System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting air quality data; means for storing the collected air quality data in a time series; means for visualizing the stored air quality data; means for generating a report based on the visualized data; and means for periodically outputting the generated report.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Many companies and facilities are required to continuously monitor and report on air quality, but the manual data collection, analysis, and reporting process is time-consuming and labor-intensive. It is also difficult to maintain data accuracy and consistency, which can delay effective measures to improve air quality. Furthermore, the difficulty of regular reporting and prompt detection of abnormal values ​​makes it difficult to hold appropriate discussions in health and safety committees and other forums. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means: Means for collecting air quality data (air measuring instruments) are installed at various locations, and the collected data is stored in chronological order on a server. The stored data is extracted from a database by visualization means and converted into a visualized format, such as a graph, in chronological order. A means is provided that allows users to check the visualized data on an internet browser. In addition, a means is provided for periodically generating reports based on the visualized data, and the reports are automatically output on a regular basis. This allows users to continuously and efficiently monitor air quality data and take appropriate discussions and measures in safety and health committees, etc.

[0006] "Air quality data" refers to data that includes indicator values ​​such as pollutants in the air, their concentrations, temperature, and humidity.

[0007] "Collecting means" means the method or device for capturing air quality data by air measuring instruments installed at designated locations.

[0008] "Storage means" means a method or device for recording collected air quality data in some form in a database or other storage.

[0009] "Visualization means" means a method or device for converting stored air quality data into a visual format such as a graph or chart.

[0010] A "means for generating a report" is a method or device for generating a report, such as a document or PDF format, based on visualized or aggregated data.

[0011] A "periodic output means" is a method or device for automatically generating, storing, or distributing reports based on a set schedule.

[0012] A "sensor identifier" is an ID or label that uniquely identifies each air measurement device.

[0013] An "Internet browser" is a software graphical user interface that a user uses to view web pages. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

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

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

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

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

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] The construction and operation of a system for implementing the present invention, which automatically collects, stores, visualizes, and reports on air quality data, is described below.

[0036] Data collection

[0037] server

[0038] The server provides an API endpoint for receiving air quality data sent from the air measurement device. The air measurement device periodically sends JSON data containing the sensor identifier and air quality data. The server receives this data and stores it in a database.

[0039] The server implements API endpoints using a web framework such as Flask, and a relational database such as SQLite is used to efficiently store and manage the collected data.

[0040] Data visualization

[0041] User

[0042] Users access the system from their terminals and check visualized air quality data. The data in the database is retrieved from the server and converted into visualization formats such as time series graphs using Python's Matplotlib library.

[0043] For example, if you want to visualize data from a sensor with ID "sensor_1," you can retrieve all data related to "sensor_1" from the database and plot it along a time axis, allowing you to visually confirm the progress of air quality.

[0044] Generate reports

[0045] server

[0046] The server schedules the generation of periodic reports every month. The reports summarize data for a specific period (e.g., one month) and include statistical information such as averages, maximums, and minimums. The reports are generated and saved in PDF format.

[0047] The server uses a PDF generation library such as FPDF to automatically create a report header, chapter titles for each sensor, and the body of the report. The report is then submitted to the health and safety committee and used to consider measures to improve air quality.

[0048] Specific examples

[0049] For example, data from a sensor with ID "sensor_A" installed in an office can be used. The server receives air quality data sent from "sensor_A" on a daily basis and stores it in a database. At the end of the month, users access the system from their terminals and check graphs of the monthly data. The server automatically generates a monthly report, saves it as a PDF file, and uses it at the next health and safety committee meeting.

[0050] The system described above provides efficient and automated air quality monitoring and reporting, allowing users to access and analyze important data hassle-free, making it extremely useful for continuously monitoring the air quality of a specific location.

[0051] The processing flow will be explained below.

[0052] Step 1: Data collection

[0053] server

[0054] The server provides an API endpoint for receiving data from the air quality measurement device. The air quality measurement device periodically sends JSON-formatted data containing the sensor identifier and air quality data to the server. The server receives this data, extracts it, and stores it in a database. The measurement date and time are also stored in the database.

[0055] Step 2: Save data

[0056] server

[0057] The server parses the received JSON data, extracts the air quality data, the sensor identifier of the air quality monitor, and the date and time of receipt, creates and executes SQL instructions to store this data in an SQLite database, and then completes the process after confirming that the database has been updated appropriately.

[0058] Step 3: Data Acquisition

[0059] User

[0060] When a user runs a visualization program from their device, they specify a specific sensor identifier. The server executes an SQL query to retrieve the data corresponding to this sensor identifier from the database. The retrieved data is then prepared as time-series data.

[0061] Step 4: Data visualization

[0062] User

[0063] After acquiring the data, users can use a visualization library such as Matplotlib to display the data in graph form. The visualization program running on the user's device generates and displays time series graphs and histograms using the acquired data, allowing users to visually confirm the progress of air quality.

[0064] Step 5: Generate reports

[0065] server

[0066] The server sets up a task schedule to automatically generate monthly reports. At the scheduled time (e.g., the beginning of the month), the server runs the report generation program. This program retrieves air quality data from the database for the past month and compiles the results into a report. The report is generated in PDF format and saved on the server.

[0067] Step 6: Report output

[0068] server

[0069] The server automatically saves the generated PDF report to a specified location. Additional output options, such as emailing the report, can be configured as needed. This allows monthly reports to be automatically generated and submitted to the health and safety committee, etc.

[0070] In this way, a series of processes from collecting air quality data to storing, visualizing, generating and outputting reports are carried out automatically, creating a system that allows users to efficiently monitor and report on air quality.

[0071] Example 1

[0072] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0073] Monitoring and improving air quality is becoming increasingly important in modern society. However, conventional air quality monitoring systems require manual data collection, storage, visualization, and report generation, which is time-consuming and inefficient. Furthermore, data is scattered, making integrated management difficult. For this reason, there is a demand for a system that can automate and consistently manage air quality data, from collection to visualization and report generation.

[0074] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0075] In this invention, the server includes means for collecting air quality data, means for saving the collected air quality data in chronological order, means for acquiring the saved air quality data, means for visualizing the acquired air quality data, means for generating a chart for visualization, means for generating a report based on the visualized data, and means for periodically outputting the generated report, thereby enabling consistent collection, management, visualization, and report generation of air quality data.

[0076] "Air quality data" is data that numerically represents the concentration and amount of various substances and pollutants in the air (e.g., PM2.5, carbon dioxide, carbon monoxide, ozone, etc.).

[0077] "Means of collection" refers to the function of acquiring air quality data using sensors such as air measuring devices and sending it to a server.

[0078] "Means for storing data in chronological order" refers to a function for recording and accumulating air quality data along with date and time information in a database or other storage device.

[0079] The "means of acquisition" is a function that extracts air quality data stored in the database based on specified conditions and converts it into a reusable format within the server.

[0080] "Visualization means" refers to the function of converting acquired air quality data into a visual format such as a graph or chart, and displaying it in a way that is easily understandable to the user.

[0081] The "means for generating charts" is a function for drawing charts such as line graphs and bar graphs based on visualized data.

[0082] A "means for generating reports" is a function that compiles visualized data and statistical information and creates a document in a specific format (e.g., a PDF file).

[0083] The "means for periodic output" is a function that automatically creates a report at a certain period and saves it as an electronic file or prints it.

[0084] A "classification means" is a function that divides collected air quality data into categories based on specific sensor identifiers and location information.

[0085] The "aggregation means" is a function that performs statistical processing on classified data and calculates statistical information such as average values, maximum values, and minimum values.

[0086] The "means for displaying on a browser" is a function for displaying visualized data on a user interface through an internet browser.

[0087] The system of the present invention includes means for automatically collecting, storing, visualizing, and generating reports on air quality data, specific embodiments of which are described in detail below.

[0088] Data collection

[0089] server

[0090] The server provides an API endpoint for receiving air quality data sent from the air measurement devices. The air measurement devices periodically send JSON data containing the sensor identifier and air quality data to the server. The server implements the API endpoint using a web framework such as Flask and stores the received data in a database.

[0091] The server parses the received JSON data and extracts the necessary data (sensor identifier, date and time, air quality data). It then efficiently stores and manages the data using a relational database such as SQLite. This process ensures that all data sent from the air measuring devices is collected in a consistent manner.

[0092] Data visualization

[0093] User

[0094] Users access the system from their terminals and check the visualization results of the stored air quality data. The server retrieves the necessary data from the SQLite database in response to user requests and visualizes it using the Python Matplotlib library.

[0095] Specifically, data for the sensor ID and period specified by the user is displayed in the form of a time series graph, etc. This allows the user to visually check the progress of air quality.

[0096] Generate reports

[0097] server

[0098] The server generates air quality reports periodically every month. The reports include aggregated data (average, maximum, minimum, and other statistical information) for a specific period (e.g., one month). The reports are generated and saved in PDF format using a PDF generation library such as FPDF.

[0099] The server uses a Python scheduling library (e.g., APScheduler) to set up a process to automatically generate the report every month, allowing users to access their monthly air quality reports without any hassle.

[0100] Examples and prompts

[0101] For example, consider a case where air quality is monitored and managed based on data sent from a sensor ID "sensor_A" installed in an office. The server periodically receives air quality data from "sensor_A" and stores it in a database. At the end of the month, users can access the system from their terminals and check a graph of the monthly air quality data. Furthermore, the server automatically generates a monthly report and saves it as a PDF file, which can be used at the next health and safety committee meeting.

[0102] Example prompt sentence:

[0103] "Please explain the program process of the system that automates the collection, storage, visualization, and report generation of air quality data. Please specify the names of the specific hardware and software, and provide a detailed description of the data processing and calculations that are performed. Also, please include the following example: Using data from a sensor with ID "sensor_A" installed in an office."

[0104] This embodiment provides efficient, automated air quality monitoring and reporting, allowing users to access and analyze important data. This system is highly effective for continuously monitoring air quality in a specific location.

[0105] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0106] Step 1: Receiving data

[0107] server

[0108] The server provides an API endpoint to receive data sent from the air quality measurement device. As input, it receives JSON-formatted data from the air quality measurement device. The server implements an endpoint called / api / data using the Flask framework. The received data has elements such as a sensor identifier, date and time, and air quality data.

[0109] Specifically, the server receives an HTTP POST request and extracts JSON data from the request body, outputting the extracted sensor identifier, date and time, and air quality data.

[0110] Step 2: Save data

[0111] server

[0112] The server stores the received air quality data in an SQLite database. It uses the sensor identifier, date and time, and air quality data as input. It first opens a database connection and then generates the appropriate SQL statements to insert the data.

[0113] Specifically, it inserts data into the database using an SQL INSERT statement, and outputs a success status indicating that the data was successfully saved.

[0114] Step 3: Data Acquisition

[0115] server

[0116] The server retrieves the required data from the database based on the user request. It receives the sensor ID and the period as input. It executes an SQL query to the database to extract the relevant data.

[0117] Specifically, the SELECT statement is used to extract data related to the specified sensor ID and period from the database, and the output is a list of the acquired air quality data.

[0118] Step 4: Data visualization

[0119] server

[0120] The server visualizes the retrieved data, using the extracted air quality data as input and plotting these data on time series graphs using Python's Matplotlib library.

[0121] Specifically, the server plots the data on the x-axis (date and time) and y-axis (air quality data) and saves the visualization as an image file. The output is the generated graph image.

[0122] Step 5: Generate reports

[0123] server

[0124] The server generates air quality reports periodically. As input, it receives data for a specific period (e.g., one month). It aggregates the data and calculates statistics (average, maximum, minimum).

[0125] Specifically, it uses the FPDF library to compose a report in PDF format, embeds the required statistics and visualizations in the report, and the output is the generated PDF report.

[0126] Step 6: Report output

[0127] server

[0128] The server periodically saves or sends the generated reports. It receives the generated PDF reports as input. It schedules the report generation every month using the scheduling library mentioned above (e.g., APScheduler).

[0129] Specifically, the generated report is saved in a specified folder and sent as needed via email, etc. The output is a saved PDF report file.

[0130] Step 7: View the data visualization

[0131] User

[0132] The user accesses the system from a terminal and checks the visualized air quality data. As input, the system receives the sensor ID and period specified by the user. The server retrieves the visualized data from the database and displays it on the network browser.

[0133] Specifically, the server displays the acquired data in the browser using HTML and JavaScript. The output is visualized air quality data displayed on the browser.

[0134] The above is the main processing flow of this system.

[0135] (Application example 1)

[0136] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0137] In conventional air quality monitoring systems, data collection, visualization, and report generation are often done manually, which is time-consuming and labor-intensive, and makes it difficult to detect abnormalities in real time or send prompt alerts. Furthermore, data visualization mainly requires the use of an internet browser, making it difficult to intuitively and quickly monitor air quality on a terminal. There is a need for a system that can resolve these issues and efficiently monitor and manage air quality in real time.

[0138] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0139] In this invention, the server includes means for detecting abnormalities in air quality data and notifying the user, means for classifying the air quality data based on a specified sensor identifier, means for aggregating the classified data and calculating statistics, and means for displaying the visualized data on a terminal application. This allows air quality abnormalities to be detected in real time and for the user to be promptly notified. Furthermore, data visualization can be performed intuitively on the terminal, enabling efficient air quality monitoring and management.

[0140] "Air quality data" is a collection of measurements that indicate the concentration of harmful substances and particulates in the air, as well as other information about air quality.

[0141] "Collection means" is a general term for devices and technologies, including sensors and their communication functions, that acquire air quality data and transmit it to a server.

[0142] "Means for storing data chronologically" refers to a technology that records collected air quality data sequentially over time and manages it centrally in a database.

[0143] "Visualization means" refers to technology that converts collected air quality data into a visual format such as graphs and charts and displays it in a way that users can intuitively understand.

[0144] A "report generation means" is a technology that automatically generates a formatted document by compiling statistics and trends based on collected and visualized air quality data.

[0145] The "means for periodic output" is a mechanism for saving or transmitting reports generated at automatically set time intervals.

[0146] "Means for detecting abnormalities and notifying users" refers to technology that automatically issues a warning when an abnormality exceeding a preset standard value is detected based on air quality data.

[0147] The "means for classifying based on designated sensor identifiers" is a mechanism for organizing, classifying, and efficiently managing data from multiple air quality sensors based on identifiers.

[0148] The "means for calculating statistical values" is a technique for calculating statistical information such as average values, maximum values, and minimum values ​​using the classified air quality data.

[0149] "Means for displaying on a device application" refers to a mechanism for displaying air quality data through an application installed on a device such as a smartphone or tablet.

[0150] A system for implementing the present invention efficiently and automatically collects, stores, visualizes, generates reports, and detects anomalies in air quality data. This system includes a sensor that collects air quality data, a server that stores and manages the data, and a terminal application that visualizes the data. The detailed configuration and operation are described below.

[0151] Data collection

[0152] The server provides an API endpoint that receives data sent from multiple air quality sensors. The air quality sensors periodically send JSON-formatted data, including concentration data of harmful substances and fine particles in the air. This data is received by the server via an API endpoint built using a web framework such as Flask and stored in a relational database such as SQLite.

[0153] Data visualization

[0154] Users access the system from devices such as smartphones and tablets to view visualized air quality data. Data in the database is retrieved from the server and visualized in the form of time series graphs using Python's Matplotlib library, etc. This visualization allows users to intuitively understand fluctuations in air quality.

[0155] Anomaly detection and notification

[0156] The server monitors the collected air quality data in real time and can detect abnormalities. If an abnormality is detected, the server sends a notification to the user's device. This notification can be in the form of a push notification or email, allowing the user to respond quickly.

[0157] Report Generation

[0158] The server automatically generates regular monthly reports. The reports summarize data for a specific period (e.g., one month) and include statistical information such as average, maximum, and minimum values. The reports are generated in PDF format and built using a PDF generation library such as FPDF, and are regularly saved and distributed. This allows users to regularly check the status of air quality and take necessary measures.

[0159] Specific examples

[0160] For example, if data is used from a sensor with ID "sensor_1" installed in an office, the server receives air quality data sent from "sensor_1" on a daily basis and stores it in a database. Users can visualize and check the data from "sensor_1" on their smartphones. Monthly reports are also automatically generated by the server and can be downloaded as PDF files. An anomaly detection function immediately notifies users if the air quality standard is exceeded.

[0161] Prompt Sentence Examples

[0162] Get the air quality data from "sensor_1" and generate a time series graph. Also, generate a PDF report based on the data from the same sensor.

[0163] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0164] Processing Steps

[0165] Step 1: Data collection

[0166] The server receives data from the air quality sensor. The sensor sends air quality data in JSON format at regular intervals. This data includes the sensor identifier and various air quality parameters. The server implements an API endpoint using the Flask framework to receive the sent JSON data. The received data is stored in a SQLite database.

[0167] Input: JSON data from air quality sensors

[0168] Output: Save the received data to the database

[0169] Step 2: Save data

[0170] The server stores the processed air quality data in a database in chronological order, including the sensor identifier, timestamp, and measurement value. The SQLite database allows for efficient management of air quality data.

[0171] Input: Received air quality data

[0172] Output: Data stored in chronological order

[0173] Step 3: Data visualization

[0174] When a user accesses the system from a terminal, the server retrieves the air quality data of the specified sensor from the stored database, then uses the Python Matplotlib library to generate a time series graph, which is then converted into a format that can be visually displayed on the terminal application.

[0175] Input: Air quality data retrieved from a database

[0176] Output: Visualized time series graph

[0177] Step 4: Anomaly detection and notification

[0178] The server monitors the collected air quality data and sends a notification to the user's device if an abnormality is detected. For example, if harmful substances exceeding the standard value are detected, the server will immediately send a push notification or email. This allows the user to understand the abnormality in air quality in real time and take prompt action.

[0179] Input: Air quality data being monitored

[0180] Output: Abnormality notification (push notification or email)

[0181] Step 5: Generate reports

[0182] The server aggregates data from the database for the relevant period to generate regular monthly reports. It calculates statistical information such as averages, maximums, and minimums based on the data, and generates PDF reports using the FPDF library. These reports are periodically saved or distributed to users' devices.

[0183] Input: Air quality data for the period of interest

[0184] Output: Report (PDF format)

[0185] Step 6: Print and distribute the report

[0186] The generated PDF report is sent from the server to the user's device, where the user can download the report and use it in monthly meetings, etc.

[0187] Input: Generated PDF report

[0188] Output: Sending a PDF report to the user's device

[0189] Examples:

[0190] As a concrete example, consider a scenario where a user wants to visualize and check air quality data from "sensor_1" on their smartphone. In this case, the server retrieves the data from "sensor_1" from the database, generates a time series graph using Matplotlib, and displays it on the device. If an abnormality is detected, the user is notified immediately. At the end of the month, an automatically generated PDF report is distributed to the user's device.

[0191] Prompt Sentence Examples

[0192] Get the air quality data from "sensor_1" and generate a time series graph. Also, generate a PDF report based on the data from the same sensor.

[0193] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0194] The system for implementing the present invention includes an emotion engine that recognizes and analyzes user emotions, in addition to collecting, storing, visualizing, and generating reports on air quality data. The configuration and operation of the system are described below.

[0195] Data collection

[0196] server

[0197] The server provides an API endpoint to receive air quality data sent from the air measurement device. The air measurement device periodically sends JSON-formatted data containing the sensor identifier and air quality data to the server. The server analyzes the received data and stores it in a database, along with the measurement date and time.

[0198] Data storage

[0199] server

[0200] The server parses the received JSON data and extracts the air quality data, sensor identifier, and date and time of reception. It then stores this data in an SQLite database. To ensure that the data is properly stored, it sends a completion notification after the database is updated.

[0201] Data Visualization

[0202] User

[0203] Users access the system from their terminals and check visualized air quality data. By specifying a specific sensor identifier, data is retrieved from the server and displayed in graph form using a visualization library such as Matplotlib. This allows the transition of air quality to be visualized.

[0204] Manipulating the Emotion Engine

[0205] User

[0206] When a user checks air quality data, the emotion engine analyzes the user's facial expressions and tone of voice to obtain emotional data. This emotional data is saved along with the air quality data. For example, the engine can detect emotional reactions such as "relief" or "anxiety" in response to changes in air quality perceived by the user.

[0207] Storing Emotional Data

[0208] server

[0209] The system receives user emotion data recognized by the emotion engine, associates it with air quality data, and stores it in a database for later analysis and report generation.

[0210] Report Generation

[0211] server

[0212] The server schedules the generation of monthly reports, which include statistical information based on the air quality data and user sentiment data from the past month. The reports are generated in PDF format and stored on the server.

[0213] Report Output

[0214] server

[0215] The server automatically saves the generated PDF report in a specified location and sends it via email or other means as needed. The report can also include the results of user sentiment analysis, making it possible to comprehensively evaluate the impact of air quality and the user's emotional response.

[0216] Viewing in an Internet browser

[0217] User

[0218] Users can view real-time air quality and emotion data through an internet browser. This includes visualizations in graphs and charts, as well as indicators and numerical values ​​that show the user's emotional state. For example, the worsening air quality can indicate an increase in the user's anxiety level.

[0219] This system not only enables efficient and automated air quality monitoring and reporting, but also enables comprehensive analysis that takes into account the user's emotional state, making it a useful tool for improving living and working environments in particular.

[0220] The processing flow will be explained below.

[0221] Step 1: Data collection

[0222] server

[0223] The server provides an API endpoint to receive air quality data sent from the air measurement device. The air measurement device periodically sends JSON-formatted data including the sensor identifier and air quality data to the server. The server receives this data and stores it in a database, along with the date and time.

[0224] Step 2: Data analysis

[0225] server

[0226] The server parses the received JSON data, extracts the sensor identifier, air quality data, and date and time, and stores them in an SQLite database. To ensure the data is stored properly, it sends a completion notification after the database is updated.

[0227] Step 3: Collecting Emotional Data

[0228] User

[0229] The user displays and checks the air quality data on the device. An emotion engine is activated, analyzing the user's facial expressions and voice in real time to detect the user's emotional state (e.g., relief, anxiety, excitement, etc.). The emotion engine generates emotion data and sends it to the server.

[0230] Step 4: Emotion data storage

[0231] server

[0232] The server receives the emotion data sent from the emotion engine, and associates the received emotion data with the air quality data and stores it in a database, thereby recording the user's emotional response to the specific air quality data.

[0233] Step 5: Data visualization

[0234] User

[0235] Users access the system from their devices and view visualized air quality and emotion data. The server retrieves the relevant data from the database based on the specified sensor identifier and generates a time series graph and emotion indicator. These can then be displayed using a visualization library such as Matplotlib to visualize the progress of air quality and the corresponding changes in emotion.

[0236] Step 6: Generate reports

[0237] server

[0238] The server schedules a task to generate reports periodically. For example, at the beginning of each month, it aggregates the air quality data and user emotion data from the past month and generates a PDF report containing air quality statistics and an analysis of the user's emotional response.

[0239] Step 7: Report Output

[0240] server

[0241] The server automatically saves the generated PDF report in a specified folder and sends it by email as needed. This allows it to be used as a reference for meetings such as safety and health committees. The output report includes the trend of air quality fluctuations and the user's emotional response to them.

[0242] Step 8: Browser display

[0243] User

[0244] Users access the system using an internet browser to view air quality and emotion data in real time. Visualized data includes time series graphs, statistical information, and indicators of the user's emotional state. For example, users can see at a glance whether their anxiety levels tend to increase as air quality worsens.

[0245] The above is a specific processing flow of the system of the present invention. This system not only monitors air quality but also makes it possible to comprehensively evaluate the environment, including the user's emotional response.

[0246] Example 2

[0247] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0248] Conventional air quality monitoring systems simply collect, store, visualize, and report on air quality data, but lack the ability to address user emotions. This makes it difficult to assess the impact of air quality fluctuations on users' emotions and behavior, making it difficult to comprehensively improve living and working environments.

[0249] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting air quality data, means for saving the collected air quality data in chronological order, means for visualizing the saved air quality data, means for generating a report based on the visualized data, means for periodically outputting the generated report, means for analyzing the user's emotions, and means for saving the analyzed emotion data in association with the air quality data. This enables a comprehensive evaluation that associates the air quality data with the user's emotion data, which is useful for improving living and working environments.

[0250] "Air quality data" refers to data that includes information on pollutants, chemical components, temperature, humidity, and so on in the air.

[0251] "Means of collection" refers to the function of acquiring air quality data using sensors and measuring devices and incorporating it into the system.

[0252] The "means for storing data in chronological order" is a function that records air quality data at regular time intervals and stores data from the past to the present.

[0253] "Visualization means" refers to the ability to display stored air quality data in the form of graphs, charts, indicators, etc., to clearly show trends and fluctuations in the data.

[0254] "Means for generating reports" refers to a function that creates reports summarizing statistical information and analytical results based on collected and stored air quality data.

[0255] The "means for periodic output" refers to a function for automatically outputting the generated report at regular intervals such as monthly or weekly, and providing it to the user.

[0256] The "means for analyzing user emotions" is a function that analyzes the user's facial expressions and tone of voice to obtain emotional data such as relief, anxiety, surprise, etc.

[0257] The "means for storing analyzed emotion data in association with air quality data" is a function that stores acquired emotion data together with the corresponding air quality data, enabling the association between them to be analyzed.

[0258] As a specific embodiment for carrying out the invention, the configuration and operation of the following system will be described. This system not only collects, stores, visualizes, and generates reports on air quality data, but also includes an emotion engine that recognizes and analyzes user emotions.

[0259] Hardware and software used

[0260] Server: Receives, analyzes, stores, and generates reports on air quality and emotion data.

[0261] Air measurement device: Equipped with sensors that measure pollutants and chemical components in the air and send the data to a server.

[0262] Terminal: A device through which a user accesses the system and checks air quality and emotion data. Examples include a PC or smartphone.

[0263] Emotion engine: Software that analyzes the user's facial expressions and tone of voice to obtain emotional data. It uses the camera and microphone.

[0264] Database: Used to store data, such as SQLite.

[0265] Visualization libraries: Used to visualize data, such as Matplotlib.

[0266] Data collection

[0267] The server provides an API endpoint to receive air quality data sent from the air measurement devices. The air measurement devices periodically send JSON-formatted data containing the sensor identifier and air quality data to the server. Specifically, the server exposes an endpoint called " / api / airquality" and automatically starts analyzing the data as it arrives.

[0268] Data storage

[0269] The received JSON data is parsed and the sensor identifier of the air measuring device, the air quality data, and the date and time of receipt are extracted. This data is then stored in an SQLite database. When the data has been saved, the server logs "New data has been added to the database." For example, the server saves the data "sensor_001", "35μg / m³", "2023-10-01 12:00:00" to SQLite.

[0270] Data Visualization

[0271] Users can log in to the system from a terminal and view visualized air quality data. By specifying a specific sensor identifier, data is retrieved from the server and displayed in graph form using a visualization library such as Matplotlib. For example, if a user selects "sensor_001" and clicks the "Graph Display" button, data for the past week will be displayed as a graph.

[0272] Manipulating the Emotion Engine

[0273] While the user is checking the air quality data, the emotion engine begins to operate. The emotion engine analyzes the user's facial expressions and tone of voice through the camera and microphone and sends emotional data to the server. For example, while the user is checking the data, the camera captures their facial expressions, and if the emotion "anxiety" is detected, the data "anxiety" is sent to the server.

[0274] Storing Emotional Data

[0275] The server receives the emotion data sent from the emotion engine, associates it with the air quality data, and stores it in an SQLite database. For example, the server stores data such as "2023-10-01 12:00:00: Anxiety" along with the air quality data.

[0276] Report Generation

[0277] The server sets a schedule for report generation at the end of each month. It aggregates air quality data and emotion data from the database for the past month and automatically generates a report in PDF format containing statistical information. Specifically, the server generates a file named "September_2023_Report.pdf" and saves it in the specified directory.

[0278] Report Output

[0279] The server saves the generated PDF report in a specified location and notifies the user by email if necessary. Depending on the user's settings, the report can also include the results of the emotion data analysis. For example, the server can attach the generated PDF report to an email and send it to a specified email address.

[0280] Viewing in an Internet browser

[0281] Users can access the system with an internet browser and check air quality data and emotion data in real time. For example, when a user accesses the system with a browser, "real-time air quality data" and an "emotional state indicator" are displayed on the screen. When air quality deteriorates, the emotion indicator can show "anxiety."

[0282] Prompt Sentence Examples

[0283] Example prompts to enter into the generative AI model:

[0284] "Write a program that correlates air quality data with user sentiment data to generate a statistical report for the past month."

[0285] The system not only enables efficient and automated air quality monitoring and reporting, but also enables comprehensive analysis that takes into account the user's emotional state, helping to improve living and working environments.

[0286] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0287] Step 1: Data collection

[0288] The server provides an API endpoint for receiving data in JSON format. It periodically receives JSON-formatted data sent from air measurement devices, including sensor identifiers and air quality data. It analyzes the received data and temporarily stores the sensor identifiers, air quality data, and reception date and time.

[0289] Input: Air quality data in JSON format from an air measurement device

[0290] Processing: Parse the data to extract the sensor identifier, air quality data, and date and time of receipt.

[0291] Output: Extracted data stored in temporary storage

[0292] Specific operation: The server exposes an endpoint called " / api / airquality" and automatically starts analyzing data as it arrives.

[0293] Step 2: Save data

[0294] The server reads the temporarily saved data and records it in the SQLite database. When saving is complete, it logs "New data has been added to the database."

[0295] Input: Temporarily stored sensor identifier, air quality data, date and time of receipt

[0296] Process: Save data to SQLite database

[0297] Output: Notification of database update completion

[0298] Specific operation: The server saves the data "sensor_001", "35μg / m³", and "2023-10-01 12:00:00" to SQLite.

[0299] Step 3: Data visualization

[0300] A user logs into the system from a terminal and sends a visualization request to the server specifying a specific sensor identifier. The server retrieves the necessary data from the database and sends it to the terminal, which then generates a graph using a visualization library such as Matplotlib.

[0301] Input: Visualization request from user (sensor identifier)

[0302] Processing: Retrieve the relevant data from the database and send it to the device

[0303] Output: Display the graph on the terminal

[0304] Specific operation: When the user selects "sensor_001" and clicks the "Graph display" button, the data for the past week will be displayed as a graph.

[0305] Step 4: Emotion Engine Analysis

[0306] While the user is checking the air quality data, the emotion engine analyzes the user's facial expressions and tone of voice, and transmits the analyzed emotion data to the server.

[0307] Input: User's facial expressions and tone of voice (real-time data)

[0308] Processing: The emotion engine analyzes the data and generates emotion data

[0309] Output: Send emotion data to the server

[0310] Specific operation: While the user is checking the data, the camera captures their facial expressions, and if the emotion "anxiety" is detected, the data "anxiety" is sent to the server.

[0311] Step 5: Storing emotion data

[0312] The server receives the emotion data sent from the emotion engine, associates it with the air quality data, and stores it in an SQLite database.

[0313] Input: Emotion data sent from the emotion engine

[0314] Processing: Emotion data is associated with air quality data and stored in a database

[0315] Output: Emotion data stored in a database

[0316] What happens: The server stores data such as "2023-10-01 12:00:00: Anxiety" along with air quality data.

[0317] Step 6: Generate reports

[0318] The server aggregates air quality data and emotion data for the past month at regularly scheduled times, and generates a PDF report based on the aggregated results.

[0319] Input: Air quality data and sentiment data from a database

[0320] Processing: Aggregate data and generate PDF report

[0321] Output: Report in PDF format

[0322] Specific behavior: The server generates a file named "September_2023_Report.pdf" and saves it in the specified directory.

[0323] Step 7: Report Output

[0324] The server saves the generated PDF report in a specified location and notifies the user by email if necessary. Depending on the user's settings, the report can also include the results of the emotion data analysis.

[0325] Input: Generated PDF report

[0326] Action: Print and send report

[0327] Output: Saved PDF report and notification of successful submission

[0328] Specific behavior: The server generates a PDF report and sends it to the specified email address as an attachment.

[0329] Step 8: View in your Internet browser

[0330] Users access the system through an internet browser and view real-time air quality and sentiment data, which is visualized using graphs and indicators.

[0331] Input: Browser access request from user

[0332] Processing: Retrieving real-time data from the database and displaying it in a visual format

[0333] Output: Visualized data displayed in a browser

[0334] Specific operation: A user accesses the system through a browser and the screen displays "real-time air quality data" and an "emotional state indicator." For example, when the air quality deteriorates, the indicator displays "anxiety."

[0335] (Application example 2)

[0336] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0337] While conventional air quality management systems can collect, visualize, and generate reports on air quality data, it is difficult to directly grasp the impact of air quality fluctuations on users. Furthermore, there is a lack of means to monitor in real time the emotional state of workers in response to deteriorating air quality at the workplace, which creates challenges in ensuring safety and improving work efficiency. To solve these challenges, there is a need for integrated management of air quality data and users' emotional state, and a comprehensive assessment of the impact of air quality.

[0338] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0339] In this invention, the server includes means for collecting air quality data, means for saving the air quality data in chronological order, means for visualizing the saved air quality data, means for generating a report based on the visualized data, means for periodically outputting the generated report, means for collecting emotion data using an emotion engine that recognizes and analyzes user emotion data, means for saving the emotion data together with the air quality data, and means for visualizing the emotion data in association with the air quality data. This makes it possible to grasp in real time the impact of fluctuations in air quality on workers in factories and work sites, ensuring safety and improving work efficiency.

[0340] "Air quality data" refers to data that includes indicators such as the concentration of harmful substances and particulates in the air, temperature, and humidity.

[0341] "Means for collection" refers to methods and equipment for acquiring air quality data and emotion data using sensors and measuring devices.

[0342] The "means for storing in chronological order" refers to a method and system for storing acquired data in an electronic recording medium in a format arranged in chronological order.

[0343] "Visualization means" are methods and tools that display collected data in a user-friendly manner as graphs, charts, or diagrams.

[0344] A "report generating means" is a method or device that analyzes collected data and produces a report summarizing statistics and trends.

[0345] A "periodic output means" is a method or system that automatically generates reports or data at set intervals and notifies or transmits them to users.

[0346] An "emotion engine" is software or hardware that analyzes a user's facial expressions, tone of voice, etc. to recognize their emotional state and record it as data.

[0347] "Emotion data" is data that includes numerical values ​​and categories that represent the user's emotional state.

[0348] A "connected visualization" is a method and tool that connects air quality data and emotion data and displays them together.

[0349] To implement this invention, it is necessary to build a system that utilizes an air measurement device, an emotion recognition engine, a server, and a visualization tool.

[0350] First, the air measurement device periodically collects air quality data and sends it to the server. The server analyzes the data received from the air measurement device and stores it in a database in chronological order. Specifically, the data is stored in a format that includes the sensor identifier, air quality data, and the date and time of reception.

[0351] Next, users collect emotional data using cameras and microphones installed on their devices or factory robots. An emotion recognition engine analyzes this data and quantifies or categorizes the user's emotional state.

[0352] The server stores these emotion data together with the air quality data, which are then integrated and visualized using a visualization tool (e.g., Matplotlib) to display the air quality data and the user's emotion data in graphs and charts.

[0353] The server also periodically generates reports and saves statistical information, including air quality data and emotion data, in PDF format. These reports are periodically notified or sent to the user.

[0354] For example, if the air quality in a factory deteriorates, an emotion recognition engine may detect high levels of anxiety among workers, allowing managers to immediately decide to activate air purifiers or halt work processes.

[0355] Example prompt sentence:

[0356] "Please suggest what to do if the air quality in the factory deteriorates and workers are feeling uneasy."

[0357] This system will enable monitoring and management of air quality in factories and workplaces, as well as real-time assessment of workers' emotional state, which is expected to ensure safety and improve work efficiency.

[0358] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0359] Step 1:

[0360] Air quality data collection

[0361] The server receives air quality data periodically sent from the air measurement device. The input is the air quality data sent from the air measurement device and the sensor identifier. The server receives this data and parses it in JSON format. The data obtained as a result of the analysis is the sensor identifier, air quality data, and reception date and time.

[0362] Step 2:

[0363] Air quality data storage

[0364] The server stores the air quality data received and analyzed in step 1 in chronological order. The input is the sensor identifier, air quality data, and reception date and time obtained in step 1. The server stores this data in an SQLite database and confirms that the database update is complete.

[0365] Step 3:

[0366] Collecting Emotional Data

[0367] Users collect emotional data through cameras and microphones installed on terminals or factory robots. The input is facial expression data captured by the camera and voice data recorded by the microphone. The emotion engine analyzes this data and quantifies or categorizes the user's emotional state. The output is emotional data.

[0368] Step 4:

[0369] Storing Emotional Data

[0370] The server stores the emotion data obtained in step 3 together with the air quality data. The inputs are the sensor identifier, emotion data, and the date and time of reception. The server stores these data in the database and confirms that the database update is complete. The output is the emotion data and air quality data stored in the database.

[0371] Step 5:

[0372] Data visualization

[0373] The user accesses the server from a terminal and checks visualized air quality data and emotion data. The input is a specific sensor identifier specified by the user, and the server retrieves the air quality data and emotion data from the database based on this sensor identifier. The retrieved data is displayed in graph form using a visualization library such as Matplotlib. The output is the visualized graph.

[0374] Step 6:

[0375] Report Generation

[0376] The server aggregates air quality data and emotion data on a monthly basis and generates a report containing statistical information. The input is the air quality data and emotion data from the past month. The server analyzes this data and creates a report in PDF format. The output is the generated PDF report.

[0377] Step 7:

[0378] Sending a report

[0379] The server saves the report generated in step 6 in the specified location and sends it to the user by email, etc. as needed. The input is the generated PDF report, which the server saves in the specified location and notifies the user. The output is the sent PDF report.

[0380] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0381] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0382] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0383] [Second embodiment]

[0384] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0385] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0386] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0387] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0388] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0389] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0390] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0391] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0392] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0393] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0394] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0395] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0396] The construction and operation of a system for implementing the present invention, which automatically collects, stores, visualizes, and reports on air quality data, is described below.

[0397] Data collection

[0398] server

[0399] The server provides an API endpoint for receiving air quality data sent from the air measurement device. The air measurement device periodically sends JSON data containing the sensor identifier and air quality data. The server receives this data and stores it in a database.

[0400] The server implements API endpoints using a web framework such as Flask, and a relational database such as SQLite is used to efficiently store and manage the collected data.

[0401] Data visualization

[0402] User

[0403] Users access the system from their terminals and check visualized air quality data. The data in the database is retrieved from the server and converted into visualization formats such as time series graphs using Python's Matplotlib library.

[0404] For example, if you want to visualize data from a sensor with ID "sensor_1," you can retrieve all data related to "sensor_1" from the database and plot it along a time axis, allowing you to visually confirm the progress of air quality.

[0405] Generate reports

[0406] server

[0407] The server schedules the generation of periodic reports every month. The reports summarize data for a specific period (e.g., one month) and include statistical information such as averages, maximums, and minimums. The reports are generated and saved in PDF format.

[0408] The server uses a PDF generation library such as FPDF to automatically create a report header, chapter titles for each sensor, and the body of the report. The report is then submitted to the health and safety committee and used to consider measures to improve air quality.

[0409] Specific examples

[0410] For example, data from a sensor with ID "sensor_A" installed in an office can be used. The server receives air quality data sent from "sensor_A" on a daily basis and stores it in a database. At the end of the month, users access the system from their terminals and check graphs of the monthly data. The server automatically generates a monthly report, saves it as a PDF file, and uses it at the next health and safety committee meeting.

[0411] The system described above provides efficient and automated air quality monitoring and reporting, allowing users to access and analyze important data hassle-free, making it extremely useful for continuously monitoring the air quality of a specific location.

[0412] The processing flow will be explained below.

[0413] Step 1: Data collection

[0414] server

[0415] The server provides an API endpoint for receiving data from the air quality measurement device. The air quality measurement device periodically sends JSON-formatted data containing the sensor identifier and air quality data to the server. The server receives this data, extracts it, and stores it in a database. The measurement date and time are also stored in the database.

[0416] Step 2: Save data

[0417] server

[0418] The server parses the received JSON data, extracts the air quality data, the sensor identifier of the air quality monitor, and the date and time of receipt, creates and executes SQL instructions to store this data in an SQLite database, and then completes the process after confirming that the database has been updated appropriately.

[0419] Step 3: Data Acquisition

[0420] User

[0421] When a user runs a visualization program from their device, they specify a specific sensor identifier. The server executes an SQL query to retrieve the data corresponding to this sensor identifier from the database. The retrieved data is then prepared as time-series data.

[0422] Step 4: Data visualization

[0423] User

[0424] After acquiring the data, users can use a visualization library such as Matplotlib to display the data in graph form. The visualization program running on the user's device generates and displays time series graphs and histograms using the acquired data, allowing users to visually confirm the progress of air quality.

[0425] Step 5: Generate reports

[0426] server

[0427] The server sets up a task schedule to automatically generate monthly reports. At the scheduled time (e.g., the beginning of the month), the server runs the report generation program. This program retrieves air quality data from the database for the past month and compiles the results into a report. The report is generated in PDF format and saved on the server.

[0428] Step 6: Report output

[0429] server

[0430] The server automatically saves the generated PDF report to a specified location. Additional output options, such as emailing the report, can be configured as needed. This allows monthly reports to be automatically generated and submitted to the health and safety committee, etc.

[0431] In this way, a series of processes from collecting air quality data to storing, visualizing, generating and outputting reports are carried out automatically, creating a system that allows users to efficiently monitor and report on air quality.

[0432] Example 1

[0433] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0434] Monitoring and improving air quality is becoming increasingly important in modern society. However, conventional air quality monitoring systems require manual data collection, storage, visualization, and report generation, which is time-consuming and inefficient. Furthermore, data is scattered, making integrated management difficult. For this reason, there is a demand for a system that can automate and consistently manage air quality data, from collection to visualization and report generation.

[0435] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0436] In this invention, the server includes means for collecting air quality data, means for saving the collected air quality data in chronological order, means for acquiring the saved air quality data, means for visualizing the acquired air quality data, means for generating a chart for visualization, means for generating a report based on the visualized data, and means for periodically outputting the generated report, thereby enabling consistent collection, management, visualization, and report generation of air quality data.

[0437] "Air quality data" is data that numerically represents the concentration and amount of various substances and pollutants in the air (e.g., PM2.5, carbon dioxide, carbon monoxide, ozone, etc.).

[0438] "Means of collection" refers to the function of acquiring air quality data using sensors such as air measuring devices and sending it to a server.

[0439] "Means for storing data in chronological order" refers to a function for recording and accumulating air quality data along with date and time information in a database or other storage device.

[0440] The "means of acquisition" is a function that extracts air quality data stored in the database based on specified conditions and converts it into a reusable format within the server.

[0441] "Visualization means" refers to the function of converting acquired air quality data into a visual format such as a graph or chart, and displaying it in a way that is easily understandable to the user.

[0442] The "means for generating charts" is a function for drawing charts such as line graphs and bar graphs based on visualized data.

[0443] A "means for generating reports" is a function that compiles visualized data and statistical information and creates a document in a specific format (e.g., a PDF file).

[0444] The "means for periodic output" is a function that automatically creates a report at a certain period and saves it as an electronic file or prints it.

[0445] A "classification means" is a function that divides collected air quality data into categories based on specific sensor identifiers and location information.

[0446] The "aggregation means" is a function that performs statistical processing on classified data and calculates statistical information such as average values, maximum values, and minimum values.

[0447] The "means for displaying on a browser" is a function for displaying visualized data on a user interface through an internet browser.

[0448] The system of the present invention includes means for automatically collecting, storing, visualizing, and generating reports on air quality data, specific embodiments of which are described in detail below.

[0449] Data collection

[0450] server

[0451] The server provides an API endpoint for receiving air quality data sent from the air measurement devices. The air measurement devices periodically send JSON data containing the sensor identifier and air quality data to the server. The server implements the API endpoint using a web framework such as Flask and stores the received data in a database.

[0452] The server parses the received JSON data and extracts the necessary data (sensor identifier, date and time, air quality data). It then efficiently stores and manages the data using a relational database such as SQLite. This process ensures that all data sent from the air measuring devices is collected in a consistent manner.

[0453] Data visualization

[0454] User

[0455] Users access the system from their terminals and check the visualization results of the stored air quality data. The server retrieves the necessary data from the SQLite database in response to user requests and visualizes it using the Python Matplotlib library.

[0456] Specifically, data for the sensor ID and period specified by the user is displayed in the form of a time series graph, etc. This allows the user to visually check the progress of air quality.

[0457] Generate reports

[0458] server

[0459] The server generates air quality reports periodically every month. The reports include aggregated data (average, maximum, minimum, and other statistical information) for a specific period (e.g., one month). The reports are generated and saved in PDF format using a PDF generation library such as FPDF.

[0460] The server uses a Python scheduling library (e.g., APScheduler) to set up a process to automatically generate the report every month, allowing users to access their monthly air quality reports without any hassle.

[0461] Examples and prompts

[0462] For example, consider a case where air quality is monitored and managed based on data sent from a sensor ID "sensor_A" installed in an office. The server periodically receives air quality data from "sensor_A" and stores it in a database. At the end of the month, users can access the system from their terminals and check a graph of the monthly air quality data. Furthermore, the server automatically generates a monthly report and saves it as a PDF file, which can be used at the next health and safety committee meeting.

[0463] Example prompt sentence:

[0464] "Please explain the program process of the system that automates the collection, storage, visualization, and report generation of air quality data. Please specify the names of the specific hardware and software, and provide a detailed description of the data processing and calculations that are performed. Also, please include the following example: Using data from a sensor with ID "sensor_A" installed in an office."

[0465] This embodiment provides efficient, automated air quality monitoring and reporting, allowing users to access and analyze important data. This system is highly effective for continuously monitoring air quality in a specific location.

[0466] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0467] Step 1: Receiving data

[0468] server

[0469] The server provides an API endpoint to receive data sent from the air quality measurement device. As input, it receives JSON-formatted data from the air quality measurement device. The server implements an endpoint called / api / data using the Flask framework. The received data has elements such as a sensor identifier, date and time, and air quality data.

[0470] Specifically, the server receives an HTTP POST request and extracts JSON data from the request body, outputting the extracted sensor identifier, date and time, and air quality data.

[0471] Step 2: Save data

[0472] server

[0473] The server stores the received air quality data in an SQLite database. It uses the sensor identifier, date and time, and air quality data as input. It first opens a database connection and then generates the appropriate SQL statements to insert the data.

[0474] Specifically, it inserts data into the database using an SQL INSERT statement, and outputs a success status indicating that the data was successfully saved.

[0475] Step 3: Data Acquisition

[0476] server

[0477] The server retrieves the required data from the database based on the user request. It receives the sensor ID and the period as input. It executes an SQL query to the database to extract the relevant data.

[0478] Specifically, the SELECT statement is used to extract data related to the specified sensor ID and period from the database, and the output is a list of the acquired air quality data.

[0479] Step 4: Data visualization

[0480] server

[0481] The server visualizes the retrieved data, using the extracted air quality data as input and plotting these data on time series graphs using Python's Matplotlib library.

[0482] Specifically, the server plots the data on the x-axis (date and time) and y-axis (air quality data) and saves the visualization as an image file. The output is the generated graph image.

[0483] Step 5: Generate reports

[0484] server

[0485] The server generates air quality reports periodically. As input, it receives data for a specific period (e.g., one month). It aggregates the data and calculates statistics (average, maximum, minimum).

[0486] Specifically, it uses the FPDF library to compose a report in PDF format, embeds the required statistics and visualizations in the report, and the output is the generated PDF report.

[0487] Step 6: Report output

[0488] server

[0489] The server periodically saves or sends the generated reports. It receives the generated PDF reports as input. It schedules the report generation every month using the scheduling library mentioned above (e.g., APScheduler).

[0490] Specifically, the generated report is saved in a specified folder and sent as needed via email, etc. The output is a saved PDF report file.

[0491] Step 7: View the data visualization

[0492] User

[0493] The user accesses the system from a terminal and checks the visualized air quality data. As input, the system receives the sensor ID and period specified by the user. The server retrieves the visualized data from the database and displays it on the network browser.

[0494] Specifically, the server displays the acquired data in the browser using HTML and JavaScript, and the output is visualized air quality data displayed on the browser.

[0495] The above is the main processing flow of this system.

[0496] (Application example 1)

[0497] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0498] In conventional air quality monitoring systems, data collection, visualization, and report generation are often done manually, which is time-consuming and labor-intensive, and makes it difficult to detect abnormalities in real time or send prompt alerts. Furthermore, data visualization mainly requires the use of an internet browser, making it difficult to intuitively and quickly monitor air quality on a terminal. There is a need for a system that can resolve these issues and efficiently monitor and manage air quality in real time.

[0499] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0500] In this invention, the server includes means for detecting abnormalities in air quality data and notifying the user, means for classifying the air quality data based on a specified sensor identifier, means for aggregating the classified data and calculating statistics, and means for displaying the visualized data on a terminal application. This allows air quality abnormalities to be detected in real time and for the user to be promptly notified. Furthermore, data visualization can be performed intuitively on the terminal, enabling efficient air quality monitoring and management.

[0501] "Air quality data" is a collection of measurements that indicate the concentration of harmful substances and particulates in the air, as well as other information about air quality.

[0502] "Collection means" is a general term for devices and technologies, including sensors and their communication functions, that acquire air quality data and transmit it to a server.

[0503] "Means for storing data chronologically" refers to a technology that records collected air quality data sequentially over time and manages it centrally in a database.

[0504] "Visualization means" refers to technology that converts collected air quality data into a visual format such as graphs and charts and displays it in a way that users can intuitively understand.

[0505] A "report generation means" is a technology that automatically generates a formatted document by compiling statistics and trends based on collected and visualized air quality data.

[0506] The "means for periodic output" is a mechanism for saving or transmitting reports generated at automatically set time intervals.

[0507] "Means for detecting abnormalities and notifying users" refers to technology that automatically issues a warning when an abnormality exceeding a preset standard value is detected based on air quality data.

[0508] The "means for classifying based on designated sensor identifiers" is a mechanism for organizing, classifying, and efficiently managing data from multiple air quality sensors based on identifiers.

[0509] The "means for calculating statistical values" is a technique for calculating statistical information such as average values, maximum values, and minimum values ​​using the classified air quality data.

[0510] "Means for displaying on a device application" refers to a mechanism for displaying air quality data through an application installed on a device such as a smartphone or tablet.

[0511] A system for implementing the present invention efficiently and automatically collects, stores, visualizes, generates reports, and detects anomalies in air quality data. This system includes a sensor that collects air quality data, a server that stores and manages the data, and a terminal application that visualizes the data. The detailed configuration and operation are described below.

[0512] Data collection

[0513] The server provides an API endpoint that receives data sent from multiple air quality sensors. The air quality sensors periodically send JSON-formatted data, including concentration data of harmful substances and fine particles in the air. This data is received by the server via an API endpoint built using a web framework such as Flask and stored in a relational database such as SQLite.

[0514] Data visualization

[0515] Users access the system from devices such as smartphones and tablets to view visualized air quality data. Data in the database is retrieved from the server and visualized in the form of time series graphs using Python's Matplotlib library, etc. This visualization allows users to intuitively understand fluctuations in air quality.

[0516] Anomaly detection and notification

[0517] The server monitors the collected air quality data in real time and can detect abnormalities. If an abnormality is detected, the server sends a notification to the user's device. This notification can be in the form of a push notification or email, allowing the user to respond quickly.

[0518] Report Generation

[0519] The server automatically generates regular monthly reports. The reports summarize data for a specific period (e.g., one month) and include statistical information such as average, maximum, and minimum values. The reports are generated in PDF format and built using a PDF generation library such as FPDF, and are regularly saved and distributed. This allows users to regularly check the status of air quality and take necessary measures.

[0520] Specific examples

[0521] For example, if data is used from a sensor with ID "sensor_1" installed in an office, the server receives air quality data sent from "sensor_1" on a daily basis and stores it in a database. Users can visualize and check the data from "sensor_1" on their smartphones. Monthly reports are also automatically generated by the server and can be downloaded as PDF files. An anomaly detection function immediately notifies users if the air quality standard is exceeded.

[0522] Prompt Sentence Examples

[0523] Get the air quality data from "sensor_1" and generate a time series graph. Also, generate a PDF report based on the data from the same sensor.

[0524] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0525] Processing Steps

[0526] Step 1: Data collection

[0527] The server receives data from the air quality sensor. The sensor sends air quality data in JSON format at regular intervals. This data includes the sensor identifier and various air quality parameters. The server implements an API endpoint using the Flask framework to receive the sent JSON data. The received data is stored in a SQLite database.

[0528] Input: JSON data from air quality sensors

[0529] Output: Save the received data to the database

[0530] Step 2: Save data

[0531] The server stores the processed air quality data in a database in chronological order, including the sensor identifier, timestamp, and measurement value. The SQLite database allows for efficient management of air quality data.

[0532] Input: Received air quality data

[0533] Output: Data stored in chronological order

[0534] Step 3: Data visualization

[0535] When a user accesses the system from a terminal, the server retrieves the air quality data of the specified sensor from the stored database, then uses the Python Matplotlib library to generate a time series graph, which is then converted into a format that can be visually displayed on the terminal application.

[0536] Input: Air quality data retrieved from a database

[0537] Output: Visualized time series graph

[0538] Step 4: Anomaly detection and notification

[0539] The server monitors the collected air quality data and sends a notification to the user's device if an abnormality is detected. For example, if harmful substances exceeding the standard value are detected, the server will immediately send a push notification or email. This allows the user to understand the abnormality in air quality in real time and take prompt action.

[0540] Input: Air quality data being monitored

[0541] Output: Abnormality notification (push notification or email)

[0542] Step 5: Generate reports

[0543] The server aggregates data from the database for the relevant period to generate regular monthly reports. It calculates statistical information such as averages, maximums, and minimums based on the data, and generates PDF reports using the FPDF library. These reports are periodically saved or distributed to users' devices.

[0544] Input: Air quality data for the period of interest

[0545] Output: Report (PDF format)

[0546] Step 6: Print and distribute the report

[0547] The generated PDF report is sent from the server to the user's device, where the user can download the report and use it in monthly meetings, etc.

[0548] Input: Generated PDF report

[0549] Output: Sending a PDF report to the user's device

[0550] Examples:

[0551] As a concrete example, consider a scenario where a user wants to visualize and check air quality data from "sensor_1" on their smartphone. In this case, the server retrieves the data from "sensor_1" from the database, generates a time series graph using Matplotlib, and displays it on the device. If an abnormality is detected, the user is notified immediately. At the end of the month, an automatically generated PDF report is distributed to the user's device.

[0552] Prompt Sentence Examples

[0553] Get the air quality data from "sensor_1" and generate a time series graph. Also, generate a PDF report based on the data from the same sensor.

[0554] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0555] The system for implementing the present invention includes an emotion engine that recognizes and analyzes user emotions, in addition to collecting, storing, visualizing, and generating reports on air quality data. The configuration and operation of the system are described below.

[0556] Data collection

[0557] server

[0558] The server provides an API endpoint to receive air quality data sent from the air measurement device. The air measurement device periodically sends JSON-formatted data containing the sensor identifier and air quality data to the server. The server analyzes the received data and stores it in a database, along with the measurement date and time.

[0559] Data storage

[0560] server

[0561] The server parses the received JSON data and extracts the air quality data, sensor identifier, and date and time of reception. It then stores this data in an SQLite database. To ensure that the data is properly stored, it sends a completion notification after the database is updated.

[0562] Data Visualization

[0563] User

[0564] Users access the system from their terminals and check visualized air quality data. By specifying a specific sensor identifier, data is retrieved from the server and displayed in graph form using a visualization library such as Matplotlib. This allows the transition of air quality to be visualized.

[0565] Manipulating the Emotion Engine

[0566] User

[0567] When a user checks air quality data, the emotion engine analyzes the user's facial expressions and tone of voice to obtain emotional data. This emotional data is saved along with the air quality data. For example, the engine can detect emotional reactions such as "relief" or "anxiety" in response to changes in air quality perceived by the user.

[0568] Storing Emotional Data

[0569] server

[0570] The system receives user emotion data recognized by the emotion engine, associates it with air quality data, and stores it in a database for later analysis and report generation.

[0571] Report Generation

[0572] server

[0573] The server schedules the generation of monthly reports, which include statistical information based on the air quality data and user sentiment data from the past month. The reports are generated in PDF format and stored on the server.

[0574] Report Output

[0575] server

[0576] The server automatically saves the generated PDF report in a specified location and sends it via email or other means as needed. The report can also include the results of user sentiment analysis, making it possible to comprehensively evaluate the impact of air quality and the user's emotional response.

[0577] Viewing in an Internet browser

[0578] User

[0579] Users can view real-time air quality and emotion data through an internet browser. This includes visualizations in graphs and charts, as well as indicators and numerical values ​​that show the user's emotional state. For example, the worsening air quality can indicate an increase in the user's anxiety level.

[0580] This system not only enables efficient and automated air quality monitoring and reporting, but also enables comprehensive analysis that takes into account the user's emotional state, making it a useful tool for improving living and working environments in particular.

[0581] The processing flow will be explained below.

[0582] Step 1: Data collection

[0583] server

[0584] The server provides an API endpoint to receive air quality data sent from the air measurement device. The air measurement device periodically sends JSON-formatted data including the sensor identifier and air quality data to the server. The server receives this data and stores it in a database, along with the date and time.

[0585] Step 2: Data analysis

[0586] server

[0587] The server parses the received JSON data, extracts the sensor identifier, air quality data, and date and time, and stores them in an SQLite database. To ensure the data is stored properly, it sends a completion notification after the database is updated.

[0588] Step 3: Collecting Emotional Data

[0589] User

[0590] The user displays and checks the air quality data on the device. An emotion engine is activated, analyzing the user's facial expressions and voice in real time to detect the user's emotional state (e.g., relief, anxiety, excitement, etc.). The emotion engine generates emotion data and sends it to the server.

[0591] Step 4: Emotion data storage

[0592] server

[0593] The server receives the emotion data sent from the emotion engine, and associates the received emotion data with the air quality data and stores it in a database, thereby recording the user's emotional response to the specific air quality data.

[0594] Step 5: Data visualization

[0595] User

[0596] Users access the system from their devices and view visualized air quality and emotion data. The server retrieves the relevant data from the database based on the specified sensor identifier and generates a time series graph and emotion indicator. These can then be displayed using a visualization library such as Matplotlib to visualize the progress of air quality and the corresponding changes in emotion.

[0597] Step 6: Generate reports

[0598] server

[0599] The server schedules a task to generate reports periodically. For example, at the beginning of each month, it aggregates the air quality data and user emotion data from the past month and generates a PDF report containing air quality statistics and an analysis of the user's emotional response.

[0600] Step 7: Report Output

[0601] server

[0602] The server automatically saves the generated PDF report in a specified folder and sends it by email as needed. This allows it to be used as a reference for meetings such as safety and health committees. The output report includes the trend of air quality fluctuations and the user's emotional response to them.

[0603] Step 8: Browser display

[0604] User

[0605] Users access the system using an internet browser to view air quality and emotion data in real time. Visualized data includes time series graphs, statistical information, and indicators of the user's emotional state. For example, users can see at a glance whether their anxiety levels tend to increase as air quality worsens.

[0606] The above is a specific processing flow of the system of the present invention. This system not only monitors air quality but also makes it possible to comprehensively evaluate the environment, including the user's emotional response.

[0607] Example 2

[0608] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0609] Conventional air quality monitoring systems simply collect, store, visualize, and report on air quality data, but lack the ability to address user emotions. This makes it difficult to assess the impact of air quality fluctuations on users' emotions and behavior, making it difficult to comprehensively improve living and working environments.

[0610] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting air quality data, means for saving the collected air quality data in chronological order, means for visualizing the saved air quality data, means for generating a report based on the visualized data, means for periodically outputting the generated report, means for analyzing the user's emotions, and means for saving the analyzed emotion data in association with the air quality data. This enables a comprehensive evaluation that associates the air quality data with the user's emotion data, which is useful for improving living and working environments.

[0611] "Air quality data" refers to data that includes information on pollutants, chemical components, temperature, humidity, and so on in the air.

[0612] "Means of collection" refers to the function of acquiring air quality data using sensors and measuring devices and incorporating it into the system.

[0613] The "means for storing data in chronological order" is a function that records air quality data at regular time intervals and stores data from the past to the present.

[0614] "Visualization means" refers to the ability to display stored air quality data in the form of graphs, charts, indicators, etc., to clearly show trends and fluctuations in the data.

[0615] "Means for generating reports" refers to a function that creates reports summarizing statistical information and analytical results based on collected and stored air quality data.

[0616] The "means for periodic output" refers to a function for automatically outputting the generated report at regular intervals such as monthly or weekly, and providing it to the user.

[0617] The "means for analyzing user emotions" is a function that analyzes the user's facial expressions and tone of voice to obtain emotional data such as relief, anxiety, surprise, etc.

[0618] The "means for storing analyzed emotion data in association with air quality data" is a function that stores acquired emotion data together with the corresponding air quality data, enabling the association between them to be analyzed.

[0619] As a specific embodiment for carrying out the invention, the configuration and operation of the following system will be described. This system not only collects, stores, visualizes, and generates reports on air quality data, but also includes an emotion engine that recognizes and analyzes user emotions.

[0620] Hardware and software used

[0621] Server: Receives, analyzes, stores, and generates reports on air quality and emotion data.

[0622] Air measurement device: Equipped with sensors that measure pollutants and chemical components in the air and send the data to a server.

[0623] Terminal: A device through which a user accesses the system and checks air quality and emotion data. Examples include a PC or smartphone.

[0624] Emotion engine: Software that analyzes the user's facial expressions and tone of voice to obtain emotional data. It uses the camera and microphone.

[0625] Database: Used to store data, such as SQLite.

[0626] Visualization libraries: Used to visualize data, such as Matplotlib.

[0627] Data collection

[0628] The server provides an API endpoint to receive air quality data sent from the air measurement devices. The air measurement devices periodically send JSON-formatted data containing the sensor identifier and air quality data to the server. Specifically, the server exposes an endpoint called " / api / airquality" and automatically starts analyzing the data as it arrives.

[0629] Data storage

[0630] The received JSON data is parsed and the sensor identifier of the air measuring device, the air quality data, and the date and time of receipt are extracted. This data is then stored in an SQLite database. When the data has been saved, the server logs "New data has been added to the database." For example, the server saves the data "sensor_001", "35μg / m³", "2023-10-01 12:00:00" to SQLite.

[0631] Data Visualization

[0632] Users can log in to the system from a terminal and view visualized air quality data. By specifying a specific sensor identifier, data is retrieved from the server and displayed in graph form using a visualization library such as Matplotlib. For example, if a user selects "sensor_001" and clicks the "Graph Display" button, data for the past week will be displayed as a graph.

[0633] Manipulating the Emotion Engine

[0634] While the user is checking the air quality data, the emotion engine begins to operate. The emotion engine analyzes the user's facial expressions and tone of voice through the camera and microphone and sends emotional data to the server. For example, while the user is checking the data, the camera captures their facial expressions, and if the emotion "anxiety" is detected, the data "anxiety" is sent to the server.

[0635] Storing Emotional Data

[0636] The server receives the emotion data sent from the emotion engine, associates it with the air quality data, and stores it in an SQLite database. For example, the server stores data such as "2023-10-01 12:00:00: Anxiety" along with the air quality data.

[0637] Report Generation

[0638] The server sets a schedule for report generation at the end of each month. It aggregates air quality data and emotion data from the database for the past month and automatically generates a report in PDF format containing statistical information. Specifically, the server generates a file named "September_2023_Report.pdf" and saves it in the specified directory.

[0639] Report Output

[0640] The server saves the generated PDF report in a specified location and notifies the user by email if necessary. Depending on the user's settings, the report can also include the results of the emotion data analysis. For example, the server can attach the generated PDF report to an email and send it to a specified email address.

[0641] Viewing in an Internet browser

[0642] Users can access the system with an internet browser and check air quality data and emotion data in real time. For example, when a user accesses the system with a browser, "real-time air quality data" and an "emotional state indicator" are displayed on the screen. When air quality deteriorates, the emotion indicator can show "anxiety."

[0643] Prompt Sentence Examples

[0644] Example prompts to enter into the generative AI model:

[0645] "Write a program that correlates air quality data with user sentiment data to generate a statistical report for the past month."

[0646] The system not only enables efficient and automated air quality monitoring and reporting, but also enables comprehensive analysis that takes into account the user's emotional state, helping to improve living and working environments.

[0647] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0648] Step 1: Data collection

[0649] The server provides an API endpoint for receiving data in JSON format. It periodically receives JSON-formatted data sent from air measurement devices, including sensor identifiers and air quality data. It analyzes the received data and temporarily stores the sensor identifiers, air quality data, and reception date and time.

[0650] Input: Air quality data in JSON format from an air measurement device

[0651] Processing: Parse the data to extract the sensor identifier, air quality data, and date and time of receipt.

[0652] Output: Extracted data stored in temporary storage

[0653] Specific operation: The server exposes an endpoint called " / api / airquality" and automatically starts analyzing data as it arrives.

[0654] Step 2: Save data

[0655] The server reads the temporarily saved data and records it in the SQLite database. When saving is complete, it logs "New data has been added to the database."

[0656] Input: Temporarily stored sensor identifier, air quality data, date and time of receipt

[0657] Process: Save data to SQLite database

[0658] Output: Notification of database update completion

[0659] Specific operation: The server saves the data "sensor_001", "35μg / m³", and "2023-10-01 12:00:00" to SQLite.

[0660] Step 3: Data visualization

[0661] A user logs into the system from a terminal and sends a visualization request to the server specifying a specific sensor identifier. The server retrieves the necessary data from the database and sends it to the terminal, which then generates a graph using a visualization library such as Matplotlib.

[0662] Input: Visualization request from user (sensor identifier)

[0663] Processing: Retrieve the relevant data from the database and send it to the device

[0664] Output: Display the graph on the terminal

[0665] Specific operation: When the user selects "sensor_001" and clicks the "Graph display" button, the data for the past week will be displayed as a graph.

[0666] Step 4: Emotion Engine Analysis

[0667] While the user is checking the air quality data, the emotion engine analyzes the user's facial expressions and tone of voice, and transmits the analyzed emotion data to the server.

[0668] Input: User's facial expressions and tone of voice (real-time data)

[0669] Processing: The emotion engine analyzes the data and generates emotion data

[0670] Output: Send emotion data to the server

[0671] Specific operation: While the user is checking the data, the camera captures their facial expressions, and if the emotion "anxiety" is detected, the data "anxiety" is sent to the server.

[0672] Step 5: Storing emotion data

[0673] The server receives the emotion data sent from the emotion engine, associates it with the air quality data, and stores it in an SQLite database.

[0674] Input: Emotion data sent from the emotion engine

[0675] Processing: Emotion data is associated with air quality data and stored in a database

[0676] Output: Emotion data stored in a database

[0677] What happens: The server stores data such as "2023-10-01 12:00:00: Anxiety" along with air quality data.

[0678] Step 6: Generate reports

[0679] The server aggregates air quality data and emotion data for the past month at regularly scheduled times, and generates a PDF report based on the aggregated results.

[0680] Input: Air quality data and sentiment data from a database

[0681] Processing: Aggregate data and generate PDF report

[0682] Output: Report in PDF format

[0683] Specific behavior: The server generates a file named "September_2023_Report.pdf" and saves it in the specified directory.

[0684] Step 7: Report Output

[0685] The server saves the generated PDF report in a specified location and notifies the user by email if necessary. Depending on the user's settings, the report can also include the results of the emotion data analysis.

[0686] Input: Generated PDF report

[0687] Action: Print and send report

[0688] Output: Saved PDF report and notification of successful submission

[0689] Specific behavior: The server generates a PDF report and sends it to the specified email address as an attachment.

[0690] Step 8: View in your Internet browser

[0691] Users access the system through an internet browser and view real-time air quality and sentiment data, which is visualized using graphs and indicators.

[0692] Input: Browser access request from user

[0693] Processing: Retrieving real-time data from the database and displaying it in a visual format

[0694] Output: Visualized data displayed in a browser

[0695] Specific operation: A user accesses the system through a browser and the screen displays "real-time air quality data" and an "emotional state indicator." For example, when the air quality deteriorates, the indicator displays "anxiety."

[0696] (Application example 2)

[0697] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0698] While conventional air quality management systems can collect, visualize, and generate reports on air quality data, it is difficult to directly grasp the impact of air quality fluctuations on users. Furthermore, there is a lack of means to monitor in real time the emotional state of workers in response to deteriorating air quality at the workplace, which creates challenges in ensuring safety and improving work efficiency. To solve these challenges, there is a need for integrated management of air quality data and users' emotional state, and a comprehensive assessment of the impact of air quality.

[0699] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0700] In this invention, the server includes means for collecting air quality data, means for saving the air quality data in chronological order, means for visualizing the saved air quality data, means for generating a report based on the visualized data, means for periodically outputting the generated report, means for collecting emotion data using an emotion engine that recognizes and analyzes user emotion data, means for saving the emotion data together with the air quality data, and means for visualizing the emotion data in association with the air quality data. This makes it possible to grasp in real time the impact of fluctuations in air quality on workers in factories and work sites, ensuring safety and improving work efficiency.

[0701] "Air quality data" refers to data that includes indicators such as the concentration of harmful substances and particulates in the air, temperature, and humidity.

[0702] "Means for collection" refers to methods and equipment for acquiring air quality data and emotion data using sensors and measuring devices.

[0703] The "means for storing in chronological order" refers to a method and system for storing acquired data in an electronic recording medium in a format arranged in chronological order.

[0704] "Visualization means" are methods and tools that display collected data in a user-friendly manner as graphs, charts, or diagrams.

[0705] A "report generating means" is a method or device that analyzes collected data and produces a report summarizing statistics and trends.

[0706] A "periodic output means" is a method or system that automatically generates reports or data at set intervals and notifies or transmits them to users.

[0707] An "emotion engine" is software or hardware that analyzes a user's facial expressions, tone of voice, etc. to recognize their emotional state and record it as data.

[0708] "Emotion data" is data that includes numerical values ​​and categories that represent the user's emotional state.

[0709] A "connected visualization" is a method and tool that connects air quality data and emotion data and displays them together.

[0710] To implement this invention, it is necessary to build a system that utilizes an air measurement device, an emotion recognition engine, a server, and a visualization tool.

[0711] First, the air measurement device periodically collects air quality data and sends it to the server. The server analyzes the data received from the air measurement device and stores it in a database in chronological order. Specifically, the data is stored in a format that includes the sensor identifier, air quality data, and the date and time of reception.

[0712] Next, users collect emotional data using cameras and microphones installed on their devices or factory robots. An emotion recognition engine analyzes this data and quantifies or categorizes the user's emotional state.

[0713] The server stores these emotion data together with the air quality data, which are then integrated and visualized using a visualization tool (e.g., Matplotlib) to display the air quality data and the user's emotion data in graphs and charts.

[0714] The server also periodically generates reports and saves statistical information, including air quality data and emotion data, in PDF format. These reports are periodically notified or sent to the user.

[0715] For example, if the air quality in a factory deteriorates, an emotion recognition engine may detect high levels of anxiety among workers, allowing managers to immediately decide to activate air purifiers or halt work processes.

[0716] Example prompt sentence:

[0717] "Please suggest what to do if the air quality in the factory deteriorates and workers are feeling uneasy."

[0718] This system will enable monitoring and management of air quality in factories and workplaces, as well as real-time assessment of workers' emotional state, which is expected to ensure safety and improve work efficiency.

[0719] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0720] Step 1:

[0721] Air quality data collection

[0722] The server receives air quality data periodically sent from the air measurement device. The input is the air quality data sent from the air measurement device and the sensor identifier. The server receives this data and parses it in JSON format. The data obtained as a result of the analysis is the sensor identifier, air quality data, and reception date and time.

[0723] Step 2:

[0724] Air quality data storage

[0725] The server stores the air quality data received and analyzed in step 1 in chronological order. The input is the sensor identifier, air quality data, and reception date and time obtained in step 1. The server stores this data in an SQLite database and confirms that the database update is complete.

[0726] Step 3:

[0727] Collecting Emotional Data

[0728] Users collect emotional data through cameras and microphones installed on terminals or factory robots. The input is facial expression data captured by the camera and voice data recorded by the microphone. The emotion engine analyzes this data and quantifies or categorizes the user's emotional state. The output is emotional data.

[0729] Step 4:

[0730] Storing Emotional Data

[0731] The server stores the emotion data obtained in step 3 together with the air quality data. The inputs are the sensor identifier, emotion data, and the date and time of reception. The server stores these data in the database and confirms that the database update is complete. The output is the emotion data and air quality data stored in the database.

[0732] Step 5:

[0733] Data visualization

[0734] The user accesses the server from a terminal and checks visualized air quality data and emotion data. The input is a specific sensor identifier specified by the user, and the server retrieves the air quality data and emotion data from the database based on this sensor identifier. The retrieved data is displayed in graph form using a visualization library such as Matplotlib. The output is the visualized graph.

[0735] Step 6:

[0736] Report Generation

[0737] The server aggregates air quality data and emotion data on a monthly basis and generates a report containing statistical information. The input is the air quality data and emotion data from the past month. The server analyzes this data and creates a report in PDF format. The output is the generated PDF report.

[0738] Step 7:

[0739] Sending a report

[0740] The server saves the report generated in step 6 in the specified location and sends it to the user by email, etc. as needed. The input is the generated PDF report, which the server saves in the specified location and notifies the user. The output is the sent PDF report.

[0741] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0742] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0743] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0744] [Third embodiment]

[0745] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0746] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0747] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0748] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0749] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0750] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0751] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0752] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0753] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0754] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0755] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0756] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0757] The construction and operation of a system for implementing the present invention, which automatically collects, stores, visualizes, and reports on air quality data, is described below.

[0758] Data collection

[0759] server

[0760] The server provides an API endpoint for receiving air quality data sent from the air measurement device. The air measurement device periodically sends JSON data containing the sensor identifier and air quality data. The server receives this data and stores it in a database.

[0761] The server implements API endpoints using a web framework such as Flask, and a relational database such as SQLite is used to efficiently store and manage the collected data.

[0762] Data visualization

[0763] User

[0764] Users access the system from their terminals and check visualized air quality data. The data in the database is retrieved from the server and converted into visualization formats such as time series graphs using Python's Matplotlib library.

[0765] For example, if you want to visualize data from a sensor with ID "sensor_1," you can retrieve all data related to "sensor_1" from the database and plot it along a time axis, allowing you to visually confirm the progress of air quality.

[0766] Generate reports

[0767] server

[0768] The server schedules the generation of periodic reports every month. The reports summarize data for a specific period (e.g., one month) and include statistical information such as averages, maximums, and minimums. The reports are generated and saved in PDF format.

[0769] The server uses a PDF generation library such as FPDF to automatically create a report header, chapter titles for each sensor, and the body of the report. The report is then submitted to the health and safety committee and used to consider measures to improve air quality.

[0770] Specific examples

[0771] For example, data from a sensor with ID "sensor_A" installed in an office can be used. The server receives air quality data sent from "sensor_A" on a daily basis and stores it in a database. At the end of the month, users access the system from their terminals and check graphs of the monthly data. The server automatically generates a monthly report, saves it as a PDF file, and uses it at the next health and safety committee meeting.

[0772] The system described above provides efficient and automated air quality monitoring and reporting, allowing users to access and analyze important data hassle-free, making it extremely useful for continuously monitoring the air quality of a specific location.

[0773] The processing flow will be explained below.

[0774] Step 1: Data collection

[0775] server

[0776] The server provides an API endpoint for receiving data from the air quality measurement device. The air quality measurement device periodically sends JSON-formatted data containing the sensor identifier and air quality data to the server. The server receives this data, extracts it, and stores it in a database. The measurement date and time are also stored in the database.

[0777] Step 2: Save data

[0778] server

[0779] The server parses the received JSON data, extracts the air quality data, the sensor identifier of the air quality monitor, and the date and time of receipt, creates and executes SQL instructions to store this data in an SQLite database, and then completes the process after confirming that the database has been updated appropriately.

[0780] Step 3: Data Acquisition

[0781] User

[0782] When a user runs a visualization program from their device, they specify a specific sensor identifier. The server executes an SQL query to retrieve the data corresponding to this sensor identifier from the database. The retrieved data is then prepared as time-series data.

[0783] Step 4: Data visualization

[0784] User

[0785] After acquiring the data, users can use a visualization library such as Matplotlib to display the data in graph form. The visualization program running on the user's device generates and displays time series graphs and histograms using the acquired data, allowing users to visually confirm the progress of air quality.

[0786] Step 5: Generate reports

[0787] server

[0788] The server sets up a task schedule to automatically generate monthly reports. At the scheduled time (e.g., the beginning of the month), the server runs the report generation program. This program retrieves air quality data from the database for the past month and compiles the results into a report. The report is generated in PDF format and saved on the server.

[0789] Step 6: Report output

[0790] server

[0791] The server automatically saves the generated PDF report to a specified location. Additional output options, such as emailing the report, can be configured as needed. This allows monthly reports to be automatically generated and submitted to the health and safety committee, etc.

[0792] In this way, a series of processes from collecting air quality data to storing, visualizing, generating and outputting reports are carried out automatically, creating a system that allows users to efficiently monitor and report on air quality.

[0793] Example 1

[0794] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0795] Monitoring and improving air quality is becoming increasingly important in modern society. However, conventional air quality monitoring systems require manual data collection, storage, visualization, and report generation, which is time-consuming and inefficient. Furthermore, data is scattered, making integrated management difficult. For this reason, there is a demand for a system that can automate and consistently manage air quality data, from collection to visualization and report generation.

[0796] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0797] In this invention, the server includes means for collecting air quality data, means for saving the collected air quality data in chronological order, means for acquiring the saved air quality data, means for visualizing the acquired air quality data, means for generating a chart for visualization, means for generating a report based on the visualized data, and means for periodically outputting the generated report, thereby enabling consistent collection, management, visualization, and report generation of air quality data.

[0798] "Air quality data" is data that numerically represents the concentration and amount of various substances and pollutants in the air (e.g., PM2.5, carbon dioxide, carbon monoxide, ozone, etc.).

[0799] "Means of collection" refers to the function of acquiring air quality data using sensors such as air measuring devices and sending it to a server.

[0800] "Means for storing data in chronological order" refers to a function for recording and accumulating air quality data along with date and time information in a database or other storage device.

[0801] The "means of acquisition" is a function that extracts air quality data stored in the database based on specified conditions and converts it into a reusable format within the server.

[0802] "Visualization means" refers to the function of converting acquired air quality data into a visual format such as a graph or chart, and displaying it in a way that is easily understandable to the user.

[0803] The "means for generating charts" is a function for drawing charts such as line graphs and bar graphs based on visualized data.

[0804] A "means for generating reports" is a function that compiles visualized data and statistical information and creates a document in a specific format (e.g., a PDF file).

[0805] The "means for periodic output" is a function that automatically creates a report at a certain period and saves it as an electronic file or prints it.

[0806] A "classification means" is a function that divides collected air quality data into categories based on specific sensor identifiers and location information.

[0807] The "aggregation means" is a function that performs statistical processing on classified data and calculates statistical information such as average values, maximum values, and minimum values.

[0808] The "means for displaying on a browser" is a function for displaying visualized data on a user interface through an internet browser.

[0809] The system of the present invention includes means for automatically collecting, storing, visualizing, and generating reports on air quality data, specific embodiments of which are described in detail below.

[0810] Data collection

[0811] server

[0812] The server provides an API endpoint for receiving air quality data sent from the air measurement devices. The air measurement devices periodically send JSON data containing the sensor identifier and air quality data to the server. The server implements the API endpoint using a web framework such as Flask and stores the received data in a database.

[0813] The server parses the received JSON data and extracts the necessary data (sensor identifier, date and time, air quality data). It then efficiently stores and manages the data using a relational database such as SQLite. This process ensures that all data sent from the air measuring devices is collected in a consistent manner.

[0814] Data visualization

[0815] User

[0816] Users access the system from their terminals and check the visualization results of the stored air quality data. The server retrieves the necessary data from the SQLite database in response to user requests and visualizes it using the Python Matplotlib library.

[0817] Specifically, data for the sensor ID and period specified by the user is displayed in the form of a time series graph, etc. This allows the user to visually check the progress of air quality.

[0818] Generate reports

[0819] server

[0820] The server generates air quality reports periodically every month. The reports include aggregated data (average, maximum, minimum, and other statistical information) for a specific period (e.g., one month). The reports are generated and saved in PDF format using a PDF generation library such as FPDF.

[0821] The server uses a Python scheduling library (e.g., APScheduler) to set up a process to automatically generate the report every month, allowing users to access their monthly air quality reports without any hassle.

[0822] Examples and prompts

[0823] For example, consider a case where air quality is monitored and managed based on data sent from a sensor ID "sensor_A" installed in an office. The server periodically receives air quality data from "sensor_A" and stores it in a database. At the end of the month, users can access the system from their terminals and check a graph of the monthly air quality data. Furthermore, the server automatically generates a monthly report and saves it as a PDF file, which can be used at the next health and safety committee meeting.

[0824] Example prompt sentence:

[0825] "Please explain the program process of the system that automates the collection, storage, visualization, and report generation of air quality data. Please specify the names of the specific hardware and software, and provide a detailed description of the data processing and calculations that are performed. Also, please include the following example: Using data from a sensor with ID "sensor_A" installed in an office."

[0826] This embodiment provides efficient, automated air quality monitoring and reporting, allowing users to access and analyze important data. This system is highly effective for continuously monitoring air quality in a specific location.

[0827] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0828] Step 1: Receiving data

[0829] server

[0830] The server provides an API endpoint to receive data sent from the air quality measurement device. As input, it receives JSON-formatted data from the air quality measurement device. The server implements an endpoint called / api / data using the Flask framework. The received data has elements such as a sensor identifier, date and time, and air quality data.

[0831] Specifically, the server receives an HTTP POST request and extracts JSON data from the request body, outputting the extracted sensor identifier, date and time, and air quality data.

[0832] Step 2: Save data

[0833] server

[0834] The server stores the received air quality data in an SQLite database. It uses the sensor identifier, date and time, and air quality data as input. It first opens a database connection and then generates the appropriate SQL statements to insert the data.

[0835] Specifically, it inserts data into the database using an SQL INSERT statement, and outputs a success status indicating that the data was successfully saved.

[0836] Step 3: Data Acquisition

[0837] server

[0838] The server retrieves the required data from the database based on the user request. It receives the sensor ID and the period as input. It executes an SQL query to the database to extract the relevant data.

[0839] Specifically, the SELECT statement is used to extract data related to the specified sensor ID and period from the database, and the output is a list of the acquired air quality data.

[0840] Step 4: Data visualization

[0841] server

[0842] The server visualizes the retrieved data, using the extracted air quality data as input and plotting these data on time series graphs using Python's Matplotlib library.

[0843] Specifically, the server plots the data on the x-axis (date and time) and y-axis (air quality data) and saves the visualization as an image file. The output is the generated graph image.

[0844] Step 5: Generate reports

[0845] server

[0846] The server generates air quality reports periodically. As input, it receives data for a specific period (e.g., one month). It aggregates the data and calculates statistics (average, maximum, minimum).

[0847] Specifically, it uses the FPDF library to compose a report in PDF format, embeds the required statistics and visualizations in the report, and the output is the generated PDF report.

[0848] Step 6: Report output

[0849] server

[0850] The server periodically saves or sends the generated reports. It receives the generated PDF reports as input. It schedules the report generation every month using the scheduling library mentioned above (e.g., APScheduler).

[0851] Specifically, the generated report is saved in a specified folder and sent as needed via email, etc. The output is a saved PDF report file.

[0852] Step 7: View the data visualization

[0853] User

[0854] The user accesses the system from a terminal and checks the visualized air quality data. As input, the system receives the sensor ID and period specified by the user. The server retrieves the visualized data from the database and displays it on the network browser.

[0855] Specifically, the server displays the acquired data in the browser using HTML and JavaScript, and the output is visualized air quality data displayed on the browser.

[0856] The above is the main processing flow of this system.

[0857] (Application example 1)

[0858] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0859] In conventional air quality monitoring systems, data collection, visualization, and report generation are often done manually, which is time-consuming and labor-intensive, and makes it difficult to detect abnormalities in real time or send prompt alerts. Furthermore, data visualization mainly requires the use of an internet browser, making it difficult to intuitively and quickly monitor air quality on a terminal. There is a need for a system that can resolve these issues and efficiently monitor and manage air quality in real time.

[0860] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0861] In this invention, the server includes means for detecting abnormalities in air quality data and notifying the user, means for classifying the air quality data based on a specified sensor identifier, means for aggregating the classified data and calculating statistics, and means for displaying the visualized data on a terminal application. This allows air quality abnormalities to be detected in real time and for the user to be promptly notified. Furthermore, data visualization can be performed intuitively on the terminal, enabling efficient air quality monitoring and management.

[0862] "Air quality data" is a collection of measurements that indicate the concentration of harmful substances and particulates in the air, as well as other information about air quality.

[0863] "Collection means" is a general term for devices and technologies, including sensors and their communication functions, that acquire air quality data and transmit it to a server.

[0864] "Means for storing data chronologically" refers to a technology that records collected air quality data sequentially over time and manages it centrally in a database.

[0865] "Visualization means" refers to technology that converts collected air quality data into a visual format such as graphs and charts and displays it in a way that users can intuitively understand.

[0866] A "report generation means" is a technology that automatically generates a formatted document by compiling statistics and trends based on collected and visualized air quality data.

[0867] The "means for periodic output" is a mechanism for saving or transmitting reports generated at automatically set time intervals.

[0868] "Means for detecting abnormalities and notifying users" refers to technology that automatically issues a warning when an abnormality exceeding a preset standard value is detected based on air quality data.

[0869] The "means for classifying based on designated sensor identifiers" is a mechanism for organizing, classifying, and efficiently managing data from multiple air quality sensors based on identifiers.

[0870] The "means for calculating statistical values" is a technique for calculating statistical information such as average values, maximum values, and minimum values ​​using the classified air quality data.

[0871] "Means for displaying on a device application" refers to a mechanism for displaying air quality data through an application installed on a device such as a smartphone or tablet.

[0872] A system for implementing the present invention efficiently and automatically collects, stores, visualizes, generates reports, and detects anomalies in air quality data. This system includes a sensor that collects air quality data, a server that stores and manages the data, and a terminal application that visualizes the data. The detailed configuration and operation are described below.

[0873] Data collection

[0874] The server provides an API endpoint that receives data sent from multiple air quality sensors. The air quality sensors periodically send JSON-formatted data, including concentration data of harmful substances and fine particles in the air. This data is received by the server via an API endpoint built using a web framework such as Flask and stored in a relational database such as SQLite.

[0875] Data visualization

[0876] Users access the system from devices such as smartphones and tablets to view visualized air quality data. Data in the database is retrieved from the server and visualized in the form of time series graphs using Python's Matplotlib library, etc. This visualization allows users to intuitively understand fluctuations in air quality.

[0877] Anomaly detection and notification

[0878] The server monitors the collected air quality data in real time and can detect abnormalities. If an abnormality is detected, the server sends a notification to the user's device. This notification can be in the form of a push notification or email, allowing the user to respond quickly.

[0879] Report Generation

[0880] The server automatically generates regular monthly reports. The reports summarize data for a specific period (e.g., one month) and include statistical information such as average, maximum, and minimum values. The reports are generated in PDF format and built using a PDF generation library such as FPDF, and are regularly saved and distributed. This allows users to regularly check the status of air quality and take necessary measures.

[0881] Specific examples

[0882] For example, if data is used from a sensor with ID "sensor_1" installed in an office, the server receives air quality data sent from "sensor_1" on a daily basis and stores it in a database. Users can visualize and check the data from "sensor_1" on their smartphones. Monthly reports are also automatically generated by the server and can be downloaded as PDF files. An anomaly detection function immediately notifies users if the air quality standard is exceeded.

[0883] Prompt Sentence Examples

[0884] Get the air quality data from "sensor_1" and generate a time series graph. Also, generate a PDF report based on the data from the same sensor.

[0885] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0886] Processing Steps

[0887] Step 1: Data collection

[0888] The server receives data from the air quality sensor. The sensor sends air quality data in JSON format at regular intervals. This data includes the sensor identifier and various air quality parameters. The server implements an API endpoint using the Flask framework to receive the sent JSON data. The received data is stored in a SQLite database.

[0889] Input: JSON data from air quality sensors

[0890] Output: Save the received data to the database

[0891] Step 2: Save data

[0892] The server stores the processed air quality data in a database in chronological order, including the sensor identifier, timestamp, and measurement value. The SQLite database allows for efficient management of air quality data.

[0893] Input: Received air quality data

[0894] Output: Data stored in chronological order

[0895] Step 3: Data visualization

[0896] When a user accesses the system from a terminal, the server retrieves the air quality data of the specified sensor from the stored database, then uses the Python Matplotlib library to generate a time series graph, which is then converted into a format that can be visually displayed on the terminal application.

[0897] Input: Air quality data retrieved from a database

[0898] Output: Visualized time series graph

[0899] Step 4: Anomaly detection and notification

[0900] The server monitors the collected air quality data and sends a notification to the user's device if an abnormality is detected. For example, if harmful substances exceeding the standard value are detected, the server will immediately send a push notification or email. This allows the user to understand the abnormality in air quality in real time and take prompt action.

[0901] Input: Air quality data being monitored

[0902] Output: Abnormality notification (push notification or email)

[0903] Step 5: Generate reports

[0904] The server aggregates data from the database for the relevant period to generate regular monthly reports. It calculates statistical information such as averages, maximums, and minimums based on the data, and generates PDF reports using the FPDF library. These reports are periodically saved or distributed to users' devices.

[0905] Input: Air quality data for the period of interest

[0906] Output: Report (PDF format)

[0907] Step 6: Print and distribute the report

[0908] The generated PDF report is sent from the server to the user's device, where the user can download the report and use it in monthly meetings, etc.

[0909] Input: Generated PDF report

[0910] Output: Sending a PDF report to the user's device

[0911] Examples:

[0912] As a concrete example, consider a scenario where a user wants to visualize and check air quality data from "sensor_1" on their smartphone. In this case, the server retrieves the data from "sensor_1" from the database, generates a time series graph using Matplotlib, and displays it on the device. If an abnormality is detected, the user is notified immediately. At the end of the month, an automatically generated PDF report is distributed to the user's device.

[0913] Prompt Sentence Examples

[0914] Get the air quality data from "sensor_1" and generate a time series graph. Also, generate a PDF report based on the data from the same sensor.

[0915] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0916] The system for implementing the present invention includes an emotion engine that recognizes and analyzes user emotions, in addition to collecting, storing, visualizing, and generating reports on air quality data. The configuration and operation of the system are described below.

[0917] Data collection

[0918] server

[0919] The server provides an API endpoint to receive air quality data sent from the air measurement device. The air measurement device periodically sends JSON-formatted data containing the sensor identifier and air quality data to the server. The server analyzes the received data and stores it in a database, along with the measurement date and time.

[0920] Data storage

[0921] server

[0922] The server parses the received JSON data and extracts the air quality data, sensor identifier, and date and time of reception. It then stores this data in an SQLite database. To ensure that the data is properly stored, it sends a completion notification after the database is updated.

[0923] Data Visualization

[0924] User

[0925] Users access the system from their terminals and check visualized air quality data. By specifying a specific sensor identifier, data is retrieved from the server and displayed in graph form using a visualization library such as Matplotlib. This allows the transition of air quality to be visualized.

[0926] Manipulating the Emotion Engine

[0927] User

[0928] When a user checks air quality data, the emotion engine analyzes the user's facial expressions and tone of voice to obtain emotional data. This emotional data is saved along with the air quality data. For example, the engine can detect emotional reactions such as "relief" or "anxiety" in response to changes in air quality perceived by the user.

[0929] Storing Emotional Data

[0930] server

[0931] The system receives user emotion data recognized by the emotion engine, associates it with air quality data, and stores it in a database for later analysis and report generation.

[0932] Report Generation

[0933] server

[0934] The server schedules the generation of monthly reports, which include statistical information based on the air quality data and user sentiment data from the past month. The reports are generated in PDF format and stored on the server.

[0935] Report Output

[0936] server

[0937] The server automatically saves the generated PDF report in a specified location and sends it via email or other means as needed. The report can also include the results of user sentiment analysis, making it possible to comprehensively evaluate the impact of air quality and the user's emotional response.

[0938] Viewing in an Internet browser

[0939] User

[0940] Users can view real-time air quality and emotion data through an internet browser. This includes visualizations in graphs and charts, as well as indicators and numerical values ​​that show the user's emotional state. For example, the worsening air quality can indicate an increase in the user's anxiety level.

[0941] This system not only enables efficient and automated air quality monitoring and reporting, but also enables comprehensive analysis that takes into account the user's emotional state, making it a useful tool for improving living and working environments in particular.

[0942] The processing flow will be explained below.

[0943] Step 1: Data collection

[0944] server

[0945] The server provides an API endpoint to receive air quality data sent from the air measurement device. The air measurement device periodically sends JSON-formatted data including the sensor identifier and air quality data to the server. The server receives this data and stores it in a database, along with the date and time.

[0946] Step 2: Data analysis

[0947] server

[0948] The server parses the received JSON data, extracts the sensor identifier, air quality data, and date and time, and stores them in an SQLite database. To ensure the data is stored properly, it sends a completion notification after the database is updated.

[0949] Step 3: Collecting Emotional Data

[0950] User

[0951] The user displays and checks the air quality data on the device. An emotion engine is activated, analyzing the user's facial expressions and voice in real time to detect the user's emotional state (e.g., relief, anxiety, excitement, etc.). The emotion engine generates emotion data and sends it to the server.

[0952] Step 4: Emotion data storage

[0953] server

[0954] The server receives the emotion data sent from the emotion engine, and associates the received emotion data with the air quality data and stores it in a database, thereby recording the user's emotional response to the specific air quality data.

[0955] Step 5: Data visualization

[0956] User

[0957] Users access the system from their devices and view visualized air quality and emotion data. The server retrieves the relevant data from the database based on the specified sensor identifier and generates a time series graph and emotion indicator. These can then be displayed using a visualization library such as Matplotlib to visualize the progress of air quality and the corresponding changes in emotion.

[0958] Step 6: Generate reports

[0959] server

[0960] The server schedules a task to generate reports periodically. For example, at the beginning of each month, it aggregates the air quality data and user emotion data from the past month and generates a PDF report containing air quality statistics and an analysis of the user's emotional response.

[0961] Step 7: Report Output

[0962] server

[0963] The server automatically saves the generated PDF report in a specified folder and sends it by email as needed. This allows it to be used as a reference for meetings such as safety and health committees. The output report includes the trend of air quality fluctuations and the user's emotional response to them.

[0964] Step 8: Browser display

[0965] User

[0966] Users access the system using an internet browser to view air quality and emotion data in real time. Visualized data includes time series graphs, statistical information, and indicators of the user's emotional state. For example, users can see at a glance whether their anxiety levels tend to increase as air quality worsens.

[0967] The above is a specific processing flow of the system of the present invention. This system not only monitors air quality but also makes it possible to comprehensively evaluate the environment, including the user's emotional response.

[0968] Example 2

[0969] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0970] Conventional air quality monitoring systems simply collect, store, visualize, and report on air quality data, but lack the ability to address user emotions. This makes it difficult to assess the impact of air quality fluctuations on users' emotions and behavior, making it difficult to comprehensively improve living and working environments.

[0971] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting air quality data, means for saving the collected air quality data in chronological order, means for visualizing the saved air quality data, means for generating a report based on the visualized data, means for periodically outputting the generated report, means for analyzing the user's emotions, and means for saving the analyzed emotion data in association with the air quality data. This enables a comprehensive evaluation that associates the air quality data with the user's emotion data, which is useful for improving living and working environments.

[0972] "Air quality data" refers to data that includes information on pollutants, chemical components, temperature, humidity, and so on in the air.

[0973] "Means of collection" refers to the function of acquiring air quality data using sensors and measuring devices and incorporating it into the system.

[0974] The "means for storing data in chronological order" is a function that records air quality data at regular time intervals and stores data from the past to the present.

[0975] "Visualization means" refers to the ability to display stored air quality data in the form of graphs, charts, indicators, etc., to clearly show trends and fluctuations in the data.

[0976] "Means for generating reports" refers to a function that creates reports summarizing statistical information and analytical results based on collected and stored air quality data.

[0977] The "means for periodic output" refers to a function for automatically outputting the generated report at regular intervals such as monthly or weekly, and providing it to the user.

[0978] The "means for analyzing user emotions" is a function that analyzes the user's facial expressions and tone of voice to obtain emotional data such as relief, anxiety, surprise, etc.

[0979] The "means for storing analyzed emotion data in association with air quality data" is a function that stores acquired emotion data together with the corresponding air quality data, enabling the association between them to be analyzed.

[0980] As a specific embodiment for carrying out the invention, the configuration and operation of the following system will be described. This system not only collects, stores, visualizes, and generates reports on air quality data, but also includes an emotion engine that recognizes and analyzes user emotions.

[0981] Hardware and software used

[0982] Server: Receives, analyzes, stores, and generates reports on air quality and emotion data.

[0983] Air measurement device: Equipped with sensors that measure pollutants and chemical components in the air and send the data to a server.

[0984] Terminal: A device through which a user accesses the system and checks air quality and emotion data. Examples include a PC or smartphone.

[0985] Emotion engine: Software that analyzes the user's facial expressions and tone of voice to obtain emotional data. It uses the camera and microphone.

[0986] Database: Used to store data, such as SQLite.

[0987] Visualization libraries: Used to visualize data, such as Matplotlib.

[0988] Data collection

[0989] The server provides an API endpoint to receive air quality data sent from the air measurement devices. The air measurement devices periodically send JSON-formatted data containing the sensor identifier and air quality data to the server. Specifically, the server exposes an endpoint called " / api / airquality" and automatically starts analyzing the data as it arrives.

[0990] Data storage

[0991] The received JSON data is parsed and the sensor identifier of the air measuring device, the air quality data, and the date and time of receipt are extracted. This data is then stored in an SQLite database. When the data has been saved, the server logs "New data has been added to the database." For example, the server saves the data "sensor_001", "35μg / m³", "2023-10-01 12:00:00" to SQLite.

[0992] Data Visualization

[0993] Users can log in to the system from a terminal and view visualized air quality data. By specifying a specific sensor identifier, data is retrieved from the server and displayed in graph form using a visualization library such as Matplotlib. For example, if a user selects "sensor_001" and clicks the "Graph Display" button, data for the past week will be displayed as a graph.

[0994] Manipulating the Emotion Engine

[0995] While the user is checking the air quality data, the emotion engine begins to operate. The emotion engine analyzes the user's facial expressions and tone of voice through the camera and microphone and sends emotional data to the server. For example, while the user is checking the data, the camera captures their facial expressions, and if the emotion "anxiety" is detected, the data "anxiety" is sent to the server.

[0996] Storing Emotional Data

[0997] The server receives the emotion data sent from the emotion engine, associates it with the air quality data, and stores it in an SQLite database. For example, the server stores data such as "2023-10-01 12:00:00: Anxiety" along with the air quality data.

[0998] Report Generation

[0999] The server sets a schedule for report generation at the end of each month. It aggregates air quality data and emotion data from the database for the past month and automatically generates a report in PDF format containing statistical information. Specifically, the server generates a file named "September_2023_Report.pdf" and saves it in the specified directory.

[1000] Report Output

[1001] The server saves the generated PDF report in a specified location and notifies the user by email if necessary. Depending on the user's settings, the report can also include the results of the emotion data analysis. For example, the server can attach the generated PDF report to an email and send it to a specified email address.

[1002] Viewing in an Internet browser

[1003] Users can access the system with an internet browser and check air quality data and emotion data in real time. For example, when a user accesses the system with a browser, "real-time air quality data" and an "emotional state indicator" are displayed on the screen. When air quality deteriorates, the emotion indicator can show "anxiety."

[1004] Prompt Sentence Examples

[1005] Example prompts to enter into the generative AI model:

[1006] "Write a program that correlates air quality data with user sentiment data to generate a statistical report for the past month."

[1007] The system not only enables efficient and automated air quality monitoring and reporting, but also enables comprehensive analysis that takes into account the user's emotional state, helping to improve living and working environments.

[1008] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1009] Step 1: Data collection

[1010] The server provides an API endpoint for receiving data in JSON format. It periodically receives JSON-formatted data sent from air measurement devices, including sensor identifiers and air quality data. It analyzes the received data and temporarily stores the sensor identifiers, air quality data, and reception date and time.

[1011] Input: Air quality data in JSON format from an air measurement device

[1012] Processing: Parse the data to extract the sensor identifier, air quality data, and date and time of receipt.

[1013] Output: Extracted data stored in temporary storage

[1014] Specific operation: The server exposes an endpoint called " / api / airquality" and automatically starts analyzing data as it arrives.

[1015] Step 2: Save data

[1016] The server reads the temporarily saved data and records it in the SQLite database. When saving is complete, it logs "New data has been added to the database."

[1017] Input: Temporarily stored sensor identifier, air quality data, date and time of receipt

[1018] Process: Save data to SQLite database

[1019] Output: Notification of database update completion

[1020] Specific operation: The server saves the data "sensor_001", "35μg / m³", and "2023-10-01 12:00:00" to SQLite.

[1021] Step 3: Data visualization

[1022] A user logs into the system from a terminal and sends a visualization request to the server specifying a specific sensor identifier. The server retrieves the necessary data from the database and sends it to the terminal, which then generates a graph using a visualization library such as Matplotlib.

[1023] Input: Visualization request from user (sensor identifier)

[1024] Processing: Retrieve the relevant data from the database and send it to the device

[1025] Output: Display the graph on the terminal

[1026] Specific operation: When the user selects "sensor_001" and clicks the "Graph display" button, the data for the past week will be displayed as a graph.

[1027] Step 4: Emotion Engine Analysis

[1028] While the user is checking the air quality data, the emotion engine analyzes the user's facial expressions and tone of voice, and transmits the analyzed emotion data to the server.

[1029] Input: User's facial expressions and tone of voice (real-time data)

[1030] Processing: The emotion engine analyzes the data and generates emotion data

[1031] Output: Send emotion data to the server

[1032] Specific operation: While the user is checking the data, the camera captures their facial expressions, and if the emotion "anxiety" is detected, the data "anxiety" is sent to the server.

[1033] Step 5: Storing emotion data

[1034] The server receives the emotion data sent from the emotion engine, associates it with the air quality data, and stores it in an SQLite database.

[1035] Input: Emotion data sent from the emotion engine

[1036] Processing: Emotion data is associated with air quality data and stored in a database

[1037] Output: Emotion data stored in a database

[1038] What happens: The server stores data such as "2023-10-01 12:00:00: Anxiety" along with air quality data.

[1039] Step 6: Generate reports

[1040] The server aggregates air quality data and emotion data for the past month at regularly scheduled times, and generates a PDF report based on the aggregated results.

[1041] Input: Air quality data and sentiment data from a database

[1042] Processing: Aggregate data and generate PDF report

[1043] Output: Report in PDF format

[1044] Specific behavior: The server generates a file named "September_2023_Report.pdf" and saves it in the specified directory.

[1045] Step 7: Report Output

[1046] The server saves the generated PDF report in a specified location and notifies the user by email if necessary. Depending on the user's settings, the report can also include the results of the emotion data analysis.

[1047] Input: Generated PDF report

[1048] Action: Print and send report

[1049] Output: Saved PDF report and notification of successful submission

[1050] Specific behavior: The server generates a PDF report and sends it to the specified email address as an attachment.

[1051] Step 8: View in your Internet browser

[1052] Users access the system through an internet browser and view real-time air quality and sentiment data, which is visualized using graphs and indicators.

[1053] Input: Browser access request from user

[1054] Processing: Retrieving real-time data from the database and displaying it in a visual format

[1055] Output: Visualized data displayed in a browser

[1056] Specific operation: A user accesses the system through a browser and the screen displays "real-time air quality data" and an "emotional state indicator." For example, when the air quality deteriorates, the indicator displays "anxiety."

[1057] (Application example 2)

[1058] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1059] While conventional air quality management systems can collect, visualize, and generate reports on air quality data, it is difficult to directly grasp the impact of air quality fluctuations on users. Furthermore, there is a lack of means to monitor in real time the emotional state of workers in response to deteriorating air quality at the workplace, which creates challenges in ensuring safety and improving work efficiency. To solve these challenges, there is a need for integrated management of air quality data and users' emotional state, and a comprehensive assessment of the impact of air quality.

[1060] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1061] In this invention, the server includes means for collecting air quality data, means for saving the air quality data in chronological order, means for visualizing the saved air quality data, means for generating a report based on the visualized data, means for periodically outputting the generated report, means for collecting emotion data using an emotion engine that recognizes and analyzes user emotion data, means for saving the emotion data together with the air quality data, and means for visualizing the emotion data in association with the air quality data. This makes it possible to grasp in real time the impact of fluctuations in air quality on workers in factories and work sites, ensuring safety and improving work efficiency.

[1062] "Air quality data" refers to data that includes indicators such as the concentration of harmful substances and particulates in the air, temperature, and humidity.

[1063] "Means for collection" refers to methods and equipment for acquiring air quality data and emotion data using sensors and measuring devices.

[1064] The "means for storing in chronological order" refers to a method and system for storing acquired data in an electronic recording medium in a format arranged in chronological order.

[1065] "Visualization means" are methods and tools that display collected data in a user-friendly manner as graphs, charts, or diagrams.

[1066] A "report generating means" is a method or device that analyzes collected data and produces a report summarizing statistics and trends.

[1067] A "periodic output means" is a method or system that automatically generates reports or data at set intervals and notifies or transmits them to users.

[1068] An "emotion engine" is software or hardware that analyzes a user's facial expressions, tone of voice, etc. to recognize their emotional state and record it as data.

[1069] "Emotion data" is data that includes numerical values ​​and categories that represent the user's emotional state.

[1070] A "connected visualization" is a method and tool that connects air quality data and emotion data and displays them together.

[1071] To implement this invention, it is necessary to build a system that utilizes an air measurement device, an emotion recognition engine, a server, and a visualization tool.

[1072] First, the air measurement device periodically collects air quality data and sends it to the server. The server analyzes the data received from the air measurement device and stores it in a database in chronological order. Specifically, the data is stored in a format that includes the sensor identifier, air quality data, and the date and time of reception.

[1073] Next, users collect emotional data using cameras and microphones installed on their devices or factory robots. An emotion recognition engine analyzes this data and quantifies or categorizes the user's emotional state.

[1074] The server stores these emotion data together with the air quality data, which are then integrated and visualized using a visualization tool (e.g., Matplotlib) to display the air quality data and the user's emotion data in graphs and charts.

[1075] The server also periodically generates reports and saves statistical information, including air quality data and emotion data, in PDF format. These reports are periodically notified or sent to the user.

[1076] For example, if the air quality in a factory deteriorates, an emotion recognition engine may detect high levels of anxiety among workers, allowing managers to immediately decide to activate air purifiers or halt work processes.

[1077] Example prompt sentence:

[1078] "Please suggest what to do if the air quality in the factory deteriorates and workers are feeling uneasy."

[1079] This system will enable monitoring and management of air quality in factories and workplaces, as well as real-time assessment of workers' emotional state, which is expected to ensure safety and improve work efficiency.

[1080] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1081] Step 1:

[1082] Air quality data collection

[1083] The server receives air quality data periodically sent from the air measurement device. The input is the air quality data sent from the air measurement device and the sensor identifier. The server receives this data and parses it in JSON format. The data obtained as a result of the analysis is the sensor identifier, air quality data, and reception date and time.

[1084] Step 2:

[1085] Air quality data storage

[1086] The server stores the air quality data received and analyzed in step 1 in chronological order. The input is the sensor identifier, air quality data, and reception date and time obtained in step 1. The server stores this data in an SQLite database and confirms that the database update is complete.

[1087] Step 3:

[1088] Collecting Emotional Data

[1089] Users collect emotional data through cameras and microphones installed on terminals or factory robots. The input is facial expression data captured by the camera and voice data recorded by the microphone. The emotion engine analyzes this data and quantifies or categorizes the user's emotional state. The output is emotional data.

[1090] Step 4:

[1091] Storing Emotional Data

[1092] The server stores the emotion data obtained in step 3 together with the air quality data. The inputs are the sensor identifier, emotion data, and the date and time of reception. The server stores these data in the database and confirms that the database update is complete. The output is the emotion data and air quality data stored in the database.

[1093] Step 5:

[1094] Data visualization

[1095] The user accesses the server from a terminal and checks visualized air quality data and emotion data. The input is a specific sensor identifier specified by the user, and the server retrieves the air quality data and emotion data from the database based on this sensor identifier. The retrieved data is displayed in graph form using a visualization library such as Matplotlib. The output is the visualized graph.

[1096] Step 6:

[1097] Report Generation

[1098] The server aggregates air quality data and emotion data on a monthly basis and generates a report containing statistical information. The input is the air quality data and emotion data from the past month. The server analyzes this data and creates a report in PDF format. The output is the generated PDF report.

[1099] Step 7:

[1100] Sending a report

[1101] The server saves the report generated in step 6 in the specified location and sends it to the user by email, etc. as needed. The input is the generated PDF report, which the server saves in the specified location and notifies the user. The output is the sent PDF report.

[1102] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1103] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1104] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1105] [Fourth embodiment]

[1106] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1107] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1108] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1109] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1110] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1111] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1112] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1113] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1114] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1115] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1116] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1117] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1118] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1119] The construction and operation of a system for implementing the present invention, which automatically collects, stores, visualizes, and reports on air quality data, is described below.

[1120] Data collection

[1121] server

[1122] The server provides an API endpoint for receiving air quality data sent from the air measurement device. The air measurement device periodically sends JSON data containing the sensor identifier and air quality data. The server receives this data and stores it in a database.

[1123] The server implements API endpoints using a web framework such as Flask, and a relational database such as SQLite is used to efficiently store and manage the collected data.

[1124] Data visualization

[1125] User

[1126] Users access the system from their terminals and check visualized air quality data. The data in the database is retrieved from the server and converted into visualization formats such as time series graphs using Python's Matplotlib library.

[1127] For example, if you want to visualize data from a sensor with ID "sensor_1," you can retrieve all data related to "sensor_1" from the database and plot it along a time axis, allowing you to visually confirm the progress of air quality.

[1128] Generate reports

[1129] server

[1130] The server schedules the generation of periodic reports every month. The reports summarize data for a specific period (e.g., one month) and include statistical information such as averages, maximums, and minimums. The reports are generated and saved in PDF format.

[1131] The server uses a PDF generation library such as FPDF to automatically create a report header, chapter titles for each sensor, and the body of the report. The report is then submitted to the health and safety committee and used to consider measures to improve air quality.

[1132] Specific examples

[1133] For example, data from a sensor with ID "sensor_A" installed in an office can be used. The server receives air quality data sent from "sensor_A" on a daily basis and stores it in a database. At the end of the month, users access the system from their terminals and check graphs of the monthly data. The server automatically generates a monthly report, saves it as a PDF file, and uses it at the next health and safety committee meeting.

[1134] The system described above provides efficient and automated air quality monitoring and reporting, allowing users to access and analyze important data hassle-free, making it extremely useful for continuously monitoring the air quality of a specific location.

[1135] The processing flow will be explained below.

[1136] Step 1: Data collection

[1137] server

[1138] The server provides an API endpoint for receiving data from the air quality measurement device. The air quality measurement device periodically sends JSON-formatted data containing the sensor identifier and air quality data to the server. The server receives this data, extracts it, and stores it in a database. The measurement date and time are also stored in the database.

[1139] Step 2: Save data

[1140] server

[1141] The server parses the received JSON data, extracts the air quality data, the sensor identifier of the air quality monitor, and the date and time of receipt, creates and executes SQL instructions to store this data in an SQLite database, and then completes the process after confirming that the database has been updated appropriately.

[1142] Step 3: Data Acquisition

[1143] User

[1144] When a user runs a visualization program from their device, they specify a specific sensor identifier. The server executes an SQL query to retrieve the data corresponding to this sensor identifier from the database. The retrieved data is then prepared as time-series data.

[1145] Step 4: Data visualization

[1146] User

[1147] After acquiring the data, users can use a visualization library such as Matplotlib to display the data in graph form. The visualization program running on the user's device generates and displays time series graphs and histograms using the acquired data, allowing users to visually confirm the progress of air quality.

[1148] Step 5: Generate reports

[1149] server

[1150] The server sets up a task schedule to automatically generate monthly reports. At the scheduled time (e.g., the beginning of the month), the server runs the report generation program. This program retrieves air quality data from the database for the past month and compiles the results into a report. The report is generated in PDF format and saved on the server.

[1151] Step 6: Report output

[1152] server

[1153] The server automatically saves the generated PDF report to a specified location. Additional output options, such as emailing the report, can be configured as needed. This allows monthly reports to be automatically generated and submitted to the health and safety committee, etc.

[1154] In this way, a series of processes from collecting air quality data to storing, visualizing, generating and outputting reports are carried out automatically, creating a system that allows users to efficiently monitor and report on air quality.

[1155] Example 1

[1156] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1157] Monitoring and improving air quality is becoming increasingly important in modern society. However, conventional air quality monitoring systems require manual data collection, storage, visualization, and report generation, which is time-consuming and inefficient. Furthermore, data is scattered, making integrated management difficult. For this reason, there is a demand for a system that can automate and consistently manage air quality data, from collection to visualization and report generation.

[1158] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1159] In this invention, the server includes means for collecting air quality data, means for saving the collected air quality data in chronological order, means for acquiring the saved air quality data, means for visualizing the acquired air quality data, means for generating a chart for visualization, means for generating a report based on the visualized data, and means for periodically outputting the generated report, thereby enabling consistent collection, management, visualization, and report generation of air quality data.

[1160] "Air quality data" is data that numerically represents the concentration and amount of various substances and pollutants in the air (e.g., PM2.5, carbon dioxide, carbon monoxide, ozone, etc.).

[1161] "Means of collection" refers to the function of acquiring air quality data using sensors such as air measuring devices and sending it to a server.

[1162] "Means for storing data in chronological order" refers to a function for recording and accumulating air quality data along with date and time information in a database or other storage device.

[1163] The "means of acquisition" is a function that extracts air quality data stored in the database based on specified conditions and converts it into a reusable format within the server.

[1164] "Visualization means" refers to the function of converting acquired air quality data into a visual format such as a graph or chart, and displaying it in a way that is easily understandable to the user.

[1165] The "means for generating charts" is a function for drawing charts such as line graphs and bar graphs based on visualized data.

[1166] A "means for generating reports" is a function that compiles visualized data and statistical information and creates a document in a specific format (e.g., a PDF file).

[1167] The "means for periodic output" is a function that automatically creates a report at a certain period and saves it as an electronic file or prints it.

[1168] A "classification means" is a function that divides collected air quality data into categories based on specific sensor identifiers and location information.

[1169] The "aggregation means" is a function that performs statistical processing on classified data and calculates statistical information such as average values, maximum values, and minimum values.

[1170] The "means for displaying on a browser" is a function for displaying visualized data on a user interface through an internet browser.

[1171] The system of the present invention includes means for automatically collecting, storing, visualizing, and generating reports on air quality data, specific embodiments of which are described in detail below.

[1172] Data collection

[1173] server

[1174] The server provides an API endpoint for receiving air quality data sent from the air measurement devices. The air measurement devices periodically send JSON data containing the sensor identifier and air quality data to the server. The server implements the API endpoint using a web framework such as Flask and stores the received data in a database.

[1175] The server parses the received JSON data and extracts the necessary data (sensor identifier, date and time, air quality data). It then efficiently stores and manages the data using a relational database such as SQLite. This process ensures that all data sent from the air measuring devices is collected in a consistent manner.

[1176] Data visualization

[1177] User

[1178] Users access the system from their terminals and check the visualization results of the stored air quality data. The server retrieves the necessary data from the SQLite database in response to user requests and visualizes it using the Python Matplotlib library.

[1179] Specifically, data for the sensor ID and period specified by the user is displayed in the form of a time series graph, etc. This allows the user to visually check the progress of air quality.

[1180] Generate reports

[1181] server

[1182] The server generates air quality reports periodically every month. The reports include aggregated data (average, maximum, minimum, and other statistical information) for a specific period (e.g., one month). The reports are generated and saved in PDF format using a PDF generation library such as FPDF.

[1183] The server uses a Python scheduling library (e.g., APScheduler) to set up a process to automatically generate the report every month, allowing users to access their monthly air quality reports without any hassle.

[1184] Examples and prompts

[1185] For example, consider a case where air quality is monitored and managed based on data sent from a sensor ID "sensor_A" installed in an office. The server periodically receives air quality data from "sensor_A" and stores it in a database. At the end of the month, users can access the system from their terminals and check a graph of the monthly air quality data. Furthermore, the server automatically generates a monthly report and saves it as a PDF file, which can be used at the next health and safety committee meeting.

[1186] Example prompt sentence:

[1187] "Please explain the program process of the system that automates the collection, storage, visualization, and report generation of air quality data. Please specify the names of the specific hardware and software, and provide a detailed description of the data processing and calculations that are performed. Also, please include the following example: Using data from a sensor with ID "sensor_A" installed in an office."

[1188] This embodiment provides efficient, automated air quality monitoring and reporting, allowing users to access and analyze important data. This system is highly effective for continuously monitoring air quality in a specific location.

[1189] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1190] Step 1: Receiving data

[1191] server

[1192] The server provides an API endpoint to receive data sent from the air quality measurement device. As input, it receives JSON-formatted data from the air quality measurement device. The server implements an endpoint called / api / data using the Flask framework. The received data has elements such as a sensor identifier, date and time, and air quality data.

[1193] Specifically, the server receives an HTTP POST request and extracts JSON data from the request body, outputting the extracted sensor identifier, date and time, and air quality data.

[1194] Step 2: Save data

[1195] server

[1196] The server stores the received air quality data in an SQLite database. It uses the sensor identifier, date and time, and air quality data as input. It first opens a database connection and then generates the appropriate SQL statements to insert the data.

[1197] Specifically, it inserts data into the database using an SQL INSERT statement, and outputs a success status indicating that the data was successfully saved.

[1198] Step 3: Data Acquisition

[1199] server

[1200] The server retrieves the required data from the database based on the user request. It receives the sensor ID and the period as input. It executes an SQL query to the database to extract the relevant data.

[1201] Specifically, the SELECT statement is used to extract data related to the specified sensor ID and period from the database, and the output is a list of the acquired air quality data.

[1202] Step 4: Data visualization

[1203] server

[1204] The server visualizes the retrieved data, using the extracted air quality data as input and plotting these data on time series graphs using Python's Matplotlib library.

[1205] Specifically, the server plots the data on the x-axis (date and time) and y-axis (air quality data) and saves the visualization as an image file. The output is the generated graph image.

[1206] Step 5: Generate reports

[1207] server

[1208] The server generates air quality reports periodically. As input, it receives data for a specific period (e.g., one month). It aggregates the data and calculates statistics (average, maximum, minimum).

[1209] Specifically, it uses the FPDF library to compose a report in PDF format, embeds the required statistics and visualizations in the report, and the output is the generated PDF report.

[1210] Step 6: Report output

[1211] server

[1212] The server periodically saves or sends the generated reports. It receives the generated PDF reports as input. It schedules the report generation every month using the scheduling library mentioned above (e.g., APScheduler).

[1213] Specifically, the generated report is saved in a specified folder and sent as needed via email, etc. The output is a saved PDF report file.

[1214] Step 7: View the data visualization

[1215] User

[1216] The user accesses the system from a terminal and checks the visualized air quality data. As input, the system receives the sensor ID and period specified by the user. The server retrieves the visualized data from the database and displays it on the network browser.

[1217] Specifically, the server displays the acquired data in the browser using HTML and JavaScript, and the output is visualized air quality data displayed on the browser.

[1218] The above is the main processing flow of this system.

[1219] (Application example 1)

[1220] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1221] In conventional air quality monitoring systems, data collection, visualization, and report generation are often done manually, which is time-consuming and labor-intensive, and makes it difficult to detect abnormalities in real time or send prompt alerts. Furthermore, data visualization mainly requires the use of an internet browser, making it difficult to intuitively and quickly monitor air quality on a terminal. There is a need for a system that can resolve these issues and efficiently monitor and manage air quality in real time.

[1222] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1223] In this invention, the server includes means for detecting abnormalities in air quality data and notifying the user, means for classifying the air quality data based on a specified sensor identifier, means for aggregating the classified data and calculating statistics, and means for displaying the visualized data on a terminal application. This allows air quality abnormalities to be detected in real time and for the user to be promptly notified. Furthermore, data visualization can be performed intuitively on the terminal, enabling efficient air quality monitoring and management.

[1224] "Air quality data" is a collection of measurements that indicate the concentration of harmful substances and particulates in the air, as well as other information about air quality.

[1225] "Collection means" is a general term for devices and technologies, including sensors and their communication functions, that acquire air quality data and transmit it to a server.

[1226] "Means for storing data chronologically" refers to a technology that records collected air quality data sequentially over time and manages it centrally in a database.

[1227] "Visualization means" refers to technology that converts collected air quality data into a visual format such as graphs and charts and displays it in a way that users can intuitively understand.

[1228] A "report generation means" is a technology that automatically generates a formatted document by compiling statistics and trends based on collected and visualized air quality data.

[1229] The "means for periodic output" is a mechanism for saving or transmitting reports generated at automatically set time intervals.

[1230] "Means for detecting abnormalities and notifying users" refers to technology that automatically issues a warning when an abnormality exceeding a preset standard value is detected based on air quality data.

[1231] The "means for classifying based on designated sensor identifiers" is a mechanism for organizing, classifying, and efficiently managing data from multiple air quality sensors based on identifiers.

[1232] The "means for calculating statistical values" is a technique for calculating statistical information such as average values, maximum values, and minimum values ​​using the classified air quality data.

[1233] "Means for displaying on a device application" refers to a mechanism for displaying air quality data through an application installed on a device such as a smartphone or tablet.

[1234] A system for implementing the present invention efficiently and automatically collects, stores, visualizes, generates reports, and detects anomalies in air quality data. This system includes a sensor that collects air quality data, a server that stores and manages the data, and a terminal application that visualizes the data. The detailed configuration and operation are described below.

[1235] Data collection

[1236] The server provides an API endpoint that receives data sent from multiple air quality sensors. The air quality sensors periodically send JSON-formatted data, including concentration data of harmful substances and fine particles in the air. This data is received by the server via an API endpoint built using a web framework such as Flask and stored in a relational database such as SQLite.

[1237] Data visualization

[1238] Users access the system from devices such as smartphones and tablets to view visualized air quality data. Data in the database is retrieved from the server and visualized in the form of time series graphs using Python's Matplotlib library, etc. This visualization allows users to intuitively understand fluctuations in air quality.

[1239] Anomaly detection and notification

[1240] The server monitors the collected air quality data in real time and can detect abnormalities. If an abnormality is detected, the server sends a notification to the user's device. This notification can be in the form of a push notification or email, allowing the user to respond quickly.

[1241] Report Generation

[1242] The server automatically generates regular monthly reports. The reports summarize data for a specific period (e.g., one month) and include statistical information such as average, maximum, and minimum values. The reports are generated in PDF format and built using a PDF generation library such as FPDF, and are regularly saved and distributed. This allows users to regularly check the status of air quality and take necessary measures.

[1243] Specific examples

[1244] For example, if data is used from a sensor with ID "sensor_1" installed in an office, the server receives air quality data sent from "sensor_1" on a daily basis and stores it in a database. Users can visualize and check the data from "sensor_1" on their smartphones. Monthly reports are also automatically generated by the server and can be downloaded as PDF files. An anomaly detection function immediately notifies users if the air quality standard is exceeded.

[1245] Prompt Sentence Examples

[1246] Get the air quality data from "sensor_1" and generate a time series graph. Also, generate a PDF report based on the data from the same sensor.

[1247] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1248] Processing Steps

[1249] Step 1: Data collection

[1250] The server receives data from the air quality sensor. The sensor sends air quality data in JSON format at regular intervals. This data includes the sensor identifier and various air quality parameters. The server implements an API endpoint using the Flask framework to receive the sent JSON data. The received data is stored in a SQLite database.

[1251] Input: JSON data from air quality sensors

[1252] Output: Save the received data to the database

[1253] Step 2: Save data

[1254] The server stores the processed air quality data in a database in chronological order, including the sensor identifier, timestamp, and measurement value. The SQLite database allows for efficient management of air quality data.

[1255] Input: Received air quality data

[1256] Output: Data stored in chronological order

[1257] Step 3: Data visualization

[1258] When a user accesses the system from a terminal, the server retrieves the air quality data of the specified sensor from the stored database, then uses the Python Matplotlib library to generate a time series graph, which is then converted into a format that can be visually displayed on the terminal application.

[1259] Input: Air quality data retrieved from a database

[1260] Output: Visualized time series graph

[1261] Step 4: Anomaly detection and notification

[1262] The server monitors the collected air quality data and sends a notification to the user's device if an abnormality is detected. For example, if harmful substances exceeding the standard value are detected, the server will immediately send a push notification or email. This allows the user to understand the abnormality in air quality in real time and take prompt action.

[1263] Input: Air quality data being monitored

[1264] Output: Abnormality notification (push notification or email)

[1265] Step 5: Generate reports

[1266] The server aggregates data from the database for the relevant period to generate regular monthly reports. It calculates statistical information such as averages, maximums, and minimums based on the data, and generates PDF reports using the FPDF library. These reports are periodically saved or distributed to users' devices.

[1267] Input: Air quality data for the period of interest

[1268] Output: Report (PDF format)

[1269] Step 6: Print and distribute the report

[1270] The generated PDF report is sent from the server to the user's device, where the user can download the report and use it in monthly meetings, etc.

[1271] Input: Generated PDF report

[1272] Output: Sending a PDF report to the user's device

[1273] Examples:

[1274] As a concrete example, consider a scenario where a user wants to visualize and check air quality data from "sensor_1" on their smartphone. In this case, the server retrieves the data from "sensor_1" from the database, generates a time series graph using Matplotlib, and displays it on the device. If an abnormality is detected, the user is notified immediately. At the end of the month, an automatically generated PDF report is distributed to the user's device.

[1275] Prompt Sentence Examples

[1276] Get the air quality data from "sensor_1" and generate a time series graph. Also, generate a PDF report based on the data from the same sensor.

[1277] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1278] The system for implementing the present invention includes an emotion engine that recognizes and analyzes user emotions, in addition to collecting, storing, visualizing, and generating reports on air quality data. The configuration and operation of the system are described below.

[1279] Data collection

[1280] server

[1281] The server provides an API endpoint to receive air quality data sent from the air measurement device. The air measurement device periodically sends JSON-formatted data containing the sensor identifier and air quality data to the server. The server analyzes the received data and stores it in a database, along with the measurement date and time.

[1282] Data storage

[1283] server

[1284] The server parses the received JSON data and extracts the air quality data, sensor identifier, and date and time of reception. It then stores this data in an SQLite database. To ensure that the data is properly stored, it sends a completion notification after the database is updated.

[1285] Data Visualization

[1286] User

[1287] Users access the system from their terminals and check visualized air quality data. By specifying a specific sensor identifier, data is retrieved from the server and displayed in graph form using a visualization library such as Matplotlib. This allows the transition of air quality to be visualized.

[1288] Manipulating the Emotion Engine

[1289] User

[1290] When a user checks air quality data, the emotion engine analyzes the user's facial expressions and tone of voice to obtain emotional data. This emotional data is saved along with the air quality data. For example, the engine can detect emotional reactions such as "relief" or "anxiety" in response to changes in air quality perceived by the user.

[1291] Storing Emotional Data

[1292] server

[1293] The system receives user emotion data recognized by the emotion engine, associates it with air quality data, and stores it in a database for later analysis and report generation.

[1294] Report Generation

[1295] server

[1296] The server schedules the generation of monthly reports, which include statistical information based on the air quality data and user sentiment data from the past month. The reports are generated in PDF format and stored on the server.

[1297] Report Output

[1298] server

[1299] The server automatically saves the generated PDF report in a specified location and sends it via email or other means as needed. The report can also include the results of user sentiment analysis, making it possible to comprehensively evaluate the impact of air quality and the user's emotional response.

[1300] Viewing in an Internet browser

[1301] User

[1302] Users can view real-time air quality and emotion data through an internet browser. This includes visualizations in graphs and charts, as well as indicators and numerical values ​​that show the user's emotional state. For example, the worsening air quality can indicate an increase in the user's anxiety level.

[1303] This system not only enables efficient and automated air quality monitoring and reporting, but also enables comprehensive analysis that takes into account the user's emotional state, making it a useful tool for improving living and working environments in particular.

[1304] The processing flow will be explained below.

[1305] Step 1: Data collection

[1306] server

[1307] The server provides an API endpoint to receive air quality data sent from the air measurement device. The air measurement device periodically sends JSON-formatted data including the sensor identifier and air quality data to the server. The server receives this data and stores it in a database, along with the date and time.

[1308] Step 2: Data analysis

[1309] server

[1310] The server parses the received JSON data, extracts the sensor identifier, air quality data, and date and time, and stores them in an SQLite database. To ensure the data is stored properly, it sends a completion notification after the database is updated.

[1311] Step 3: Collecting Emotional Data

[1312] User

[1313] The user displays and checks the air quality data on the device. An emotion engine is activated, analyzing the user's facial expressions and voice in real time to detect the user's emotional state (e.g., relief, anxiety, excitement, etc.). The emotion engine generates emotion data and sends it to the server.

[1314] Step 4: Emotion data storage

[1315] server

[1316] The server receives the emotion data sent from the emotion engine, and associates the received emotion data with the air quality data and stores it in a database, thereby recording the user's emotional response to the specific air quality data.

[1317] Step 5: Data visualization

[1318] User

[1319] Users access the system from their devices and view visualized air quality and emotion data. The server retrieves the relevant data from the database based on the specified sensor identifier and generates a time series graph and emotion indicator. These can then be displayed using a visualization library such as Matplotlib to visualize the progress of air quality and the corresponding changes in emotion.

[1320] Step 6: Generate reports

[1321] server

[1322] The server schedules a task to generate reports periodically. For example, at the beginning of each month, it aggregates the air quality data and user emotion data from the past month and generates a PDF report containing air quality statistics and an analysis of the user's emotional response.

[1323] Step 7: Report Output

[1324] server

[1325] The server automatically saves the generated PDF report in a specified folder and sends it by email as needed. This allows it to be used as a reference for meetings such as safety and health committees. The output report includes the trend of air quality fluctuations and the user's emotional response to them.

[1326] Step 8: Browser display

[1327] User

[1328] Users access the system using an internet browser to view air quality and emotion data in real time. Visualized data includes time series graphs, statistical information, and indicators of the user's emotional state. For example, users can see at a glance whether their anxiety levels tend to increase as air quality worsens.

[1329] The above is a specific processing flow of the system of the present invention. This system not only monitors air quality but also makes it possible to comprehensively evaluate the environment, including the user's emotional response.

[1330] Example 2

[1331] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1332] Conventional air quality monitoring systems simply collect, store, visualize, and report on air quality data, but lack the ability to address user emotions. This makes it difficult to assess the impact of air quality fluctuations on users' emotions and behavior, making it difficult to comprehensively improve living and working environments.

[1333] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting air quality data, means for saving the collected air quality data in chronological order, means for visualizing the saved air quality data, means for generating a report based on the visualized data, means for periodically outputting the generated report, means for analyzing the user's emotions, and means for saving the analyzed emotion data in association with the air quality data. This enables a comprehensive evaluation that associates the air quality data with the user's emotion data, which is useful for improving living and working environments.

[1334] "Air quality data" refers to data that includes information on pollutants, chemical components, temperature, humidity, and so on in the air.

[1335] "Means of collection" refers to the function of acquiring air quality data using sensors and measuring devices and incorporating it into the system.

[1336] The "means for storing data in chronological order" is a function that records air quality data at regular time intervals and stores data from the past to the present.

[1337] "Visualization means" refers to the ability to display stored air quality data in the form of graphs, charts, indicators, etc., to clearly show trends and fluctuations in the data.

[1338] "Means for generating reports" refers to a function that creates reports summarizing statistical information and analytical results based on collected and stored air quality data.

[1339] The "means for periodic output" refers to a function for automatically outputting the generated report at regular intervals such as monthly or weekly, and providing it to the user.

[1340] The "means for analyzing user emotions" is a function that analyzes the user's facial expressions and tone of voice to obtain emotional data such as relief, anxiety, surprise, etc.

[1341] The "means for storing analyzed emotion data in association with air quality data" is a function that stores acquired emotion data together with the corresponding air quality data, enabling the association between them to be analyzed.

[1342] As a specific embodiment for carrying out the invention, the configuration and operation of the following system will be described. This system not only collects, stores, visualizes, and generates reports on air quality data, but also includes an emotion engine that recognizes and analyzes user emotions.

[1343] Hardware and software used

[1344] Server: Receives, analyzes, stores, and generates reports on air quality and emotion data.

[1345] Air measurement device: Equipped with sensors that measure pollutants and chemical components in the air and send the data to a server.

[1346] Terminal: A device through which a user accesses the system and checks air quality and emotion data. Examples include a PC or smartphone.

[1347] Emotion engine: Software that analyzes the user's facial expressions and tone of voice to obtain emotional data. It uses the camera and microphone.

[1348] Database: Used to store data, such as SQLite.

[1349] Visualization libraries: Used to visualize data, such as Matplotlib.

[1350] Data collection

[1351] The server provides an API endpoint to receive air quality data sent from the air measurement devices. The air measurement devices periodically send JSON-formatted data containing the sensor identifier and air quality data to the server. Specifically, the server exposes an endpoint called " / api / airquality" and automatically starts analyzing the data as it arrives.

[1352] Data storage

[1353] The received JSON data is parsed and the sensor identifier of the air measuring device, the air quality data, and the date and time of receipt are extracted. This data is then stored in an SQLite database. When the data has been saved, the server logs "New data has been added to the database." For example, the server saves the data "sensor_001", "35μg / m³", "2023-10-01 12:00:00" to SQLite.

[1354] Data Visualization

[1355] Users can log in to the system from a terminal and view visualized air quality data. By specifying a specific sensor identifier, data is retrieved from the server and displayed in graph form using a visualization library such as Matplotlib. For example, if a user selects "sensor_001" and clicks the "Graph Display" button, data for the past week will be displayed as a graph.

[1356] Manipulating the Emotion Engine

[1357] While the user is checking the air quality data, the emotion engine begins to operate. The emotion engine analyzes the user's facial expressions and tone of voice through the camera and microphone and sends emotional data to the server. For example, while the user is checking the data, the camera captures their facial expressions, and if the emotion "anxiety" is detected, the data "anxiety" is sent to the server.

[1358] Storing Emotional Data

[1359] The server receives the emotion data sent from the emotion engine, associates it with the air quality data, and stores it in an SQLite database. For example, the server stores data such as "2023-10-01 12:00:00: Anxiety" along with the air quality data.

[1360] Report Generation

[1361] The server sets a schedule for report generation at the end of each month. It aggregates air quality data and emotion data from the database for the past month and automatically generates a report in PDF format containing statistical information. Specifically, the server generates a file named "September_2023_Report.pdf" and saves it in the specified directory.

[1362] Report Output

[1363] The server saves the generated PDF report in a specified location and notifies the user by email if necessary. Depending on the user's settings, the report can also include the results of the emotion data analysis. For example, the server can attach the generated PDF report to an email and send it to a specified email address.

[1364] Viewing in an Internet browser

[1365] Users can access the system with an internet browser and check air quality data and emotion data in real time. For example, when a user accesses the system with a browser, "real-time air quality data" and an "emotional state indicator" are displayed on the screen. When air quality deteriorates, the emotion indicator can show "anxiety."

[1366] Prompt Sentence Examples

[1367] Example prompts to enter into the generative AI model:

[1368] "Write a program that correlates air quality data with user sentiment data to generate a statistical report for the past month."

[1369] The system not only enables efficient and automated air quality monitoring and reporting, but also enables comprehensive analysis that takes into account the user's emotional state, helping to improve living and working environments.

[1370] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1371] Step 1: Data collection

[1372] The server provides an API endpoint for receiving data in JSON format. It periodically receives JSON-formatted data sent from air measurement devices, including sensor identifiers and air quality data. It analyzes the received data and temporarily stores the sensor identifiers, air quality data, and reception date and time.

[1373] Input: Air quality data in JSON format from an air measurement device

[1374] Processing: Parse the data to extract the sensor identifier, air quality data, and date and time of receipt.

[1375] Output: Extracted data stored in temporary storage

[1376] Specific operation: The server exposes an endpoint called " / api / airquality" and automatically starts analyzing data as it arrives.

[1377] Step 2: Save data

[1378] The server reads the temporarily saved data and records it in the SQLite database. When saving is complete, it logs "New data has been added to the database."

[1379] Input: Temporarily stored sensor identifier, air quality data, date and time of receipt

[1380] Process: Save data to SQLite database

[1381] Output: Notification of database update completion

[1382] Specific operation: The server saves the data "sensor_001", "35μg / m³", and "2023-10-01 12:00:00" to SQLite.

[1383] Step 3: Data visualization

[1384] A user logs into the system from a terminal and sends a visualization request to the server specifying a specific sensor identifier. The server retrieves the necessary data from the database and sends it to the terminal, which then generates a graph using a visualization library such as Matplotlib.

[1385] Input: Visualization request from user (sensor identifier)

[1386] Processing: Retrieve the relevant data from the database and send it to the device

[1387] Output: Display the graph on the terminal

[1388] Specific operation: When the user selects "sensor_001" and clicks the "Graph display" button, the data for the past week will be displayed as a graph.

[1389] Step 4: Emotion Engine Analysis

[1390] While the user is checking the air quality data, the emotion engine analyzes the user's facial expressions and tone of voice, and transmits the analyzed emotion data to the server.

[1391] Input: User's facial expressions and tone of voice (real-time data)

[1392] Processing: The emotion engine analyzes the data and generates emotion data

[1393] Output: Send emotion data to the server

[1394] Specific operation: While the user is checking the data, the camera captures their facial expressions, and if the emotion "anxiety" is detected, the data "anxiety" is sent to the server.

[1395] Step 5: Storing emotion data

[1396] The server receives the emotion data sent from the emotion engine, associates it with the air quality data, and stores it in an SQLite database.

[1397] Input: Emotion data sent from the emotion engine

[1398] Processing: Emotion data is associated with air quality data and stored in a database

[1399] Output: Emotion data stored in a database

[1400] What happens: The server stores data such as "2023-10-01 12:00:00: Anxiety" along with air quality data.

[1401] Step 6: Generate reports

[1402] The server aggregates air quality data and emotion data for the past month at regularly scheduled times, and generates a PDF report based on the aggregated results.

[1403] Input: Air quality data and sentiment data from a database

[1404] Processing: Aggregate data and generate PDF report

[1405] Output: Report in PDF format

[1406] Specific behavior: The server generates a file named "September_2023_Report.pdf" and saves it in the specified directory.

[1407] Step 7: Report Output

[1408] The server saves the generated PDF report in a specified location and notifies the user by email if necessary. Depending on the user's settings, the report can also include the results of the emotion data analysis.

[1409] Input: Generated PDF report

[1410] Action: Print and send report

[1411] Output: Saved PDF report and notification of successful submission

[1412] Specific behavior: The server generates a PDF report and sends it to the specified email address as an attachment.

[1413] Step 8: View in your Internet browser

[1414] Users access the system through an internet browser and view real-time air quality and sentiment data, which is visualized using graphs and indicators.

[1415] Input: Browser access request from user

[1416] Processing: Retrieving real-time data from the database and displaying it in a visual format

[1417] Output: Visualized data displayed in a browser

[1418] Specific operation: A user accesses the system through a browser and the screen displays "real-time air quality data" and an "emotional state indicator." For example, when the air quality deteriorates, the indicator displays "anxiety."

[1419] (Application example 2)

[1420] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1421] While conventional air quality management systems can collect, visualize, and generate reports on air quality data, it is difficult to directly grasp the impact of air quality fluctuations on users. Furthermore, there is a lack of means to monitor in real time the emotional state of workers in response to deteriorating air quality at the workplace, which creates challenges in ensuring safety and improving work efficiency. To solve these challenges, there is a need for integrated management of air quality data and users' emotional state, and a comprehensive assessment of the impact of air quality.

[1422] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1423] In this invention, the server includes means for collecting air quality data, means for saving the air quality data in chronological order, means for visualizing the saved air quality data, means for generating a report based on the visualized data, means for periodically outputting the generated report, means for collecting emotion data using an emotion engine that recognizes and analyzes user emotion data, means for saving the emotion data together with the air quality data, and means for visualizing the emotion data in association with the air quality data. This makes it possible to grasp in real time the impact of fluctuations in air quality on workers in factories and work sites, ensuring safety and improving work efficiency.

[1424] "Air quality data" refers to data that includes indicators such as the concentration of harmful substances and particulates in the air, temperature, and humidity.

[1425] "Means for collection" refers to methods and equipment for acquiring air quality data and emotion data using sensors and measuring devices.

[1426] The "means for storing in chronological order" refers to a method and system for storing acquired data in an electronic recording medium in a format arranged in chronological order.

[1427] "Visualization means" are methods and tools that display collected data in a user-friendly manner as graphs, charts, or diagrams.

[1428] A "report generating means" is a method or device that analyzes collected data and produces a report summarizing statistics and trends.

[1429] A "periodic output means" is a method or system that automatically generates reports or data at set intervals and notifies or transmits them to users.

[1430] An "emotion engine" is software or hardware that analyzes a user's facial expressions, tone of voice, etc. to recognize their emotional state and record it as data.

[1431] "Emotion data" is data that includes numerical values ​​and categories that represent the user's emotional state.

[1432] A "connected visualization" is a method and tool that connects air quality data and emotion data and displays them together.

[1433] To implement this invention, it is necessary to build a system that utilizes an air measurement device, an emotion recognition engine, a server, and a visualization tool.

[1434] First, the air measurement device periodically collects air quality data and sends it to the server. The server analyzes the data received from the air measurement device and stores it in a database in chronological order. Specifically, the data is stored in a format that includes the sensor identifier, air quality data, and the date and time of reception.

[1435] Next, users collect emotional data using cameras and microphones installed on their devices or factory robots. An emotion recognition engine analyzes this data and quantifies or categorizes the user's emotional state.

[1436] The server stores these emotion data together with the air quality data, which are then integrated and visualized using a visualization tool (e.g., Matplotlib) to display the air quality data and the user's emotion data in graphs and charts.

[1437] The server also periodically generates reports and saves statistical information, including air quality data and emotion data, in PDF format. These reports are periodically notified or sent to the user.

[1438] For example, if the air quality in a factory deteriorates, an emotion recognition engine may detect high levels of anxiety among workers, allowing managers to immediately decide to activate air purifiers or halt work processes.

[1439] Example prompt sentence:

[1440] "Please suggest what to do if the air quality in the factory deteriorates and workers are feeling uneasy."

[1441] This system will enable monitoring and management of air quality in factories and workplaces, as well as real-time assessment of workers' emotional state, which is expected to ensure safety and improve work efficiency.

[1442] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1443] Step 1:

[1444] Air quality data collection

[1445] The server receives air quality data periodically sent from the air measurement device. The input is the air quality data sent from the air measurement device and the sensor identifier. The server receives this data and parses it in JSON format. The data obtained as a result of the analysis is the sensor identifier, air quality data, and reception date and time.

[1446] Step 2:

[1447] Air quality data storage

[1448] The server stores the air quality data received and analyzed in step 1 in chronological order. The input is the sensor identifier, air quality data, and reception date and time obtained in step 1. The server stores this data in an SQLite database and confirms that the database update is complete.

[1449] Step 3:

[1450] Collecting Emotional Data

[1451] Users collect emotional data through cameras and microphones installed on terminals or factory robots. The input is facial expression data captured by the camera and voice data recorded by the microphone. The emotion engine analyzes this data and quantifies or categorizes the user's emotional state. The output is emotional data.

[1452] Step 4:

[1453] Storing Emotional Data

[1454] The server stores the emotion data obtained in step 3 together with the air quality data. The inputs are the sensor identifier, emotion data, and the date and time of reception. The server stores these data in the database and confirms that the database update is complete. The output is the emotion data and air quality data stored in the database.

[1455] Step 5:

[1456] Data visualization

[1457] The user accesses the server from a terminal and checks visualized air quality data and emotion data. The input is a specific sensor identifier specified by the user, and the server retrieves the air quality data and emotion data from the database based on this sensor identifier. The retrieved data is displayed in graph form using a visualization library such as Matplotlib. The output is the visualized graph.

[1458] Step 6:

[1459] Report Generation

[1460] The server aggregates air quality data and emotion data on a monthly basis and generates a report containing statistical information. The input is the air quality data and emotion data from the past month. The server analyzes this data and creates a report in PDF format. The output is the generated PDF report.

[1461] Step 7:

[1462] Sending a report

[1463] The server saves the report generated in step 6 in the specified location and sends it to the user by email, etc. as needed. The input is the generated PDF report, which the server saves in the specified location and notifies the user. The output is the sent PDF report.

[1464] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1465] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1466] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1467] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1468] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1469] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1470] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1471] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1472] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1473] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1474] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1475] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1476] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1477] 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.

[1478] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1479] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1480] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1481] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1482] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1483] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1484] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1485] The following is further disclosed regarding the above embodiment.

[1486] (Claim 1)

[1487] a means for collecting air quality data;

[1488] a means for storing the collected air quality data in a time series;

[1489] a means for visualizing the stored air quality data;

[1490] A means of generating reports based on the visualized data;

[1491] a means for periodically outputting the generated reports;

[1492] A system including:

[1493] (Claim 2)

[1494] means for classifying the air quality data based on a designated sensor identifier;

[1495] 10. The system of claim 1, further comprising means for aggregating the categorized data.

[1496] (Claim 3)

[1497] The system of claim 1, further comprising means for displaying the visualized data on an internet browser.

[1498] "Example 1"

[1499] (Claim 1)

[1500] a means for collecting air quality data;

[1501] a means for storing the collected air quality data in a time series;

[1502] a means for retrieving the stored air quality data;

[1503] a means for visualizing the acquired air quality data;

[1504] means for generating a diagram for visualization;

[1505] A means of generating reports based on the visualized data;

[1506] a means for periodically outputting the generated reports;

[1507] A system including:

[1508] (Claim 2)

[1509] means for classifying the air quality data based on a designated identifier;

[1510] 10. The system of claim 1, further comprising means for aggregating the categorized data.

[1511] (Claim 3)

[1512] The system of claim 1, further comprising means for displaying the visualized data on a network browser.

[1513] "Application Example 1"

[1514] (Claim 1)

[1515] a means for collecting air quality data;

[1516] a means for storing the collected air quality data in a time series;

[1517] a means for visualizing the stored air quality data;

[1518] a means for generating reports based on the visualized air quality data;

[1519] a means for periodically outputting the generated reports;

[1520] means for detecting anomalies in the air quality data and notifying a user;

[1521] A system including:

[1522] (Claim 2)

[1523] means for classifying the air quality data based on a designated sensor identifier;

[1524] 10. The system of claim 1, further comprising means for aggregating the classified data and calculating statistics.

[1525] (Claim 3)

[1526] The system according to claim 1, further comprising means for displaying the visualized data on an application of a terminal.

[1527] "Example 2: Combining Emotion Engines"

[1528] (Claim 1)

[1529] a means for collecting air quality data;

[1530] a means for storing the collected air quality data in a time series;

[1531] a means for visualizing the stored air quality data;

[1532] A means of generating reports based on the visualized data;

[1533] a means for periodically outputting the generated reports;

[1534] means for analyzing user emotions;

[1535] means for storing the analyzed emotion data in association with the air quality data;

[1536] A system including:

[1537] (Claim 2)

[1538] means for classifying the air quality data based on a designated sensor identifier;

[1539] 10. The system of claim 1, further comprising means for aggregating the categorized data.

[1540] (Claim 3)

[1541] The system of claim 1, further comprising means for displaying the visualized data on an internet browser.

[1542] "Application example 2 when combining emotion engines"

[1543] (Claim 1)

[1544] a means for collecting air quality data;

[1545] a means for storing the collected air quality data in a time series;

[1546] a means for visualizing the stored air quality data;

[1547] A means of generating reports based on the visualized data;

[1548] a means for periodically outputting the generated reports;

[1549] means for collecting emotion data using an emotion engine that recognizes and analyzes emotion data of a user;

[1550] means for storing the emotion data together with the air quality data;

[1551] a means of visualizing the association between emotion data and air quality data;

[1552] A system including:

[1553] (Claim 2)

[1554] means for classifying the air quality data based on a designated sensor identifier;

[1555] 10. The system of claim 1, further comprising means for aggregating the categorized data.

[1556] (Claim 3)

[1557] 10. The system of claim 1, further comprising means for displaying the visualized data and the emotion data on an internet browser. [Explanation of symbols]

[1558] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting air quality data; a means for storing the collected air quality data in a time series; a means for visualizing the stored air quality data; A means of generating reports based on the visualized data; a means for periodically outputting the generated reports; A system including:

2. means for classifying the air quality data based on a designated sensor identifier; 10. The system of claim 1, further comprising means for aggregating the categorized data.

3. The system of claim 1 , further comprising: means for displaying the visualized data on an internet browser.

Images