easy for the user to intuitively understand.

[0223] For example, if a user enters a company name, the server uses previously collected data to investigate its connection to that company. Network analysis determines that the company is linked to a specific anti-social group, and a risk score is calculated based on the level of risk. The terminal classifies this score as "high risk," "medium risk," or "low risk" and warns the user with a color-coded signal.

[0224] This system enables companies and local governments to efficiently and accurately detect relevant risks and sever unnecessary relationships early on.

[0225] The following describes the processing flow.

[0226] Step 1:

[0227] The server automatically collects data from publicly available sources on the internet. It retrieves text, images, and audio data from news articles, social media, and government databases, and stores them in storage.

[0228] Step 2:

[0229] The server preprocesses the collected data. Text data undergoes noise reduction and normalization, while image and audio data are subjected to feature extraction. This prepares the data for analysis in a suitable format.

[0230] Step 3:

[0231] The server performs network analysis using pre-processed data. Utilizing natural language processing techniques, it extracts individuals and organizations associated with anti-social forces from text data and constructs a network structure.

[0232] Step 4:

[0233] The server uses a reinforcement learning algorithm to update its decision logic. It references past data and results to make adjustments to improve the accuracy of the decision process.

[0234] Step 5:

[0235] The user enters customer information on their terminal. The terminal sends this information to the server and requests a real-time risk assessment.

[0236] Step 6:

[0237] The server performs a risk assessment based on the received information. It refers to relevant network information and analyzes and generates a risk score for a specific business partner.

[0238] Step 7:

[0239] The server sends the assessment results to the terminal. This includes risk scores and information about related individuals and organizations.

[0240] Step 8:

[0241] The device visually displays the received risk assessment results to the user. It provides color-coded indicators based on score levels and detailed information, allowing the user to intuitively understand the risk.

[0242] (Example 1)

[0243] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0244] In society and for businesses, it is crucial to detect early on if business partners or related entities are involved with groups considered socially dangerous, and to assess the risks in advance. Traditional methods have been problematic due to the time-consuming nature of information gathering and analysis, as well as the inconsistent accuracy of risk assessments. Therefore, there is a need to provide a system that can quickly and accurately determine risks and present them in a visually easy-to-understand format.

[0245] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0246] In this invention, the server includes means for automatically collecting information from public sources, means for preprocessing the collected information and extracting relevant content, means for analyzing networks of socially dangerous groups and identifying relevant entities, means for dynamically improving the judgment logic using a computer learning algorithm, means for evaluating risk by inputting transaction-related information and outputting the evaluation results, means for visually outputting the evaluation results and presenting the risk level to the user using color, and means for displaying a list of important entities and key related information based on the evaluation. This enables rapid and accurate risk assessment and allows users to intuitively understand the degree of risk.

[0247] "Public information sources" generally refer to information sources that are accessible on the internet, such as news sites, social media, and government databases.

[0248] "Preprocessing" refers to the process of removing noise from collected raw data and preparing it in a format suitable for data analysis.

[0249] A "socially dangerous group" refers to an organization or group that has the potential to cause legal or moral harm to society.

[0250] A "computer learning algorithm" refers to a mathematical process by which a computer uses data to learn empirically and make predictions and decisions.

[0251] "Decision logic" refers to a set of criteria used to evaluate risk and relevance based on data.

[0252] "Visual output" refers to displaying results in a way that is easy for users to understand intuitively, typically using colors and shapes.

[0253] "Key actors" refer to influential individuals or organizations identified based on network analysis results.

[0254] To implement this invention, a system based on interaction between a server, a terminal, and a user is constructed. The server plays a central role in information gathering and analysis. Specifically, the server automatically collects information periodically from news sites, social networking services, and government databases on the internet by executing a crawler program. This process often utilizes scraping techniques using scripting languages ​​such as Python and JavaScript.

[0255] The server preprocesses the collected data. This includes formatting the data using data processing libraries such as Python's pandas and numpy, and removing irrelevant elements. For image and audio data, feature extraction and speech recognition technologies using OpenCV and TensorFlow are applied.

[0256] Furthermore, the server utilizes libraries such as scikit-learn and NetworkX to execute network analysis algorithms. This allows it to identify related keywords, individuals, and organizations from the collected data and analyze networks of groups considered socially dangerous. The data obtained from the analysis is further evaluated using computer learning algorithms to improve the accuracy of the results. By introducing a reinforcement learning approach, the model is optimized through a feedback loop based on past results.

[0257] Users can access the system via their terminals. For example, when a user enters information about a trading partner into their terminal, that information is sent to the server, where the risk is quickly assessed. The assessment results are presented to the user in a color-coded graphical interface, allowing them to intuitively understand the risk situation. For instance, if the risk is deemed "high," a warning is displayed in red.

[0258] When utilizing generative AI models, one might consider using prompt statements like the following:

[0259] "Please conduct a risk assessment of the company name. Based on information on relevant social risk groups, calculate a risk score and provide the visualized results."

[0260] This system provides a powerful tool for businesses and local governments to efficiently and accurately identify risks and proactively avoid problematic relationships.

[0261] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0262] Step 1:

[0263] The server automatically collects necessary data from publicly accessible sources. Inputs include news site URLs, social media accounts, and government database APIs. A crawler program visits these sources to retrieve text, images, and audio data. The output is stored as raw data in temporary data storage on the server.

[0264] Step 2:

[0265] The server preprocesses the collected raw data. The input is the raw data obtained in step 1. A data cleansing tool is used to remove HTML tags and unnecessary characters from text data and reduce noise from image data. Audio data is converted to text using speech recognition software. The output is clean data in an organized format, optimized for analysis and training.

[0266] Step 3:

[0267] The server performs network analysis using clean data. The input is the output data from step 2. It runs a network analysis algorithm to identify relevant person names, organization names, and keywords from the text data. A reinforcement learning algorithm is integrated into this, and the analysis model is improved using past results. The output is a relationship map and risk-related data.

[0268] Step 4:

[0269] The user inputs information about their business partners into the system using a terminal. This information is specifically defined, such as company names or individual names. This information is sent from the terminal to the server, which then compares the received information with the analysis results from step 3. The output is the risk assessment result.

[0270] Step 5:

[0271] The server visualizes the risk assessment results and sends them to the terminal. The input is the risk assessment results from step 4. The results are displayed as a warning screen corresponding to the risk level using a color scheme (e.g., red, yellow, green). The output is a warning display in a format that is easy for the user to understand. This visualization enables the user to make quick and appropriate decisions.

[0272] (Application Example 1)

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

[0274] Modern businesses and local governments are required to quickly and accurately assess risks associated with their business partners. However, traditional methods have the problem of being time-consuming and labor-intensive when assessing connections with anti-social forces. Furthermore, the visual and intuitive understanding of risks is difficult, which can lead to misjudgments.

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

[0276] In this invention, the server includes means for automatically acquiring data from publicly available information sources on the Internet, means for preprocessing the acquired data and extracting relevant information, means for analyzing anti-social force networks and identifying relevant individuals or organizations, means for updating the judgment logic using a reinforcement learning algorithm, and means for determining risk when business partner information is input and displaying the risk score as a color-coded graphical indicator based on the analysis results. This makes it possible to quickly and accurately determine the risk of business partners and present it in a format that is easy for users to understand intuitively.

[0277] "Publicly available information sources on the internet" refer to online information media that are accessible to anyone, such as websites, news articles, social media, and government databases.

[0278] The means for automatically acquiring data is a process of continuously collecting information from the Internet by a program.

[0279] The means for preprocessing and extracting relevant information is a process of unifying the format to facilitate data analysis and extracting only the necessary information.

[0280] The means for analyzing the network of anti-social forces refers to data analysis techniques for identifying the connections of individuals and organizations involved in criminal acts and illegal activities.

[0281] The means for updating the judgment logic using a reinforcement learning algorithm is a machine learning method for improving the accuracy of risk judgment based on past analysis results.

[0282] The means for judging risk when inputting business partner information is a process of evaluating the risks associated with the business partner based on the information provided by the user.

[0283] The means for displaying as a color-coded graphical indicator is a method of using indicators of different colors and shapes to visually show the level of risk.

[0284] In the implementation of this invention, mainly the server and the terminal play roles. First, the server automatically collects data from public information sources on the Internet. The data includes text, images, and voices, and they are preprocessed within the server. The hardware used is a general server, and for software, Python, Scrapy, etc. are used for data collection and management. The preprocessed data is subjected to network analysis using machine learning frameworks such as TensorFlow and PyTorch.

[0285] The server analyzes networks related to anti-social forces using reinforcement learning algorithms. Through this process, it evaluates the risks of trading partners while automatically updating the logic based on past judgment results. The analysis is performed in real time, and the results are sent to the terminal.

[0286] On the terminal side, the user inputs trading partner information. This information is sent to the server, and the analysis results are returned to the terminal and displayed as a risk score. The risk score is indicated by a color-coded graphical indicator, and a visually intuitive user interface is designed using React Native.

[0287] As a specific example, when a company wants to evaluate a new trading partner, by using this terminal app, it can identify in advance trading partners that may have been involved in anti-social activities in the past.

[0288] Examples of prompt texts for generative AI models include content such as "Please teach me the specific steps for implementing a reinforcement learning model for conducting risk assessments of trading partners in a smartphone app." Based on this prompt, the generative AI can support the generation of specific implementation methods.

[0289] The flow of specific processing in Application Example 1 will be described using FIG. 12.

[0290] Step 1:

[0291] The user uses the terminal to input information such as the name of the trading partner. The input data is formatted in the format specified by the interface. Since this data is sent to the server as it is, an operation to check the accuracy of the data is included.

[0292] Step 2:

[0293] The terminal sends the entered data to the server. HTTPS is used as a secure communication method for this process. The transmitted data is temporarily stored on the server and prepared for analysis. This stored data becomes the input for the next analysis.

[0294] Step 3:

[0295] The server automatically retrieves relevant data from publicly available sources on the internet based on the stored data. Web crawling technology, such as Python or Scrapy, is used for this process. The retrieved data serves as input for preprocessing in the next step.

[0296] Step 4:

[0297] The server preprocesses the acquired data to extract the necessary information. For example, if the data is text, natural language processing techniques are used to remove noise and extract important keywords and sentences. This preprocessing filters out unnecessary information, preparing it as input data for the analysis algorithm.

[0298] Step 5:

[0299] The server uses reinforcement learning algorithms to perform network analysis. It identifies individuals and organizations associated with anti-social forces and assesses the associated risks, improving analysis accuracy by utilizing past analysis results as logic. The output is a risk score for business partners.

[0300] Step 6:

[0301] The server sends the resulting risk score to the terminal, which displays the risk as a color-coded graphical indicator. This allows the user to grasp the risk level of their trading partners at a glance and prepare to make further decisions based on detailed text information.

[0302] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion specific model 59 and perform specific processing using the user's emotion.

[0303] To implement this invention, it is necessary to integrate an emotion engine that recognizes the user's emotion into a system based on the interaction between the server, the terminal, and the user. The server has a function of automatically collecting data from various information sources on the Internet. This collected data is used to evaluate the risk associated with anti-social forces through network analysis and reinforcement learning. Thereby, real-time risk determination for the business partner information is provided.

[0304] Furthermore, when the user inputs business partner information into the terminal, the information is determined whether there is a risk, and the result is presented to the terminal. Here, the emotion engine recognizes the user's current emotional state. This engine analyzes the user's voice, expression, input speed, interaction pattern, and evaluates the emotional state.

[0305] For example, when the emotion engine determines that the user is in a high-stress state, the terminal provides the risk information more gently and step by step to reduce the information burden on the user. Also, when the user is calm, the risk score and related detailed information are provided immediately to ensure the immediacy of the information.

[0306] With this system, companies and local governments can not only perform efficient and accurate risk assessment, but also optimize the user experience through information provision according to the user's emotional state.

[0307] The processing flow will be described below.

[0308] Step 1:

[0309] The server collects data from publicly available sources on the internet. It retrieves text, images, and audio data from news articles, social media, and government databases, and stores them on the server.

[0310] Step 2:

[0311] The server preprocesses the collected data. It performs text noise reduction, extracts features from images and audio, and converts the data into a format suitable for analysis.

[0312] Step 3:

[0313] The server performs network analysis based on the pre-processed data. To reveal connections with anti-social forces, it uses natural language processing to identify related individuals and organizations.

[0314] Step 4:

[0315] The server analyzes the processed data using a reinforcement learning algorithm and updates the judgment logic. This is designed to continuously improve accuracy.

[0316] Step 5:

[0317] The user enters the trading partner's information on the terminal. The terminal sends this information to the server, which then requests a risk assessment.

[0318] Step 6:

[0319] The server uses the transmitted customer information to assess risk. It calculates a risk score for a specific customer using relevant network data.

[0320] Step 7:

[0321] The device receives the judgment result sent from the server. Simultaneously, the emotion engine installed in the device analyzes and determines the user's emotional state through voice and facial expression data.

[0322] Step 8:

[0323] The emotion engine recognizes the user's emotions, and based on that, the device displays risk information in a format most appropriate to the user's state. If the user is stressed, information is provided in stages; if they are calm, detailed information is provided immediately.

[0324] Step 9:

[0325] Users review the displayed information and, if necessary, decide whether or not to proceed with the transaction. This allows for risk management while taking emotions into consideration.

[0326] (Example 2)

[0327] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0328] In modern business operations, there is a need to quickly and accurately assess risks related to business partners and stakeholders. However, manually analyzing vast amounts of data on the internet is inefficient and can lead to delays in response. Furthermore, presenting information without considering the emotional state of users may hinder appropriate decision-making. To address these problems, a system is needed that enables efficient data collection and analysis, as well as information provision that takes users' emotions into consideration.

[0329] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0330] In this invention, the server includes means for automatically acquiring information from a data source, means for extracting relevant information using the acquired information, means for analyzing a network of social stakeholders to identify relevant individuals or groups, means for updating the judgment logic using a machine learning algorithm, means including an engine for performing risk assessment and evaluating the emotional state of the user for providing information, and means for visualizing and presenting the information. This enables efficient and accurate risk assessment and the provision of appropriate information according to the user's situation.

[0331] A "data source" refers to the starting point or the information provider from which information is obtained.

[0332] "Means of automatically acquiring information" refers to methods of collecting information using computers and network systems without human intervention.

[0333] "Means of extracting relevant information" refers to the process of selecting useful and necessary information from collected data.

[0334] "Means of analyzing networks of social stakeholders to identify relevant individuals or groups" refers to methods of investigating connections between stakeholders and using that information to identify individuals or organizations with significant relationships.

[0335] "Methods for updating judgment logic using machine learning algorithms" refer to computational methods that learn from empirical data and improve prediction and judgment methods.

[0336] "Means including an engine that evaluates the emotional state of users for risk assessment and information provision" refers to programs or devices that analyze the emotional state of users and present appropriate information based on that analysis.

[0337] "Means of visualizing and presenting information" refers to methods and devices for displaying data and analysis results in a way that is easy for users to understand.

[0338] To implement this invention, a system involving a server, a terminal, and a user is primarily required. The server collects information from various data sources on the internet. This collection process is achieved by using the Python library Requests to automatically send HTTP requests to API endpoints.

[0339] The server further performs risk assessment by analyzing data with Scikit-learn and applying machine learning algorithms using TensorFlow. This makes it possible to assess risks associated with antisocial elements in real time. This information is transmitted to terminals via a dedicated network interface.

[0340] Users enter business partner information on the terminal. This input is done using a standard keyboard or touch panel, and the entered information is immediately transmitted to the server. The terminal is equipped with an engine that evaluates the user's emotional state, using Google Cloud Speech-to-Text and OpenCV to analyze the user's voice, facial expressions, and input speed to determine their emotions.

[0341] As a concrete example, suppose a user enters information about a new business partner into the system. When this information is sent to the server, the server calculates a risk score for the business partner based on relevant data collected from the internet. In this process, if the data collected by the server indicates past involvement with anti-social forces, the score for that business partner is increased. Once the risk assessment is complete, the results are returned to the terminal and presented to the user visually.

[0342] Furthermore, depending on the user's emotional state, this information can be provided either gradually or immediately in detail. An example of a specific prompt might be, "Describe a system that collects the information necessary for the user to assess the risks of a new business partner and adjusts the information presentation method based on the stress assessment by the emotion engine." In this way, the system can promote appropriate risk management while reducing the burden on the user.

[0343] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0344] Step 1:

[0345] The server automatically retrieves information from publicly available data sources on the internet. Specifically, it uses the Python library Requests to obtain real-time data from news sites, government databases, social media, etc., via APIs. The input to this process is pre-configured keywords and customer names, and the output is a collection of data that matches specific conditions.

[0346] Step 2:

[0347] The server preprocesses the acquired data and extracts relevant information. Here, Scikit-learn is used to analyze the data and perform natural language processing to filter out useful information. The input is the data collected in step 1, and the output is clear information necessary for risk assessment.

[0348] Step 3:

[0349] The server applies a reinforcement learning algorithm to calculate a risk score. Specifically, it uses TensorFlow to build a model that assesses risk based on the past behavior and relevant data of the trading partner. The input is the information obtained in step 2, and the output is a specific risk score.

[0350] Step 4:

[0351] The user enters the business partner's information into the terminal and sends it to the server. The information entered by the user includes the business partner's name, address, and industry, and processing begins once this information is sent to the server.

[0352] Step 5:

[0353] The terminal receives the risk score sent from the server and displays it on the screen. Here, the information is presented to the user in an easy-to-understand way by visually displaying the risk level with different colors. Specifically, a red indicator is displayed on the screen if the risk is high, and a green indicator is displayed if the risk is low. The input is the output of step 3, and the output is the visual information presented to the user.

[0354] Step 6:

[0355] The device's emotion engine detects the user's emotional state and adjusts how information is presented. Using OpenCV and Google Cloud Speech-to-Text, it analyzes the user's facial expressions and tone of voice to assess their emotional state. The input is the user's voice and facial expression data, and the output is a proposal that reflects this in the format of information presentation. Specifically, if a high-stress state is detected, information will be presented in stages.

[0356] (Application Example 2)

[0357] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0358] Risk assessment of business partners is becoming increasingly important in modern business activities. However, current risk assessment systems do not provide information that takes into account the emotional state of users, which can lead to user stress and decision-making errors due to information overload. Furthermore, collecting and analyzing data in real time from numerous sources is difficult. Therefore, there is a need for a system that can consider the emotional state of users and present risk information intuitively and effectively.

[0359] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0360] In this invention, the server includes means for automatically acquiring data from publicly available information sources on the Internet, means for preprocessing the acquired data and extracting relevant information, means for analyzing anti-social groups and identifying relevant individuals or organizations, means for updating the judgment logic using a reinforcement learning algorithm, means for determining risk when business partner information is input and displaying the results, means for sentiment analysis that analyzes the user's voice and facial expressions and evaluates their emotional state, and means for adjusting the presentation of information based on the user's emotional state. This enables efficient and accurate risk assessment by presenting risk information in the most appropriate way according to the user's emotional state.

[0361] "Publicly available information sources on the Internet" refer to a collection of information that exists on the Internet in a form that is generally accessible, such as websites and databases.

[0362] A "function that automatically acquires data" is a mechanism that collects information from the internet according to set criteria without user intervention.

[0363] The "preprocessing and information extraction function" refers to the process of identifying important information from acquired data and converting it into an appropriate format for analysis.

[0364] The "function for analyzing antisocial groups" refers to a mechanism for identifying individuals and groups exhibiting antisocial behavior and analyzing their networks.

[0365] The "emotion analysis function" is a process that evaluates the user's emotional state from their voice and facial expressions, and is used to adjust the information presented.

[0366] A "reinforcement learning algorithm" is a computational method that allows a system to improve its decision-making logic through learning and perform accurate risk assessments.

[0367] A "function to adjust the presentation of information" is a mechanism that optimizes the way information is displayed and its content according to the user's emotional state.

[0368] The "risk assessment and display of results function" is a process that evaluates risk based on input data and visualizes the results for the user.

[0369] To implement this system, the server automatically retrieves data from publicly available sources on the internet. The server preprocesses this data, performing data filtering and analysis to extract relevant information. To identify individuals or groups associated with anti-social forces, the server uses network analysis techniques. Based on the results of this analysis, a reinforcement learning algorithm is employed, and the server continuously improves its judgment logic.

[0370] The device uses emotion analysis to assess the user's emotional state in real time from their voice and facial expressions. This function utilizes services such as the Google Cloud Speech-to-Text API and the Microsoft Azure Face API. Depending on the user's emotional state, the device adjusts how it presents risk information, communicating the risk level to the user in a gentle manner.

[0371] As a concrete example, consider a scenario where a user enters information about a new business partner into a terminal. The server assesses the risk associated with that information in real time, and the terminal displays the results according to the user's emotional state. If the user is feeling stressed, the risk information is displayed more gently and gradually; if the user is calm, a comprehensive risk assessment is provided quickly.

[0372] An example of a prompt is: "Design an AI system that assesses security risks in real time during meetings with new business partners. This system should have the ability to change how information is presented based on the user's emotional state." Using this example, a generative AI model can build a system that presents information appropriately according to the context.

[0373] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0374] Step 1:

[0375] The server automatically retrieves data from publicly available sources on the internet. It receives configured queries and information filtering conditions as input. Based on this, the server uses APIs and web scraping tools to collect the appropriate information. The output is stored in raw data format.

[0376] Step 2:

[0377] The server preprocesses the acquired raw data and extracts relevant information. The input is the raw data collected in step 1. Data cleaning and transformation processes are performed to convert it into structured data that can be handled by machine learning models. The output is data that has been formatted to be analyzable.

[0378] Step 3:

[0379] The server analyzes antisocial groups and identifies relevant individuals or organizations. The input is the formatted data obtained in step 2. Network analysis algorithms are used to visualize relationships within the data and identify risk factors. The output is a list of high-risk, relevant individuals or organizations.

[0380] Step 4:

[0381] The server updates the decision logic using a reinforcement learning algorithm. The input is the analysis result from step 3. It incorporates feedback data and continues to train the risk assessment model. The output is the updated risk decision logic.

[0382] Step 5:

[0383] The device analyzes the user's voice and facial expressions to assess their emotional state. The input is real-time voice and facial expression data from the user. Facial recognition and speech recognition technologies are used to quantify the user's emotional state. The output is a numerical value or category indicating the emotional state.

[0384] Step 6:

[0385] The device adjusts the information presentation based on the user's emotional state. Inputs are the emotional assessment results from step 5 and risk assessment data from the server. If the user is stressed, an algorithm is applied that presents information gradually and in stages. The output is the method of information presentation tailored to the user's current emotional state.

[0386] Step 7:

[0387] The user inputs customer information via a terminal and assesses the risk. The input consists of detailed customer information provided by the user. The terminal sends the input information to a server, where the risk is assessed in real time. The output is the risk assessment result displayed on the terminal.

[0388] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0389] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0390] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0391] [Third Embodiment]

[0392] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0393] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0394] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0395] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0396] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0397] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0398] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0399] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0400] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0401] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0402] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0403] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0404] To implement this invention, a system based on interaction between a server, a terminal, and a user will be constructed. The server will have the function of automatically collecting data from various information sources on the internet. This includes news, social networking services, and publicly available government databases. The data types include text, images, and audio, which will be pre-processed after being taken into the server.

[0405] The pre-processed data is analyzed by a network analysis algorithm running on the server. This analysis algorithm constructs a network of anti-social forces and identifies related individuals and organizations. Furthermore, reinforcement learning is incorporated into this process, updating the judgment logic using historical data to improve accuracy over time.

[0406] The user enters the name of the business partner and related information via a terminal. The terminal sends this information to a server, which immediately determines the risk based on the received information. The result is returned to the terminal and presented to the user. The display visually indicates the risk level, using colors and graphical indicators to present it in a format that is easy for the user to intuitively understand.

[0407] For example, if a user enters a company name, the server uses previously collected data to investigate its connection to that company. Network analysis determines that the company is linked to a specific anti-social group, and a risk score is calculated based on the level of risk. The terminal classifies this score as "high risk," "medium risk," or "low risk" and warns the user with a color-coded signal.

[0408] This system enables companies and local governments to efficiently and accurately detect relevant risks and sever unnecessary relationships early on.

[0409] The following describes the processing flow.

[0410] Step 1:

[0411] The server automatically collects data from publicly available sources on the internet. It retrieves text, images, and audio data from news articles, social media, and government databases, and stores them in storage.

[0412] Step 2:

[0413] The server preprocesses the collected data. Text data undergoes noise reduction and normalization, while image and audio data are subjected to feature extraction. This prepares the data for analysis in a suitable format.

[0414] Step 3:

[0415] The server performs network analysis using pre-processed data. Utilizing natural language processing techniques, it extracts individuals and organizations associated with anti-social forces from text data and constructs a network structure.

[0416] Step 4:

[0417] The server uses a reinforcement learning algorithm to update its decision logic. It references past data and results to make adjustments to improve the accuracy of the decision process.

[0418] Step 5:

[0419] The user enters customer information on their terminal. The terminal sends this information to the server and requests a real-time risk assessment.

[0420] Step 6:

[0421] The server performs a risk assessment based on the received information. It refers to relevant network information and analyzes and generates a risk score for a specific business partner.

[0422] Step 7:

[0423] The server sends the assessment results to the terminal. This includes risk scores and information about related individuals and organizations.

[0424] Step 8:

[0425] The device visually displays the received risk assessment results to the user. It provides color-coded indicators based on score levels and detailed information, allowing the user to intuitively understand the risk.

[0426] (Example 1)

[0427] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0428] In society and for businesses, it is crucial to detect early on if business partners or related entities are involved with groups considered socially dangerous, and to assess the risks in advance. Traditional methods have been problematic due to the time-consuming nature of information gathering and analysis, as well as the inconsistent accuracy of risk assessments. Therefore, there is a need to provide a system that can quickly and accurately determine risks and present them in a visually easy-to-understand format.

[0429] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0430] In this invention, the server includes means for automatically collecting information from public sources, means for preprocessing the collected information and extracting relevant content, means for analyzing networks of socially dangerous groups and identifying relevant entities, means for dynamically improving the judgment logic using a computer learning algorithm, means for evaluating risk by inputting transaction-related information and outputting the evaluation results, means for visually outputting the evaluation results and presenting the risk level to the user using color, and means for displaying a list of important entities and key related information based on the evaluation. This enables rapid and accurate risk assessment and allows users to intuitively understand the degree of risk.

[0431] "Public information sources" generally refer to information sources that are accessible on the internet, such as news sites, social media, and government databases.

[0432] "Preprocessing" refers to the process of removing noise from collected raw data and preparing it in a format suitable for data analysis.

[0433] A "socially dangerous group" refers to an organization or group that has the potential to cause legal or moral harm to society.

[0434] A "computer learning algorithm" refers to a mathematical process by which a computer uses data to learn empirically and make predictions and decisions.

[0435] "Decision logic" refers to a set of criteria used to evaluate risk and relevance based on data.

[0436] "Visual output" refers to displaying results in a way that is easy for users to understand intuitively, typically using colors and shapes.

[0437] "Key actors" refer to influential individuals or organizations identified based on network analysis results.

[0438] To implement this invention, a system based on interaction between a server, a terminal, and a user is constructed. The server plays a central role in information gathering and analysis. Specifically, the server automatically collects information periodically from news sites, social networking services, and government databases on the internet by executing a crawler program. This process often utilizes scraping techniques using scripting languages ​​such as Python and JavaScript.

[0439] The server preprocesses the collected data. This includes formatting the data using data processing libraries such as Python's pandas and numpy, and removing irrelevant elements. For image and audio data, feature extraction and speech recognition technologies using OpenCV and TensorFlow are applied.

[0440] Furthermore, the server utilizes libraries such as scikit-learn and NetworkX to execute network analysis algorithms. This allows it to identify related keywords, individuals, and organizations from the collected data and analyze networks of groups considered socially dangerous. The data obtained from the analysis is further evaluated using computer learning algorithms to improve the accuracy of the results. By introducing a reinforcement learning approach, the model is optimized through a feedback loop based on past results.

[0441] Users can access the system via their terminals. For example, when a user enters information about a trading partner into their terminal, that information is sent to the server, where the risk is quickly assessed. The assessment results are presented to the user in a color-coded graphical interface, allowing them to intuitively understand the risk situation. For instance, if the risk is deemed "high," a warning is displayed in red.

[0442] When utilizing generative AI models, one might consider using prompt statements like the following:

[0443] "Please conduct a risk assessment of the company name. Based on information on relevant social risk groups, calculate a risk score and provide the visualized results."

[0444] This system provides a powerful tool for businesses and local governments to efficiently and accurately identify risks and proactively avoid problematic relationships.

[0445] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0446] Step 1:

[0447] The server automatically collects necessary data from publicly accessible sources. Inputs include news site URLs, social media accounts, and government database APIs. A crawler program visits these sources to retrieve text, images, and audio data. The output is stored as raw data in temporary data storage on the server.

[0448] Step 2:

[0449] The server preprocesses the collected raw data. The input is the raw data obtained in step 1. A data cleansing tool is used to remove HTML tags and unnecessary characters from text data and reduce noise from image data. Audio data is converted to text using speech recognition software. The output is clean data in an organized format, optimized for analysis and training.

[0450] Step 3:

[0451] The server performs network analysis using clean data. The input is the output data from step 2. It runs a network analysis algorithm to identify relevant person names, organization names, and keywords from the text data. A reinforcement learning algorithm is integrated into this, and the analysis model is improved using past results. The output is a relationship map and risk-related data.

[0452] Step 4:

[0453] The user inputs information about their business partners into the system using a terminal. This information is specifically defined, such as company names or individual names. This information is sent from the terminal to the server, which then compares the received information with the analysis results from step 3. The output is the risk assessment result.

[0454] Step 5:

[0455] The server visualizes the risk assessment results and sends them to the terminal. The input is the risk assessment results from step 4. The results are displayed as a warning screen corresponding to the risk level using a color scheme (e.g., red, yellow, green). The output is a warning display in a format that is easy for the user to understand. This visualization enables the user to make quick and appropriate decisions.

[0456] (Application Example 1)

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

[0458] Modern businesses and local governments are required to quickly and accurately assess risks associated with their business partners. However, traditional methods have the problem of being time-consuming and labor-intensive when assessing connections with anti-social forces. Furthermore, the visual and intuitive understanding of risks is difficult, which can lead to misjudgments.

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

[0460] In this invention, the server includes means for automatically acquiring data from publicly available information sources on the Internet, means for preprocessing the acquired data and extracting relevant information, means for analyzing anti-social force networks and identifying relevant individuals or organizations, means for updating the judgment logic using a reinforcement learning algorithm, and means for determining risk when business partner information is input and displaying the risk score as a color-coded graphical indicator based on the analysis results. This makes it possible to quickly and accurately determine the risk of business partners and present it in a format that is easy for users to understand intuitively.

[0461] "Publicly available information sources on the internet" refer to online information media that are accessible to anyone, such as websites, news articles, social media, and government databases.

[0462] "Means of automatically acquiring data" refers to the process of continuously collecting information from the internet using a program.

[0463] "Preprocessing and extracting relevant information" refers to the process of standardizing the format of data to make it easier to analyze and extracting only the necessary information.

[0464] "Methods for analyzing anti-social force networks" refers to data analysis techniques used to identify connections between individuals and organizations involved in criminal acts and illegal activities.

[0465] "A method for updating the judgment logic using a reinforcement learning algorithm" refers to a machine learning technique that improves the accuracy of risk assessment based on past analysis results.

[0466] "A method for determining risk by inputting business partner information" refers to a process that evaluates the risks associated with a business partner based on the information provided by the user.

[0467] "Displaying as a color-coded graphical indicator" refers to using indicators of different colors and shapes to visually represent the level of risk.

[0468] In implementing this invention, a server and a terminal primarily play the roles of the server and terminal. First, the server automatically collects data from publicly available information sources on the internet. The data includes text, images, and audio, which are preprocessed within the server. The hardware used is a general-purpose server, and software such as Python or Scrapy is used for data collection and management. The preprocessed data is then subjected to network analysis using machine learning frameworks such as TensorFlow or PyTorch.

[0469] The server analyzes networks associated with anti-social forces using reinforcement learning algorithms. This process automatically updates the logic based on past judgment results while evaluating the risks of business partners. The analysis is performed in real time, and the results are sent to the terminal.

[0470] On the terminal, the user enters customer information. This information is sent to the server, and the analysis results are returned to the terminal and displayed as a risk score. The risk score is shown with color-coded graphical indicators, and a visually intuitive user interface has been designed using React Native.

[0471] For example, if a company wants to evaluate a potential business partner, this terminal app can be used to identify in advance any business partners who may have been involved in antisocial activities in the past.

[0472] An example of a prompt for a generative AI model would be, "Please provide specific steps on how to implement a reinforcement learning model for conducting risk assessments of business partners using a smartphone app." Based on this prompt, the generative AI can provide support for specific implementation steps.

[0473] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0474] Step 1:

[0475] The user uses a terminal to enter information such as the name of a business partner. The entered data is formatted according to the format specified in the interface. Since this data is sent directly to the server, a check for data accuracy is included.

[0476] Step 2:

[0477] The terminal sends the entered data to the server. HTTPS is used as a secure communication method for this process. The transmitted data is temporarily stored on the server and prepared for analysis. This stored data becomes the input for the next analysis.

[0478] Step 3:

[0479] The server automatically retrieves relevant data from publicly available sources on the internet based on the stored data. Web crawling technology, such as Python or Scrapy, is used for this process. The retrieved data serves as input for preprocessing in the next step.

[0480] Step 4:

[0481] The server preprocesses the acquired data to extract the necessary information. For example, if the data is text, natural language processing techniques are used to remove noise and extract important keywords and sentences. This preprocessing filters out unnecessary information, preparing it as input data for the analysis algorithm.

[0482] Step 5:

[0483] The server uses reinforcement learning algorithms to perform network analysis. It identifies individuals and organizations associated with anti-social forces and assesses the associated risks, improving analysis accuracy by utilizing past analysis results as logic. The output is a risk score for business partners.

[0484] Step 6:

[0485] The server sends the resulting risk score to the terminal, which displays the risk as a color-coded graphical indicator. This allows the user to grasp the risk level of their trading partners at a glance and prepare to make further decisions based on detailed text information.

[0486] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0487] To implement this invention, it is necessary to integrate an emotion engine that recognizes user emotions into a system based on server, terminal, and user interaction. The server has the ability to automatically collect data from various sources on the internet. This collected data is used to evaluate the risks associated with anti-social forces using network analysis and reinforcement learning. This provides real-time risk assessment for business partner information.

[0488] Furthermore, when a user enters business partner information into the terminal, the information is assessed to determine if it poses a risk, and the result is displayed on the terminal. At this point, the emotion engine recognizes the user's current emotional state. This engine analyzes the user's voice, facial expressions, input speed, and interaction patterns to evaluate their emotional state.

[0489] For example, if the emotion engine determines that a user is in a high-stress state, the device will reduce the information burden on the user by providing risk information more gently and gradually. Conversely, if the user is calm, the device will ensure the timeliness of the information by immediately providing the risk score and related detailed information.

[0490] This system will enable companies and local governments to conduct efficient and accurate risk assessments, as well as optimize the user experience by providing information tailored to the user's emotional state.

[0491] The following describes the processing flow.

[0492] Step 1:

[0493] The server collects data from publicly available sources on the internet. It retrieves text, images, and audio data from news articles, social media, and government databases, and stores them on the server.

[0494] Step 2:

[0495] The server preprocesses the collected data. It performs text noise reduction, extracts features from images and audio, and converts the data into a format suitable for analysis.

[0496] Step 3:

[0497] The server performs network analysis based on the pre-processed data. To reveal connections with anti-social forces, it uses natural language processing to identify related individuals and organizations.

[0498] Step 4:

[0499] The server analyzes the processed data using a reinforcement learning algorithm and updates the judgment logic. This is designed to continuously improve accuracy.

[0500] Step 5:

[0501] The user enters the trading partner's information on the terminal. The terminal sends this information to the server, which then requests a risk assessment.

[0502] Step 6:

[0503] The server uses the transmitted customer information to assess risk. It calculates a risk score for a specific customer using relevant network data.

[0504] Step 7:

[0505] The device receives the judgment result sent from the server. Simultaneously, the emotion engine installed in the device analyzes and determines the user's emotional state through voice and facial expression data.

[0506] Step 8:

[0507] The emotion engine recognizes the user's emotions, and based on that, the device displays risk information in a format most appropriate to the user's state. If the user is stressed, information is provided in stages; if they are calm, detailed information is provided immediately.

[0508] Step 9:

[0509] Users review the displayed information and, if necessary, decide whether or not to proceed with the transaction. This allows for risk management while taking emotions into consideration.

[0510] (Example 2)

[0511] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0512] In modern business operations, there is a need to quickly and accurately assess risks related to business partners and stakeholders. However, manually analyzing vast amounts of data on the internet is inefficient and can lead to delays in response. Furthermore, presenting information without considering the emotional state of users may hinder appropriate decision-making. To address these problems, a system is needed that enables efficient data collection and analysis, as well as information provision that takes users' emotions into consideration.

[0513] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0514] In this invention, the server includes means for automatically acquiring information from a data source, means for extracting relevant information using the acquired information, means for analyzing a network of social stakeholders to identify relevant individuals or groups, means for updating the judgment logic using a machine learning algorithm, means including an engine for performing risk assessment and evaluating the emotional state of the user for providing information, and means for visualizing and presenting the information. This enables efficient and accurate risk assessment and the provision of appropriate information according to the user's situation.

[0515] A "data source" refers to the starting point or the information provider from which information is obtained.

[0516] "Means of automatically acquiring information" refers to methods of collecting information using computers and network systems without human intervention.

[0517] "Means of extracting relevant information" refers to the process of selecting useful and necessary information from collected data.

[0518] "Means of analyzing networks of social stakeholders to identify relevant individuals or groups" refers to methods of investigating connections between stakeholders and using that information to identify individuals or organizations with significant relationships.

[0519] "Methods for updating judgment logic using machine learning algorithms" refer to computational methods that learn from empirical data and improve prediction and judgment methods.

[0520] "Means including an engine that evaluates the emotional state of users for risk assessment and information provision" refers to programs or devices that analyze the emotional state of users and present appropriate information based on that analysis.

[0521] "Means of visualizing and presenting information" refers to methods and devices for displaying data and analysis results in a way that is easy for users to understand.

[0522] To implement this invention, a system involving a server, a terminal, and a user is primarily required. The server collects information from various data sources on the internet. This collection process is achieved by using the Python library Requests to automatically send HTTP requests to API endpoints.

[0523] The server further performs risk assessment by analyzing data with Scikit-learn and applying machine learning algorithms using TensorFlow. This makes it possible to assess risks associated with antisocial elements in real time. This information is transmitted to terminals via a dedicated network interface.

[0524] Users enter business partner information on the terminal. This input is done using a standard keyboard or touch panel, and the entered information is immediately transmitted to the server. The terminal is equipped with an engine that evaluates the user's emotional state, using Google Cloud Speech-to-Text and OpenCV to analyze the user's voice, facial expressions, and input speed to determine their emotions.

[0525] As a concrete example, suppose a user enters information about a new business partner into the system. When this information is sent to the server, the server calculates a risk score for the business partner based on relevant data collected from the internet. In this process, if the data collected by the server indicates past involvement with anti-social forces, the score for that business partner is increased. Once the risk assessment is complete, the results are returned to the terminal and presented to the user visually.

[0526] Furthermore, depending on the user's emotional state, this information can be provided either gradually or immediately in detail. An example of a specific prompt might be, "Describe a system that collects the information necessary for the user to assess the risks of a new business partner and adjusts the information presentation method based on the stress assessment by the emotion engine." In this way, the system can promote appropriate risk management while reducing the burden on the user.

[0527] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0528] Step 1:

[0529] The server automatically retrieves information from publicly available data sources on the internet. Specifically, it uses the Python library Requests to obtain real-time data from news sites, government databases, social media, etc., via APIs. The input to this process is pre-configured keywords and customer names, and the output is a collection of data that matches specific conditions.

[0530] Step 2:

[0531] The server preprocesses the acquired data and extracts relevant information. Here, Scikit-learn is used to analyze the data and perform natural language processing to filter out useful information. The input is the data collected in step 1, and the output is clear information necessary for risk assessment.

[0532] Step 3:

[0533] The server applies a reinforcement learning algorithm to calculate a risk score. Specifically, it uses TensorFlow to build a model that assesses risk based on the past behavior and relevant data of the trading partner. The input is the information obtained in step 2, and the output is a specific risk score.

[0534] Step 4:

[0535] The user enters the business partner's information into the terminal and sends it to the server. The information entered by the user includes the business partner's name, address, and industry, and processing begins once this information is sent to the server.

[0536] Step 5:

[0537] The terminal receives the risk score sent from the server and displays it on the screen. Here, the information is presented to the user in an easy-to-understand way by visually displaying the risk level with different colors. Specifically, a red indicator is displayed on the screen if the risk is high, and a green indicator is displayed if the risk is low. The input is the output of step 3, and the output is the visual information presented to the user.

[0538] Step 6:

[0539] The device's emotion engine detects the user's emotional state and adjusts how information is presented. Using OpenCV and Google Cloud Speech-to-Text, it analyzes the user's facial expressions and tone of voice to assess their emotional state. The input is the user's voice and facial expression data, and the output is a proposal that reflects this in the format of information presentation. Specifically, if a high-stress state is detected, information will be presented in stages.

[0540] (Application Example 2)

[0541] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0542] Risk assessment of business partners is becoming increasingly important in modern business activities. However, current risk assessment systems do not provide information that takes into account the emotional state of users, which can lead to user stress and decision-making errors due to information overload. Furthermore, collecting and analyzing data in real time from numerous sources is difficult. Therefore, there is a need for a system that can consider the emotional state of users and present risk information intuitively and effectively.

[0543] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0544] In this invention, the server includes means for automatically acquiring data from publicly available information sources on the Internet, means for preprocessing the acquired data and extracting relevant information, means for analyzing anti-social groups and identifying relevant individuals or organizations, means for updating the judgment logic using a reinforcement learning algorithm, means for determining risk when business partner information is input and displaying the results, means for sentiment analysis that analyzes the user's voice and facial expressions and evaluates their emotional state, and means for adjusting the presentation of information based on the user's emotional state. This enables efficient and accurate risk assessment by presenting risk information in the most appropriate way according to the user's emotional state.

[0545] "Publicly available information sources on the Internet" refer to a collection of information that exists on the Internet in a form that is generally accessible, such as websites and databases.

[0546] A "function that automatically acquires data" is a mechanism that collects information from the internet according to set criteria without user intervention.

[0547] The "preprocessing and information extraction function" refers to the process of identifying important information from acquired data and converting it into an appropriate format for analysis.

[0548] The "function for analyzing antisocial groups" refers to a mechanism for identifying individuals and groups exhibiting antisocial behavior and analyzing their networks.

[0549] The "emotion analysis function" is a process that evaluates the user's emotional state from their voice and facial expressions, and is used to adjust the information presented.

[0550] A "reinforcement learning algorithm" is a computational method that allows a system to improve its decision-making logic through learning and perform accurate risk assessments.

[0551] A "function to adjust the presentation of information" is a mechanism that optimizes the way information is displayed and its content according to the user's emotional state.

[0552] The "risk assessment and display of results function" is a process that evaluates risk based on input data and visualizes the results for the user.

[0553] To implement this system, the server automatically retrieves data from publicly available sources on the internet. The server preprocesses this data, performing data filtering and analysis to extract relevant information. To identify individuals or groups associated with anti-social forces, the server uses network analysis techniques. Based on the results of this analysis, a reinforcement learning algorithm is employed, and the server continuously improves its judgment logic.

[0554] The device uses emotion analysis to assess the user's emotional state in real time from their voice and facial expressions. This function utilizes services such as the Google Cloud Speech-to-Text API and the Microsoft Azure Face API. Depending on the user's emotional state, the device adjusts how it presents risk information, communicating the risk level to the user in a gentle manner.

[0555] As a concrete example, consider a scenario where a user enters information about a new business partner into a terminal. The server assesses the risk associated with that information in real time, and the terminal displays the results according to the user's emotional state. If the user is feeling stressed, the risk information is displayed more gently and gradually; if the user is calm, a comprehensive risk assessment is provided quickly.

[0556] An example of a prompt is: "Design an AI system that assesses security risks in real time during meetings with new business partners. This system should have the ability to change how information is presented based on the user's emotional state." Using this example, a generative AI model can build a system that presents information appropriately according to the context.

[0557] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0558] Step 1:

[0559] The server automatically retrieves data from publicly available sources on the internet. It receives configured queries and information filtering conditions as input. Based on this, the server uses APIs and web scraping tools to collect the appropriate information. The output is stored in raw data format.

[0560] Step 2:

[0561] The server preprocesses the acquired raw data and extracts relevant information. The input is the raw data collected in step 1. Data cleaning and transformation processes are performed to convert it into structured data that can be handled by machine learning models. The output is data that has been formatted to be analyzable.

[0562] Step 3:

[0563] The server analyzes antisocial groups and identifies relevant individuals or organizations. The input is the formatted data obtained in step 2. Network analysis algorithms are used to visualize relationships within the data and identify risk factors. The output is a list of high-risk, relevant individuals or organizations.

[0564] Step 4:

[0565] The server updates the decision logic using a reinforcement learning algorithm. The input is the analysis result from step 3. It incorporates feedback data and continues to train the risk assessment model. The output is the updated risk decision logic.

[0566] Step 5:

[0567] The device analyzes the user's voice and facial expressions to assess their emotional state. The input is real-time voice and facial expression data from the user. Facial recognition and speech recognition technologies are used to quantify the user's emotional state. The output is a numerical value or category indicating the emotional state.

[0568] Step 6:

[0569] The device adjusts the information presentation based on the user's emotional state. Inputs are the emotional assessment results from step 5 and risk assessment data from the server. If the user is stressed, an algorithm is applied that presents information gradually and in stages. The output is the method of information presentation tailored to the user's current emotional state.

[0570] Step 7:

[0571] The user inputs customer information via a terminal and assesses the risk. The input consists of detailed customer information provided by the user. The terminal sends the input information to a server, where the risk is assessed in real time. The output is the risk assessment result displayed on the terminal.

[0572] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0573] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0574] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0575] [Fourth Embodiment]

[0576] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0577] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0578] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0579] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0580] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0581] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0582] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0583] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0584] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0585] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0586] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0587] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0588] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0589] To implement this invention, a system based on interaction between a server, a terminal, and a user will be constructed. The server will have the function of automatically collecting data from various information sources on the internet. This includes news, social networking services, and publicly available government databases. The data types include text, images, and audio, which will be pre-processed after being taken into the server.

[0590] The pre-processed data is analyzed by a network analysis algorithm running on the server. This analysis algorithm constructs a network of anti-social forces and identifies related individuals and organizations. Furthermore, reinforcement learning is incorporated into this process, updating the judgment logic using historical data to improve accuracy over time.

[0591] The user enters the name of the business partner and related information via a terminal. The terminal sends this information to a server, which immediately determines the risk based on the received information. The result is returned to the terminal and presented to the user. The display visually indicates the risk level, using colors and graphical indicators to present it in a format that is easy for the user to intuitively understand.

[0592] For example, if a user enters a company name, the server uses previously collected data to investigate its connection to that company. Network analysis determines that the company is linked to a specific anti-social group, and a risk score is calculated based on the level of risk. The terminal classifies this score as "high risk," "medium risk," or "low risk" and warns the user with a color-coded signal.

[0593] This system enables companies and local governments to efficiently and accurately detect relevant risks and sever unnecessary relationships early on.

[0594] The following describes the processing flow.

[0595] Step 1:

[0596] The server automatically collects data from publicly available sources on the internet. It retrieves text, images, and audio data from news articles, social media, and government databases, and stores them in storage.

[0597] Step 2:

[0598] The server preprocesses the collected data. Text data undergoes noise reduction and normalization, while image and audio data are subjected to feature extraction. This prepares the data for analysis in a suitable format.

[0599] Step 3:

[0600] The server performs network analysis using pre-processed data. Utilizing natural language processing techniques, it extracts individuals and organizations associated with anti-social forces from text data and constructs a network structure.

[0601] Step 4:

[0602] The server uses a reinforcement learning algorithm to update its decision logic. It references past data and results to make adjustments to improve the accuracy of the decision process.

[0603] Step 5:

[0604] The user enters customer information on their terminal. The terminal sends this information to the server and requests a real-time risk assessment.

[0605] Step 6:

[0606] The server performs a risk assessment based on the received information. It refers to relevant network information and analyzes and generates a risk score for a specific business partner.

[0607] Step 7:

[0608] The server sends the assessment results to the terminal. This includes risk scores and information about related individuals and organizations.

[0609] Step 8:

[0610] The device visually displays the received risk assessment results to the user. It provides color-coded indicators based on score levels and detailed information, allowing the user to intuitively understand the risk.

[0611] (Example 1)

[0612] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0613] In society and for businesses, it is crucial to detect early on if business partners or related entities are involved with groups considered socially dangerous, and to assess the risks in advance. Traditional methods have been problematic due to the time-consuming nature of information gathering and analysis, as well as the inconsistent accuracy of risk assessments. Therefore, there is a need to provide a system that can quickly and accurately determine risks and present them in a visually easy-to-understand format.

[0614] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0615] In this invention, the server includes means for automatically collecting information from public sources, means for preprocessing the collected information and extracting relevant content, means for analyzing networks of socially dangerous groups and identifying relevant entities, means for dynamically improving the judgment logic using a computer learning algorithm, means for evaluating risk by inputting transaction-related information and outputting the evaluation results, means for visually outputting the evaluation results and presenting the risk level to the user using color, and means for displaying a list of important entities and key related information based on the evaluation. This enables rapid and accurate risk assessment and allows users to intuitively understand the degree of risk.

[0616] "Public information sources" generally refer to information sources that are accessible on the internet, such as news sites, social media, and government databases.

[0617] "Preprocessing" refers to the process of removing noise from collected raw data and preparing it in a format suitable for data analysis.

[0618] A "socially dangerous group" refers to an organization or group that has the potential to cause legal or moral harm to society.

[0619] A "computer learning algorithm" refers to a mathematical process by which a computer uses data to learn empirically and make predictions and decisions.

[0620] "Decision logic" refers to a set of criteria used to evaluate risk and relevance based on data.

[0621] "Visual output" refers to displaying results in a way that is easy for users to understand intuitively, typically using colors and shapes.

[0622] "Key actors" refer to influential individuals or organizations identified based on network analysis results.

[0623] To implement this invention, a system based on interaction between a server, a terminal, and a user is constructed. The server plays a central role in information gathering and analysis. Specifically, the server automatically collects information periodically from news sites, social networking services, and government databases on the internet by executing a crawler program. This process often utilizes scraping techniques using scripting languages ​​such as Python and JavaScript.

[0624] The server preprocesses the collected data. This includes formatting the data using data processing libraries such as Python's pandas and numpy, and removing irrelevant elements. For image and audio data, feature extraction and speech recognition technologies using OpenCV and TensorFlow are applied.

[0625] Furthermore, the server utilizes libraries such as scikit-learn and NetworkX to execute network analysis algorithms. This allows it to identify related keywords, individuals, and organizations from the collected data and analyze networks of groups considered socially dangerous. The data obtained from the analysis is further evaluated using computer learning algorithms to improve the accuracy of the results. By introducing a reinforcement learning approach, the model is optimized through a feedback loop based on past results.

[0626] Users can access the system via their terminals. For example, when a user enters information about a trading partner into their terminal, that information is sent to the server, where the risk is quickly assessed. The assessment results are presented to the user in a color-coded graphical interface, allowing them to intuitively understand the risk situation. For instance, if the risk is deemed "high," a warning is displayed in red.

[0627] When utilizing generative AI models, one might consider using prompt statements like the following:

[0628] "Please conduct a risk assessment of the company name. Based on information on relevant social risk groups, calculate a risk score and provide the visualized results."

[0629] This system provides a powerful tool for businesses and local governments to efficiently and accurately identify risks and proactively avoid problematic relationships.

[0630] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0631] Step 1:

[0632] The server automatically collects necessary data from publicly accessible sources. Inputs include news site URLs, social media accounts, and government database APIs. A crawler program visits these sources to retrieve text, images, and audio data. The output is stored as raw data in temporary data storage on the server.

[0633] Step 2:

[0634] The server preprocesses the collected raw data. The input is the raw data obtained in step 1. A data cleansing tool is used to remove HTML tags and unnecessary characters from text data and reduce noise from image data. Audio data is converted to text using speech recognition software. The output is clean data in an organized format, optimized for analysis and training.

[0635] Step 3:

[0636] The server performs network analysis using clean data. The input is the output data from step 2. It runs a network analysis algorithm to identify relevant person names, organization names, and keywords from the text data. A reinforcement learning algorithm is integrated into this, and the analysis model is improved using past results. The output is a relationship map and risk-related data.

[0637] Step 4:

[0638] The user inputs information about their business partners into the system using a terminal. This information is specifically defined, such as company names or individual names. This information is sent from the terminal to the server, which then compares the received information with the analysis results from step 3. The output is the risk assessment result.

[0639] Step 5:

[0640] The server visualizes the risk assessment results and sends them to the terminal. The input is the risk assessment results from step 4. The results are displayed as a warning screen corresponding to the risk level using a color scheme (e.g., red, yellow, green). The output is a warning display in a format that is easy for the user to understand. This visualization enables the user to make quick and appropriate decisions.

[0641] (Application Example 1)

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

[0643] Modern businesses and local governments are required to quickly and accurately assess risks associated with their business partners. However, traditional methods have the problem of being time-consuming and labor-intensive when assessing connections with anti-social forces. Furthermore, the visual and intuitive understanding of risks is difficult, which can lead to misjudgments.

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

[0645] In this invention, the server includes means for automatically acquiring data from publicly available information sources on the Internet, means for preprocessing the acquired data and extracting relevant information, means for analyzing anti-social force networks and identifying relevant individuals or organizations, means for updating the judgment logic using a reinforcement learning algorithm, and means for determining risk when business partner information is input and displaying the risk score as a color-coded graphical indicator based on the analysis results. This makes it possible to quickly and accurately determine the risk of business partners and present it in a format that is easy for users to understand intuitively.

[0646] "Publicly available information sources on the internet" refer to online information media that are accessible to anyone, such as websites, news articles, social media, and government databases.

[0647] "Means of automatically acquiring data" refers to the process of continuously collecting information from the internet using a program.

[0648] "Preprocessing and extracting relevant information" refers to the process of standardizing the format of data to make it easier to analyze and extracting only the necessary information.

[0649] "Methods for analyzing anti-social force networks" refers to data analysis techniques used to identify connections between individuals and organizations involved in criminal acts and illegal activities.

[0650] "A method for updating the judgment logic using a reinforcement learning algorithm" refers to a machine learning technique that improves the accuracy of risk assessment based on past analysis results.

[0651] "A method for determining risk by inputting business partner information" refers to a process that evaluates the risks associated with a business partner based on the information provided by the user.

[0652] "Displaying as a color-coded graphical indicator" refers to using indicators of different colors and shapes to visually represent the level of risk.

[0653] In implementing this invention, a server and a terminal primarily play the roles of the server and terminal. First, the server automatically collects data from publicly available information sources on the internet. The data includes text, images, and audio, which are preprocessed within the server. The hardware used is a general-purpose server, and software such as Python or Scrapy is used for data collection and management. The preprocessed data is then subjected to network analysis using machine learning frameworks such as TensorFlow or PyTorch.

[0654] The server analyzes networks associated with anti-social forces using reinforcement learning algorithms. This process automatically updates the logic based on past judgment results while evaluating the risks of business partners. The analysis is performed in real time, and the results are sent to the terminal.

[0655] On the terminal, the user enters customer information. This information is sent to the server, and the analysis results are returned to the terminal and displayed as a risk score. The risk score is shown with color-coded graphical indicators, and a visually intuitive user interface has been designed using React Native.

[0656] For example, if a company wants to evaluate a potential business partner, this terminal app can be used to identify in advance any business partners who may have been involved in antisocial activities in the past.

[0657] An example of a prompt for a generative AI model would be, "Please provide specific steps on how to implement a reinforcement learning model for conducting risk assessments of business partners using a smartphone app." Based on this prompt, the generative AI can provide support for specific implementation steps.

[0658] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0659] Step 1:

[0660] The user uses a terminal to enter information such as the name of a business partner. The entered data is formatted according to the format specified in the interface. Since this data is sent directly to the server, a check for data accuracy is included.

[0661] Step 2:

[0662] The terminal sends the entered data to the server. HTTPS is used as a secure communication method for this process. The transmitted data is temporarily stored on the server and prepared for analysis. This stored data becomes the input for the next analysis.

[0663] Step 3:

[0664] The server automatically retrieves relevant data from publicly available sources on the internet based on the stored data. Web crawling technology, such as Python or Scrapy, is used for this process. The retrieved data serves as input for preprocessing in the next step.

[0665] Step 4:

[0666] The server preprocesses the acquired data to extract the necessary information. For example, if the data is text, natural language processing techniques are used to remove noise and extract important keywords and sentences. This preprocessing filters out unnecessary information, preparing it as input data for the analysis algorithm.

[0667] Step 5:

[0668] The server uses reinforcement learning algorithms to perform network analysis. It identifies individuals and organizations associated with anti-social forces and assesses the associated risks, improving analysis accuracy by utilizing past analysis results as logic. The output is a risk score for business partners.

[0669] Step 6:

[0670] The server sends the resulting risk score to the terminal, which displays the risk as a color-coded graphical indicator. This allows the user to grasp the risk level of their trading partners at a glance and prepare to make further decisions based on detailed text information.

[0671] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0672] To implement this invention, it is necessary to integrate an emotion engine that recognizes user emotions into a system based on server, terminal, and user interaction. The server has the ability to automatically collect data from various sources on the internet. This collected data is used to evaluate the risks associated with anti-social forces using network analysis and reinforcement learning. This provides real-time risk assessment for business partner information.

[0673] Furthermore, when a user enters business partner information into the terminal, the information is assessed to determine if it poses a risk, and the result is displayed on the terminal. At this point, the emotion engine recognizes the user's current emotional state. This engine analyzes the user's voice, facial expressions, input speed, and interaction patterns to evaluate their emotional state.

[0674] For example, if the emotion engine determines that a user is in a high-stress state, the device will reduce the information burden on the user by providing risk information more gently and gradually. Conversely, if the user is calm, the device will ensure the timeliness of the information by immediately providing the risk score and related detailed information.

[0675] This system will enable companies and local governments to conduct efficient and accurate risk assessments, as well as optimize the user experience by providing information tailored to the user's emotional state.

[0676] The following describes the processing flow.

[0677] Step 1:

[0678] The server collects data from publicly available sources on the internet. It retrieves text, images, and audio data from news articles, social media, and government databases, and stores them on the server.

[0679] Step 2:

[0680] The server preprocesses the collected data. It performs text noise reduction, extracts features from images and audio, and converts the data into a format suitable for analysis.

[0681] Step 3:

[0682] The server performs network analysis based on the pre-processed data. To reveal connections with anti-social forces, it uses natural language processing to identify related individuals and organizations.

[0683] Step 4:

[0684] The server analyzes the processed data using a reinforcement learning algorithm and updates the judgment logic. This is designed to continuously improve accuracy.

[0685] Step 5:

[0686] The user enters the trading partner's information on the terminal. The terminal sends this information to the server, which then requests a risk assessment.

[0687] Step 6:

[0688] The server uses the transmitted customer information to assess risk. It calculates a risk score for a specific customer using relevant network data.

[0689] Step 7:

[0690] The device receives the judgment result sent from the server. Simultaneously, the emotion engine installed in the device analyzes and determines the user's emotional state through voice and facial expression data.

[0691] Step 8:

[0692] The emotion engine recognizes the user's emotions, and based on that, the device displays risk information in a format most appropriate to the user's state. If the user is stressed, information is provided in stages; if they are calm, detailed information is provided immediately.

[0693] Step 9:

[0694] Users review the displayed information and, if necessary, decide whether or not to proceed with the transaction. This allows for risk management while taking emotions into consideration.

[0695] (Example 2)

[0696] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0697] In modern business operations, there is a need to quickly and accurately assess risks related to business partners and stakeholders. However, manually analyzing vast amounts of data on the internet is inefficient and can lead to delays in response. Furthermore, presenting information without considering the emotional state of users may hinder appropriate decision-making. To address these problems, a system is needed that enables efficient data collection and analysis, as well as information provision that takes users' emotions into consideration.

[0698] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0699] In this invention, the server includes means for automatically acquiring information from a data source, means for extracting relevant information using the acquired information, means for analyzing a network of social stakeholders to identify relevant individuals or groups, means for updating the judgment logic using a machine learning algorithm, means including an engine for performing risk assessment and evaluating the emotional state of the user for providing information, and means for visualizing and presenting the information. This enables efficient and accurate risk assessment and the provision of appropriate information according to the user's situation.

[0700] A "data source" refers to the starting point or the information provider from which information is obtained.

[0701] "Means of automatically acquiring information" refers to methods of collecting information using computers and network systems without human intervention.

[0702] "Means of extracting relevant information" refers to the process of selecting useful and necessary information from collected data.

[0703] "Means of analyzing networks of social stakeholders to identify relevant individuals or groups" refers to methods of investigating connections between stakeholders and using that information to identify individuals or organizations with significant relationships.

[0704] "Methods for updating judgment logic using machine learning algorithms" refer to computational methods that learn from empirical data and improve prediction and judgment methods.

[0705] "Means including an engine that evaluates the emotional state of users for risk assessment and information provision" refers to programs or devices that analyze the emotional state of users and present appropriate information based on that analysis.

[0706] "Means of visualizing and presenting information" refers to methods and devices for displaying data and analysis results in a way that is easy for users to understand.

[0707] To implement this invention, a system involving a server, a terminal, and a user is primarily required. The server collects information from various data sources on the internet. This collection process is achieved by using the Python library Requests to automatically send HTTP requests to API endpoints.

[0708] The server further performs risk assessment by analyzing data with Scikit-learn and applying machine learning algorithms using TensorFlow. This makes it possible to assess risks associated with antisocial elements in real time. This information is transmitted to terminals via a dedicated network interface.

[0709] Users enter business partner information on the terminal. This input is done using a standard keyboard or touch panel, and the entered information is immediately transmitted to the server. The terminal is equipped with an engine that evaluates the user's emotional state, using Google Cloud Speech-to-Text and OpenCV to analyze the user's voice, facial expressions, and input speed to determine their emotions.

[0710] As a concrete example, suppose a user enters information about a new business partner into the system. When this information is sent to the server, the server calculates a risk score for the business partner based on relevant data collected from the internet. In this process, if the data collected by the server indicates past involvement with anti-social forces, the score for that business partner is increased. Once the risk assessment is complete, the results are returned to the terminal and presented to the user visually.

[0711] Furthermore, depending on the user's emotional state, this information can be provided either gradually or immediately in detail. An example of a specific prompt might be, "Describe a system that collects the information necessary for the user to assess the risks of a new business partner and adjusts the information presentation method based on the stress assessment by the emotion engine." In this way, the system can promote appropriate risk management while reducing the burden on the user.

[0712] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0713] Step 1:

[0714] The server automatically retrieves information from publicly available data sources on the internet. Specifically, it uses the Python library Requests to obtain real-time data from news sites, government databases, social media, etc., via APIs. The input to this process is pre-configured keywords and customer names, and the output is a collection of data that matches specific conditions.

[0715] Step 2:

[0716] The server preprocesses the acquired data and extracts relevant information. Here, Scikit-learn is used to analyze the data and perform natural language processing to filter out useful information. The input is the data collected in step 1, and the output is clear information necessary for risk assessment.

[0717] Step 3:

[0718] The server applies a reinforcement learning algorithm to calculate a risk score. Specifically, it uses TensorFlow to build a model that assesses risk based on the past behavior and relevant data of the trading partner. The input is the information obtained in step 2, and the output is a specific risk score.

[0719] Step 4:

[0720] The user enters the business partner's information into the terminal and sends it to the server. The information entered by the user includes the business partner's name, address, and industry, and processing begins once this information is sent to the server.

[0721] Step 5:

[0722] The terminal receives the risk score sent from the server and displays it on the screen. Here, the information is presented to the user in an easy-to-understand way by visually displaying the risk level with different colors. Specifically, a red indicator is displayed on the screen if the risk is high, and a green indicator is displayed if the risk is low. The input is the output of step 3, and the output is the visual information presented to the user.

[0723] Step 6:

[0724] The device's emotion engine detects the user's emotional state and adjusts how information is presented. Using OpenCV and Google Cloud Speech-to-Text, it analyzes the user's facial expressions and tone of voice to assess their emotional state. The input is the user's voice and facial expression data, and the output is a proposal that reflects this in the format of information presentation. Specifically, if a high-stress state is detected, information will be presented in stages.

[0725] (Application Example 2)

[0726] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0727] Risk assessment of business partners is becoming increasingly important in modern business activities. However, current risk assessment systems do not provide information that takes into account the emotional state of users, which can lead to user stress and decision-making errors due to information overload. Furthermore, collecting and analyzing data in real time from numerous sources is difficult. Therefore, there is a need for a system that can consider the emotional state of users and present risk information intuitively and effectively.

[0728] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0729] In this invention, the server includes means for automatically acquiring data from publicly available information sources on the Internet, means for preprocessing the acquired data and extracting relevant information, means for analyzing anti-social groups and identifying relevant individuals or organizations, means for updating the judgment logic using a reinforcement learning algorithm, means for determining risk when business partner information is input and displaying the results, means for sentiment analysis that analyzes the user's voice and facial expressions and evaluates their emotional state, and means for adjusting the presentation of information based on the user's emotional state. This enables efficient and accurate risk assessment by presenting risk information in the most appropriate way according to the user's emotional state.

[0730] "Publicly available information sources on the Internet" refer to a collection of information that exists on the Internet in a form that is generally accessible, such as websites and databases.

[0731] A "function that automatically acquires data" is a mechanism that collects information from the internet according to set criteria without user intervention.

[0732] The "preprocessing and information extraction function" refers to the process of identifying important information from acquired data and converting it into an appropriate format for analysis.

[0733] The "function for analyzing antisocial groups" refers to a mechanism for identifying individuals and groups exhibiting antisocial behavior and analyzing their networks.

[0734] The "emotion analysis function" is a process that evaluates the user's emotional state from their voice and facial expressions, and is used to adjust the information presented.

[0735] A "reinforcement learning algorithm" is a computational method that allows a system to improve its decision-making logic through learning and perform accurate risk assessments.

[0736] A "function to adjust the presentation of information" is a mechanism that optimizes the way information is displayed and its content according to the user's emotional state.

[0737] The "risk assessment and display of results function" is a process that evaluates risk based on input data and visualizes the results for the user.

[0738] To implement this system, the server automatically retrieves data from publicly available sources on the internet. The server preprocesses this data, performing data filtering and analysis to extract relevant information. To identify individuals or groups associated with anti-social forces, the server uses network analysis techniques. Based on the results of this analysis, a reinforcement learning algorithm is employed, and the server continuously improves its judgment logic.

[0739] The device uses emotion analysis to assess the user's emotional state in real time from their voice and facial expressions. This function utilizes services such as the Google Cloud Speech-to-Text API and the Microsoft Azure Face API. Depending on the user's emotional state, the device adjusts how it presents risk information, communicating the risk level to the user in a gentle manner.

[0740] As a concrete example, consider a scenario where a user enters information about a new business partner into a terminal. The server assesses the risk associated with that information in real time, and the terminal displays the results according to the user's emotional state. If the user is feeling stressed, the risk information is displayed more gently and gradually; if the user is calm, a comprehensive risk assessment is provided quickly.

[0741] An example of a prompt is: "Design an AI system that assesses security risks in real time during meetings with new business partners. This system should have the ability to change how information is presented based on the user's emotional state." Using this example, a generative AI model can build a system that presents information appropriately according to the context.

[0742] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0743] Step 1:

[0744] The server automatically retrieves data from publicly available sources on the internet. It receives configured queries and information filtering conditions as input. Based on this, the server uses APIs and web scraping tools to collect the appropriate information. The output is stored in raw data format.

[0745] Step 2:

[0746] The server preprocesses the acquired raw data and extracts relevant information. The input is the raw data collected in step 1. Data cleaning and transformation processes are performed to convert it into structured data that can be handled by machine learning models. The output is data that has been formatted to be analyzable.

[0747] Step 3:

[0748] The server analyzes antisocial groups and identifies relevant individuals or organizations. The input is the formatted data obtained in step 2. Network analysis algorithms are used to visualize relationships within the data and identify risk factors. The output is a list of high-risk, relevant individuals or organizations.

[0749] Step 4:

[0750] The server updates the decision logic using a reinforcement learning algorithm. The input is the analysis result from step 3. It incorporates feedback data and continues to train the risk assessment model. The output is the updated risk decision logic.

[0751] Step 5:

[0752] The device analyzes the user's voice and facial expressions to assess their emotional state. The input is real-time voice and facial expression data from the user. Facial recognition and speech recognition technologies are used to quantify the user's emotional state. The output is a numerical value or category indicating the emotional state.

[0753] Step 6:

[0754] The device adjusts the information presentation based on the user's emotional state. Inputs are the emotional assessment results from step 5 and risk assessment data from the server. If the user is stressed, an algorithm is applied that presents information gradually and in stages. The output is the method of information presentation tailored to the user's current emotional state.

[0755] Step 7:

[0756] The user inputs customer information via a terminal and assesses the risk. The input consists of detailed customer information provided by the user. The terminal sends the input information to a server, where the risk is assessed in real time. The output is the risk assessment result displayed on the terminal.

[0757] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0758] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0759] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0760] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0761] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0762] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0763] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0764] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0765] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0766] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0767] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0768] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0769] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0770] 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.

[0771] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0772] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0773] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0774] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0775] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0776] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0777] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0778] The following is further disclosed regarding the embodiments described above.

[0779] (Claim 1)

[0780] A means of automatically obtaining data from publicly available information sources on the internet,

[0781] A means for preprocessing acquired data and extracting relevant information,

[0782] Means for analyzing anti-social force networks and identifying related individuals or organizations,

[0783] A means of updating the decision logic using a reinforcement learning algorithm,

[0784] A system that includes a means to assess risk based on input of business partner information and display the results.

[0785] (Claim 2)

[0786] The system according to claim 1, further comprising means for visually displaying the risk assessment results, wherein the risk levels are presented to the user in different colors.

[0787] (Claim 3)

[0788] The system according to claim 1, which, based on the determination results, lists and outputs key individuals or organizations that are relevant and their key related information.

[0789] "Example 1"

[0790] (Claim 1)

[0791] Means for automatically collecting information from public sources,

[0792] A means for preprocessing collected information and extracting relevant content,

[0793] A means of analyzing the networks of groups considered socially dangerous and identifying relevant actors,

[0794] A means of dynamically improving the judgment logic using a computer learning algorithm,

[0795] A system that includes a means to assess risk by inputting transaction-related information and outputting the assessment results.

[0796] (Claim 2)

[0797] The system according to claim 1, which visually outputs the evaluation results and presents the level of risk to the user using color.

[0798] (Claim 3)

[0799] The system according to claim 1, which lists key entities and related key information based on an evaluation.

[0800] "Application Example 1"

[0801] (Claim 1)

[0802] A means of automatically obtaining data from publicly available information sources on the internet,

[0803] A means for preprocessing acquired data and extracting relevant information,

[0804] Means for analyzing anti-social force networks and identifying related individuals or organizations,

[0805] A means of updating the decision logic using a reinforcement learning algorithm,

[0806] A system that includes a means of determining risk based on input of business partner information and displaying the risk score as a color-coded graphical indicator based on the analysis results.

[0807] (Claim 2)

[0808] The system according to claim 1, which visually displays the risk assessment results and presents the risk level to the user using a color-coded graphical indicator.

[0809] (Claim 3)

[0810] The system according to claim 1, which, based on the determination results, lists and outputs key relevant individuals or organizations and key related information, and displays the information via a smart device.

[0811] "Example 2 of combining an emotion engine"

[0812] (Claim 1)

[0813] A means of automatically acquiring information from a data source,

[0814] A means of extracting relevant information using acquired information,

[0815] A means of analyzing the network of social stakeholders to identify relevant individuals or groups,

[0816] A means of updating the judgment logic using a machine learning algorithm,

[0817] A means including an engine that performs risk assessment and evaluates the emotional state of users in order to provide information,

[0818] A system that includes means for visualizing and presenting information.

[0819] (Claim 2)

[0820] The system according to claim 1, which provides information in stages based on the user's emotional state.

[0821] (Claim 3)

[0822] The system according to claim 1, which outputs a list of major related organizations and important related information based on the judgment result.

[0823] "Application example 2 when combining with an emotional engine"

[0824] (Claim 1)

[0825] A means of automatically acquiring data from publicly available information sources on the internet,

[0826] A means that has the function of preprocessing acquired data and extracting relevant information,

[0827] A means equipped with the function of analyzing anti-social groups and identifying related individuals or organizations,

[0828] A means that includes a function to update the judgment logic using a reinforcement learning algorithm,

[0829] A means that takes customer information as input, assesses the risk, and displays the result.

[0830] A means equipped with an emotion analysis function that analyzes the user's voice and facial expressions and evaluates their emotional state,

[0831] A system that includes means for adjusting the presentation of information based on the user's emotional state.

[0832] (Claim 2)

[0833] The system according to claim 1, further comprising a function to visually display the risk assessment results, presenting the risk levels to the user in different colors, and providing information in stages in a manner that corresponds to the user's emotional state.

[0834] (Claim 3)

[0835] The system according to claim 1, which outputs a list of key individuals or organizations and key related information based on the determination results. [Explanation of symbols]

[0836] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of automatically obtaining data from publicly available information sources on the internet, A means for preprocessing acquired data and extracting relevant information, Means for analyzing anti-social force networks and identifying related individuals or organizations, A means of updating the decision logic using a reinforcement learning algorithm, A system that includes a means to assess risk based on input of business partner information and display the results.

2. The system according to claim 1, further comprising means for visually displaying the risk assessment results, wherein the risk levels are presented to the user in different colors.

3. The system according to claim 1, which, based on the determination results, lists and outputs key individuals or organizations that are relevant and their key related information.

Images