system

Abstract

The system according to this embodiment aims to quickly detect abnormalities and take appropriate action. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a detection unit, a notification unit, a report generation unit, and a safety information generation unit. The collection unit collects data. The analysis unit analyzes the data collected by the collection unit. The detection unit detects anomalies based on the analysis results obtained by the analysis unit. The notification unit issues an alert based on the anomalies detected by the detection unit. The report generation unit generates a detailed situation report based on the information notified by the notification unit. The safety information generation unit generates safety information for local residents based on the report generated by the report generation unit.

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 performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that the process from anomaly detection to response is delayed and it is difficult to respond promptly.

[0005] The system according to the embodiment aims to quickly detect anomalies and take appropriate actions.

Means for Solving the Problems

[0006] The system according to the embodiment comprises a data collection unit, an analysis unit, a detection unit, a notification unit, a report generation unit, and a safety information generation unit. The data collection unit collects data. The analysis unit analyzes the data collected by the data collection unit. The detection unit detects anomalies based on the analysis results obtained by the analysis unit. The notification unit issues an alert based on the anomalies detected by the detection unit. The report generation unit generates a detailed situation report based on the information notified by the notification unit. The safety information generation unit generates safety information for local residents based on the report generated by the report generation unit. [Effects of the Invention]

[0007] The system according to this embodiment can quickly detect abnormalities and take appropriate action. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 comprises a computer 36, a receiving 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 receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice 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 unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The gas leak detection system according to an embodiment of the present invention is a system that combines an AI algorithm and a generative AI to detect gas leaks early and respond quickly. This gas leak detection system collects data from IoT sensors installed in urban areas, and the AI ​​algorithm analyzes the collected data to immediately identify deviations from normal background levels. When an abnormality is detected, the gas leak detection system automatically issues an alert and notifies the gas company and emergency response team. This notification includes a detailed situation report automatically generated by the generative AI. Furthermore, the generative AI also automatically creates safety information for local residents. This significantly reduces the risk of accidents caused by gas leaks and improves urban safety. In addition, minimizing gas loss through early detection contributes to improved energy efficiency, achieving both environmental protection and economic viability. For example, methane is said to have 28 times the greenhouse effect of carbon dioxide (CO2) and is considered important for climate change countermeasures after CO2. This gas leak detection system contributes to the realization of a sustainable society through methane absorption / reduction. For example, the gas leak detection system collects data from IoT sensors installed in urban areas. These sensors are designed to detect even minute methane leaks. The gas leak detection system then uses AI algorithms to analyze the collected data, instantly identifying deviations from normal background levels. For example, if methane concentration rises sharply, the AI ​​detects the anomaly and issues an alert. Upon detection, the gas leak detection system automatically notifies the gas company and emergency response team. This notification includes a detailed situation report automatically generated by the generative AI. For instance, it reports the exact location, size, and extent of the leak. This allows the response team to obtain accurate information before arriving on-site, enabling a quick and efficient response. Furthermore, the gas leak detection system also uses the generative AI to automatically create safety information for local residents. For example, it generates clear and concise messages about the need for evacuation and how to ensure safety, depending on the size and location of the leak. This allows residents to take appropriate action without panicking. This gas leak detection system significantly reduces the risk of accidents caused by gas leaks, improving urban safety.Furthermore, minimizing gas loss through early detection contributes to improved energy efficiency, achieving both environmental protection and economic viability. For example, methane is said to have 28 times the greenhouse effect of carbon dioxide (CO2), making it the second most important mitigator of global warming after CO2. This gas leak detection system contributes to the realization of a sustainable society through methane absorption / reduction. As a result, the gas leak detection system can detect gas leaks early and respond quickly.

[0029] The gas leak detection system according to the embodiment comprises a collection unit, an analysis unit, a detection unit, a notification unit, a report generation unit, and a safety information generation unit. The collection unit collects data. The collection unit collects data from, for example, IoT sensors installed in urban areas. The collection unit can collect data using, for example, IoT sensors such as temperature sensors, humidity sensors, and gas sensors. The collection unit can collect data such as sensor data, log data, and user data. The analysis unit analyzes the data collected by the collection unit. The analysis unit analyzes the collected data and identifies deviations from the normal background level. The analysis unit can set a normal background level based on the mean and standard deviation of past data, and identify deviations when the collected data exceeds that range. The detection unit detects anomalies based on the analysis results obtained by the analysis unit. The detection unit can detect anomalies based on, for example, values ​​exceeding a threshold or deviations from the normal pattern based on the analysis results. The detection unit can detect anomalies based on, for example, the frequency of anomaly occurrence and the scope of its impact. The notification unit issues an alert based on the anomaly detected by the detection unit. The notification unit can, for example, issue alerts to gas companies and emergency response teams when an anomaly is detected. The notification unit can issue alerts in various forms, such as email notifications, SMS notifications, and app notifications. The report generation unit generates detailed situation reports based on the information notified by the notification unit. The report generation unit can, for example, automatically generate detailed situation reports of detected anomalies using generation AI. The report generation unit can generate detailed situation reports that include information such as the exact location of the gas leak, the scale of the leak, and the scope of the impact. The safety information generation unit generates safety information for local residents based on the reports generated by the report generation unit. The safety information generation unit can, for example, use generation AI to generate messages that clearly and concisely convey the need for evacuation and methods for ensuring safety, depending on the scale and location of the gas leak. The safety information generation unit can generate safety information that includes information such as evacuation orders, warnings, and emergency contact information.As a result, the gas leak detection system according to the embodiment can consistently perform tasks from data collection to anomaly detection, notification, report generation, and safety information generation.

[0030] The data collection unit collects data. For example, the data collection unit collects data from IoT sensors installed in urban areas. Specifically, the data collection unit can collect data using IoT sensors such as temperature sensors, humidity sensors, and gas sensors. These sensors are installed in various locations in urban areas and acquire environmental data in real time. Temperature sensors measure ambient temperature, and humidity sensors measure humidity in the air. Gas sensors can detect the concentration of specific gases and can detect signs of gas leaks. The data collection unit centrally manages this sensor data and transmits it to a central database. Furthermore, the data collection unit can collect not only sensor data but also log data and user data. Log data includes system operation status and records of past events, and user data includes information about user behavior and the environment. This allows the data collection unit to collect a wide range of data from diverse data sources and understand the overall system status in real time. By adjusting the frequency and accuracy of data collection, the data collection unit can respond flexibly to specific situations and conditions. For example, by increasing the sensitivity of the gas sensor, even minute gas leaks can be detected. Furthermore, the data collection unit is equipped with a filtering function to detect data anomalies early, eliminating noise and false positives. This allows the data collection unit to collect data efficiently and effectively, improving the overall system performance.

[0031] The analysis unit analyzes the data collected by the data collection unit. Specifically, the analysis unit analyzes the collected data and identifies deviations from normal background levels. The analysis unit sets normal background levels based on the mean and standard deviation of past data, and can identify deviations when the collected data exceeds that range. For example, if data from a gas sensor exceeds the normal background level, the analysis unit identifies that data as an anomaly. The analysis unit uses AI to analyze the data in real time and identify patterns of anomalies. The AI ​​learns from past data using machine learning algorithms and can perform highly accurate analyses on new data. This allows the analysis unit to analyze collected data quickly and accurately, enabling early detection of anomalies. Furthermore, the analysis unit can evaluate the frequency and scope of anomalies and determine the severity of the anomalies. For example, if gas leaks occur frequently or have a wide scope of impact, the analysis unit identifies the anomaly as serious. The analysis unit can also perform detailed analyses to identify the cause of the anomaly. This allows the analysis unit to contribute not only to the early detection of anomalies but also to investigating the causes of anomalies and formulating countermeasures.

[0032] The detection unit detects anomalies based on the analysis results obtained by the analysis unit. Specifically, the detection unit can detect values ​​exceeding a threshold or deviations from normal patterns as anomalies based on the analysis results. For example, if gas sensor data exceeds a set threshold, the detection unit detects that data as an anomaly. The detection unit can also detect anomalies based on the frequency of occurrence and the scope of impact. For example, if gas leaks occur frequently or have a wide scope of impact, the detection unit identifies the anomaly as serious. The detection unit uses AI to identify anomaly patterns, enabling early detection of anomalies. The AI ​​learns from past data using machine learning algorithms and can perform highly accurate analysis on new data. This allows the detection unit to quickly and accurately analyze collected data, enabling early detection of anomalies. Furthermore, the detection unit can perform detailed analysis to identify the cause of the anomaly. This allows the detection unit to contribute not only to early detection of anomalies but also to investigating the cause of anomalies and formulating countermeasures.

[0033] The notification unit issues alerts based on anomalies detected by the detection unit. Specifically, the notification unit can issue alerts to gas companies and emergency response teams when an anomaly is detected. The notification unit can issue alerts in various formats, such as email, SMS, and app notifications. For example, if a gas leak is detected, the notification unit will send an alert to the gas company via email and notify the emergency response team via SMS. It can also provide real-time information to relevant parties using app notifications. The notification unit can configure the content of alerts in detail, including information such as the type of anomaly, its location, and the scope of its impact. This allows the notification unit to provide quick and accurate information to relevant parties and encourage appropriate responses. Furthermore, the notification unit can set alert priorities, and serious anomalies can be notified with a higher priority. This allows the notification unit to support early detection and rapid response to anomalies, improving the overall safety of the system.

[0034] The report generation unit generates detailed situation reports based on information notified by the notification unit. Specifically, the report generation unit can automatically generate detailed situation reports of detected anomalies using generation AI. The generation AI uses natural language processing technology to create detailed reports based on collected data and analysis results. For example, it can generate detailed situation reports that include information such as the exact location of a gas leak, the scale of the leak, and the scope of its impact. The report generation unit provides the generated reports to relevant parties to support a rapid response. Furthermore, the report generation unit can customize the content of the reports and provide necessary information to specific parties. For example, it can provide gas companies with technical details and emergency response teams with information including response procedures and evacuation orders. This allows the report generation unit to provide relevant parties with appropriate information and support a rapid and effective response.

[0035] The safety information generation unit generates safety information for local residents based on reports generated by the report generation unit. Specifically, the safety information generation unit can use a generation AI to generate clear and concise messages that convey the necessity of evacuation and methods for ensuring safety, depending on the scale and location of the gas leak. The generation AI uses natural language processing technology to create messages for local residents based on collected data and analysis results. For example, it can generate safety information that includes evacuation orders, warnings, and emergency contact information. The safety information generation unit provides the generated messages to local residents to support rapid evacuation and ensuring safety. Furthermore, the safety information generation unit can customize the content of the messages and provide information tailored to specific areas and situations. For example, it can emphasize evacuation orders for certain areas and issue warnings for other areas. This allows the safety information generation unit to provide appropriate information to local residents and support a rapid and effective response.

[0036] The data collection unit collects data from IoT sensors installed in urban areas. The data collection unit can collect data using IoT sensors such as temperature sensors, humidity sensors, and gas sensors installed in urban areas. The data collection unit can collect data from IoT sensors installed in specific municipalities or densely populated areas within urban areas. The data collection unit can collect data such as sensor data, log data, and user data. This allows for the acquisition of data over a wide area by collecting data from IoT sensors installed in urban areas. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input data collected from IoT sensors installed in urban areas into an AI and have the AI ​​perform the data collection.

[0037] The analysis unit can analyze the collected data and identify deviations from normal background levels. For example, the analysis unit can analyze the collected data, set normal background levels based on the mean and standard deviation of past data, and identify deviations when the collected data exceeds that range. For example, the analysis unit can identify deviations when methane concentration rises sharply. For example, the analysis unit can identify deviations based on fluctuations in temperature or humidity data. In this way, deviations from normal background levels can be identified through data analysis. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the collected data into AI and have the AI ​​perform the data analysis.

[0038] The detection unit can detect anomalies based on the analysis results. For example, the detection unit can detect values ​​exceeding a threshold or deviations from normal patterns as anomalies based on the analysis results. For example, the detection unit can detect anomalies based on the frequency of occurrence or the scope of impact of the anomaly. For example, the detection unit can detect anomalies when the methane concentration rises sharply. For example, the detection unit can detect anomalies based on fluctuations in temperature data or humidity data. This enables a rapid response by detecting anomalies based on the analysis results. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input the analysis results into AI and have AI perform anomaly detection.

[0039] The notification unit can issue alerts to gas companies and emergency response teams when an anomaly is detected. The notification unit can issue alerts in the form of email notifications, SMS notifications, app notifications, etc., when an anomaly is detected. The notification unit can issue alerts that include information such as the location, scale, and scope of the anomaly. The notification unit can expedite the response by quickly issuing alerts to gas companies and emergency response teams, for example. This expedites the response by quickly issuing alerts when an anomaly is detected. Some or all of the above processing in the notification unit may be performed using AI, for example, or not using AI. For example, the notification unit can have AI issue an alert when an anomaly is detected.

[0040] The report generation unit can automatically generate detailed status reports of detected anomalies using a generation AI. For example, the report generation unit can use the generation AI to automatically generate detailed status reports that include information such as the exact location of a gas leak, the scale of the leak, and the scope of its impact. For example, the report generation unit can use the generation AI to report in detail the cause of the anomaly and the scope of its impact. For example, the report generation unit can use the generation AI to report the time the anomaly occurred and the response status. This allows the response team to quickly obtain accurate information by automatically generating detailed status reports using the generation AI. Some or all of the above-described processes in the report generation unit may be performed using the generation AI or not. For example, the report generation unit can input the detected anomaly data into the generation AI and have the generation AI generate a detailed status report.

[0041] The safety information generation unit can use a generating AI to generate clear and concise messages that convey the necessity of evacuation and methods for ensuring safety, depending on the scale and location of the gas leak. For example, the safety information generation unit can use the generating AI to generate messages that include information such as evacuation orders, warnings, and emergency contact information, depending on the scale and location of the gas leak. For example, the safety information generation unit can use the generating AI to provide local residents with quick and accurate safety information. For example, the safety information generation unit can use the generating AI to generate messages that clearly convey the scope of the gas leak's impact and evacuation routes. In this way, by automatically generating safety information using the generating AI, local residents can be provided with quick and accurate information. Some or all of the above-described processes in the safety information generation unit may be performed using the generating AI, or they may be performed without using the generating AI. For example, the safety information generation unit can input gas leak data into the generating AI and have the generating AI perform the generation of safety information.

[0042] The data collection unit can optimize the data collection method based on the sensor's location and environmental conditions during data acquisition. For example, if the sensor is installed in a high-humidity environment, the data collection unit can collect data while correcting for humidity. For example, if the sensor is installed in a high-temperature environment, the data collection unit can collect data while correcting for temperature. For example, if the sensor is installed in a windy location, the data collection unit can collect data while correcting for wind speed. By optimizing the data collection method based on the sensor's location and environmental conditions, accurate data collection becomes possible. Some or all of the above processing in the data collection unit may be performed using AI, or not. For example, the data collection unit can input data on the sensor's location and environmental conditions into the AI ​​and have the AI ​​optimize the data collection method.

[0043] The data collection unit can set a data collection schedule that takes into account the time periods when anomalies are likely to occur. For example, if anomalies are likely to occur at night, the data collection unit can set a higher frequency for nighttime data collection. For example, if anomalies are likely to occur on weekends, the data collection unit can set a higher frequency for weekend data collection. For example, if anomalies are likely to occur during a particular season, the data collection unit can set a higher frequency for that season's data collection. By setting a data collection schedule that takes into account the time periods when anomalies are likely to occur, early detection of anomalies becomes possible. Some or all of the above processing in the data collection unit may be performed using AI, or it may be performed without using AI. For example, the data collection unit can input data from time periods when anomalies are likely to occur into the AI ​​and have the AI ​​set the data collection schedule.

[0044] The data collection unit can customize the data collection method based on the type and performance of the sensor during data acquisition. For example, if a high-precision sensor is used, the data collection unit can collect detailed data. For example, if a low-precision sensor is used, the data collection unit can collect only basic data. For example, if a particular sensor is malfunctioning, the data collection unit can supplementarily collect data from other sensors. This allows for optimal data collection by customizing the data collection method based on the type and performance of the sensor. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input data on the type and performance of the sensor into the AI ​​and have the AI ​​perform the customization of the data collection method.

[0045] The data collection unit can set criteria for early detection of anomalies by comparing the data collected with data from other urban areas. For example, the data collection unit can set criteria for anomalies by comparing the data with data from other urban areas. For example, the data collection unit can set criteria based on the frequency of anomalies by comparing the data with data from other urban areas. For example, the data collection unit can set criteria based on the scope of anomaly impact by comparing the data with data from other urban areas. This enables early detection of anomalies by setting criteria for early detection of anomalies by comparing the data with data from other urban areas. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input data from other urban areas into the AI ​​and have the AI ​​perform the setting of anomaly detection criteria.

[0046] The analysis unit can identify anomaly patterns by comparing them with past data during analysis. For example, the analysis unit can identify the frequency of anomaly occurrences by comparing them with past data. For example, the analysis unit can identify the time period during which anomalies occur by comparing them with past data. For example, the analysis unit can identify the scope of anomaly impacts by comparing them with past data. This improves the accuracy of anomaly detection by identifying anomaly patterns by comparing them with past data. Some or all of the above-described processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input past data into AI and have AI perform the identification of anomaly patterns.

[0047] The analysis unit can apply different analytical methods depending on the type and characteristics of the data during analysis. For example, the analysis unit can apply a specific analytical method to methane concentration data. For example, the analysis unit can apply a different analytical method to temperature data. For example, the analysis unit can apply yet another analytical method to humidity data. This allows for optimal analysis by applying different analytical methods depending on the type and characteristics of the data. Some or all of the above-described processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input the type and characteristics of the data into the AI ​​and have the AI ​​execute the application of the analytical method.

[0048] The analysis unit can analyze the trend of anomalies by comparing the data with data from other urban areas during the analysis. For example, the analysis unit can analyze the frequency of anomalies by comparing the data with data from other urban areas. For example, the analysis unit can analyze the time period during which anomalies occur by comparing the data with data from other urban areas. For example, the analysis unit can analyze the scope of impact of anomalies by comparing the data with data from other urban areas. This improves the accuracy of anomaly detection by analyzing the trend of anomalies by comparing the data with data from other urban areas. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input data from other urban areas into an AI and have the AI ​​perform the analysis of anomaly trends.

[0049] The analysis unit can identify the cause of anomalies by considering the correlation between data during analysis. For example, the analysis unit can identify the cause of anomalies by analyzing the correlation between methane concentration and temperature data. For example, the analysis unit can identify the cause of anomalies by analyzing the correlation between methane concentration and humidity data. For example, the analysis unit can identify the cause of anomalies by analyzing the correlation between methane concentration and wind speed data. In this way, by considering the correlation between data, the cause of anomalies can be accurately identified. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input the data correlations into AI and have the AI ​​perform the identification of the cause of anomalies.

[0050] The detection unit can apply different detection algorithms depending on the type and scale of the anomaly at the time of detection. For example, the detection unit can apply a simple detection algorithm to small-scale anomalies. For example, the detection unit can apply a detailed detection algorithm to medium-scale anomalies. For example, the detection unit can apply a rapid detection algorithm to large-scale anomalies. This improves the accuracy of anomaly detection by applying the optimal detection algorithm according to the type and scale of the anomaly. Some or all of the above processing in the detection unit may be performed using AI or not. For example, the detection unit can input data on the type and scale of the anomaly into the AI ​​and have the AI ​​execute the application of the detection algorithm.

[0051] The detection unit can improve detection accuracy by referring to past anomaly data during detection. The detection unit can, for example, adjust the detection algorithm based on past anomaly data. The detection unit can, for example, set criteria for anomaly detection based on past anomaly data. The detection unit can, for example, identify anomaly occurrence patterns based on past anomaly data. As a result, the accuracy of anomaly detection is improved by referring to past anomaly data. Some or all of the above processing in the detection unit may be performed using AI or not. For example, the detection unit can input past anomaly data into the AI ​​and have the AI ​​perform the improvement of detection accuracy.

[0052] The detection unit can customize its detection method when detecting an anomaly, taking into account the location and time of the anomaly. For example, in locations where anomalies are likely to occur at night, the detection unit can enhance its nighttime detection method. For example, in locations where anomalies are likely to occur on weekends, the detection unit can enhance its weekend detection method. For example, in locations where anomalies are likely to occur during a particular season, the detection unit can enhance its seasonal detection method. By customizing the detection method to take into account the location and time of the anomaly, the accuracy of anomaly detection is improved. Some or all of the above processing in the detection unit may be performed using AI or not. For example, the detection unit can input data on the location and time of the anomaly into the AI ​​and have the AI ​​perform the customization of the detection method.

[0053] The detection unit can improve detection accuracy by comparing it with anomaly data from other urban areas during detection. The detection unit can adjust its detection algorithm by comparing it with anomaly data from other urban areas, for example. The detection unit can set criteria for anomaly detection by comparing it with anomaly data from other urban areas, for example. The detection unit can identify patterns of anomaly occurrence by comparing it with anomaly data from other urban areas, for example. This improves the accuracy of anomaly detection by comparing it with anomaly data from other urban areas. Some or all of the above processing in the detection unit may be performed using AI or not. For example, the detection unit can input anomaly data from other urban areas into an AI and have the AI ​​perform the task of improving detection accuracy.

[0054] The notification unit can apply different notification methods depending on the type and scale of the anomaly when issuing a notification. For example, the notification unit can apply a simple notification method to small-scale anomalies. For example, the notification unit can apply a detailed notification method to medium-scale anomalies. For example, the notification unit can apply a rapid notification method to large-scale anomalies. This improves the accuracy of notifications by applying the most appropriate notification method according to the type and scale of the anomaly. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit can input data on the type and scale of the anomaly into the AI ​​and have the AI ​​execute the application of the notification method.

[0055] The notification unit can select the optimal notification method by referring to past notification history when issuing a notification. For example, the notification unit can select a notification method preferred by the user based on past notification history. For example, the notification unit can select the most effective notification method based on past notification history. For example, the notification unit can optimize the timing of notifications based on past notification history. This allows the optimal notification method to be selected by referring to past notification history. Some or all of the above processes in the notification unit may be performed using AI or not. For example, the notification unit can input past notification history into AI and have the AI ​​select the notification method.

[0056] The notification unit can customize the notification method when an anomaly occurs, taking into account the location and time of occurrence. For example, if an anomaly occurs at night, the notification unit can provide a quiet notification method. For example, if an anomaly occurs on a weekend, the notification unit can provide a notification method suitable for the weekend. For example, if an anomaly occurs during a specific season, the notification unit can provide a notification method suitable for that season. By customizing the notification method to take into account the location and time of occurrence of the anomaly, the accuracy of notifications is improved. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit can input data on the location and time of occurrence of the anomaly into the AI ​​and have the AI ​​perform the customization of the notification method.

[0057] The notification unit can improve notification accuracy by comparing it with notification data from other urban areas at the time of notification. The notification unit can adjust the notification method by comparing it with notification data from other urban areas, for example. The notification unit can optimize the timing of notifications by comparing it with notification data from other urban areas, for example. The notification unit can optimize the content of notifications by comparing it with notification data from other urban areas, for example. This improves notification accuracy by comparing it with notification data from other urban areas. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit can input notification data from other urban areas into the AI ​​and have the AI ​​perform the improvement of notification accuracy.

[0058] The report generation unit can apply different reporting methods depending on the type and scale of the anomaly when generating a report. For example, the report generation unit can apply a simple reporting method to small-scale anomalies. For example, the report generation unit can apply a detailed reporting method to medium-scale anomalies. For example, the report generation unit can apply a rapid reporting method to large-scale anomalies. This improves the accuracy of the report by applying the most appropriate reporting method according to the type and scale of the anomaly. Some or all of the above-described processes in the report generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the report generation unit can input data on the type and scale of the anomaly into the generation AI and have the generation AI execute the application of the reporting method.

[0059] The report generation unit can improve report accuracy by referring to past report data when generating a report. For example, the report generation unit can adjust the report content based on past report data. For example, the report generation unit can optimize the timing of reports based on past report data. For example, the report generation unit can optimize the report format based on past report data. As a result, report accuracy is improved by referring to past report data. Some or all of the above processes in the report generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the report generation unit can input past report data into a generation AI and have the generation AI perform the improvement of report accuracy.

[0060] The report generation unit can customize the reporting method when generating reports, taking into account the location and time of the anomaly. For example, if an anomaly occurs at night, the report generation unit can provide a reporting method suitable for nighttime. For example, if an anomaly occurs on a weekend, the report generation unit can provide a reporting method suitable for a weekend. For example, if an anomaly occurs during a specific season, the report generation unit can provide a reporting method suitable for that season. By customizing the reporting method to take into account the location and time of the anomaly, the accuracy of the report is improved. Some or all of the above processing in the report generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the report generation unit can input data on the location and time of the anomaly into the generation AI and have the generation AI perform the customization of the reporting method.

[0061] The report generation unit can improve report accuracy by comparing it with report data from other urban areas during report generation. For example, the report generation unit can adjust the report content by comparing it with report data from other urban areas. For example, the report generation unit can optimize the timing of reports by comparing it with report data from other urban areas. For example, the report generation unit can optimize the report format by comparing it with report data from other urban areas. This improves report accuracy by comparing it with report data from other urban areas. Some or all of the above processing in the report generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the report generation unit can input report data from other urban areas into a generation AI and have the generation AI perform the improvement of report accuracy.

[0062] The safety information generation unit can apply different safety information depending on the type and scale of the anomaly when generating safety information. For example, the safety information generation unit can apply simple safety information to small-scale anomalies. For example, the safety information generation unit can apply detailed safety information to medium-scale anomalies. For example, the safety information generation unit can apply rapid safety information to large-scale anomalies. This makes it possible to provide optimal safety information according to the type and scale of the anomaly. Some or all of the above processing in the safety information generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the safety information generation unit can input data on the type and scale of the anomaly into a generation AI and have the generation AI execute the application of safety information.

[0063] The safety information generation unit can improve the accuracy of safety information by referring to past safety information data when generating safety information. For example, the safety information generation unit can adjust the content of safety information based on past safety information data. For example, the safety information generation unit can optimize the timing of safety information based on past safety information data. For example, the safety information generation unit can optimize the format of safety information based on past safety information data. As a result, the accuracy of safety information is improved by referring to past safety information data. Some or all of the above processing in the safety information generation unit may be performed using a generation AI, or it may be performed without using a generation AI. For example, the safety information generation unit can input past safety information data into a generation AI and have the generation AI perform the improvement of the accuracy of safety information.

[0064] The safety information generation unit can customize safety information when generating it, taking into account the location and time of the anomaly. For example, if an anomaly occurs at night, the safety information generation unit can provide safety information suitable for nighttime. For example, if an anomaly occurs on a weekend, the safety information generation unit can provide safety information suitable for a weekend. For example, if an anomaly occurs during a specific season, the safety information generation unit can provide safety information suitable for that season. By customizing the safety information to take into account the location and time of the anomaly, the accuracy of the safety information is improved. Some or all of the above processing in the safety information generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the safety information generation unit can input data on the location and time of the anomaly into the generation AI and have the generation AI perform the customization of the safety information.

[0065] The safety information generation unit can improve the accuracy of safety information by comparing it with safety information data from other urban areas during the generation process. For example, the safety information generation unit can adjust the content of safety information by comparing it with safety information data from other urban areas. For example, the safety information generation unit can optimize the timing of safety information by comparing it with safety information data from other urban areas. For example, the safety information generation unit can optimize the format of safety information by comparing it with safety information data from other urban areas. This improves the accuracy of safety information by comparing it with safety information data from other urban areas. Some or all of the above-described processes in the safety information generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the safety information generation unit can input safety information data from other urban areas into a generation AI and have the generation AI perform the task of improving the accuracy of safety information.

[0066] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0067] The gas leak detection system can also be equipped with a prediction unit. The prediction unit can predict the likelihood of future gas leaks based on collected data. For example, it can compare past and current data and predict the risk of a gas leak if a specific pattern is repeated. Furthermore, the prediction unit can combine external data, such as weather data and earthquake data, to more accurately predict the risk of gas leaks. In addition, the prediction unit can issue warnings in advance and take preventative measures based on the prediction results. This allows for the identification and prevention of gas leak risks before they occur.

[0068] The gas leak detection system can also be equipped with a learning unit. The learning unit can learn from the collected data to improve the system's accuracy. For example, it can improve the anomaly detection algorithm based on past gas leak incidents. Furthermore, the learning unit can incorporate user feedback to improve the system's usability. Additionally, the learning unit can expand the system's coverage by adding new sensors and data sources. This allows the gas leak detection system to constantly improve its accuracy based on the latest information.

[0069] The gas leak detection system can also be equipped with a diagnostic unit. The diagnostic unit can identify the cause of the gas leak based on the collected data. For example, it can analyze the location, time of day, and environmental conditions of the leak to determine its cause. Furthermore, the diagnostic unit can assess the scope of the leak's impact and propose measures to prevent further damage. In addition, the diagnostic unit can provide improvement measures to prevent recurrence of the gas leak. This allows for the rapid identification of the cause of the gas leak and the implementation of appropriate countermeasures.

[0070] The gas leak detection system can also be equipped with a connectivity unit. This connectivity unit can share information by coordinating with other disaster prevention systems and infrastructure management systems. For example, in the event of a disaster such as an earthquake or fire, it can notify other systems of the risk of a gas leak, enabling comprehensive disaster prevention measures. The connectivity unit can also coordinate with urban infrastructure management systems to share gas pipe maintenance information. Furthermore, the connectivity unit can facilitate information sharing with local residents and businesses, raising awareness of gas leaks. This allows for the implementation of comprehensive measures against gas leaks.

[0071] The gas leak detection system can also be equipped with an energy management unit. The energy management unit can monitor energy usage simultaneously with gas leak detection, enabling efficient energy management. For example, in the event of a gas leak, it can automatically shut off the energy supply, preventing wasteful energy consumption. Furthermore, the energy management unit can analyze energy usage patterns and propose measures to improve energy efficiency. In addition, the energy management unit can promote the use of renewable energy, contributing to a reduction in environmental impact. This allows for efficient energy use while reducing the risk of gas leaks.

[0072] The following briefly describes the processing flow for example form 1.

[0073] Step 1: The collection unit collects data. The collection unit collects data from IoT sensors installed in urban areas, for example. The collection unit can collect data using IoT sensors such as temperature sensors, humidity sensors, and gas sensors. It can also collect data such as sensor data, log data, and user data. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis unit analyzes the collected data and identifies deviations from the normal background level. The normal background level can be set based on the mean and standard deviation of past data, and deviations can be identified when the collected data exceeds that range. Step 3: The detection unit detects anomalies based on the analysis results obtained by the analysis unit. Based on the analysis results, the detection unit can detect values ​​exceeding a threshold or deviations from normal patterns as anomalies. Anomalies can also be detected based on the frequency of occurrence and the scope of their impact. Step 4: The notification unit issues an alert based on the anomaly detected by the detection unit. The notification unit can send an alert to the gas company or emergency response team when an anomaly is detected. Alerts can be sent in the form of email notifications, SMS notifications, app notifications, etc. Step 5: The report generation unit generates a detailed situation report based on the information notified by the notification unit. The report generation unit can automatically generate a detailed situation report of the detected anomaly using the generation AI. It can generate a detailed situation report that includes information such as the exact location of the gas leak, the scale of the leak, and the scope of its impact. Step 6: The safety information generation unit generates safety information for local residents based on the reports generated by the report generation unit. Using generation AI, the safety information generation unit can generate clear and concise messages that convey the necessity of evacuation and methods for ensuring safety, depending on the scale and location of the gas leak. It can generate safety information including evacuation orders, warnings, and emergency contact information.

[0074] (Example of form 2) The gas leak detection system according to an embodiment of the present invention is a system that combines an AI algorithm and a generative AI to detect gas leaks early and respond quickly. This gas leak detection system collects data from IoT sensors installed in urban areas, and the AI ​​algorithm analyzes the collected data to immediately identify deviations from normal background levels. When an abnormality is detected, the gas leak detection system automatically issues an alert and notifies the gas company and emergency response team. This notification includes a detailed situation report automatically generated by the generative AI. Furthermore, the generative AI also automatically creates safety information for local residents. This significantly reduces the risk of accidents caused by gas leaks and improves urban safety. In addition, minimizing gas loss through early detection contributes to improved energy efficiency, achieving both environmental protection and economic viability. For example, methane is said to have 28 times the greenhouse effect of carbon dioxide (CO2) and is considered important for climate change countermeasures after CO2. This gas leak detection system contributes to the realization of a sustainable society through methane absorption / reduction. For example, the gas leak detection system collects data from IoT sensors installed in urban areas. These sensors are designed to detect even minute methane leaks. The gas leak detection system then uses AI algorithms to analyze the collected data, instantly identifying deviations from normal background levels. For example, if methane concentration rises sharply, the AI ​​detects the anomaly and issues an alert. Upon detection, the gas leak detection system automatically notifies the gas company and emergency response team. This notification includes a detailed situation report automatically generated by the generative AI. For instance, it reports the exact location, size, and extent of the leak. This allows the response team to obtain accurate information before arriving on-site, enabling a quick and efficient response. Furthermore, the gas leak detection system also uses the generative AI to automatically create safety information for local residents. For example, it generates clear and concise messages about the need for evacuation and how to ensure safety, depending on the size and location of the leak. This allows residents to take appropriate action without panicking. This gas leak detection system significantly reduces the risk of accidents caused by gas leaks, improving urban safety.Furthermore, minimizing gas loss through early detection contributes to improved energy efficiency, achieving both environmental protection and economic viability. For example, methane is said to have 28 times the greenhouse effect of carbon dioxide (CO2), making it the second most important mitigator of global warming after CO2. This gas leak detection system contributes to the realization of a sustainable society through methane absorption / reduction. As a result, the gas leak detection system can detect gas leaks early and respond quickly.

[0075] The gas leak detection system according to the embodiment comprises a collection unit, an analysis unit, a detection unit, a notification unit, a report generation unit, and a safety information generation unit. The collection unit collects data. The collection unit collects data from, for example, IoT sensors installed in urban areas. The collection unit can collect data using, for example, IoT sensors such as temperature sensors, humidity sensors, and gas sensors. The collection unit can collect data such as sensor data, log data, and user data. The analysis unit analyzes the data collected by the collection unit. The analysis unit analyzes the collected data and identifies deviations from the normal background level. The analysis unit can set a normal background level based on the mean and standard deviation of past data, and identify deviations when the collected data exceeds that range. The detection unit detects anomalies based on the analysis results obtained by the analysis unit. The detection unit can detect anomalies based on, for example, values ​​exceeding a threshold or deviations from the normal pattern based on the analysis results. The detection unit can detect anomalies based on, for example, the frequency of anomaly occurrence and the scope of its impact. The notification unit issues an alert based on the anomaly detected by the detection unit. The notification unit can, for example, issue alerts to gas companies and emergency response teams when an anomaly is detected. The notification unit can issue alerts in various forms, such as email notifications, SMS notifications, and app notifications. The report generation unit generates detailed situation reports based on the information notified by the notification unit. The report generation unit can, for example, automatically generate detailed situation reports of detected anomalies using generation AI. The report generation unit can generate detailed situation reports that include information such as the exact location of the gas leak, the scale of the leak, and the scope of the impact. The safety information generation unit generates safety information for local residents based on the reports generated by the report generation unit. The safety information generation unit can, for example, use generation AI to generate messages that clearly and concisely convey the need for evacuation and methods for ensuring safety, depending on the scale and location of the gas leak. The safety information generation unit can generate safety information that includes information such as evacuation orders, warnings, and emergency contact information.As a result, the gas leak detection system according to the embodiment can consistently perform tasks from data collection to anomaly detection, notification, report generation, and safety information generation.

[0076] The data collection unit collects data. For example, the data collection unit collects data from IoT sensors installed in urban areas. Specifically, the data collection unit can collect data using IoT sensors such as temperature sensors, humidity sensors, and gas sensors. These sensors are installed in various locations in urban areas and acquire environmental data in real time. Temperature sensors measure ambient temperature, and humidity sensors measure humidity in the air. Gas sensors can detect the concentration of specific gases and can detect signs of gas leaks. The data collection unit centrally manages this sensor data and transmits it to a central database. Furthermore, the data collection unit can collect not only sensor data but also log data and user data. Log data includes system operation status and records of past events, and user data includes information about user behavior and the environment. This allows the data collection unit to collect a wide range of data from diverse data sources and understand the overall system status in real time. By adjusting the frequency and accuracy of data collection, the data collection unit can respond flexibly to specific situations and conditions. For example, by increasing the sensitivity of the gas sensor, even minute gas leaks can be detected. Furthermore, the data collection unit is equipped with a filtering function to detect data anomalies early, eliminating noise and false positives. This allows the data collection unit to collect data efficiently and effectively, improving the overall system performance.

[0077] The analysis unit analyzes the data collected by the data collection unit. Specifically, the analysis unit analyzes the collected data and identifies deviations from normal background levels. The analysis unit sets normal background levels based on the mean and standard deviation of past data, and can identify deviations when the collected data exceeds that range. For example, if data from a gas sensor exceeds the normal background level, the analysis unit identifies that data as an anomaly. The analysis unit uses AI to analyze the data in real time and identify patterns of anomalies. The AI ​​learns from past data using machine learning algorithms and can perform highly accurate analyses on new data. This allows the analysis unit to analyze collected data quickly and accurately, enabling early detection of anomalies. Furthermore, the analysis unit can evaluate the frequency and scope of anomalies and determine the severity of the anomalies. For example, if gas leaks occur frequently or have a wide scope of impact, the analysis unit identifies the anomaly as serious. The analysis unit can also perform detailed analyses to identify the cause of the anomaly. This allows the analysis unit to contribute not only to the early detection of anomalies but also to investigating the causes of anomalies and formulating countermeasures.

[0078] The detection unit detects anomalies based on the analysis results obtained by the analysis unit. Specifically, the detection unit can detect values ​​exceeding a threshold or deviations from normal patterns as anomalies based on the analysis results. For example, if gas sensor data exceeds a set threshold, the detection unit detects that data as an anomaly. The detection unit can also detect anomalies based on the frequency of occurrence and the scope of impact. For example, if gas leaks occur frequently or have a wide scope of impact, the detection unit identifies the anomaly as serious. The detection unit uses AI to identify anomaly patterns, enabling early detection of anomalies. The AI ​​learns from past data using machine learning algorithms and can perform highly accurate analysis on new data. This allows the detection unit to quickly and accurately analyze collected data, enabling early detection of anomalies. Furthermore, the detection unit can perform detailed analysis to identify the cause of the anomaly. This allows the detection unit to contribute not only to early detection of anomalies but also to investigating the cause of anomalies and formulating countermeasures.

[0079] The notification unit issues alerts based on anomalies detected by the detection unit. Specifically, the notification unit can issue alerts to gas companies and emergency response teams when an anomaly is detected. The notification unit can issue alerts in various formats, such as email, SMS, and app notifications. For example, if a gas leak is detected, the notification unit will send an alert to the gas company via email and notify the emergency response team via SMS. It can also provide real-time information to relevant parties using app notifications. The notification unit can configure the content of alerts in detail, including information such as the type of anomaly, its location, and the scope of its impact. This allows the notification unit to provide quick and accurate information to relevant parties and encourage appropriate responses. Furthermore, the notification unit can set alert priorities, and serious anomalies can be notified with a higher priority. This allows the notification unit to support early detection and rapid response to anomalies, improving the overall safety of the system.

[0080] The report generation unit generates detailed situation reports based on information notified by the notification unit. Specifically, the report generation unit can automatically generate detailed situation reports of detected anomalies using generation AI. The generation AI uses natural language processing technology to create detailed reports based on collected data and analysis results. For example, it can generate detailed situation reports that include information such as the exact location of a gas leak, the scale of the leak, and the scope of its impact. The report generation unit provides the generated reports to relevant parties to support a rapid response. Furthermore, the report generation unit can customize the content of the reports and provide necessary information to specific parties. For example, it can provide gas companies with technical details and emergency response teams with information including response procedures and evacuation orders. This allows the report generation unit to provide relevant parties with appropriate information and support a rapid and effective response.

[0081] The safety information generation unit generates safety information for local residents based on reports generated by the report generation unit. Specifically, the safety information generation unit can use a generation AI to generate clear and concise messages that convey the necessity of evacuation and methods for ensuring safety, depending on the scale and location of the gas leak. The generation AI uses natural language processing technology to create messages for local residents based on collected data and analysis results. For example, it can generate safety information that includes evacuation orders, warnings, and emergency contact information. The safety information generation unit provides the generated messages to local residents to support rapid evacuation and ensuring safety. Furthermore, the safety information generation unit can customize the content of the messages and provide information tailored to specific areas and situations. For example, it can emphasize evacuation orders for certain areas and issue warnings for other areas. This allows the safety information generation unit to provide appropriate information to local residents and support a rapid and effective response.

[0082] The data collection unit collects data from IoT sensors installed in urban areas. The data collection unit can collect data using IoT sensors such as temperature sensors, humidity sensors, and gas sensors installed in urban areas. The data collection unit can collect data from IoT sensors installed in specific municipalities or densely populated areas within urban areas. The data collection unit can collect data such as sensor data, log data, and user data. This allows for the acquisition of data over a wide area by collecting data from IoT sensors installed in urban areas. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input data collected from IoT sensors installed in urban areas into an AI and have the AI ​​perform the data collection.

[0083] The analysis unit can analyze the collected data and identify deviations from normal background levels. For example, the analysis unit can analyze the collected data, set normal background levels based on the mean and standard deviation of past data, and identify deviations when the collected data exceeds that range. For example, the analysis unit can identify deviations when methane concentration rises sharply. For example, the analysis unit can identify deviations based on fluctuations in temperature or humidity data. In this way, deviations from normal background levels can be identified through data analysis. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the collected data into AI and have the AI ​​perform the data analysis.

[0084] The detection unit can detect anomalies based on the analysis results. For example, the detection unit can detect values ​​exceeding a threshold or deviations from normal patterns as anomalies based on the analysis results. For example, the detection unit can detect anomalies based on the frequency of occurrence or the scope of impact of the anomaly. For example, the detection unit can detect anomalies when the methane concentration rises sharply. For example, the detection unit can detect anomalies based on fluctuations in temperature data or humidity data. This enables a rapid response by detecting anomalies based on the analysis results. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input the analysis results into AI and have AI perform anomaly detection.

[0085] The notification unit can issue alerts to gas companies and emergency response teams when an anomaly is detected. The notification unit can issue alerts in the form of email notifications, SMS notifications, app notifications, etc., when an anomaly is detected. The notification unit can issue alerts that include information such as the location, scale, and scope of the anomaly. The notification unit can expedite the response by quickly issuing alerts to gas companies and emergency response teams, for example. This expedites the response by quickly issuing alerts when an anomaly is detected. Some or all of the above processing in the notification unit may be performed using AI, for example, or not using AI. For example, the notification unit can have AI issue an alert when an anomaly is detected.

[0086] The report generation unit can automatically generate detailed status reports of detected anomalies using a generation AI. For example, the report generation unit can use the generation AI to automatically generate detailed status reports that include information such as the exact location of a gas leak, the scale of the leak, and the scope of its impact. For example, the report generation unit can use the generation AI to report in detail the cause of the anomaly and the scope of its impact. For example, the report generation unit can use the generation AI to report the time the anomaly occurred and the response status. This allows the response team to quickly obtain accurate information by automatically generating detailed status reports using the generation AI. Some or all of the above-described processes in the report generation unit may be performed using the generation AI or not. For example, the report generation unit can input the detected anomaly data into the generation AI and have the generation AI generate a detailed status report.

[0087] The safety information generation unit can use a generating AI to generate clear and concise messages that convey the necessity of evacuation and methods for ensuring safety, depending on the scale and location of the gas leak. For example, the safety information generation unit can use the generating AI to generate messages that include information such as evacuation orders, warnings, and emergency contact information, depending on the scale and location of the gas leak. For example, the safety information generation unit can use the generating AI to provide local residents with quick and accurate safety information. For example, the safety information generation unit can use the generating AI to generate messages that clearly convey the scope of the gas leak's impact and evacuation routes. In this way, by automatically generating safety information using the generating AI, local residents can be provided with quick and accurate information. Some or all of the above-described processes in the safety information generation unit may be performed using the generating AI, or they may be performed without using the generating AI. For example, the safety information generation unit can input gas leak data into the generating AI and have the generating AI perform the generation of safety information.

[0088] The data collection unit can estimate the user's emotions and adjust the frequency of data collection based on the estimated emotions. For example, if the user is stressed, the data collection unit can set a lower frequency of data collection to reduce the system load. For example, if the user is relaxed, the data collection unit can set a higher frequency of data collection to collect more detailed data. For example, if the user is in an emergency, the data collection unit can set a maximum frequency of data collection to enable a rapid response. In this way, the system load can be optimized by adjusting the frequency of data collection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into an AI and have the AI ​​adjust the frequency of data collection.

[0089] The data collection unit can optimize the data collection method based on the sensor's location and environmental conditions during data acquisition. For example, if the sensor is installed in a high-humidity environment, the data collection unit can collect data while correcting for humidity. For example, if the sensor is installed in a high-temperature environment, the data collection unit can collect data while correcting for temperature. For example, if the sensor is installed in a windy location, the data collection unit can collect data while correcting for wind speed. By optimizing the data collection method based on the sensor's location and environmental conditions, accurate data collection becomes possible. Some or all of the above processing in the data collection unit may be performed using AI, or not. For example, the data collection unit can input data on the sensor's location and environmental conditions into the AI ​​and have the AI ​​optimize the data collection method.

[0090] The data collection unit can set a data collection schedule that takes into account the time periods when anomalies are likely to occur. For example, if anomalies are likely to occur at night, the data collection unit can set a higher frequency for nighttime data collection. For example, if anomalies are likely to occur on weekends, the data collection unit can set a higher frequency for weekend data collection. For example, if anomalies are likely to occur during a particular season, the data collection unit can set a higher frequency for that season's data collection. By setting a data collection schedule that takes into account the time periods when anomalies are likely to occur, early detection of anomalies becomes possible. Some or all of the above processing in the data collection unit may be performed using AI, or it may be performed without using AI. For example, the data collection unit can input data from time periods when anomalies are likely to occur into the AI ​​and have the AI ​​set the data collection schedule.

[0091] The data collection unit can estimate the user's emotions and determine the priority of data to collect based on the estimated emotions. For example, if the user is stressed, the data collection unit can prioritize collecting only important data. For example, if the user is relaxed, the data collection unit can prioritize collecting detailed data. For example, if the user is in an emergency, the data collection unit can prioritize collecting emergency data. This allows for the priority collection of important data by determining the priority of data to collect according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into an AI and have the AI ​​determine the priority of the data.

[0092] The data collection unit can customize the data collection method based on the type and performance of the sensor during data acquisition. For example, if a high-precision sensor is used, the data collection unit can collect detailed data. For example, if a low-precision sensor is used, the data collection unit can collect only basic data. For example, if a particular sensor is malfunctioning, the data collection unit can supplementarily collect data from other sensors. This allows for optimal data collection by customizing the data collection method based on the type and performance of the sensor. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input data on the type and performance of the sensor into the AI ​​and have the AI ​​perform the customization of the data collection method.

[0093] The data collection unit can set criteria for early detection of anomalies by comparing the data collected with data from other urban areas. For example, the data collection unit can set criteria for anomalies by comparing the data with data from other urban areas. For example, the data collection unit can set criteria based on the frequency of anomalies by comparing the data with data from other urban areas. For example, the data collection unit can set criteria based on the scope of anomaly impact by comparing the data with data from other urban areas. This enables early detection of anomalies by setting criteria for early detection of anomalies by comparing the data with data from other urban areas. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input data from other urban areas into the AI ​​and have the AI ​​perform the setting of anomaly detection criteria.

[0094] The analysis unit can estimate the user's emotions and adjust the analysis algorithm based on the estimated emotions. For example, if the user is stressed, the analysis unit can use a simple analysis algorithm. For example, if the user is relaxed, the analysis unit can use a detailed analysis algorithm. For example, if the user is in an emergency, the analysis unit can use a rapid analysis algorithm. This allows for optimal analysis by adjusting the analysis algorithm according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input user emotion data into AI and have the AI ​​adjust the analysis algorithm.

[0095] The analysis unit can identify anomaly patterns by comparing them with past data during analysis. For example, the analysis unit can identify the frequency of anomaly occurrences by comparing them with past data. For example, the analysis unit can identify the time period during which anomalies occur by comparing them with past data. For example, the analysis unit can identify the scope of anomaly impacts by comparing them with past data. This improves the accuracy of anomaly detection by identifying anomaly patterns by comparing them with past data. Some or all of the above-described processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input past data into AI and have AI perform the identification of anomaly patterns.

[0096] The analysis unit can apply different analytical methods depending on the type and characteristics of the data during analysis. For example, the analysis unit can apply a specific analytical method to methane concentration data. For example, the analysis unit can apply a different analytical method to temperature data. For example, the analysis unit can apply yet another analytical method to humidity data. This allows for optimal analysis by applying different analytical methods depending on the type and characteristics of the data. Some or all of the above-described processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input the type and characteristics of the data into the AI ​​and have the AI ​​execute the application of the analytical method.

[0097] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is stressed, the analysis unit can provide a concise display method. For example, if the user is relaxed, the analysis unit can provide a detailed display method. For example, if the user is in an emergency, the analysis unit can provide a rapid display method. This allows for optimal display for the user by adjusting the display method of the analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input user emotion data into an AI and have the AI ​​adjust the display method.

[0098] The analysis unit can analyze the trend of anomalies by comparing the data with data from other urban areas during the analysis. For example, the analysis unit can analyze the frequency of anomalies by comparing the data with data from other urban areas. For example, the analysis unit can analyze the time period during which anomalies occur by comparing the data with data from other urban areas. For example, the analysis unit can analyze the scope of impact of anomalies by comparing the data with data from other urban areas. This improves the accuracy of anomaly detection by analyzing the trend of anomalies by comparing the data with data from other urban areas. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input data from other urban areas into an AI and have the AI ​​perform the analysis of anomaly trends.

[0099] The analysis unit can identify the cause of anomalies by considering the correlation between data during analysis. For example, the analysis unit can identify the cause of anomalies by analyzing the correlation between methane concentration and temperature data. For example, the analysis unit can identify the cause of anomalies by analyzing the correlation between methane concentration and humidity data. For example, the analysis unit can identify the cause of anomalies by analyzing the correlation between methane concentration and wind speed data. In this way, by considering the correlation between data, the cause of anomalies can be accurately identified. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input the data correlations into AI and have the AI ​​perform the identification of the cause of anomalies.

[0100] The detection unit can estimate the user's emotions and adjust the anomaly detection criteria based on the estimated user emotions. For example, the detection unit can relax the anomaly detection criteria if the user is stressed. For example, the detection unit can tighten the anomaly detection criteria if the user is relaxed. For example, the detection unit can maximize the anomaly detection criteria if the user is in an emergency. This allows for optimal anomaly detection by adjusting the anomaly detection criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the detection unit may be performed using AI or not. For example, the detection unit can input user emotion data into AI and have the AI ​​adjust the anomaly detection criteria.

[0101] The detection unit can apply different detection algorithms depending on the type and scale of the anomaly at the time of detection. For example, the detection unit can apply a simple detection algorithm to small-scale anomalies. For example, the detection unit can apply a detailed detection algorithm to medium-scale anomalies. For example, the detection unit can apply a rapid detection algorithm to large-scale anomalies. This improves the accuracy of anomaly detection by applying the optimal detection algorithm according to the type and scale of the anomaly. Some or all of the above processing in the detection unit may be performed using AI or not. For example, the detection unit can input data on the type and scale of the anomaly into the AI ​​and have the AI ​​execute the application of the detection algorithm.

[0102] The detection unit can improve detection accuracy by referring to past anomaly data during detection. The detection unit can, for example, adjust the detection algorithm based on past anomaly data. The detection unit can, for example, set criteria for anomaly detection based on past anomaly data. The detection unit can, for example, identify anomaly occurrence patterns based on past anomaly data. As a result, the accuracy of anomaly detection is improved by referring to past anomaly data. Some or all of the above processing in the detection unit may be performed using AI or not. For example, the detection unit can input past anomaly data into the AI ​​and have the AI ​​perform the improvement of detection accuracy.

[0103] The detection unit can estimate the user's emotions and determine the priority of anomaly detection based on the estimated user emotions. For example, if the user is stressed, the detection unit can prioritize detecting important anomalies. For example, if the user is relaxed, the detection unit can prioritize detecting detailed anomalies. For example, if the user is in an emergency, the detection unit can prioritize detecting urgent anomalies. In this way, important anomalies can be detected preferentially by determining the priority of anomaly detection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the detection unit may be performed using AI or not. For example, the detection unit can input user emotion data into AI and have the AI ​​perform the determination of anomaly detection priorities.

[0104] The detection unit can customize its detection method when detecting an anomaly, taking into account the location and time of the anomaly. For example, in locations where anomalies are likely to occur at night, the detection unit can enhance its nighttime detection method. For example, in locations where anomalies are likely to occur on weekends, the detection unit can enhance its weekend detection method. For example, in locations where anomalies are likely to occur during a particular season, the detection unit can enhance its seasonal detection method. By customizing the detection method to take into account the location and time of the anomaly, the accuracy of anomaly detection is improved. Some or all of the above processing in the detection unit may be performed using AI or not. For example, the detection unit can input data on the location and time of the anomaly into the AI ​​and have the AI ​​perform the customization of the detection method.

[0105] The detection unit can improve detection accuracy by comparing it with anomaly data from other urban areas during detection. The detection unit can adjust its detection algorithm by comparing it with anomaly data from other urban areas, for example. The detection unit can set criteria for anomaly detection by comparing it with anomaly data from other urban areas, for example. The detection unit can identify patterns of anomaly occurrence by comparing it with anomaly data from other urban areas, for example. This improves the accuracy of anomaly detection by comparing it with anomaly data from other urban areas. Some or all of the above processing in the detection unit may be performed using AI or not. For example, the detection unit can input anomaly data from other urban areas into an AI and have the AI ​​perform the task of improving detection accuracy.

[0106] The notification unit can estimate the user's emotions and adjust the content and format of the notification based on the estimated emotions. For example, if the user is stressed, the notification unit can provide a concise notification. For example, if the user is relaxed, the notification unit can provide a detailed notification. For example, if the user is in an emergency, the notification unit can provide a rapid notification. This allows for optimal notifications by adjusting the content and format of the notification according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit can input user emotion data into AI and have the AI ​​adjust the content and format of the notification.

[0107] The notification unit can apply different notification methods depending on the type and scale of the anomaly when issuing a notification. For example, the notification unit can apply a simple notification method to small-scale anomalies. For example, the notification unit can apply a detailed notification method to medium-scale anomalies. For example, the notification unit can apply a rapid notification method to large-scale anomalies. This improves the accuracy of notifications by applying the most appropriate notification method according to the type and scale of the anomaly. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit can input data on the type and scale of the anomaly into the AI ​​and have the AI ​​execute the application of the notification method.

[0108] The notification unit can select the optimal notification method by referring to past notification history when issuing a notification. For example, the notification unit can select a notification method preferred by the user based on past notification history. For example, the notification unit can select the most effective notification method based on past notification history. For example, the notification unit can optimize the timing of notifications based on past notification history. This allows the optimal notification method to be selected by referring to past notification history. Some or all of the above processes in the notification unit may be performed using AI or not. For example, the notification unit can input past notification history into AI and have the AI ​​select the notification method.

[0109] The notification unit can estimate the user's emotions and determine the priority of notifications based on the estimated emotions. For example, if the user is stressed, the notification unit can prioritize important notifications. For example, if the user is relaxed, the notification unit can prioritize detailed notifications. For example, if the user is in an emergency, the notification unit can prioritize urgent notifications. In this way, important notifications can be prioritized by determining the priority of notifications according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit can input user emotion data into AI and have the AI ​​determine the priority of notifications.

[0110] The notification unit can customize the notification method when an anomaly occurs, taking into account the location and time of occurrence. For example, if an anomaly occurs at night, the notification unit can provide a quiet notification method. For example, if an anomaly occurs on a weekend, the notification unit can provide a notification method suitable for the weekend. For example, if an anomaly occurs during a specific season, the notification unit can provide a notification method suitable for that season. By customizing the notification method to take into account the location and time of occurrence of the anomaly, the accuracy of notifications is improved. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit can input data on the location and time of occurrence of the anomaly into the AI ​​and have the AI ​​perform the customization of the notification method.

[0111] The notification unit can improve notification accuracy by comparing it with notification data from other urban areas at the time of notification. The notification unit can adjust the notification method by comparing it with notification data from other urban areas, for example. The notification unit can optimize the timing of notifications by comparing it with notification data from other urban areas, for example. The notification unit can optimize the content of notifications by comparing it with notification data from other urban areas, for example. This improves notification accuracy by comparing it with notification data from other urban areas. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit can input notification data from other urban areas into the AI ​​and have the AI ​​perform the improvement of notification accuracy.

[0112] The report generation unit can estimate the user's emotions and adjust the content and format of the report based on the estimated emotions. For example, if the user is stressed, the report generation unit can provide a concise report. For example, if the user is relaxed, the report generation unit can provide a detailed report. For example, if the user is in an emergency, the report generation unit can provide a rapid report. This allows for optimal reporting by adjusting the content and format of the report according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the report generation unit may be performed using the generative AI or not. For example, the report generation unit can input user emotion data into the generative AI and have the generative AI adjust the content and format of the report.

[0113] The report generation unit can apply different reporting methods depending on the type and scale of the anomaly when generating a report. For example, the report generation unit can apply a simple reporting method to small-scale anomalies. For example, the report generation unit can apply a detailed reporting method to medium-scale anomalies. For example, the report generation unit can apply a rapid reporting method to large-scale anomalies. This improves the accuracy of the report by applying the most appropriate reporting method according to the type and scale of the anomaly. Some or all of the above-described processes in the report generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the report generation unit can input data on the type and scale of the anomaly into the generation AI and have the generation AI execute the application of the reporting method.

[0114] The report generation unit can improve report accuracy by referring to past report data when generating a report. For example, the report generation unit can adjust the report content based on past report data. For example, the report generation unit can optimize the timing of reports based on past report data. For example, the report generation unit can optimize the report format based on past report data. As a result, report accuracy is improved by referring to past report data. Some or all of the above processes in the report generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the report generation unit can input past report data into a generation AI and have the generation AI perform the improvement of report accuracy.

[0115] The report generation unit can estimate the user's emotions and determine the priority of reports based on the estimated emotions. For example, if the user is stressed, the report generation unit can prioritize important reports. For example, if the user is relaxed, the report generation unit can prioritize detailed reports. For example, if the user is in an emergency, the report generation unit can prioritize urgent reports. In this way, by determining the priority of reports according to the user's emotions, important reports can be prioritized. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the report generation unit may be performed using a generative AI or not. For example, the report generation unit can input user emotion data into a generative AI and have the generative AI determine the priority of reports.

[0116] The report generation unit can customize the reporting method when generating reports, taking into account the location and time of the anomaly. For example, if an anomaly occurs at night, the report generation unit can provide a reporting method suitable for nighttime. For example, if an anomaly occurs on a weekend, the report generation unit can provide a reporting method suitable for a weekend. For example, if an anomaly occurs during a specific season, the report generation unit can provide a reporting method suitable for that season. By customizing the reporting method to take into account the location and time of the anomaly, the accuracy of the report is improved. Some or all of the above processing in the report generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the report generation unit can input data on the location and time of the anomaly into the generation AI and have the generation AI perform the customization of the reporting method.

[0117] The report generation unit can improve report accuracy by comparing it with report data from other urban areas during report generation. For example, the report generation unit can adjust the report content by comparing it with report data from other urban areas. For example, the report generation unit can optimize the timing of reports by comparing it with report data from other urban areas. For example, the report generation unit can optimize the report format by comparing it with report data from other urban areas. This improves report accuracy by comparing it with report data from other urban areas. Some or all of the above processing in the report generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the report generation unit can input report data from other urban areas into a generation AI and have the generation AI perform the improvement of report accuracy.

[0118] The safety information generation unit can estimate the user's emotions and adjust the content and format of the safety information based on the estimated emotions. For example, if the user is feeling stressed, the safety information generation unit can provide concise safety information. For example, if the user is relaxed, the safety information generation unit can provide detailed safety information. For example, if the user is in an emergency, the safety information generation unit can provide rapid safety information. In this way, optimal safety information can be provided by adjusting the content and format of the safety information according to the user's emotions. Emotion estimation is achieved using an emotion estimation function with an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the safety information generation unit may be performed using a generation AI or not. For example, the safety information generation unit can input user emotion data into a generation AI and have the generation AI perform adjustments to the content and format of the safety information.

[0119] The safety information generation unit can apply different safety information depending on the type and scale of the anomaly when generating safety information. For example, the safety information generation unit can apply simple safety information to small-scale anomalies. For example, the safety information generation unit can apply detailed safety information to medium-scale anomalies. For example, the safety information generation unit can apply rapid safety information to large-scale anomalies. This makes it possible to provide optimal safety information according to the type and scale of the anomaly. Some or all of the above processing in the safety information generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the safety information generation unit can input data on the type and scale of the anomaly into a generation AI and have the generation AI execute the application of safety information.

[0120] The safety information generation unit can improve the accuracy of safety information by referring to past safety information data when generating safety information. For example, the safety information generation unit can adjust the content of safety information based on past safety information data. For example, the safety information generation unit can optimize the timing of safety information based on past safety information data. For example, the safety information generation unit can optimize the format of safety information based on past safety information data. As a result, the accuracy of safety information is improved by referring to past safety information data. Some or all of the above processing in the safety information generation unit may be performed using a generation AI, or it may be performed without using a generation AI. For example, the safety information generation unit can input past safety information data into a generation AI and have the generation AI perform the improvement of the accuracy of safety information.

[0121] The safety information generation unit can estimate the user's emotions and determine the priority of safety information based on the estimated user emotions. For example, if the user is feeling stressed, the safety information generation unit can prioritize providing important safety information. For example, if the user is relaxed, the safety information generation unit can prioritize providing detailed safety information. For example, if the user is in an emergency, the safety information generation unit can prioritize providing urgent safety information. In this way, by determining the priority of safety information according to the user's emotions, important safety information can be provided preferentially. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the safety information generation unit may be performed using a generative AI or not. For example, the safety information generation unit can input user emotion data into a generative AI and have the generative AI perform the determination of safety information priorities.

[0122] The safety information generation unit can customize safety information when generating it, taking into account the location and time of the anomaly. For example, if an anomaly occurs at night, the safety information generation unit can provide safety information suitable for nighttime. For example, if an anomaly occurs on a weekend, the safety information generation unit can provide safety information suitable for a weekend. For example, if an anomaly occurs during a specific season, the safety information generation unit can provide safety information suitable for that season. By customizing the safety information to take into account the location and time of the anomaly, the accuracy of the safety information is improved. Some or all of the above processing in the safety information generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the safety information generation unit can input data on the location and time of the anomaly into the generation AI and have the generation AI perform the customization of the safety information.

[0123] The safety information generation unit can improve the accuracy of safety information by comparing it with safety information data from other urban areas during the generation process. For example, the safety information generation unit can adjust the content of safety information by comparing it with safety information data from other urban areas. For example, the safety information generation unit can optimize the timing of safety information by comparing it with safety information data from other urban areas. For example, the safety information generation unit can optimize the format of safety information by comparing it with safety information data from other urban areas. This improves the accuracy of safety information by comparing it with safety information data from other urban areas. Some or all of the above-described processes in the safety information generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the safety information generation unit can input safety information data from other urban areas into a generation AI and have the generation AI perform the task of improving the accuracy of safety information.

[0124] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0125] The gas leak detection system can also be equipped with a prediction unit. The prediction unit can predict the likelihood of future gas leaks based on collected data. For example, it can compare past and current data and predict the risk of a gas leak if a specific pattern is repeated. Furthermore, the prediction unit can combine external data, such as weather data and earthquake data, to more accurately predict the risk of gas leaks. In addition, the prediction unit can issue warnings in advance and take preventative measures based on the prediction results. This allows for the identification and prevention of gas leak risks before they occur.

[0126] The gas leak detection system can also be equipped with a learning unit. The learning unit can learn from the collected data to improve the system's accuracy. For example, it can improve the anomaly detection algorithm based on past gas leak incidents. Furthermore, the learning unit can incorporate user feedback to improve the system's usability. Additionally, the learning unit can expand the system's coverage by adding new sensors and data sources. This allows the gas leak detection system to constantly improve its accuracy based on the latest information.

[0127] The gas leak detection system can also be equipped with a diagnostic unit. The diagnostic unit can identify the cause of the gas leak based on the collected data. For example, it can analyze the location, time of day, and environmental conditions of the leak to determine its cause. Furthermore, the diagnostic unit can assess the scope of the leak's impact and propose measures to prevent further damage. In addition, the diagnostic unit can provide improvement measures to prevent recurrence of the gas leak. This allows for the rapid identification of the cause of the gas leak and the implementation of appropriate countermeasures.

[0128] The gas leak detection system can also be equipped with a connectivity unit. This connectivity unit can share information by coordinating with other disaster prevention systems and infrastructure management systems. For example, in the event of a disaster such as an earthquake or fire, it can notify other systems of the risk of a gas leak, enabling comprehensive disaster prevention measures. The connectivity unit can also coordinate with urban infrastructure management systems to share gas pipe maintenance information. Furthermore, the connectivity unit can facilitate information sharing with local residents and businesses, raising awareness of gas leaks. This allows for the implementation of comprehensive measures against gas leaks.

[0129] The gas leak detection system can also be equipped with an energy management unit. The energy management unit can monitor energy usage simultaneously with gas leak detection, enabling efficient energy management. For example, in the event of a gas leak, it can automatically shut off the energy supply, preventing wasteful energy consumption. Furthermore, the energy management unit can analyze energy usage patterns and propose measures to improve energy efficiency. In addition, the energy management unit can promote the use of renewable energy, contributing to a reduction in environmental impact. This allows for efficient energy use while reducing the risk of gas leaks.

[0130] The gas leak detection system can also be equipped with an emotion estimation unit. This unit can estimate the user's emotions and adjust the system's operation based on the estimated emotions. For example, if the user is stressed, the system can reduce the frequency of notifications to lessen the user's burden. Conversely, if the user is relaxed, it can provide more detailed information to deepen the user's understanding. Furthermore, if the user is in an emergency, the alert can be enhanced to encourage a quicker response. This allows for flexible responses tailored to the user's emotions.

[0131] The gas leak detection system can also be equipped with an emotional feedback unit. This emotional feedback unit can provide feedback on how to improve the system based on the user's emotions. For example, if a user feels anxious, the cause can be identified, and the system's notification methods and content can be improved. If a user is satisfied, the factors contributing to that satisfaction can be analyzed, and a similar experience can be provided to other users. Furthermore, if a user responds appropriately to an emergency, the response method can be fed back to the system and shared with other users. This enables continuous improvement of the system based on user emotions.

[0132] The gas leak detection system can also be equipped with an emotion monitoring unit. This unit can monitor the user's emotions in real time and adjust the system's operation accordingly. For example, if the user is stressed, the system can reduce notifications to lessen the user's burden. Conversely, if the user is relaxed, it can provide more detailed information to deepen the user's understanding. Furthermore, if the user is in an emergency, alerts can be enhanced to encourage a quicker response. This allows for flexible responses tailored to the user's emotions.

[0133] The gas leak detection system can also be equipped with an emotion analysis unit. This unit can analyze user emotion data and identify areas for system improvement. For example, if a user feels anxious, the unit can identify the cause and improve the system's notification methods and content. Conversely, if a user is satisfied, the unit can analyze the factors contributing to that satisfaction and provide a similar experience to other users. Furthermore, if a user responds appropriately to an emergency, the system can provide feedback on how they responded and share that information with other users. This enables continuous system improvement based on user emotions.

[0134] The gas leak detection system can also be equipped with an emotion-adaptive unit. This unit can adapt the system's operation based on the user's emotions. For example, if the user is stressed, the system can reduce the frequency of notifications to lessen the user's burden. Conversely, if the user is relaxed, it can provide more detailed information to enhance their understanding. Furthermore, if the user is in an emergency, the alert can be strengthened to encourage a quicker response. This allows for flexible responses tailored to the user's emotions.

[0135] The following briefly describes the processing flow for example form 2.

[0136] Step 1: The collection unit collects data. The collection unit collects data from IoT sensors installed in urban areas, for example. The collection unit can collect data using IoT sensors such as temperature sensors, humidity sensors, and gas sensors. It can also collect data such as sensor data, log data, and user data. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis unit analyzes the collected data and identifies deviations from the normal background level. The normal background level can be set based on the mean and standard deviation of past data, and deviations can be identified when the collected data exceeds that range. Step 3: The detection unit detects anomalies based on the analysis results obtained by the analysis unit. Based on the analysis results, the detection unit can detect values ​​exceeding a threshold or deviations from normal patterns as anomalies. Anomalies can also be detected based on the frequency of occurrence and the scope of their impact. Step 4: The notification unit issues an alert based on the anomaly detected by the detection unit. The notification unit can send an alert to the gas company or emergency response team when an anomaly is detected. Alerts can be sent in the form of email notifications, SMS notifications, app notifications, etc. Step 5: The report generation unit generates a detailed situation report based on the information notified by the notification unit. The report generation unit can automatically generate a detailed situation report of the detected anomaly using the generation AI. It can generate a detailed situation report that includes information such as the exact location of the gas leak, the scale of the leak, and the scope of its impact. Step 6: The safety information generation unit generates safety information for local residents based on the reports generated by the report generation unit. Using generation AI, the safety information generation unit can generate clear and concise messages that convey the necessity of evacuation and methods for ensuring safety, depending on the scale and location of the gas leak. It can generate safety information including evacuation orders, warnings, and emergency contact information.

[0137] 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.

[0138] Data generation model 58 is a form of 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> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0139] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0140] Each of the multiple elements described above, including the data collection unit, analysis unit, detection unit, notification unit, report generation unit, and safety information generation unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the data collection unit collects data using the sensors of the smart device 14 and transmits it to the data processing unit 12. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12 and analyzes the collected data. The detection unit is implemented in the specific processing unit 290 of the data processing unit 12 and detects abnormalities. The notification unit is implemented in the control unit 46A of the smart device 14 and issues an alert when an abnormality is detected. The report generation unit is implemented in the specific processing unit 290 of the data processing unit 12 and generates a detailed status report. The safety information generation unit is implemented in the control unit 46A of the smart device 14 and generates safety information for local residents. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0141] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0142] 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.

[0143] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0144] 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.

[0145] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0146] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0147] 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.

[0148] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0149] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0150] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0151] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0152] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0153] 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.

[0154] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0155] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0156] Each of the multiple elements described above, including the data collection unit, analysis unit, detection unit, notification unit, report generation unit, and safety information generation unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the data collection unit collects data using the sensors of the smart glasses 214 and transmits it to the data processing unit 12. The analysis unit is implemented, for example, in the identification processing unit 290 of the data processing unit 12 and analyzes the collected data. The detection unit is implemented, for example, in the identification processing unit 290 of the data processing unit 12 and detects abnormalities. The notification unit is implemented, for example, in the control unit 46A of the smart glasses 214 and issues an alert when an abnormality is detected. The report generation unit is implemented, for example, in the identification processing unit 290 of the data processing unit 12 and generates a detailed status report. The safety information generation unit is implemented, for example, in the control unit 46A of the smart glasses 214 and generates safety information for local residents. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0157] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0158] 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.

[0159] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0160] 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.

[0161] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0162] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0163] 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.

[0164] 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.

[0165] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0166] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0167] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0168] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0169] 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.

[0170] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0171] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0172] Each of the multiple elements described above, including the data collection unit, analysis unit, detection unit, notification unit, report generation unit, and safety information generation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the data collection unit collects data using the sensors of the headset terminal 314 and transmits it to the data processing unit 12. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12 and analyzes the collected data. The detection unit is implemented in the specific processing unit 290 of the data processing unit 12 and detects abnormalities. The notification unit is implemented in the control unit 46A of the headset terminal 314 and issues an alert when an abnormality is detected. The report generation unit is implemented in the specific processing unit 290 of the data processing unit 12 and generates a detailed status report. The safety information generation unit is implemented in the control unit 46A of the headset terminal 314 and generates safety information for local residents. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0173] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0174] 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.

[0175] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0176] 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.

[0177] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0178] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0179] 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.

[0180] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0181] 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.

[0182] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0183] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0184] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0185] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0186] 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.

[0187] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0188] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0189] Each of the multiple elements described above, including the data collection unit, analysis unit, detection unit, notification unit, report generation unit, and safety information generation unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the data collection unit collects data using the sensors of the robot 414 and transmits it to the data processing unit 12. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and analyzes the collected data. The detection unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and detects abnormalities. The notification unit is implemented, for example, by the control unit 46A of the robot 414 and issues an alert when an abnormality is detected. The report generation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and generates a detailed status report. The safety information generation unit is implemented, for example, by the control unit 46A of the robot 414 and generates safety information for local residents. The correspondence between each unit and the devices and control units is not limited to the example described above and can be modified in various ways.

[0190] 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.

[0191] Figure 9 shows the 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.

[0192] 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.

[0193] 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.

[0194] 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, and motorcycles, 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 based, for example, 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.

[0195] 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."

[0196] 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.

[0197] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0206] 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 other things 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.

[0207] 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.

[0208] (Note 1) A data collection unit that collects data, An analysis unit analyzes the data collected by the aforementioned collection unit, A detection unit that detects abnormalities based on the analysis results obtained by the analysis unit, A notification unit that issues an alert based on the abnormality detected by the detection unit, A report generation unit that generates a detailed status report based on the information notified by the notification unit, The system includes a safety information generation unit that generates safety information for local residents based on reports generated by the aforementioned report generation unit. A system characterized by the following features. (Note 2) The aforementioned collection unit is Collect data from IoT sensors installed in urban areas. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit is The collected data is analyzed to identify deviations from normal background levels. The system described in Appendix 1, characterized by the features described herein. (Note 4) The detection unit is Detect anomalies based on analysis results The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned notification unit, If an abnormality is detected, an alert will be sent to the gas company or emergency response team. The system described in Appendix 1, characterized by the features described herein. (Note 6) The report generation unit, The AI ​​generates detailed status reports of detected anomalies automatically. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned safety information generation unit, The AI ​​generates clear and concise messages that convey the need for evacuation and how to ensure safety, based on the scale and location of the gas leak. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is It estimates the user's emotions and adjusts the frequency of data collection based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is When collecting data, optimize the data collection method based on the sensor placement and environmental conditions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is When collecting data, set the collection schedule considering the time periods when anomalies are more likely to occur. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is It estimates the user's emotions and prioritizes the data to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is During data collection, the collection method is customized based on the type and performance of the sensor. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned collection unit is When collecting data, establish criteria to detect anomalies early by comparing it with data from other urban areas. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit is It estimates the user's emotions and adjusts the analysis algorithm based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit is During analysis, identify patterns of anomalies by comparing them with past data. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit is When performing analysis, different analytical methods are applied depending on the type and characteristics of the data. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit is It estimates the user's emotions and adjusts how the analysis results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit is During the analysis, we will analyze the trends of anomalies by comparing them with data from other urban areas. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit is During analysis, the correlation between data is considered to identify the cause of the anomaly. The system described in Appendix 1, characterized by the features described herein. (Note 20) The detection unit is The system estimates the user's emotions and adjusts the anomaly detection criteria based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The detection unit is When detecting an anomaly, different detection algorithms are applied depending on the type and scale of the anomaly. The system described in Appendix 1, characterized by the features described herein. (Note 22) The detection unit is During detection, past anomaly data is referenced to improve detection accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 23) The detection unit is The system estimates the user's emotions and determines the priority of anomaly detection based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The detection unit is When detecting an anomaly, the detection method is customized considering the location and time of the anomaly. The system described in Appendix 1, characterized by the features described herein. (Note 25) The detection unit is When detecting anomalies, improve detection accuracy by comparing them with anomaly data from other urban areas. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned notification unit, It estimates the user's emotions and adjusts the content and format of notifications based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned notification unit, When sending notifications, different notification methods will be applied depending on the type and scale of the anomaly. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned notification unit, When sending a notification, the system will refer to past notification history to select the most suitable notification method. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned notification unit, It estimates the user's emotions and prioritizes notifications based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned notification unit, When sending notifications, customize the notification method considering the location and time of the anomaly. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned notification unit, When sending notifications, improve notification accuracy by comparing it with notification data from other urban areas. The system described in Appendix 1, characterized by the features described herein. (Note 32) The report generation unit, The system estimates the user's emotions and adjusts the content and format of the report based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The report generation unit, When generating reports, different reporting methods are applied depending on the type and scale of the anomaly. The system described in Appendix 1, characterized by the features described herein. (Note 34) The report generation unit, When generating reports, past report data is referenced to improve reporting accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 35) The report generation unit, The system estimates user sentiment and prioritizes reports based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 36) The report generation unit, When generating reports, the reporting method is customized to take into account the location and time of the anomaly. The system described in Appendix 1, characterized by the features described herein. (Note 37) The report generation unit, When generating reports, improve reporting accuracy by comparing them with reporting data from other urban areas. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned safety information generation unit, The system estimates the user's emotions and adjusts the content and format of safety information based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned safety information generation unit, When generating safety information, different safety information is applied depending on the type and scale of the anomaly. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned safety information generation unit, When generating safety information, past safety information data is referenced to improve the accuracy of the safety information. The system described in Appendix 1, characterized by the features described herein. (Note 41) The aforementioned safety information generation unit, It estimates user sentiment and prioritizes safety information based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 42) The aforementioned safety information generation unit, When generating safety information, customize the information by considering the location and time of the anomaly. The system described in Appendix 1, characterized by the features described herein. (Note 43) The aforementioned safety information generation unit, When generating safety information, improve the accuracy of the safety information by comparing it with safety information data from other urban areas. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0209] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A data collection unit that collects data, An analysis unit analyzes the data collected by the aforementioned collection unit, A detection unit that detects abnormalities based on the analysis results obtained by the analysis unit, A notification unit that issues an alert based on the abnormality detected by the detection unit, A report generation unit that generates a detailed status report based on the information notified by the notification unit, The system includes a safety information generation unit that generates safety information for local residents based on reports generated by the aforementioned report generation unit. A system characterized by the following features.

2. The aforementioned collection unit is Collect data from IoT sensors installed in urban areas. The system according to feature 1.

3. The aforementioned analysis unit is The collected data is analyzed to identify deviations from normal background levels. The system according to feature 1.

4. The detection unit is Detect anomalies based on analysis results The system according to feature 1.

5. The aforementioned notification unit, If an abnormality is detected, an alert will be sent to the gas company or emergency response team. The system according to feature 1.

6. The report generation unit, The AI ​​generates detailed status reports of detected anomalies automatically. The system according to feature 1.

7. The aforementioned safety information generation unit, The AI ​​generates clear and concise messages that convey the necessity of evacuation and how to ensure safety, based on the scale and location of the gas leak. The system according to feature 1.

8. The aforementioned collection unit is It estimates the user's emotions and adjusts the frequency of data collection based on the estimated user emotions. The system according to feature 1.

Images