system

Abstract

We provide the system. [Solution] A means for acquiring image data, audio data, and text data, An analytical method that integrates the acquired data and analyzes it in real time, An evaluation method for assessing risk from analysis results and generating a risk report, A system that includes a notification mechanism for informing users of the evaluated risk report.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, the situation where people and corporations in socially vulnerable positions face various risks has been increasing. In particular, there is a need to identify potential risks latent in daily life and business in advance and take appropriate measures, but it is difficult for current tools and systems to evaluate these risks comprehensively and in real time. To solve this problem, an effective system for individuals and corporations to perform comprehensive risk management is needed.

Means for Solving the Problems

[0005] This invention solves these problems with a system comprising acquisition means for acquiring image data, audio data, and text data; analysis means for integrating and analyzing the acquired data in real time; evaluation means for evaluating risk from the analysis results and generating a risk report; and notification means for notifying the user of the evaluated risk report. This makes it possible to comprehensively evaluate risk from diverse data sources and implement countermeasures quickly and accurately.

[0006] "Image data" refers to visual information acquired by a camera or other image capture device, and is stored in digital format.

[0007] "Audio data" refers to sound wave information collected by microphones or other acoustic sensors, and is stored in digital format.

[0008] "Text data" refers to information recorded in the form of characters or sentences, and is stored in digital format.

[0009] "Acquisition means" refers to devices and methods for collecting information such as image data, audio data, and text data.

[0010] "Analysis means" refers to devices and methods for processing data collected by acquisition means and understanding its contents.

[0011] "Evaluation means" refers to devices and methods for determining risk based on analyzed data and clearly identifying its degree and type.

[0012] "Notification means" refers to devices or methods used to communicate the results of a risk assessment to the user and prompt them to take necessary actions.

[0013] A "risk report" is information compiled using assessment methods, containing details such as the type of risk, its urgency, and countermeasures. It serves as a resource for users to appropriately address risks. [Brief explanation of the drawing]

[0014] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined. [[ID=4​​​​ Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a labeled 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.

[0018] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc. [[ID=第十九]]

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention is a system that evaluates and notifies of potential risks through the integrated analysis of various data. This system mainly consists of two components: a terminal and a server.

[0036] First, the terminal is a device owned by the user, and it acquires image data, audio data, and text data through its sensors. This terminal is equipped with a camera, microphone, and text input interface, making it possible to collect data naturally during daily life. For example, while the user is commuting, the terminal records the surrounding traffic conditions and collects information about noise and people's movements.

[0037] Next, the data acquired by the terminal is sent to the server. After receiving this data, the server first performs preprocessing and cleanses the data. After preprocessing, the server uses a dedicated analysis module to perform image recognition and speech recognition. The analysis module employs multilayer neural network technology, which enables highly accurate analysis.

[0038] Next, the server uses a generative AI module to assess the risks based on the analyzed data. This assessment process comprehensively analyzes the content of the acquired data to identify potential risks. For example, if the analysis results indicate "large crowds" and "high noise levels," the generative AI recognizes the occurrence of safety risks due to congestion.

[0039] Once risks are assessed, the server generates a risk report. This report includes the type of risk identified, its urgency, and recommended actions for the user. The server promptly notifies the user's terminal of this risk report. This allows the user to understand the potential dangers and take appropriate action.

[0040] As a concrete example, consider the case where this system is implemented in a shopping mall. When a user walks around the mall with a device, the device records the surrounding environment. The server detects congestion and unusual sounds from the collected data, and if it determines there is a risk, it sends a notification to the user suggesting a safe route. In this way, users can avoid confusion and danger and move around with peace of mind.

[0041] The system of this invention allows users and corporations to automatically evaluate and be notified of potential risks in their daily lives and work, thereby enabling improved safety and efficient risk management.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The device activates its sensors and begins acquiring image, audio, and text data. This includes taking pictures of the surroundings with the camera and recording ambient sounds with the microphone. The collected data is temporarily stored on the device.

[0045] Step 2:

[0046] The device sends the stored data to the server. This transmission is performed using a security protocol to ensure data confidentiality. The transmitted data is received within the server.

[0047] Step 3:

[0048] The server preprocesses the received data. This includes noise reduction and format standardization. Preprocessing transforms the data into a state suitable for analysis.

[0049] Step 4:

[0050] The server inputs pre-processed data into the analysis module and performs image recognition and speech recognition. Image data is used to identify objects and people, while speech data is used to identify specific sounds.

[0051] Step 5:

[0052] The server uses generated AI to assess risks based on the analyzed data. It comprehensively analyzes the situation indicated by the data and identifies potential risks.

[0053] Step 6:

[0054] The server generates a risk report based on the results of the risk assessment. The risk report specifically details the identified risks, their urgency, and recommended countermeasures.

[0055] Step 7:

[0056] The server sends the generated risk report to the terminal and notifies the user. This is done through a procedure that emphasizes immediacy.

[0057] Step 8:

[0058] The user reviews the risk report displayed on their device. Based on this, the user can adjust their actions as needed according to the suggested countermeasures.

[0059] (Example 1)

[0060] 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."

[0061] In today's complex social environment, there is a need to collect diverse information and quickly assess potential risks. However, efficiently and accurately identifying risks in a situation where various data formats coexist and presenting them as useful information to users is difficult. To solve this problem, a system is needed that analyzes diverse data in real time, identifies potential risks, and supports appropriate actions that users should take.

[0062] 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.

[0063] In this invention, the server includes processing means for preprocessing received data and ensuring consistency, analysis means for analyzing the data using a multilayer neural network, and evaluation means for evaluating risk using a generative AI model based on the analysis results. This makes it possible to comprehensively analyze diverse data in real time, evaluate potential risks with high accuracy, and immediately notify the user.

[0064] A "sensor" is a device used to acquire information about the surrounding environment, and it has the function of collecting image, sound, and text data.

[0065] "Data collection methods" refer to methods of acquiring necessary data by utilizing sensors in response to user operations and environmental conditions.

[0066] "Communication method" refers to the method by which a terminal transmits data it has collected to a server via a network.

[0067] "Processing means" refers to the process of shaping received data and performing data cleansing and format conversion to ensure consistency.

[0068] A "multilayer neural network" is an artificial intelligence technique used for data analysis, possessing a structure that enables highly accurate pattern recognition using a large number of parameters.

[0069] "Analysis method" refers to a method of analyzing acquired data using a multilayer neural network to extract important information.

[0070] A "generative AI model" refers to an artificial intelligence model that learns from large amounts of data and is used to identify and assess risks from the acquired information.

[0071] "Evaluation method" refers to a method of evaluating potential risks by using a generative AI model based on the results of the analysis.

[0072] "Notification method" refers to a system-based method for sending the evaluated risk report to the user's terminal to prompt appropriate action.

[0073] The following describes embodiments for implementing the system of the present invention.

[0074] Users collect information about their surroundings using a portable device. This device is equipped with sensors and has the ability to acquire image, audio, and text data. Specifically, the device is equipped with a camera, microphone, and text input interface, allowing it to collect data naturally in various situations in daily life. For example, while a user is walking in a shopping mall, the device collects information about the crowd and background sounds.

[0075] Data acquired by the terminal is transmitted to the server via the network. The server first performs preprocessing on the received data, such as noise reduction and formatting standardization. At this stage, extraneous and erroneous data is eliminated. The server then analyzes the data using a multi-layer neural network to perform image recognition and speech recognition. High-speed computers with GPUs are often used for this analysis.

[0076] Based on the analyzed data, the server utilizes a generative AI model to assess potential risks. This generative AI model has been pre-trained on data from a variety of situations, allowing it to accurately identify the type and urgency of risks. For example, if high noise levels are detected in a crowded area, the risk associated with congestion is assessed, and this information is notified to the user.

[0077] If a risk is identified, the server generates a risk report reflecting that information and notifies the user's terminal. This risk report includes the type of risk identified, recommended countermeasures, and suggestions for actions to take as needed. By receiving this information, the user can take appropriate action, such as choosing an alternative route to avoid congestion.

[0078] As a concrete example, an example prompt message is "Suggest a safe route within the shopping mall." Based on this prompt, the server analyzes the message and sends an appropriate notification to the terminal. This allows the user to reach their destination safely and efficiently.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The device collects environmental data (images, audio, and text) using built-in sensors. The input is real-time environmental information captured by the sensors, and the output is structured data formatted by the data collection module. Specifically, the device captures images of the user's surroundings with its camera and records ambient sounds with its microphone. For example, when a user moves through a shopping mall, photos of crowded areas and audio data including background noise are collected.

[0082] Step 2:

[0083] The terminal transmits the collected data to the server via the network. The input is the collected environmental data, and the output is the data packets transferred to the server. Specifically, the terminal encrypts the data and then transmits it to the server using Wi-Fi or mobile data communication. During this process, the terminal monitors signal strength and connection status and selects the optimal communication method.

[0084] Step 3:

[0085] The server preprocesses the received data. The input is data packets sent from the terminal, and the output is clean, parseable data. Specifically, the server removes noise from the data and imputes missing data. It also resolves data format inconsistencies and performs conversions to ensure consistency.

[0086] Step 4:

[0087] The server analyzes pre-processed data. The input is clean data, and the output is risk factor information as a result of the analysis. The server uses a multi-layer neural network to perform object recognition in images and pattern recognition in audio. Specifically, the server analyzes the density of a population and detects abnormal sound peaks to sense anomalies in the environment.

[0088] Step 5:

[0089] The server uses a generative AI model to assess risk based on the analysis results. The input is analyzed risk factor information, and the output is a risk report. The generative AI model has been trained on various data patterns and determines the type and urgency of risk from the input data. Specifically, the server assesses safety risks based on congestion and noise and proposes specific countermeasures.

[0090] Step 6:

[0091] The server notifies the user's terminal of the risk report it has generated. The input is the risk report, and the output is the notification information displayed on the terminal. Based on the content of the notification, the server sets the priority of the report and suggests recommended actions to the user. Specifically, the server guides the user along a safe route within the mall and provides the user with optimal information in real time.

[0092] (Application Example 1)

[0093] 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."

[0094] In modern society, security threats in buildings and public spaces are increasing. Under these circumstances, conventional security systems struggle to identify risks in real time and take appropriate action. In particular, there is a need for systems that can quickly detect security threats such as intrusions and unusual noises and immediately notify administrators.

[0095] 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.

[0096] In this invention, the server includes acquisition means for acquiring image data, audio data, and text data; identification means for identifying intrusions and abnormal sounds using the data from the acquisition means for security monitoring; and warning means for issuing warnings according to the urgency based on the risks identified by the identification means. This makes it possible to detect security threats in buildings and public places in real time and to direct a rapid response.

[0097] "Acquisition means" refers to devices and methods for collecting image data, audio data, and text data. This is achieved by utilizing cameras and microphones built into smartphones and other devices.

[0098] "Analysis means" refers to devices or methods that have the function of analyzing collected data in real time. These methods involve comprehensively processing the data using multilayer neural networks, etc., to extract risks.

[0099] "Evaluation tools" refer to devices or methods that have the function of evaluating risk based on the results of analyzed data and generating a risk report. They determine potential security risks from the analysis results.

[0100] "Notification means" refers to devices or methods for promptly informing users of evaluated risk reports. Specifically, this involves providing information in the form of alerts or push notifications.

[0101] "Identification means" refers to devices or methods that have the function of analyzing acquired data to identify intrusions or abnormal sounds for security monitoring purposes. These are used to identify based on information from analysis means.

[0102] A "warning device" refers to a device or method that has the function of assessing the urgency of a risk identified by an identification device and issuing a warning. This makes it possible to quickly deliver crisis information to users.

[0103] This security system consists primarily of terminals and servers. The terminals are smart devices carried by users, equipped with sensors such as cameras and microphones. This allows for the daily collection of image, audio, and text data. The data is transmitted to the server via a wireless network.

[0104] The server first preprocesses the data, removing noise and standardizing the format. Software environments such as Python and TENSORFLOW® are used for this. Next, it performs data analysis using multi-layer neural networks. Through this analysis, elements related to security risks are identified and evaluated.

[0105] Based on the evaluation results, the generating AI model further analyzes the risks. Identified risks are notified to the user's device. The notification includes specific warnings in the form of images and text, and suggests countermeasures according to the urgency.

[0106] As a concrete example, consider a case where building security is monitored at night. A terminal acquires audio and video from inside and outside the building via sensors and transmits it to a server. If the server detects an anomaly, an alert is sent to the terminal, allowing the administrator to immediately take action.

[0107] An example of a prompt message might be, "What risks arise if unusual noises are detected inside the building after 8 PM tonight?" This is highly effective when using a generative AI model to identify potential risks in advance and prepare for countermeasures.

[0108] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0109] Step 1:

[0110] The device uses its camera and microphone to acquire image, audio, and text data in real time. The acquired data is temporarily stored on the device and transmitted to the server via a wireless network. The input is raw data acquired by the camera and microphone, and the output is data packets sent to the server. The device constantly monitors changes in the external environment and quickly captures newly generated data.

[0111] Step 2:

[0112] The server receives data sent from the terminal and first performs data preprocessing. Specifically, it performs noise reduction, data format conversion, and missing value imputation. The input is raw data packets sent from the terminal, and the output is a clean dataset processed into a format that is easy to analyze. The server performs this data processing using SciPy and Pandas in a Python environment.

[0113] Step 3:

[0114] The server analyzes pre-processed data using a multi-layer neural network. This analysis detects specific patterns and anomalies latent within the data. The input is a clean dataset, and the output is a list of events deemed anomalous and their risk assessment results. The server uses TensorFlow and Keras to execute analysis modules, enabling real-time, large-scale data analysis.

[0115] Step 4:

[0116] The server further evaluates the analysis results using a generative AI model to identify specific risks. This identification process considers various risk factors and comprehensively assesses potential dangers. The input is a list of events deemed abnormal, and the output is a detailed list of the evaluated risks. The server determines the urgency of the risks and provides response guidelines based on prompt messages.

[0117] Step 5:

[0118] The server generates a risk report based on the assessed risk information and notifies the terminal. Specific actions include sending warnings via push notifications and email. The input is a detailed list of assessed risks, and the output is a warning message displayed on the user's terminal. The server supports enhanced security by presenting information in a way that allows users to take prompt action.

[0119] 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.

[0120] This invention is a system that acquires diverse data from users, analyzes it to recognize user emotions, and assesses risks. This system proposes appropriate risk mitigation measures based on the user's behavior and circumstances, and notifies the user accordingly.

[0121] First, the device has the ability to acquire data from the surrounding environment and the user using sensors. This includes acquiring image data, audio data, and text data. For example, data is collected when the user records a voice memo or enters text. In addition, an emotion engine built into the device infers the user's emotions from the audio and text data, and a dataset combining this information is sent to the server.

[0122] The server is equipped with an advanced analysis module for comprehensively analyzing incoming data. This analysis module uses a multi-layer neural network to analyze the data content and recognize specific objects and the user's emotional state. The emotion engine performs sentiment analysis, identifying emotional categories such as positive, negative, and neutral. Based on this, it is possible to identify unintended risks and the emotional states of specific users.

[0123] Based on the analysis results, the server performs a risk assessment and generates a risk report, taking into account both the situation indicated by the generated data and the user's emotional state. The risk report includes suggested countermeasures tailored to the user's current emotional state, providing guidance for the user to take specific actions. For example, if it is determined that the user is experiencing stress, the report may include a suggestion to move to a lower-risk area.

[0124] This risk report is sent from the server to the terminal. Next, when the risk report is provided to the user via a notification system, the notification content is adjusted according to the user's emotional state and presented in a way that is beneficial to the user. This enables flexible and effective communication, helping the user make appropriate decisions.

[0125] For example, in a situation where panic is likely to occur while a user is visiting a shopping center, this system can identify the user's feelings of anxiety and quickly provide more reassuring weather information, helping the user to respond appropriately. In this way, the present invention supports user safety and enables efficient risk management.

[0126] The following describes the processing flow.

[0127] Step 1:

[0128] The device acquires data related to the user's environment and behavior. This includes acquiring image data via the camera, recording voice data via the microphone, and inputting text messages. The voice data is analyzed in real time by an emotion engine to initially identify the user's emotions.

[0129] Step 2:

[0130] The terminal sends the acquired data to the server. A secure protocol is used for transmission, ensuring that the data arrives at the server in a consistent and confidential state.

[0131] Step 3:

[0132] The server preprocesses the received data, standardizing the data format and optimizing it for analysis. This process includes noise reduction and correction of missing data.

[0133] Step 4:

[0134] The server inputs pre-processed data into an analysis module for image and speech recognition. During this process, a multi-layer neural network is used to perform detailed analysis of specific patterns within the data and user sentiment.

[0135] Step 5:

[0136] Based on the analysis results, the server uses a generation AI to perform a risk assessment based on the user's situation and emotions. The emotion engine extracts information and then makes a risk determination that takes into account psychological factors such as stress and anxiety.

[0137] Step 6:

[0138] The server generates a risk report based on the risk assessment results. The risk report includes details of the identified risks, recommended countermeasures, and advice that takes into account the user's emotional state.

[0139] Step 7:

[0140] The server sends a risk report to the terminal and instructs it to notify the user directly. The notification method is adjusted according to the user's emotional state and is provided in an appropriate format and at the appropriate time.

[0141] Step 8:

[0142] Users receive notifications on their devices and review the displayed risk report. They can then follow the suggested countermeasures and advice, choose appropriate actions, and manage their emotional state.

[0143] (Example 2)

[0144] 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".

[0145] Often, prompt and appropriate risk assessments and countermeasures are not provided in accordance with the user's emotional state, making it difficult for users to respond flexibly based on their emotions. This has made it particularly difficult to provide appropriate risk information and guidance to users experiencing stress or anxiety.

[0146] 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.

[0147] In this invention, the server includes means for acquiring data and inferring emotional states, means for integrating the acquired data and analyzing it in real time, and means for evaluating risks based on the analysis results, generating risk reports, and providing notifications tailored to the user's emotions. This makes it possible to grasp the user's emotional state in real time and to make appropriate risk assessments and propose specific countermeasures.

[0148] "Means for acquiring data and inferring emotional states" refers to components of a system that collects various types of data from users, such as voice, images, and text, and uses that data to identify the user's emotional state.

[0149] "Means for integrating acquired data and analyzing it in real time" refers to a part of a system that centrally processes multiple types of collected data and has the function of analyzing the current situation and emotions.

[0150] "A means of evaluating risk based on analysis results, generating a risk report, and providing notifications tailored to the user's emotions" refers to a system process that uses analyzed data to evaluate potential dangers and risks to the user, creates a risk report summarizing the results, and provides notifications in a manner appropriate to the user's current emotional state.

[0151] A "neural network" is a type of machine learning that uses computer algorithms designed to be inspired by the nervous system of living organisms, enabling pattern recognition and analysis of data.

[0152] This invention is a system that grasps the user's emotional state in real time and proposes appropriate risk assessments and specific countermeasures. The following describes a specific embodiment for implementing this invention.

[0153] Hardware and software configuration

[0154] The device is equipped with various sensors to acquire data such as voice, images, and text. This includes a microphone and camera. The device also has a built-in emotion engine for emotion recognition, which analyzes the acquired voice and text data. A dedicated emotion inference algorithm is used for emotion recognition.

[0155] The server is equipped with an analysis module for analyzing received data, and it uses a multi-layer neural network to comprehensively analyze multiple data sets. This makes it possible to accurately understand the user's emotional state and surrounding circumstances.

[0156] Data processing

[0157] The device processes the acquired data using an emotion engine to infer the user's emotions. This inferred data is sent to the server. The server performs analysis using a neural network based on the transmitted data. Based on the results of this analysis, a risk report is generated that includes a risk assessment and action guidelines tailored to the user's current emotional state.

[0158] The generated risk report is sent back to the terminal and notified to the user in the most appropriate way through the notification system. This notification process takes into account the user's emotional state and provides the user with the most relevant information.

[0159] Examples of specific cases and prompt statements

[0160] For example, if a user is relaxing in a park and an unexpected loud noise occurs nearby, this system will detect the user's anxiety and immediately provide information suggesting they move to a safe location.

[0161] An example of a prompt message is: "Explain how to assess the current risk situation based on the user's emotions and notify them of appropriate action guidelines."

[0162] In this way, this system can comprehensively analyze the user's emotions and circumstances, and propose practical and effective risk management and countermeasures.

[0163] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0164] Step 1:

[0165] The device acquires data from the user, such as voice, images, and text. This input data is collected through the device's microphone, camera, and text input interface. The device then prepares this data for transmission to the emotion engine. Specifically, this involves saving user-entered text and recorded voice as digital data.

[0166] Step 2:

[0167] The device analyzes the acquired data using an emotion engine to infer the user's emotional state. This process employs algorithms that scrutinize voice tone and pitch in audio data, as well as text content. The acquired data is used as input, and emotion labels (e.g., positive, negative, neutral) are generated as output. The device then compiles the inference results into a dataset and performs specific actions to convert it into a data format for transmission to the server.

[0168] Step 3:

[0169] The terminal sends the inferred sentiment dataset to the server. A secure protocol (e.g., HTTPS) is used for communication. The input for this step is sentiment data and integrated environmental data, and the output is secure data communication. The terminal performs the specific action of uploading the data to the server in real time.

[0170] Step 4:

[0171] The server comprehensively analyzes the data received from the terminal using an analysis module. A multi-layer neural network is used for analysis, including the recognition of specific objects and the reconfirmation of emotional states. The transmitted emotional dataset is used as input, and the output is generated as a dataset of analysis results. The server recognizes patterns in the data and performs specific actions to deepen its understanding of the user's behavior and situation.

[0172] Step 5:

[0173] The server evaluates the risks based on the analysis results and generates a risk report. Here, potential risks are assessed considering the user's emotional state and environmental data. Using the analysis data as input, the server generates a report that presents a risk assessment and specific action guidelines as output. The server then performs the specific actions to compile a detailed risk report incorporating countermeasures.

[0174] Step 6:

[0175] The server sends the generated risk report to the terminal. The terminal receives it and provides it to the user via a notification system. The notification content is required to be adjusted based on the user's emotional state. The input is the risk report, and the output is a notification optimized for the user. The terminal includes specific actions to draw the user's attention, such as using screen displays or audio alerts.

[0176] (Application Example 2)

[0177] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0178] When users encounter abnormal situations or emotional states in their daily lives, there is a challenge in quickly and accurately assessing the risks and providing appropriate countermeasures. Therefore, an effective support system is needed to ensure the safety of users and enable them to live with peace of mind.

[0179] 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.

[0180] In this invention, the server includes information acquisition means for acquiring image data, audio data, and text data; data analysis means for integrating the acquired data and analyzing it in real time; and information evaluation means for evaluating the risk from the analysis results and generating a risk report. This allows the server to recognize the user's emotional state and provide safety guidelines as needed, enabling the user to respond quickly even in abnormal situations.

[0181] "Information acquisition means" refers to a device equipped with functions for acquiring image data, audio data, and text data.

[0182] A "data analysis means" is a processing device that integrates acquired data and analyzes it in real time.

[0183] An "information evaluation tool" is a device that has the function of evaluating risk based on analysis results and generating a risk report.

[0184] An "information notification device" is a device that has the function of notifying users of the evaluated risk report.

[0185] A "safety guidance provision device" is a device that recognizes the emotional state of the user and has the function of providing safety guidance when necessary.

[0186] This invention provides a system that allows users to receive real-time risk assessments and safety guidelines based on their environment and emotional state using a smart device. Specifically, the system is configured as follows:

[0187] First, the device uses information acquisition methods to collect data about the user's surroundings and their own voice, images, and text. Smart glasses and the camera and microphone of a smartphone are used for this data acquisition. For example, smart glasses capture video of the surroundings while simultaneously collecting audio data with the microphone.

[0188] Next, the collected data is analyzed in real time using a multi-layer neural network by a data analysis tool. During this process, an emotion estimation algorithm is applied to identify whether the user's emotional state is positive, negative, or neutral. The analysis platform used may include machine learning frameworks such as TensorFlow.

[0189] The server uses information evaluation tools to assess risk based on the analysis results and generates a risk report tailored to the user. This risk report includes specific safety guidelines that are appropriate to the user's current situation and emotional state. For example, if a user feels uneasy in a busy area, the server will notify them of a suggestion for a safer route.

[0190] The safety guidance delivery system presents risk reports to users through notification methods. Notifications are displayed as audio or text, and users can receive safety guidance via their smart devices. This helps users make quick and accurate decisions regarding specific situations they face.

[0191] As a concrete example, if a user feels anxious on a train platform, instructions to take a deep breath and directions to a quiet resting area will be displayed on the smart glasses' screen.

[0192] An example of a prompt that utilizes a generative AI model is, "If a user is in a crowded place but does not feel anxious, what action should be suggested?"

[0193] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0194] Step 1:

[0195] The device uses the cameras and microphones of smart glasses or smartphones to collect image and audio data of the environment, as well as text data entered by the user. This input data specifically reflects the user's surroundings and spoken content. This prepares the system for understanding the user's state in real time.

[0196] Step 2:

[0197] The terminal preprocesses the collected image and audio data, performing enhancements such as sharpening and noise reduction. This improves the quality of the data used for analysis. This processed data is then sent to the server.

[0198] Step 3:

[0199] The server analyzes the received data using a multilayer neural network. Image data is subjected to image recognition algorithms to identify specific visual patterns, and audio data is converted to text using speech recognition algorithms. This analysis determines the user's emotional state (positive, negative, or neutral).

[0200] Step 4:

[0201] Based on the analysis results, the server assesses the risk using information evaluation tools. In this process, it determines the risk level based on the inferred emotional state and generates a risk report. The generated report includes the risks the user may face and the necessary countermeasures.

[0202] Step 5:

[0203] The server sends the generated risk report to the terminal and notifies the user through a safety guidance provision system. The notification is made by voice or text, and real-time feedback is provided. Specifically, the user reads the information displayed on the smart glasses' screen and adjusts their actions according to the safety guidelines.

[0204] Step 6:

[0205] Users take safe actions based on the information they receive. For example, if a user feels uneasy, they can actually change their behavior according to the suggested course of action. This helps them avoid real danger.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] [Second Embodiment]

[0210] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0211] 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.

[0212] 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).

[0213] 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.

[0214] 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.

[0215] 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).

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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".

[0222] This invention is a system that evaluates and notifies of potential risks through the integrated analysis of various data. This system mainly consists of two components: a terminal and a server.

[0223] First, the terminal is a device owned by the user, and it acquires image data, audio data, and text data through its sensors. This terminal is equipped with a camera, microphone, and text input interface, making it possible to collect data naturally during daily life. For example, while the user is commuting, the terminal records the surrounding traffic conditions and collects information about noise and people's movements.

[0224] Next, the data acquired by the terminal is sent to the server. After receiving this data, the server first performs preprocessing and cleanses the data. After preprocessing, the server uses a dedicated analysis module to perform image recognition and speech recognition. The analysis module employs multilayer neural network technology, which enables highly accurate analysis.

[0225] Next, the server uses a generative AI module to assess the risks based on the analyzed data. This assessment process comprehensively analyzes the content of the acquired data to identify potential risks. For example, if the analysis results indicate "large crowds" and "high noise levels," the generative AI recognizes the occurrence of safety risks due to congestion.

[0226] Once risks are assessed, the server generates a risk report. This report includes the type of risk identified, its urgency, and recommended actions for the user. The server promptly notifies the user's terminal of this risk report. This allows the user to understand the potential dangers and take appropriate action.

[0227] As a concrete example, consider the case where this system is implemented in a shopping mall. When a user walks around the mall with a device, the device records the surrounding environment. The server detects congestion and unusual sounds from the collected data, and if it determines there is a risk, it sends a notification to the user suggesting a safe route. In this way, users can avoid confusion and danger and move around with peace of mind.

[0228] The system of this invention allows users and corporations to automatically evaluate and be notified of potential risks in their daily lives and work, thereby enabling improved safety and efficient risk management.

[0229] The following describes the processing flow.

[0230] Step 1:

[0231] The device activates its sensors and begins acquiring image, audio, and text data. This includes taking pictures of the surroundings with the camera and recording ambient sounds with the microphone. The collected data is temporarily stored on the device.

[0232] Step 2:

[0233] The device sends the stored data to the server. This transmission is performed using a security protocol to ensure data confidentiality. The transmitted data is received within the server.

[0234] Step 3:

[0235] The server preprocesses the received data. This includes noise reduction and format standardization. Preprocessing transforms the data into a state suitable for analysis.

[0236] Step 4:

[0237] The server inputs pre-processed data into the analysis module and performs image recognition and speech recognition. Image data is used to identify objects and people, while speech data is used to identify specific sounds.

[0238] Step 5:

[0239] The server uses generated AI to assess risks based on the analyzed data. It comprehensively analyzes the situation indicated by the data and identifies potential risks.

[0240] Step 6:

[0241] The server generates a risk report based on the results of the risk assessment. The risk report specifically details the identified risks, their urgency, and recommended countermeasures.

[0242] Step 7:

[0243] The server sends the generated risk report to the terminal and notifies the user. This is done through a procedure that emphasizes immediacy.

[0244] Step 8:

[0245] The user reviews the risk report displayed on their device. Based on this, the user can adjust their actions as needed according to the suggested countermeasures.

[0246] (Example 1)

[0247] 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."

[0248] In today's complex social environment, there is a need to collect diverse information and quickly assess potential risks. However, efficiently and accurately identifying risks in a situation where various data formats coexist and presenting them as useful information to users is difficult. To solve this problem, a system is needed that analyzes diverse data in real time, identifies potential risks, and supports appropriate actions that users should take.

[0249] 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.

[0250] In this invention, the server includes processing means for preprocessing received data and ensuring consistency, analysis means for analyzing the data using a multilayer neural network, and evaluation means for evaluating risk using a generative AI model based on the analysis results. This makes it possible to comprehensively analyze diverse data in real time, evaluate potential risks with high accuracy, and immediately notify the user.

[0251] A "sensor" is a device used to acquire information about the surrounding environment, and it has the function of collecting image, sound, and text data.

[0252] "Data collection methods" refer to methods of acquiring necessary data by utilizing sensors in response to user operations and environmental conditions.

[0253] "Communication method" refers to the method by which a terminal transmits data it has collected to a server via a network.

[0254] "Processing means" refers to the process of shaping received data and performing data cleansing and format conversion to ensure consistency.

[0255] A "multilayer neural network" is an artificial intelligence technique used for data analysis, possessing a structure that enables highly accurate pattern recognition using a large number of parameters.

[0256] "Analysis method" refers to a method of analyzing acquired data using a multilayer neural network to extract important information.

[0257] A "generative AI model" refers to an artificial intelligence model that learns from large amounts of data and is used to identify and assess risks from the acquired information.

[0258] "Evaluation method" refers to a method of evaluating potential risks by using a generative AI model based on the results of the analysis.

[0259] "Notification method" refers to a system-based method for sending the evaluated risk report to the user's terminal to prompt appropriate action.

[0260] The following describes embodiments for implementing the system of the present invention.

[0261] Users collect information about their surroundings using a portable device. This device is equipped with sensors and has the ability to acquire image, audio, and text data. Specifically, the device is equipped with a camera, microphone, and text input interface, allowing it to collect data naturally in various situations in daily life. For example, while a user is walking in a shopping mall, the device collects information about the crowd and background sounds.

[0262] Data acquired by the terminal is transmitted to the server via the network. The server first performs preprocessing on the received data, such as noise reduction and formatting standardization. At this stage, extraneous and erroneous data is eliminated. The server then analyzes the data using a multi-layer neural network to perform image recognition and speech recognition. High-speed computers with GPUs are often used for this analysis.

[0263] Based on the analyzed data, the server utilizes a generative AI model to assess potential risks. This generative AI model has been pre-trained on data from a variety of situations, allowing it to accurately identify the type and urgency of risks. For example, if high noise levels are detected in a crowded area, the risk associated with congestion is assessed, and this information is notified to the user.

[0264] If a risk is identified, the server generates a risk report reflecting that information and notifies the user's terminal. This risk report includes the type of risk identified, recommended countermeasures, and suggestions for actions to take as needed. By receiving this information, the user can take appropriate action, such as choosing an alternative route to avoid congestion.

[0265] As a concrete example, an example prompt message is "Suggest a safe route within the shopping mall." Based on this prompt, the server analyzes the message and sends an appropriate notification to the terminal. This allows the user to reach their destination safely and efficiently.

[0266] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0267] Step 1:

[0268] The device collects environmental data (images, audio, and text) using built-in sensors. The input is real-time environmental information captured by the sensors, and the output is structured data formatted by the data collection module. Specifically, the device captures images of the user's surroundings with its camera and records ambient sounds with its microphone. For example, when a user moves through a shopping mall, photos of crowded areas and audio data including background noise are collected.

[0269] Step 2:

[0270] The terminal transmits the collected data to the server via the network. The input is the collected environmental data, and the output is the data packets transferred to the server. Specifically, the terminal encrypts the data and then transmits it to the server using Wi-Fi or mobile data communication. During this process, the terminal monitors signal strength and connection status and selects the optimal communication method.

[0271] Step 3:

[0272] The server preprocesses the received data. The input is data packets sent from the terminal, and the output is clean, parseable data. Specifically, the server removes noise from the data and imputes missing data. It also resolves data format inconsistencies and performs conversions to ensure consistency.

[0273] Step 4:

[0274] The server analyzes pre-processed data. The input is clean data, and the output is risk factor information as a result of the analysis. The server uses a multi-layer neural network to perform object recognition in images and pattern recognition in audio. Specifically, the server analyzes the density of a population and detects abnormal sound peaks to sense anomalies in the environment.

[0275] Step 5:

[0276] The server uses a generative AI model to assess risk based on the analysis results. The input is analyzed risk factor information, and the output is a risk report. The generative AI model has been trained on various data patterns and determines the type and urgency of risk from the input data. Specifically, the server assesses safety risks based on congestion and noise and proposes specific countermeasures.

[0277] Step 6:

[0278] The server notifies the user's terminal of the risk report it has generated. The input is the risk report, and the output is the notification information displayed on the terminal. Based on the content of the notification, the server sets the priority of the report and suggests recommended actions to the user. Specifically, the server guides the user along a safe route within the mall and provides the user with optimal information in real time.

[0279] (Application Example 1)

[0280] 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."

[0281] In modern society, security threats in buildings and public spaces are increasing. Under these circumstances, conventional security systems struggle to identify risks in real time and take appropriate action. In particular, there is a need for systems that can quickly detect security threats such as intrusions and unusual noises and immediately notify administrators.

[0282] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following respective means.

[0283] In this invention, the server includes an acquisition means for acquiring image data, audio data, and text data, an identification means for identifying intrusion and abnormal sounds using the data from the acquisition means for security monitoring, and a warning means for issuing a warning according to the degree of urgency based on the risks identified by the identification means. Thereby, it becomes possible to detect security threats in buildings and public places in real time and instruct a prompt response.

[0284] The "acquisition means" refers to a device or method for collecting image data, audio data, and text data. It is realized by utilizing cameras and microphones installed in smartphones and other devices.

[0285] The "analysis means" refers to a device or method having a function of analyzing the collected data in real time. It integrally processes the data using a multi-layer neural network or the like and extracts risks.

[0286] The "evaluation means" refers to a device or method having a function of evaluating risks based on the results of the analyzed data and generating a risk report. It determines potential security risks from the analysis results.

[0287] The "notification means" refers to a device or method for promptly notifying the user of the evaluated risk report. Specifically, it provides information in the form of alerts and push notifications.

[0288] The "identification means" refers to a device or method having a function of analyzing the acquired data to identify intrusion and abnormal sounds for security monitoring. It is for identification based on the information from the analysis means.

[0289] A "warning device" refers to a device or method that has the function of assessing the urgency of a risk identified by an identification device and issuing a warning. This makes it possible to quickly deliver crisis information to users.

[0290] This security system consists primarily of terminals and servers. The terminals are smart devices carried by users, equipped with sensors such as cameras and microphones. This allows for the daily collection of image, audio, and text data. The data is transmitted to the server via a wireless network.

[0291] The server first preprocesses the data, removing noise and standardizing the format. Software environments such as Python and TensorFlow are used for this. Next, it performs data analysis using multi-layer neural networks. Through this analysis, elements related to security risks are identified and evaluated.

[0292] Based on the evaluation results, the generating AI model further analyzes the risks. Identified risks are notified to the user's device. The notification includes specific warnings in the form of images and text, and suggests countermeasures according to the urgency.

[0293] As a concrete example, consider a case where building security is monitored at night. A terminal acquires audio and video from inside and outside the building via sensors and transmits it to a server. If the server detects an anomaly, an alert is sent to the terminal, allowing the administrator to immediately take action.

[0294] An example of a prompt message might be, "What risks arise if unusual noises are detected inside the building after 8 PM tonight?" This is highly effective when using a generative AI model to identify potential risks in advance and prepare for countermeasures.

[0295] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0296] Step 1:

[0297] The device uses its camera and microphone to acquire image, audio, and text data in real time. The acquired data is temporarily stored on the device and transmitted to the server via a wireless network. The input is raw data acquired by the camera and microphone, and the output is data packets sent to the server. The device constantly monitors changes in the external environment and quickly captures newly generated data.

[0298] Step 2:

[0299] The server receives data sent from the terminal and first performs data preprocessing. Specifically, it performs noise reduction, data format conversion, and missing value imputation. The input is raw data packets sent from the terminal, and the output is a clean dataset processed into a format that is easy to analyze. The server performs this data processing using SciPy and Pandas in a Python environment.

[0300] Step 3:

[0301] The server analyzes pre-processed data using a multi-layer neural network. This analysis detects specific patterns and anomalies latent within the data. The input is a clean dataset, and the output is a list of events deemed anomalous and their risk assessment results. The server uses TensorFlow and Keras to execute analysis modules, enabling real-time, large-scale data analysis.

[0302] Step 4:

[0303] The server further evaluates the analysis results using a generative AI model to identify specific risks. In this identification process, various risk factors are considered to comprehensively evaluate potential hazards. The input is a list of events considered abnormal, and the output is a detailed list of the evaluated risks. The server determines the urgency of the risks and describes response guidelines based on the prompt text.

[0304] Step 5:

[0305] The server generates the evaluated risk information as a risk report and notifies the terminal. Specific operations include sending warnings via push notifications or emails. The input is a detailed list of the evaluated risks, and the output is a warning message displayed on the user terminal. The server supports enhanced security while devising ways to present information so that users can respond promptly.

[0306] 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 identification model 59 and perform specific processing using the user's emotion.

[0307] The present invention is a system that acquires various data from a user, analyzes it, recognizes the user's emotion, and evaluates risks. This system proposes appropriate risk response measures according to the user's behavior and situation and notifies the user.

[0308] First, the terminal has a function of acquiring data from the surrounding environment and the user using sensors. This includes acquiring image data, audio data, and text data. For example, data is accumulated when the user records an audio memo or inputs text. In addition to this, an emotion engine built into the terminal推测 the user's emotion from the audio data and text data, and a dataset combining that information is sent to the server.

[0309] The server is equipped with an advanced analysis module for comprehensively analyzing incoming data. This analysis module uses a multi-layer neural network to analyze the data content and recognize specific objects and the user's emotional state. The emotion engine performs sentiment analysis, identifying emotional categories such as positive, negative, and neutral. Based on this, it is possible to identify unintended risks and the emotional states of specific users.

[0310] Based on the analysis results, the server performs a risk assessment and generates a risk report, taking into account both the situation indicated by the generated data and the user's emotional state. The risk report includes suggested countermeasures tailored to the user's current emotional state, providing guidance for the user to take specific actions. For example, if it is determined that the user is experiencing stress, the report may include a suggestion to move to a lower-risk area.

[0311] This risk report is sent from the server to the terminal. Next, when the risk report is provided to the user via a notification system, the notification content is adjusted according to the user's emotional state and presented in a way that is beneficial to the user. This enables flexible and effective communication, helping the user make appropriate decisions.

[0312] For example, in a situation where panic is likely to occur while a user is visiting a shopping center, this system can identify the user's feelings of anxiety and quickly provide more reassuring weather information, helping the user to respond appropriately. In this way, the present invention supports user safety and enables efficient risk management.

[0313] The following describes the processing flow.

[0314] Step 1:

[0315] The device acquires data related to the user's environment and behavior. This includes acquiring image data via the camera, recording voice data via the microphone, and inputting text messages. The voice data is analyzed in real time by an emotion engine to initially identify the user's emotions.

[0316] Step 2:

[0317] The terminal sends the acquired data to the server. A secure protocol is used for transmission, ensuring that the data arrives at the server in a consistent and confidential state.

[0318] Step 3:

[0319] The server preprocesses the received data, standardizing the data format and optimizing it for analysis. This process includes noise reduction and correction of missing data.

[0320] Step 4:

[0321] The server inputs pre-processed data into an analysis module for image and speech recognition. During this process, a multi-layer neural network is used to perform detailed analysis of specific patterns within the data and user sentiment.

[0322] Step 5:

[0323] Based on the analysis results, the server uses a generation AI to perform a risk assessment based on the user's situation and emotions. The emotion engine extracts information and then makes a risk determination that takes into account psychological factors such as stress and anxiety.

[0324] Step 6:

[0325] The server generates a risk report based on the risk assessment results. The risk report includes details of the identified risks, recommended countermeasures, and advice that takes into account the user's emotional state.

[0326] Step 7:

[0327] The server sends a risk report to the terminal and instructs it to notify the user directly. The notification method is adjusted according to the user's emotional state and is provided in an appropriate format and at the appropriate time.

[0328] Step 8:

[0329] Users receive notifications on their devices and review the displayed risk report. They can then follow the suggested countermeasures and advice, choose appropriate actions, and manage their emotional state.

[0330] (Example 2)

[0331] 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".

[0332] Often, prompt and appropriate risk assessments and countermeasures are not provided in accordance with the user's emotional state, making it difficult for users to respond flexibly based on their emotions. This has made it particularly difficult to provide appropriate risk information and guidance to users experiencing stress or anxiety.

[0333] 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.

[0334] In this invention, the server includes means for acquiring data and inferring emotional states, means for integrating the acquired data and analyzing it in real time, and means for evaluating risks based on the analysis results, generating risk reports, and providing notifications tailored to the user's emotions. This makes it possible to grasp the user's emotional state in real time and to make appropriate risk assessments and propose specific countermeasures.

[0335] "Means for acquiring data and inferring emotional states" refers to components of a system that collects various types of data from users, such as voice, images, and text, and uses that data to identify the user's emotional state.

[0336] "Means for integrating acquired data and analyzing it in real time" refers to a part of a system that centrally processes multiple types of collected data and has the function of analyzing the current situation and emotions.

[0337] "A means of evaluating risk based on analysis results, generating a risk report, and providing notifications tailored to the user's emotions" refers to a system process that uses analyzed data to evaluate potential dangers and risks to the user, creates a risk report summarizing the results, and provides notifications in a manner appropriate to the user's current emotional state.

[0338] A "neural network" is a type of machine learning that uses computer algorithms designed to be inspired by the nervous system of living organisms, enabling pattern recognition and analysis of data.

[0339] This invention is a system that grasps the user's emotional state in real time and proposes appropriate risk assessments and specific countermeasures. The following describes a specific embodiment for implementing this invention.

[0340] Hardware and software configuration

[0341] The device is equipped with various sensors to acquire data such as voice, images, and text. This includes a microphone and camera. The device also has a built-in emotion engine for emotion recognition, which analyzes the acquired voice and text data. A dedicated emotion inference algorithm is used for emotion recognition.

[0342] The server is equipped with an analysis module for analyzing received data, and it uses a multi-layer neural network to comprehensively analyze multiple data sets. This makes it possible to accurately understand the user's emotional state and surrounding circumstances.

[0343] Data processing

[0344] The device processes the acquired data using an emotion engine to infer the user's emotions. This inferred data is sent to the server. The server performs analysis using a neural network based on the transmitted data. Based on the results of this analysis, a risk report is generated that includes a risk assessment and action guidelines tailored to the user's current emotional state.

[0345] The generated risk report is sent back to the terminal and notified to the user in the most appropriate way through the notification system. This notification process takes into account the user's emotional state and provides the user with the most relevant information.

[0346] Examples of specific cases and prompt statements

[0347] For example, if a user is relaxing in a park and an unexpected loud noise occurs nearby, this system will detect the user's anxiety and immediately provide information suggesting they move to a safe location.

[0348] An example of a prompt message is: "Explain how to assess the current risk situation based on the user's emotions and notify them of appropriate action guidelines."

[0349] In this way, this system can comprehensively analyze the user's emotions and circumstances, and propose practical and effective risk management and countermeasures.

[0350] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0351] Step 1:

[0352] The device acquires data from the user, such as voice, images, and text. This input data is collected through the device's microphone, camera, and text input interface. The device then prepares this data for transmission to the emotion engine. Specifically, this involves saving user-entered text and recorded voice as digital data.

[0353] Step 2:

[0354] The device analyzes the acquired data using an emotion engine to infer the user's emotional state. This process employs algorithms that scrutinize voice tone and pitch in audio data, as well as text content. The acquired data is used as input, and emotion labels (e.g., positive, negative, neutral) are generated as output. The device then compiles the inference results into a dataset and performs specific actions to convert it into a data format for transmission to the server.

[0355] Step 3:

[0356] The terminal sends the inferred sentiment dataset to the server. A secure protocol (e.g., HTTPS) is used for communication. The input for this step is sentiment data and integrated environmental data, and the output is secure data communication. The terminal performs the specific action of uploading the data to the server in real time.

[0357] Step 4:

[0358] The server comprehensively analyzes the data received from the terminal using an analysis module. A multi-layer neural network is used for analysis, including the recognition of specific objects and the reconfirmation of emotional states. The transmitted emotional dataset is used as input, and the output is generated as a dataset of analysis results. The server recognizes patterns in the data and performs specific actions to deepen its understanding of the user's behavior and situation.

[0359] Step 5:

[0360] The server evaluates the risks based on the analysis results and generates a risk report. Here, potential risks are assessed considering the user's emotional state and environmental data. Using the analysis data as input, the server generates a report that presents a risk assessment and specific action guidelines as output. The server then performs the specific actions to compile a detailed risk report incorporating countermeasures.

[0361] Step 6:

[0362] The server sends the generated risk report to the terminal. The terminal receives it and provides it to the user via a notification system. The notification content is required to be adjusted based on the user's emotional state. The input is the risk report, and the output is a notification optimized for the user. The terminal includes specific actions to draw the user's attention, such as using screen displays or audio alerts.

[0363] (Application Example 2)

[0364] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0365] When users encounter abnormal situations or emotional states in their daily lives, there is a challenge in quickly and accurately assessing the risks and providing appropriate countermeasures. Therefore, an effective support system is needed to ensure the safety of users and enable them to live with peace of mind.

[0366] 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.

[0367] In this invention, the server includes information acquisition means for acquiring image data, audio data, and text data; data analysis means for integrating the acquired data and analyzing it in real time; and information evaluation means for evaluating the risk from the analysis results and generating a risk report. This allows the server to recognize the user's emotional state and provide safety guidelines as needed, enabling the user to respond quickly even in abnormal situations.

[0368] "Information acquisition means" refers to a device equipped with functions for acquiring image data, audio data, and text data.

[0369] A "data analysis means" is a processing device that integrates acquired data and analyzes it in real time.

[0370] An "information evaluation tool" is a device that has the function of evaluating risk based on analysis results and generating a risk report.

[0371] An "information notification device" is a device that has the function of notifying users of the evaluated risk report.

[0372] A "safety guidance provision device" is a device that recognizes the emotional state of the user and has the function of providing safety guidance when necessary.

[0373] This invention provides a system that allows users to receive real-time risk assessments and safety guidelines based on their environment and emotional state using a smart device. Specifically, the system is configured as follows:

[0374] First, the device uses information acquisition methods to collect data about the user's surroundings and their own voice, images, and text. Smart glasses and the camera and microphone of a smartphone are used for this data acquisition. For example, smart glasses capture video of the surroundings while simultaneously collecting audio data with the microphone.

[0375] Next, the collected data is analyzed in real time using a multi-layer neural network by a data analysis tool. During this process, an emotion estimation algorithm is applied to identify whether the user's emotional state is positive, negative, or neutral. The analysis platform used may include machine learning frameworks such as TensorFlow.

[0376] The server uses information evaluation tools to assess risk based on the analysis results and generates a risk report tailored to the user. This risk report includes specific safety guidelines that are appropriate to the user's current situation and emotional state. For example, if a user feels uneasy in a busy area, the server will notify them of a suggestion for a safer route.

[0377] The safety guidance delivery system presents risk reports to users through notification methods. Notifications are displayed as audio or text, and users can receive safety guidance via their smart devices. This helps users make quick and accurate decisions regarding specific situations they face.

[0378] As a concrete example, if a user feels anxious on a train platform, instructions to take a deep breath and directions to a quiet resting area will be displayed on the smart glasses' screen.

[0379] An example of a prompt that utilizes a generative AI model is, "If a user is in a crowded place but does not feel anxious, what action should be suggested?"

[0380] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0381] Step 1:

[0382] The device uses the cameras and microphones of smart glasses or smartphones to collect image and audio data of the environment, as well as text data entered by the user. This input data specifically reflects the user's surroundings and spoken content. This prepares the system for understanding the user's state in real time.

[0383] Step 2:

[0384] The terminal preprocesses the collected image and audio data, performing enhancements such as sharpening and noise reduction. This improves the quality of the data used for analysis. This processed data is then sent to the server.

[0385] Step 3:

[0386] The server analyzes the received data using a multilayer neural network. Image data is subjected to image recognition algorithms to identify specific visual patterns, and audio data is converted to text using speech recognition algorithms. This analysis determines the user's emotional state (positive, negative, or neutral).

[0387] Step 4:

[0388] Based on the analysis results, the server assesses the risk using information evaluation tools. In this process, it determines the risk level based on the inferred emotional state and generates a risk report. The generated report includes the risks the user may face and the necessary countermeasures.

[0389] Step 5:

[0390] The server sends the generated risk report to the terminal and notifies the user through a safety guidance provision system. The notification is made by voice or text, and real-time feedback is provided. Specifically, the user reads the information displayed on the smart glasses' screen and adjusts their actions according to the safety guidelines.

[0391] Step 6:

[0392] Users take safe actions based on the information they receive. For example, if a user feels uneasy, they can actually change their behavior according to the suggested course of action. This helps them avoid real danger.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] [Third Embodiment]

[0397] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0398] 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.

[0399] 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).

[0400] 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.

[0401] 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.

[0402] 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).

[0403] 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.

[0404] 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.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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".

[0409] This invention is a system that evaluates and notifies of potential risks through the integrated analysis of various data. This system mainly consists of two components: a terminal and a server.

[0410] First, the terminal is a device owned by the user, and it acquires image data, audio data, and text data through its sensors. This terminal is equipped with a camera, microphone, and text input interface, making it possible to collect data naturally during daily life. For example, while the user is commuting, the terminal records the surrounding traffic conditions and collects information about noise and people's movements.

[0411] Next, the data acquired by the terminal is sent to the server. After receiving this data, the server first performs preprocessing and cleanses the data. After preprocessing, the server uses a dedicated analysis module to perform image recognition and speech recognition. The analysis module employs multilayer neural network technology, which enables highly accurate analysis.

[0412] Next, the server uses a generative AI module to assess the risks based on the analyzed data. This assessment process comprehensively analyzes the content of the acquired data to identify potential risks. For example, if the analysis results indicate "large crowds" and "high noise levels," the generative AI recognizes the occurrence of safety risks due to congestion.

[0413] Once risks are assessed, the server generates a risk report. This report includes the type of risk identified, its urgency, and recommended actions for the user. The server promptly notifies the user's terminal of this risk report. This allows the user to understand the potential dangers and take appropriate action.

[0414] As a concrete example, consider the case where this system is implemented in a shopping mall. When a user walks around the mall with a device, the device records the surrounding environment. The server detects congestion and unusual sounds from the collected data, and if it determines there is a risk, it sends a notification to the user suggesting a safe route. In this way, users can avoid confusion and danger and move around with peace of mind.

[0415] The system of this invention allows users and corporations to automatically evaluate and be notified of potential risks in their daily lives and work, thereby enabling improved safety and efficient risk management.

[0416] The following describes the processing flow.

[0417] Step 1:

[0418] The device activates its sensors and begins acquiring image, audio, and text data. This includes taking pictures of the surroundings with the camera and recording ambient sounds with the microphone. The collected data is temporarily stored on the device.

[0419] Step 2:

[0420] The device sends the stored data to the server. This transmission is performed using a security protocol to ensure data confidentiality. The transmitted data is received within the server.

[0421] Step 3:

[0422] The server preprocesses the received data. This includes noise reduction and format standardization. Preprocessing transforms the data into a state suitable for analysis.

[0423] Step 4:

[0424] The server inputs pre-processed data into the analysis module and performs image recognition and speech recognition. Image data is used to identify objects and people, while speech data is used to identify specific sounds.

[0425] Step 5:

[0426] The server uses generated AI to assess risks based on the analyzed data. It comprehensively analyzes the situation indicated by the data and identifies potential risks.

[0427] Step 6:

[0428] The server generates a risk report based on the results of the risk assessment. The risk report specifically details the identified risks, their urgency, and recommended countermeasures.

[0429] Step 7:

[0430] The server sends the generated risk report to the terminal and notifies the user. This is done through a procedure that emphasizes immediacy.

[0431] Step 8:

[0432] The user reviews the risk report displayed on their device. Based on this, the user can adjust their actions as needed according to the suggested countermeasures.

[0433] (Example 1)

[0434] 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."

[0435] In today's complex social environment, there is a need to collect diverse information and quickly assess potential risks. However, efficiently and accurately identifying risks in a situation where various data formats coexist and presenting them as useful information to users is difficult. To solve this problem, a system is needed that analyzes diverse data in real time, identifies potential risks, and supports appropriate actions that users should take.

[0436] 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.

[0437] In this invention, the server includes processing means for preprocessing received data and ensuring consistency, analysis means for analyzing the data using a multilayer neural network, and evaluation means for evaluating risk using a generative AI model based on the analysis results. This makes it possible to comprehensively analyze diverse data in real time, evaluate potential risks with high accuracy, and immediately notify the user.

[0438] A "sensor" is a device used to acquire information about the surrounding environment, and it has the function of collecting image, sound, and text data.

[0439] "Data collection methods" refer to methods of acquiring necessary data by utilizing sensors in response to user operations and environmental conditions.

[0440] "Communication method" refers to the method by which a terminal transmits data it has collected to a server via a network.

[0441] "Processing means" refers to the process of shaping received data and performing data cleansing and format conversion to ensure consistency.

[0442] A "multilayer neural network" is an artificial intelligence technique used for data analysis, possessing a structure that enables highly accurate pattern recognition using a large number of parameters.

[0443] "Analysis method" refers to a method of analyzing acquired data using a multilayer neural network to extract important information.

[0444] A "generative AI model" refers to an artificial intelligence model that learns from large amounts of data and is used to identify and assess risks from the acquired information.

[0445] "Evaluation method" refers to a method of evaluating potential risks by using a generative AI model based on the results of the analysis.

[0446] "Notification method" refers to a system-based method for sending the evaluated risk report to the user's terminal to prompt appropriate action.

[0447] The following describes embodiments for implementing the system of the present invention.

[0448] Users collect information about their surroundings using a portable device. This device is equipped with sensors and has the ability to acquire image, audio, and text data. Specifically, the device is equipped with a camera, microphone, and text input interface, allowing it to collect data naturally in various situations in daily life. For example, while a user is walking in a shopping mall, the device collects information about the crowd and background sounds.

[0449] Data acquired by the terminal is transmitted to the server via the network. The server first performs preprocessing on the received data, such as noise reduction and formatting standardization. At this stage, extraneous and erroneous data is eliminated. The server then analyzes the data using a multi-layer neural network to perform image recognition and speech recognition. High-speed computers with GPUs are often used for this analysis.

[0450] Based on the analyzed data, the server utilizes a generative AI model to assess potential risks. This generative AI model has been pre-trained on data from a variety of situations, allowing it to accurately identify the type and urgency of risks. For example, if high noise levels are detected in a crowded area, the risk associated with congestion is assessed, and this information is notified to the user.

[0451] If a risk is identified, the server generates a risk report reflecting that information and notifies the user's terminal. This risk report includes the type of risk identified, recommended countermeasures, and suggestions for actions to take as needed. By receiving this information, the user can take appropriate action, such as choosing an alternative route to avoid congestion.

[0452] As a concrete example, an example prompt message is "Suggest a safe route within the shopping mall." Based on this prompt, the server analyzes the message and sends an appropriate notification to the terminal. This allows the user to reach their destination safely and efficiently.

[0453] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0454] Step 1:

[0455] The device collects environmental data (images, audio, and text) using built-in sensors. The input is real-time environmental information captured by the sensors, and the output is structured data formatted by the data collection module. Specifically, the device captures images of the user's surroundings with its camera and records ambient sounds with its microphone. For example, when a user moves through a shopping mall, photos of crowded areas and audio data including background noise are collected.

[0456] Step 2:

[0457] The terminal transmits the collected data to the server via the network. The input is the collected environmental data, and the output is the data packets transferred to the server. Specifically, the terminal encrypts the data and then transmits it to the server using Wi-Fi or mobile data communication. During this process, the terminal monitors signal strength and connection status and selects the optimal communication method.

[0458] Step 3:

[0459] The server preprocesses the received data. The input is data packets sent from the terminal, and the output is clean, parseable data. Specifically, the server removes noise from the data and imputes missing data. It also resolves data format inconsistencies and performs conversions to ensure consistency.

[0460] Step 4:

[0461] The server analyzes pre-processed data. The input is clean data, and the output is risk factor information as a result of the analysis. The server uses a multi-layer neural network to perform object recognition in images and pattern recognition in audio. Specifically, the server analyzes the density of a population and detects abnormal sound peaks to sense anomalies in the environment.

[0462] Step 5:

[0463] The server uses a generative AI model to assess risk based on the analysis results. The input is analyzed risk factor information, and the output is a risk report. The generative AI model has been trained on various data patterns and determines the type and urgency of risk from the input data. Specifically, the server assesses safety risks based on congestion and noise and proposes specific countermeasures.

[0464] Step 6:

[0465] The server notifies the user's terminal of the risk report it has generated. The input is the risk report, and the output is the notification information displayed on the terminal. Based on the content of the notification, the server sets the priority of the report and suggests recommended actions to the user. Specifically, the server guides the user along a safe route within the mall and provides the user with optimal information in real time.

[0466] (Application Example 1)

[0467] 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."

[0468] In modern society, security threats in buildings and public spaces are increasing. Under these circumstances, conventional security systems struggle to identify risks in real time and take appropriate action. In particular, there is a need for systems that can quickly detect security threats such as intrusions and unusual noises and immediately notify administrators.

[0469] 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.

[0470] In this invention, the server includes acquisition means for acquiring image data, audio data, and text data; identification means for identifying intrusions and abnormal sounds using the data from the acquisition means for security monitoring; and warning means for issuing warnings according to the urgency based on the risks identified by the identification means. This makes it possible to detect security threats in buildings and public places in real time and to direct a rapid response.

[0471] "Acquisition means" refers to devices and methods for collecting image data, audio data, and text data. This is achieved by utilizing cameras and microphones built into smartphones and other devices.

[0472] "Analysis means" refers to devices or methods that have the function of analyzing collected data in real time. These methods involve comprehensively processing the data using multilayer neural networks, etc., to extract risks.

[0473] "Evaluation tools" refer to devices or methods that have the function of evaluating risk based on the results of analyzed data and generating a risk report. They determine potential security risks from the analysis results.

[0474] "Notification means" refers to devices or methods for promptly informing users of assessed risk reports. Specifically, this involves providing information in the form of alerts or push notifications.

[0475] "Identification means" refers to devices or methods that have the function of analyzing acquired data to identify intrusions or abnormal sounds for security monitoring purposes. These are used to identify based on information from analysis means.

[0476] A "warning device" refers to a device or method that has the function of assessing the urgency of a risk identified by an identification device and issuing a warning. This makes it possible to quickly deliver crisis information to users.

[0477] This security system consists primarily of terminals and servers. The terminals are smart devices carried by users, equipped with sensors such as cameras and microphones. This allows for the daily collection of image, audio, and text data. The data is transmitted to the server via a wireless network.

[0478] The server first preprocesses the data, removing noise and standardizing the format. Software environments such as Python and TensorFlow are used for this. Next, it performs data analysis using multi-layer neural networks. Through this analysis, elements related to security risks are identified and evaluated.

[0479] Based on the evaluation results, the generating AI model further analyzes the risks. Identified risks are notified to the user's device. The notification includes specific warnings in the form of images and text, and suggests countermeasures according to the urgency.

[0480] As a concrete example, consider a case where building security is monitored at night. A terminal acquires audio and video from inside and outside the building via sensors and transmits it to a server. If the server detects an anomaly, an alert is sent to the terminal, allowing the administrator to immediately take action.

[0481] An example of a prompt message would be, "What risks arise if unusual noises are detected inside the building after 8 PM tonight?" This is highly effective when using a generative AI model to identify potential risks in advance and prepare for countermeasures.

[0482] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0483] Step 1:

[0484] The device uses its camera and microphone to acquire image, audio, and text data in real time. The acquired data is temporarily stored on the device and transmitted to the server via a wireless network. The input is raw data acquired by the camera and microphone, and the output is data packets sent to the server. The device constantly monitors changes in the external environment and quickly captures newly generated data.

[0485] Step 2:

[0486] The server receives data sent from the terminal and first performs data preprocessing. Specifically, it performs noise reduction, data format conversion, and missing value imputation. The input is raw data packets sent from the terminal, and the output is a clean dataset processed into a format that is easy to analyze. The server performs this data processing using SciPy and Pandas in a Python environment.

[0487] Step 3:

[0488] The server analyzes pre-processed data using a multi-layer neural network. This analysis detects specific patterns and anomalies latent within the data. The input is a clean dataset, and the output is a list of events deemed anomalous and their risk assessment results. The server uses TensorFlow and Keras to execute analysis modules, enabling real-time, large-scale data analysis.

[0489] Step 4:

[0490] The server further evaluates the analysis results using a generative AI model to identify specific risks. This identification process considers various risk factors and comprehensively assesses potential dangers. The input is a list of events deemed abnormal, and the output is a detailed list of the evaluated risks. The server determines the urgency of the risks and provides response guidelines based on prompt messages.

[0491] Step 5:

[0492] The server generates a risk report based on the assessed risk information and notifies the terminal. Specific actions include sending warnings via push notifications and email. The input is a detailed list of assessed risks, and the output is a warning message displayed on the user's terminal. The server supports enhanced security by presenting information in a way that allows users to take prompt action.

[0493] 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.

[0494] This invention is a system that acquires diverse data from users, analyzes it to recognize user emotions, and assesses risks. This system proposes appropriate risk mitigation measures based on the user's behavior and circumstances, and notifies the user accordingly.

[0495] First, the device has the ability to acquire data from the surrounding environment and the user using sensors. This includes acquiring image data, audio data, and text data. For example, data is collected when the user records a voice memo or enters text. In addition, an emotion engine built into the device infers the user's emotions from the audio and text data, and a dataset combining this information is sent to the server.

[0496] The server is equipped with an advanced analysis module for comprehensively analyzing incoming data. This analysis module uses a multi-layer neural network to analyze the data content and recognize specific objects and the user's emotional state. The emotion engine performs sentiment analysis, identifying emotional categories such as positive, negative, and neutral. Based on this, it is possible to identify unintended risks and the emotional states of specific users.

[0497] Based on the analysis results, the server performs a risk assessment and generates a risk report, taking into account both the situation indicated by the generated data and the user's emotional state. The risk report includes suggested countermeasures tailored to the user's current emotional state, providing guidance for the user to take specific actions. For example, if it is determined that the user is experiencing stress, the report may include a suggestion to move to a lower-risk area.

[0498] This risk report is sent from the server to the terminal. Next, when the risk report is provided to the user via a notification system, the notification content is adjusted according to the user's emotional state and presented in a way that is beneficial to the user. This enables flexible and effective communication, helping the user make appropriate decisions.

[0499] For example, in a situation where panic is likely to occur while a user is visiting a shopping center, this system can identify the user's feelings of anxiety and quickly provide more reassuring weather information, helping the user to respond appropriately. In this way, the present invention supports user safety and enables efficient risk management.

[0500] The following describes the processing flow.

[0501] Step 1:

[0502] The device acquires data related to the user's environment and behavior. This includes acquiring image data via the camera, recording voice data via the microphone, and inputting text messages. The voice data is analyzed in real time by an emotion engine to initially identify the user's emotions.

[0503] Step 2:

[0504] The terminal sends the acquired data to the server. A secure protocol is used for transmission, ensuring that the data arrives at the server in a consistent and confidential state.

[0505] Step 3:

[0506] The server preprocesses the received data, standardizing the data format and optimizing it for analysis. This process includes noise reduction and correction of missing data.

[0507] Step 4:

[0508] The server inputs pre-processed data into an analysis module for image and speech recognition. During this process, a multi-layer neural network is used to perform detailed analysis of specific patterns within the data and user sentiment.

[0509] Step 5:

[0510] Based on the analysis results, the server uses a generation AI to perform a risk assessment based on the user's situation and emotions. The emotion engine extracts information and then makes a risk determination that takes into account psychological factors such as stress and anxiety.

[0511] Step 6:

[0512] The server generates a risk report based on the risk assessment results. The risk report includes details of the identified risks, recommended countermeasures, and advice that takes into account the user's emotional state.

[0513] Step 7:

[0514] The server sends a risk report to the terminal and instructs it to notify the user directly. The notification method is adjusted according to the user's emotional state and is provided in an appropriate format and at the appropriate time.

[0515] Step 8:

[0516] Users receive notifications on their devices and review the displayed risk report. They can then follow the suggested countermeasures and advice, choose appropriate actions, and manage their emotional state.

[0517] (Example 2)

[0518] 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."

[0519] Often, prompt and appropriate risk assessments and countermeasures are not provided in accordance with the user's emotional state, making it difficult for users to respond flexibly based on their emotions. This has made it particularly difficult to provide appropriate risk information and guidance to users experiencing stress or anxiety.

[0520] 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.

[0521] In this invention, the server includes means for acquiring data and inferring emotional states, means for integrating the acquired data and analyzing it in real time, and means for evaluating risks based on the analysis results, generating risk reports, and providing notifications tailored to the user's emotions. This makes it possible to grasp the user's emotional state in real time and to make appropriate risk assessments and propose specific countermeasures.

[0522] "Means for acquiring data and inferring emotional state" refers to components of a system that collects various data from users, such as voice, images, and text, and uses that data to identify the user's emotional state.

[0523] "Means for integrating acquired data and analyzing it in real time" refers to a part of a system that centrally processes multiple types of collected data and has the function of analyzing the current situation and emotions.

[0524] "A means of evaluating risk based on analysis results, generating a risk report, and providing notifications tailored to the user's emotions" refers to a system process that uses analyzed data to evaluate potential dangers and risks to the user, creates a risk report summarizing the results, and provides notifications in a manner appropriate to the user's current emotional state.

[0525] A "neural network" is a type of machine learning that uses computer algorithms designed to be inspired by the nervous system of living organisms, enabling pattern recognition and analysis of data.

[0526] This invention is a system that grasps the user's emotional state in real time and proposes appropriate risk assessments and specific countermeasures. The following describes a specific embodiment for implementing this invention.

[0527] Hardware and software configuration

[0528] The device is equipped with various sensors to acquire data such as voice, images, and text. This includes a microphone and camera. The device also has a built-in emotion engine for emotion recognition, which analyzes the acquired voice and text data. A dedicated emotion inference algorithm is used for emotion recognition.

[0529] The server is equipped with an analysis module for analyzing received data, and it uses a multi-layer neural network to comprehensively analyze multiple data sets. This makes it possible to accurately understand the user's emotional state and surrounding circumstances.

[0530] Data processing

[0531] The device processes the acquired data using an emotion engine to infer the user's emotions. This inferred data is sent to the server. The server performs analysis using a neural network based on the transmitted data. Based on the results of this analysis, a risk report is generated that includes a risk assessment and action guidelines tailored to the user's current emotional state.

[0532] The generated risk report is sent back to the terminal and notified to the user in the most appropriate way through the notification system. This notification process takes into account the user's emotional state and provides the user with the most relevant information.

[0533] Examples of specific cases and prompt statements

[0534] For example, if a user is relaxing in a park and an unexpected loud noise occurs nearby, this system will detect the user's anxiety and immediately provide information suggesting they move to a safe location.

[0535] An example of a prompt message is: "Explain how to assess the current risk situation based on the user's emotions and notify them of appropriate action guidelines."

[0536] In this way, this system can comprehensively analyze the user's emotions and circumstances, and propose practical and effective risk management and countermeasures.

[0537] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0538] Step 1:

[0539] The device acquires data from the user, such as voice, images, and text. This input data is collected through the device's microphone, camera, and text input interface. The device then prepares this data for transmission to the emotion engine. Specifically, this involves saving user-entered text and recorded voice as digital data.

[0540] Step 2:

[0541] The device analyzes the acquired data using an emotion engine to infer the user's emotional state. This process employs algorithms that scrutinize voice tone and pitch in audio data, as well as text content. The acquired data is used as input, and emotion labels (e.g., positive, negative, neutral) are generated as output. The device then compiles the inference results into a dataset and performs specific actions to convert it into a data format for transmission to the server.

[0542] Step 3:

[0543] The terminal sends the inferred sentiment dataset to the server. A secure protocol (e.g., HTTPS) is used for communication. The input for this step is sentiment data and integrated environmental data, and the output is secure data communication. The terminal performs the specific action of uploading the data to the server in real time.

[0544] Step 4:

[0545] The server comprehensively analyzes the data received from the terminal using an analysis module. A multi-layer neural network is used for analysis, including the recognition of specific objects and the reconfirmation of emotional states. The transmitted emotional dataset is used as input, and the output is generated as a dataset of analysis results. The server recognizes patterns in the data and performs specific actions to deepen its understanding of the user's behavior and situation.

[0546] Step 5:

[0547] The server evaluates the risks based on the analysis results and generates a risk report. Here, potential risks are assessed considering the user's emotional state and environmental data. Using the analysis data as input, the server generates a report that presents a risk assessment and specific action guidelines as output. The server then performs the specific actions to compile a detailed risk report incorporating countermeasures.

[0548] Step 6:

[0549] The server sends the generated risk report to the terminal. The terminal receives it and provides it to the user via a notification system. The notification content is required to be adjusted based on the user's emotional state. The input is the risk report, and the output is a notification optimized for the user. The terminal includes specific actions to draw the user's attention, such as using screen displays or audio alerts.

[0550] (Application Example 2)

[0551] 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."

[0552] When users encounter abnormal situations or emotional states in their daily lives, there is a challenge in quickly and accurately assessing the risks and providing appropriate countermeasures. Therefore, an effective support system is needed to ensure the safety of users and enable them to live with peace of mind.

[0553] 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.

[0554] In this invention, the server includes information acquisition means for acquiring image data, audio data, and text data; data analysis means for integrating the acquired data and analyzing it in real time; and information evaluation means for evaluating the risk from the analysis results and generating a risk report. This allows the server to recognize the user's emotional state and provide safety guidelines as needed, enabling the user to respond quickly even in abnormal situations.

[0555] "Information acquisition means" refers to a device equipped with functions for acquiring image data, audio data, and text data.

[0556] A "data analysis means" is a processing device that integrates acquired data and analyzes it in real time.

[0557] An "information evaluation tool" is a device that has the function of evaluating risk based on analysis results and generating a risk report.

[0558] An "information notification device" is a device that has the function of notifying users of the evaluated risk report.

[0559] A "safety guidance provision device" is a device that recognizes the emotional state of the user and has the function of providing safety guidance when necessary.

[0560] This invention provides a system that allows users to receive real-time risk assessments and safety guidelines based on their environment and emotional state using a smart device. Specifically, the system is configured as follows:

[0561] First, the device uses information acquisition methods to collect data about the user's surroundings and their own voice, images, and text. Smart glasses and the camera and microphone of a smartphone are used for this data acquisition. For example, smart glasses capture video of the surroundings while simultaneously collecting audio data with the microphone.

[0562] Next, the collected data is analyzed in real time using a multi-layer neural network by a data analysis tool. During this process, an emotion estimation algorithm is applied to identify whether the user's emotional state is positive, negative, or neutral. The analysis platform used may include machine learning frameworks such as TensorFlow.

[0563] The server uses information evaluation tools to assess risk based on the analysis results and generates a risk report tailored to the user. This risk report includes specific safety guidelines that are appropriate to the user's current situation and emotional state. For example, if a user feels uneasy in a busy area, the server will notify them of a suggestion for a safer route.

[0564] The safety guidance delivery system presents risk reports to users through notification methods. Notifications are displayed as audio or text, and users can receive safety guidance via their smart devices. This helps users make quick and accurate decisions regarding specific situations they face.

[0565] For example, if a user feels anxious on a train platform, the smart glasses display will show instructions to take a deep breath along with directions to a quiet resting area.

[0566] An example of a prompt that utilizes a generative AI model is, "If a user is in a crowded place but does not feel anxious, what action should be suggested?"

[0567] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0568] Step 1:

[0569] The device uses the cameras and microphones of smart glasses or smartphones to collect image and audio data of the environment, as well as text data entered by the user. This input data specifically reflects the user's surroundings and spoken content. This prepares the system for understanding the user's state in real time.

[0570] Step 2:

[0571] The terminal preprocesses the collected image and audio data, performing enhancements such as sharpening and noise reduction. This improves the quality of the data used for analysis. This processed data is then sent to the server.

[0572] Step 3:

[0573] The server analyzes the received data using a multilayer neural network. Image data is subjected to image recognition algorithms to identify specific visual patterns, and audio data is converted to text using speech recognition algorithms. This analysis determines the user's emotional state (positive, negative, or neutral).

[0574] Step 4:

[0575] Based on the analysis results, the server assesses the risk using information evaluation tools. In this process, it determines the risk level based on the inferred emotional state and generates a risk report. The generated report includes the risks the user may face and the necessary countermeasures.

[0576] Step 5:

[0577] The server sends the generated risk report to the terminal and notifies the user through a safety guidance provision system. The notification is made via voice or text, and real-time feedback is provided. Specifically, the user reads the information displayed on the smart glasses' screen and adjusts their actions according to the safety guidelines.

[0578] Step 6:

[0579] Users take safe actions based on the information they receive. For example, if a user feels uneasy, they can actually change their behavior according to the suggested course of action. This helps them avoid real danger.

[0580] 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.

[0581] 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.

[0582] 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.

[0583] [Fourth Embodiment]

[0584] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0585] 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.

[0586] 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).

[0587] 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.

[0588] 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.

[0589] 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).

[0590] 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.

[0591] 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.

[0592] 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.

[0593] 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.

[0594] 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.

[0595] 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.

[0596] 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".

[0597] This invention is a system that evaluates and notifies of potential risks through the integrated analysis of various data. This system mainly consists of two components: a terminal and a server.

[0598] First, the terminal is a device owned by the user, and it acquires image data, audio data, and text data through its sensors. This terminal is equipped with a camera, microphone, and text input interface, making it possible to collect data naturally during daily life. For example, while the user is commuting, the terminal records the surrounding traffic conditions and collects information about noise and people's movements.

[0599] Next, the data acquired by the terminal is sent to the server. After receiving this data, the server first performs preprocessing and cleanses the data. After preprocessing, the server uses a dedicated analysis module to perform image recognition and speech recognition. The analysis module employs multilayer neural network technology, which enables highly accurate analysis.

[0600] Next, the server uses a generative AI module to assess the risks based on the analyzed data. This assessment process comprehensively analyzes the content of the acquired data to identify potential risks. For example, if the analysis results indicate "large crowds" and "high noise levels," the generative AI recognizes the occurrence of safety risks due to congestion.

[0601] Once risks are assessed, the server generates a risk report. This report includes the type of risk identified, its urgency, and recommended actions for the user. The server promptly notifies the user's terminal of this risk report. This allows the user to understand the potential dangers and take appropriate action.

[0602] As a concrete example, consider the case where this system is implemented in a shopping mall. When a user walks around the mall with a device, the device records the surrounding environment. The server detects congestion and unusual sounds from the collected data, and if it determines there is a risk, it sends a notification to the user suggesting a safe route. In this way, users can avoid confusion and danger and move around with peace of mind.

[0603] The system of this invention allows users and corporations to automatically evaluate and be notified of potential risks in their daily lives and work, thereby enabling improved safety and efficient risk management.

[0604] The following describes the processing flow.

[0605] Step 1:

[0606] The device activates its sensors and begins acquiring image, audio, and text data. This includes taking pictures of the surroundings with the camera and recording ambient sounds with the microphone. The collected data is temporarily stored on the device.

[0607] Step 2:

[0608] The device sends the stored data to the server. This transmission is performed using a security protocol to ensure data confidentiality. The transmitted data is received within the server.

[0609] Step 3:

[0610] The server preprocesses the received data. This includes noise reduction and format standardization. Preprocessing transforms the data into a state suitable for analysis.

[0611] Step 4:

[0612] The server inputs pre-processed data into the analysis module and performs image recognition and speech recognition. Image data is used to identify objects and people, while speech data is used to identify specific sounds.

[0613] Step 5:

[0614] The server uses generated AI to assess risks based on the analyzed data. It comprehensively analyzes the situation indicated by the data and identifies potential risks.

[0615] Step 6:

[0616] The server generates a risk report based on the results of the risk assessment. The risk report specifically details the identified risks, their urgency, and recommended countermeasures.

[0617] Step 7:

[0618] The server sends the generated risk report to the terminal and notifies the user. This is done through a procedure that emphasizes immediacy.

[0619] Step 8:

[0620] The user reviews the risk report displayed on their device. Based on this, the user can adjust their actions as needed according to the suggested countermeasures.

[0621] (Example 1)

[0622] 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".

[0623] In today's complex social environment, there is a need to collect diverse information and quickly assess potential risks. However, efficiently and accurately identifying risks in a situation where various data formats coexist and presenting them as useful information to users is difficult. To solve this problem, a system is needed that analyzes diverse data in real time, identifies potential risks, and supports appropriate actions that users should take.

[0624] 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.

[0625] In this invention, the server includes processing means for preprocessing received data and ensuring consistency, analysis means for analyzing the data using a multilayer neural network, and evaluation means for evaluating risk using a generative AI model based on the analysis results. This makes it possible to comprehensively analyze diverse data in real time, evaluate potential risks with high accuracy, and immediately notify the user.

[0626] A "sensor" is a device used to acquire information about the surrounding environment, and it has the function of collecting image, sound, and text data.

[0627] "Data collection methods" refer to methods of acquiring necessary data by utilizing sensors in response to user operations and environmental conditions.

[0628] "Communication method" refers to the method by which a terminal transmits data it has collected to a server via a network.

[0629] "Processing means" refers to the process of shaping received data and performing data cleansing and format conversion to ensure consistency.

[0630] A "multilayer neural network" is an artificial intelligence technique used for data analysis, possessing a structure that enables highly accurate pattern recognition using a large number of parameters.

[0631] "Analysis method" refers to a method of analyzing acquired data using a multilayer neural network to extract important information.

[0632] A "generative AI model" refers to an artificial intelligence model that learns from large amounts of data and is used to identify and assess risks from the acquired information.

[0633] "Evaluation method" refers to a method of evaluating potential risks by using a generative AI model based on the results of the analysis.

[0634] "Notification method" refers to a system-based method for sending the evaluated risk report to the user's terminal to prompt appropriate action.

[0635] The following describes embodiments for implementing the system of the present invention.

[0636] Users collect information about their surroundings using a portable device. This device is equipped with sensors and has the ability to acquire image, audio, and text data. Specifically, the device is equipped with a camera, microphone, and text input interface, allowing it to collect data naturally in various situations in daily life. For example, while a user is walking in a shopping mall, the device collects information about the crowd and background sounds.

[0637] Data acquired by the terminal is transmitted to the server via the network. The server first performs preprocessing on the received data, such as noise reduction and formatting standardization. At this stage, extraneous and erroneous data is eliminated. The server then analyzes the data using a multi-layer neural network to perform image recognition and speech recognition. High-speed computers with GPUs are often used for this analysis.

[0638] Based on the analyzed data, the server utilizes a generative AI model to assess potential risks. This generative AI model has been pre-trained on data from a variety of situations, allowing it to accurately identify the type and urgency of risks. For example, if high noise levels are detected in a crowded area, the risk associated with congestion is assessed, and this information is notified to the user.

[0639] If a risk is identified, the server generates a risk report reflecting that information and notifies the user's terminal. This risk report includes the type of risk identified, recommended countermeasures, and suggestions for actions to take as needed. By receiving this information, the user can take appropriate action, such as choosing an alternative route to avoid congestion.

[0640] As a concrete example, an example prompt message is "Suggest a safe route within the shopping mall." Based on this prompt, the server analyzes the message and sends an appropriate notification to the terminal. This allows the user to reach their destination safely and efficiently.

[0641] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0642] Step 1:

[0643] The device collects environmental data (images, audio, and text) using built-in sensors. The input is real-time environmental information captured by the sensors, and the output is structured data formatted by the data collection module. Specifically, the device captures images of the user's surroundings with its camera and records ambient sounds with its microphone. For example, when a user moves through a shopping mall, photos of crowded areas and audio data including background noise are collected.

[0644] Step 2:

[0645] The terminal transmits the collected data to the server via the network. The input is the collected environmental data, and the output is the data packets transferred to the server. Specifically, the terminal encrypts the data and then transmits it to the server using Wi-Fi or mobile data communication. During this process, the terminal monitors signal strength and connection status and selects the optimal communication method.

[0646] Step 3:

[0647] The server preprocesses the received data. The input is data packets sent from the terminal, and the output is clean, parseable data. Specifically, the server removes noise from the data and imputes missing data. It also resolves data format inconsistencies and performs conversions to ensure consistency.

[0648] Step 4:

[0649] The server analyzes pre-processed data. The input is clean data, and the output is risk factor information as a result of the analysis. The server uses a multi-layer neural network to perform object recognition in images and pattern recognition in audio. Specifically, the server analyzes the density of a population and detects abnormal sound peaks to sense anomalies in the environment.

[0650] Step 5:

[0651] The server uses a generative AI model to assess risk based on the analysis results. The input is analyzed risk factor information, and the output is a risk report. The generative AI model has been trained on various data patterns and determines the type and urgency of risk from the input data. Specifically, the server assesses safety risks based on congestion and noise and proposes specific countermeasures.

[0652] Step 6:

[0653] The server notifies the user's terminal of the risk report it has generated. The input is the risk report, and the output is the notification information displayed on the terminal. Based on the content of the notification, the server sets the priority of the report and suggests recommended actions to the user. Specifically, the server guides the user along a safe route within the mall and provides the user with optimal information in real time.

[0654] (Application Example 1)

[0655] 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".

[0656] In modern society, security threats in buildings and public spaces are increasing. Under these circumstances, conventional security systems struggle to identify risks in real time and take appropriate action. In particular, there is a need for systems that can quickly detect security threats such as intrusions and unusual noises and immediately notify administrators.

[0657] 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.

[0658] In this invention, the server includes acquisition means for acquiring image data, audio data, and text data; identification means for identifying intrusions and abnormal sounds using the data from the acquisition means for security monitoring; and warning means for issuing warnings according to the urgency based on the risks identified by the identification means. This makes it possible to detect security threats in buildings and public places in real time and to direct a rapid response.

[0659] "Acquisition means" refers to devices and methods for collecting image data, audio data, and text data. This is achieved by utilizing cameras and microphones built into smartphones and other devices.

[0660] "Analysis means" refers to devices or methods that have the function of analyzing collected data in real time. These methods involve comprehensively processing the data using multilayer neural networks, etc., to extract risks.

[0661] "Evaluation tools" refer to devices or methods that have the function of evaluating risk based on the results of analyzed data and generating a risk report. They determine potential security risks from the analysis results.

[0662] "Notification means" refers to devices or methods for promptly informing users of assessed risk reports. Specifically, this involves providing information in the form of alerts or push notifications.

[0663] "Identification means" refers to devices or methods that have the function of analyzing acquired data to identify intrusions or abnormal sounds for security monitoring purposes. These are used to identify based on information from analysis means.

[0664] A "warning device" refers to a device or method that has the function of assessing the urgency of a risk identified by an identification device and issuing a warning. This makes it possible to quickly deliver crisis information to users.

[0665] This security system consists primarily of terminals and servers. The terminals are smart devices carried by users, equipped with sensors such as cameras and microphones. This allows for the daily collection of image, audio, and text data. The data is transmitted to the server via a wireless network.

[0666] The server first preprocesses the data, removing noise and standardizing the format. Software environments such as Python and TensorFlow are used for this. Next, it performs data analysis using multi-layer neural networks. Through this analysis, elements related to security risks are identified and evaluated.

[0667] Based on the evaluation results, the generating AI model further analyzes the risks. Identified risks are notified to the user's device. The notification includes specific warnings in the form of images and text, and suggests countermeasures according to the urgency.

[0668] As a concrete example, consider a case where building security is monitored at night. A terminal acquires audio and video from inside and outside the building via sensors and transmits it to a server. If the server detects an anomaly, an alert is sent to the terminal, allowing the administrator to immediately take action.

[0669] An example of a prompt message would be, "What risks arise if unusual noises are detected inside the building after 8 PM tonight?" This is highly effective when using a generative AI model to identify potential risks in advance and prepare for countermeasures.

[0670] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0671] Step 1:

[0672] The device uses its camera and microphone to acquire image, audio, and text data in real time. The acquired data is temporarily stored on the device and transmitted to the server via a wireless network. The input is raw data acquired by the camera and microphone, and the output is data packets sent to the server. The device constantly monitors changes in the external environment and quickly captures newly generated data.

[0673] Step 2:

[0674] The server receives data sent from the terminal and first performs data preprocessing. Specifically, it performs noise reduction, data format conversion, and missing value imputation. The input is raw data packets sent from the terminal, and the output is a clean dataset processed into a format that is easy to analyze. The server performs this data processing using SciPy and Pandas in a Python environment.

[0675] Step 3:

[0676] The server analyzes pre-processed data using a multi-layer neural network. This analysis detects specific patterns and anomalies latent within the data. The input is a clean dataset, and the output is a list of events deemed anomalous and their risk assessment results. The server uses TensorFlow and Keras to execute analysis modules, enabling real-time, large-scale data analysis.

[0677] Step 4:

[0678] The server further evaluates the analysis results using a generative AI model to identify specific risks. This identification process considers various risk factors and comprehensively assesses potential dangers. The input is a list of events deemed abnormal, and the output is a detailed list of the evaluated risks. The server determines the urgency of the risks and provides response guidelines based on prompt messages.

[0679] Step 5:

[0680] The server generates a risk report based on the assessed risk information and notifies the terminal. Specific actions include sending warnings via push notifications and email. The input is a detailed list of assessed risks, and the output is a warning message displayed on the user's terminal. The server supports enhanced security by presenting information in a way that allows users to take prompt action.

[0681] 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.

[0682] This invention is a system that acquires diverse data from users, analyzes it to recognize user emotions, and assesses risks. This system proposes appropriate risk mitigation measures based on the user's behavior and circumstances, and notifies the user accordingly.

[0683] First, the device has the ability to acquire data from the surrounding environment and the user using sensors. This includes acquiring image data, audio data, and text data. For example, data is collected when the user records a voice memo or enters text. In addition, an emotion engine built into the device infers the user's emotions from the audio and text data, and a dataset combining this information is sent to the server.

[0684] The server is equipped with an advanced analysis module for comprehensively analyzing incoming data. This analysis module uses a multi-layer neural network to analyze the data content and recognize specific objects and the user's emotional state. The emotion engine performs sentiment analysis, identifying emotional categories such as positive, negative, and neutral. Based on this, it is possible to identify unintended risks and the emotional states of specific users.

[0685] Based on the analysis results, the server performs a risk assessment and generates a risk report, taking into account both the situation indicated by the generated data and the user's emotional state. The risk report includes suggested countermeasures tailored to the user's current emotional state, providing guidance for the user to take specific actions. For example, if it is determined that the user is experiencing stress, the report may include a suggestion to move to a lower-risk area.

[0686] This risk report is sent from the server to the terminal. Next, when the risk report is provided to the user via a notification system, the notification content is adjusted according to the user's emotional state and presented in a way that is beneficial to the user. This enables flexible and effective communication, helping the user make appropriate decisions.

[0687] For example, in a situation where panic is likely to occur while a user is visiting a shopping center, this system can identify the user's feelings of anxiety and quickly provide more reassuring weather information, helping the user to respond appropriately. In this way, the present invention supports user safety and enables efficient risk management.

[0688] The following describes the processing flow.

[0689] Step 1:

[0690] The device acquires data related to the user's environment and behavior. This includes acquiring image data via the camera, recording voice data via the microphone, and inputting text messages. The voice data is analyzed in real time by an emotion engine to initially identify the user's emotions.

[0691] Step 2:

[0692] The terminal sends the acquired data to the server. A secure protocol is used for transmission, ensuring that the data arrives at the server in a consistent and confidential state.

[0693] Step 3:

[0694] The server preprocesses the received data, standardizing the data format and optimizing it for analysis. This process includes noise reduction and correction of missing data.

[0695] Step 4:

[0696] The server inputs pre-processed data into an analysis module for image and speech recognition. During this process, a multi-layer neural network is used to perform detailed analysis of specific patterns within the data and user sentiment.

[0697] Step 5:

[0698] Based on the analysis results, the server uses a generation AI to perform a risk assessment based on the user's situation and emotions. The emotion engine extracts information and then makes a risk determination that takes into account psychological factors such as stress and anxiety.

[0699] Step 6:

[0700] The server generates a risk report based on the risk assessment results. The risk report includes details of the identified risks, recommended countermeasures, and advice that takes into account the user's emotional state.

[0701] Step 7:

[0702] The server sends a risk report to the terminal and instructs it to notify the user directly. The notification method is adjusted according to the user's emotional state and is provided in an appropriate format and at the appropriate time.

[0703] Step 8:

[0704] Users receive notifications on their devices and review the displayed risk report. They can then follow the suggested countermeasures and advice, choose appropriate actions, and manage their emotional state.

[0705] (Example 2)

[0706] 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".

[0707] Often, prompt and appropriate risk assessments and countermeasures are not provided in accordance with the user's emotional state, making it difficult for users to respond flexibly based on their emotions. This has made it particularly difficult to provide appropriate risk information and guidance to users experiencing stress or anxiety.

[0708] 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.

[0709] In this invention, the server includes means for acquiring data and inferring emotional states, means for integrating the acquired data and analyzing it in real time, and means for evaluating risks based on the analysis results, generating risk reports, and providing notifications tailored to the user's emotions. This makes it possible to grasp the user's emotional state in real time and to make appropriate risk assessments and propose specific countermeasures.

[0710] "Means for acquiring data and inferring emotional state" refers to components of a system that collects various data from users, such as voice, images, and text, and uses that data to identify the user's emotional state.

[0711] "Means for integrating acquired data and analyzing it in real time" refers to a part of a system that centrally processes multiple types of collected data and has the function of analyzing the current situation and emotions.

[0712] "A means of evaluating risk based on analysis results, generating a risk report, and providing notifications tailored to the user's emotions" refers to a system process that uses analyzed data to evaluate potential dangers and risks to the user, creates a risk report summarizing the results, and provides notifications in a manner appropriate to the user's current emotional state.

[0713] A "neural network" is a type of machine learning that uses computer algorithms designed to be inspired by the nervous system of living organisms, enabling pattern recognition and analysis of data.

[0714] This invention is a system that grasps the user's emotional state in real time and proposes appropriate risk assessments and specific countermeasures. The following describes a specific embodiment for implementing this invention.

[0715] Hardware and software configuration

[0716] The device is equipped with various sensors to acquire data such as voice, images, and text. This includes a microphone and camera. The device also has a built-in emotion engine for emotion recognition, which analyzes the acquired voice and text data. A dedicated emotion inference algorithm is used for emotion recognition.

[0717] The server is equipped with an analysis module for analyzing received data, and it uses a multi-layer neural network to comprehensively analyze multiple data sets. This makes it possible to accurately understand the user's emotional state and surrounding circumstances.

[0718] Data processing

[0719] The device processes the acquired data using an emotion engine to infer the user's emotions. This inferred data is sent to the server. The server performs analysis using a neural network based on the transmitted data. Based on the results of this analysis, a risk report is generated that includes a risk assessment and action guidelines tailored to the user's current emotional state.

[0720] The generated risk report is sent back to the terminal and notified to the user in the most appropriate way through the notification system. This notification process takes into account the user's emotional state and provides the user with the most relevant information.

[0721] Examples of specific cases and prompt statements

[0722] For example, if a user is relaxing in a park and an unexpected loud noise occurs nearby, this system will detect the user's anxiety and immediately provide information suggesting they move to a safe location.

[0723] An example of a prompt message is: "Explain how to assess the current risk situation based on the user's emotions and notify them of appropriate action guidelines."

[0724] In this way, this system can comprehensively analyze the user's emotions and circumstances, and propose practical and effective risk management and countermeasures.

[0725] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0726] Step 1:

[0727] The device acquires data from the user, such as voice, images, and text. This input data is collected through the device's microphone, camera, and text input interface. The device then prepares this data for transmission to the emotion engine. Specifically, this involves saving user-entered text and recorded voice as digital data.

[0728] Step 2:

[0729] The device analyzes the acquired data using an emotion engine to infer the user's emotional state. This process employs algorithms that scrutinize voice tone and pitch in audio data, as well as text content. The acquired data is used as input, and emotion labels (e.g., positive, negative, neutral) are generated as output. The device then compiles the inference results into a dataset and performs specific actions to convert it into a data format for transmission to the server.

[0730] Step 3:

[0731] The terminal sends the inferred sentiment dataset to the server. A secure protocol (e.g., HTTPS) is used for communication. The input for this step is sentiment data and integrated environmental data, and the output is secure data communication. The terminal performs the specific action of uploading the data to the server in real time.

[0732] Step 4:

[0733] The server comprehensively analyzes the data received from the terminal using an analysis module. A multi-layer neural network is used for analysis, including the recognition of specific objects and the reconfirmation of emotional states. The transmitted emotional dataset is used as input, and the output is generated as a dataset of analysis results. The server recognizes patterns in the data and performs specific actions to deepen its understanding of the user's behavior and situation.

[0734] Step 5:

[0735] The server evaluates the risks based on the analysis results and generates a risk report. Here, potential risks are assessed considering the user's emotional state and environmental data. Using the analysis data as input, the server generates a report that presents a risk assessment and specific action guidelines as output. The server then performs the specific actions to compile a detailed risk report incorporating countermeasures.

[0736] Step 6:

[0737] The server sends the generated risk report to the terminal. The terminal receives it and provides it to the user via a notification system. The notification content is required to be adjusted based on the user's emotional state. The input is the risk report, and the output is a notification optimized for the user. The terminal includes specific actions to draw the user's attention, such as using screen displays or audio alerts.

[0738] (Application Example 2)

[0739] 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".

[0740] When users encounter abnormal situations or emotional states in their daily lives, there is a challenge in quickly and accurately assessing the risks and providing appropriate countermeasures. Therefore, an effective support system is needed to ensure the safety of users and enable them to live with peace of mind.

[0741] 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.

[0742] In this invention, the server includes information acquisition means for acquiring image data, audio data, and text data; data analysis means for integrating the acquired data and analyzing it in real time; and information evaluation means for evaluating the risk from the analysis results and generating a risk report. This allows the server to recognize the user's emotional state and provide safety guidelines as needed, enabling the user to respond quickly even in abnormal situations.

[0743] "Information acquisition means" refers to a device equipped with functions for acquiring image data, audio data, and text data.

[0744] A "data analysis means" is a processing device that integrates acquired data and analyzes it in real time.

[0745] An "information evaluation tool" is a device that has the function of evaluating risk based on analysis results and generating a risk report.

[0746] An "information notification device" is a device that has the function of notifying users of the evaluated risk report.

[0747] A "safety guidance provision device" is a device that recognizes the emotional state of the user and has the function of providing safety guidance when necessary.

[0748] This invention provides a system that allows users to receive real-time risk assessments and safety guidelines based on their environment and emotional state using a smart device. Specifically, the system is configured as follows:

[0749] First, the device uses information acquisition methods to collect data about the user's surroundings and their own voice, images, and text. Smart glasses and the camera and microphone of a smartphone are used for this data acquisition. For example, smart glasses capture video of the surroundings while simultaneously collecting audio data with the microphone.

[0750] Next, the collected data is analyzed in real time using a multi-layer neural network by a data analysis tool. During this process, an emotion estimation algorithm is applied to identify whether the user's emotional state is positive, negative, or neutral. The analysis platform used may include machine learning frameworks such as TensorFlow.

[0751] The server uses information evaluation tools to assess risk based on the analysis results and generates a risk report tailored to the user. This risk report includes specific safety guidelines that are appropriate to the user's current situation and emotional state. For example, if a user feels uneasy in a busy area, the server will notify them of a suggestion for a safer route.

[0752] The safety guidance delivery system presents risk reports to users through notification methods. Notifications are displayed as audio or text, and users can receive safety guidance via their smart devices. This helps users make quick and accurate decisions regarding specific situations they face.

[0753] For example, if a user feels anxious on a train platform, the smart glasses display will show instructions to take a deep breath along with directions to a quiet resting area.

[0754] An example of a prompt that utilizes a generative AI model is, "If a user is in a crowded place but does not feel anxious, what action should be suggested?"

[0755] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0756] Step 1:

[0757] The device uses the cameras and microphones of smart glasses or smartphones to collect image and audio data of the environment, as well as text data entered by the user. This input data specifically reflects the user's surroundings and spoken content. This prepares the system for understanding the user's state in real time.

[0758] Step 2:

[0759] The terminal preprocesses the collected image and audio data, performing enhancements such as sharpening and noise reduction. This improves the quality of the data used for analysis. This processed data is then sent to the server.

[0760] Step 3:

[0761] The server analyzes the received data using a multilayer neural network. Image data is subjected to image recognition algorithms to identify specific visual patterns, and audio data is converted to text using speech recognition algorithms. This analysis determines the user's emotional state (positive, negative, or neutral).

[0762] Step 4:

[0763] Based on the analysis results, the server assesses the risk using information evaluation tools. In this process, it determines the risk level based on the inferred emotional state and generates a risk report. The generated report includes the risks the user may face and the necessary countermeasures.

[0764] Step 5:

[0765] The server sends the generated risk report to the terminal and notifies the user through a safety guidance provision system. The notification is made via voice or text, and real-time feedback is provided. Specifically, the user reads the information displayed on the smart glasses' screen and adjusts their actions according to the safety guidelines.

[0766] Step 6:

[0767] Users take safe actions based on the information they receive. For example, if a user feels uneasy, they can actually change their behavior according to the suggested course of action. This helps them avoid real danger.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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."

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] The following is further disclosed regarding the embodiments described above.

[0790] (Claim 1)

[0791] A means for acquiring image data, audio data, and text data,

[0792] An analytical method that integrates the acquired data and analyzes it in real time,

[0793] An evaluation method for assessing risk from analysis results and generating a risk report,

[0794] A system that includes a notification mechanism for informing users of the evaluated risk report.

[0795] (Claim 2)

[0796] The system according to claim 1, wherein the evaluation means includes means for identifying various risks based on acquired data and proposing countermeasures.

[0797] (Claim 3)

[0798] The system according to claim 1, wherein the analysis means comprises means for analyzing data using a multilayer neural network.

[0799] "Example 1"

[0800] (Claim 1)

[0801] A means of acquiring environmental data using sensors,

[0802] A means of communication for sending data from a terminal to a server,

[0803] A processing means for preprocessing received data and ensuring consistency,

[0804] An analytical method that analyzes data using a multilayer neural network,

[0805] Based on the analysis results, an evaluation method is provided that uses a generative AI model to assess risk,

[0806] A notification system that generates a report based on the assessed risk and notifies the terminal,

[0807] A system that includes this.

[0808] (Claim 2)

[0809] The system according to claim 1, comprising an evaluation means for comprehensively analyzing acquired data, identifying various risks, and proposing countermeasures.

[0810] (Claim 3)

[0811] The system according to claim 1, comprising means for integrating and analyzing image data, audio data, and text data in real time.

[0812] "Application Example 1"

[0813] (Claim 1)

[0814] A means for acquiring image data, audio data, and text data,

[0815] An analytical method that integrates the acquired data and analyzes it in real time,

[0816] An evaluation method for assessing risk from analysis results and generating a risk report,

[0817] A notification method for informing users of the evaluated risk report,

[0818] For security monitoring, an identification means is used to identify intrusions and abnormal sounds using data from acquisition means,

[0819] A warning system that issues warnings based on the urgency of the risks identified by the identification means.

[0820] A system that includes this.

[0821] (Claim 2)

[0822] The system according to claim 1, wherein the evaluation means includes means for identifying various risks based on acquired data and proposing countermeasures.

[0823] (Claim 3)

[0824] The system according to claim 1, wherein the analysis means includes means for analyzing data using a multilayer neural network and performing an evaluation of the security status.

[0825] "Example 2 of combining an emotion engine"

[0826] (Claim 1)

[0827] A means of acquiring data and inferring emotional states,

[0828] A means of integrating the acquired data and analyzing it in real time,

[0829] A means for evaluating risk based on analysis results and generating a risk report,

[0830] A system that notifies users of generated risk reports and includes means for providing notifications that are adjusted according to their emotions.

[0831] (Claim 2)

[0832] The system according to claim 1, wherein the evaluation means includes means for identifying various risks based on acquired data and proposing countermeasures that take into account the user's emotional state.

[0833] (Claim 3)

[0834] The system according to claim 1, wherein the analysis means comprises means for analyzing data using a neural network.

[0835] "Application example 2 when combining with an emotional engine"

[0836] (Claim 1)

[0837] Information acquisition means for acquiring image data, audio data, and text data,

[0838] A data analysis method that integrates acquired data and analyzes it in real time,

[0839] An information evaluation means for evaluating risk from analysis results and generating a risk report,

[0840] An information notification method that notifies the user of the evaluated risk report,

[0841] A system that recognizes the emotional state of users and includes a safety guidance provision mechanism that provides safety guidance as needed.

[0842] (Claim 2)

[0843] The information evaluation means described above is a system according to claim 1, which has the function of identifying various risks based on acquired information and proposing countermeasures.

[0844] (Claim 3)

[0845] The system according to claim 1, wherein the data analysis means includes a function to analyze information using a multilayer neural network and estimate the user's emotional state. [Explanation of symbols]

[0846] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for acquiring image data, audio data, and text data, An analytical method that integrates the acquired data and analyzes it in real time, An evaluation method for assessing risk from analysis results and generating a risk report, A system that includes a notification mechanism for informing users of the evaluated risk report.

2. The system according to claim 1, wherein the evaluation means includes means for identifying various risks based on acquired data and proposing countermeasures.

3. The system according to claim 1, wherein the analysis means comprises means for analyzing data using a multilayer neural network.

Images