System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting audio data in a classroom; means for converting the collected audio data into text data; means for summarizing the converted text data; and means for providing the summarized data to a caregiver.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] In recent years, opportunities for parents to directly check on their children at school and in the classroom have decreased. This has made it difficult to keep track of their children's development and daily activities. Furthermore, teachers have limited time to devote to new initiatives due to their heavy workloads. Furthermore, it is difficult to quickly detect and respond to bullying and inappropriate language in the classroom, presenting many challenges. For this reason, there is a need for a method to support children's development and provide a sense of security by collecting and analyzing children's voices and sounds in the classroom and providing the information to parents. [Means for solving the problem]

[0005] The present invention provides a system including a means for collecting voice data from within a classroom, a means for converting the collected voice data into text data, a means for summarizing the converted text data, and a means for providing the summarized data to parents. Furthermore, by including a means for receiving and saving the collected voice data, a means for analyzing the converted text data and generating analysis results, and a means for outputting the generated analysis results in report format, it is possible to provide parents with detailed information on their child's daily development and classroom behavior. Furthermore, by including a means for detecting specific keywords and generating alerts, it is possible to quickly discover and respond to problems such as bullying and the use of inappropriate language.

[0006] "Classroom audio data" refers to audio information that records the remarks, conversations, and voices of children and teachers in a classroom environment.

[0007] "Means of collection" refers to the equipment and technology that captures audio data in the classroom using microphones or other audio capture devices.

[0008] "Means for converting into text data" refers to processes and devices that use speech recognition technology to convert collected voice data into a natural language text format.

[0009] "Summarizing means" refers to the process and apparatus that uses machine learning techniques, such as generative AI models, to summarize the converted text data and extract key points or highlights.

[0010] "Means for providing to parents" refers to a system that allows parents to access and view the generated summary data via the Internet using a web portal, mobile application, etc.

[0011] "Means for receiving and storing" refers to the process and device that stores the collected and converted voice data on a server or database.

[0012] "Means for analyzing and generating analytical results" refers to the processes and devices used to analyze the converted text data and derive specific patterns or insights from it.

[0013] The "means for outputting in report format" refers to a process and device that generates and outputs a report in an easy-to-understand format to communicate the analysis results to parents.

[0014] "Means for detecting specific keywords and generating alerts" refers to processes and devices that detect specific words or phrases in voice data or converted text data in real time and generate alert notifications based on the detection results. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram 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

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

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

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

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

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

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

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

[0023] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0036] This invention relates to a system that collects and analyzes children's voices and sounds in the classroom and provides parents with information about their children's growth and daily life. This system consists of multiple means for collecting, converting, analyzing, summarizing, and providing voice data.

[0037] System Configuration

[0038] 1. Terminal (sound collection microphone and processing device installed in the classroom)

[0039] Microphones installed in the classroom collect the children's conversations and comments in real time, and this audio data is automatically converted into text data by voice recognition software installed on the device.

[0040] 2. Server (centralized processing system)

[0041] The system receives and stores text data sent from the device. The server extracts important information from the received data and summarizes the text data using generative AI technology. It also generates a detailed report based on the analysis results and provides it to parents.

[0042] 3. User (Parent)

[0043] Parents can access the generated reports through a dedicated web portal or mobile app to view their child's daily activities and development.

[0044] Program processing flow

[0045] Audio data collection and text conversion

[0046] The devices use microphones installed in the classroom to capture the children's voices. This voice data is converted into text using speech recognition software. For example, by using the Google® Speech Recognition API, speech can be converted into text with high accuracy.

[0047] Sending data

[0048] The converted text data is sent to the server using a secure communication protocol (e.g., HTTPS).

[0049] Receiving and storing data

[0050] The server stores the received text data in a database and prepares it for further processing, after which the stored data can be retrieved and used for analysis.

[0051] Generative AI summarization

[0052] The server analyzes the stored text data using generative AI (e.g., Hugging Face's T5 model) to summarize the highlights and important information from the lesson. This summary forms the basis of the generated report.

[0053] Generate and deliver reports

[0054] Based on the summarized data, the server generates reports for parents, detailing their child's engagement and classroom behavior, and provides these reports to parents via a web portal or mobile app.

[0055] Specific examples

[0056] For example, consider the following conversation taking place in a classroom one day:

[0057] Teacher: "We're starting math today. Are you all ready?"

[0058] Child A: "Yes!"

[0059] Child B: "I'll do my best!"

[0060] This voice data is collected by a microphone and converted into text data by the device's voice recognition software:

[0061] "Today we will begin our math lesson. Are you all ready? Yes! Let's do our best!"

[0062] The server receives this text data and summarizes it as follows:

[0063] "Today's lesson was about math. The children participated actively and worked hard in the lesson."

[0064] Based on this summary, the server generates a report for parents and provides it to them via a web portal or mobile app, allowing them to understand their child's learning progress and daily progress.

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] Device:

[0068] Microphones installed in classrooms collect children's voices and sounds in real time. The microphones are placed in positions suitable for the classroom environment to effectively capture children's conversations and comments.

[0069] Step 2:

[0070] Device:

[0071] The collected voice data is converted into text data using voice recognition software installed on the device. This voice recognition software can convert voice data into text with high accuracy using, for example, the Google Speech Recognition API.

[0072] Step 3:

[0073] Device:

[0074] The converted text data is sent to the server using a secure communication protocol (e.g., HTTPS), which is used to ensure data integrity and security.

[0075] Step 4:

[0076] server:

[0077] The server receives text data sent from the device via the endpoint, processes the received data in real time, and stores it in a database.

[0078] Step 5:

[0079] server:

[0080] Generative AI technology (such as Hugging Face's T5 model) is used to analyze the stored text data, extracting important highlights and key points from the data and summarizing the text data.

[0081] Step 6:

[0082] server:

[0083] The summarized data is used to generate a report for parents, which includes lesson highlights, children's engagement, and any interesting behaviors observed.

[0084] Step 7:

[0085] server:

[0086] The generated reports are uploaded to a web portal or mobile application for parents to log in through a dedicated authentication system and view reports on their child's daily life and development.

[0087] Step 8:

[0088] User (Parent):

[0089] Parents can access the web portal or mobile application and view the reports provided, giving them detailed insight into their child's progress and classroom activities.

[0090] Step 9:

[0091] server:

[0092] Furthermore, the server continuously analyzes collected voice data and detects specific keywords in the text data (e.g., signs of bullying or inappropriate language) in real time. If detected, an alert is generated and relevant parties are notified, allowing for a prompt response.

[0093] Example 1

[0094] 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."

[0095] In conventional educational environments, it has been difficult to record children's comments and activities in detail in the classroom and provide appropriate and timely feedback to parents. Furthermore, converting audio data into text and summarizing it is time-consuming, making it difficult to operate efficiently. Furthermore, there has been a lack of means to quickly detect abnormalities or important information in specific situations and provide appropriate alerts.

[0096] 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.

[0097] In this invention, the server includes means for receiving and storing collected voice data, means for transmitting converted text data using a secure communication protocol, and means for summarizing the converted text data, thereby enabling efficient analysis of the activities and comments of children in the classroom and timely provision of the summary results to parents.

[0098] "Audio data" refers to electrical signals collected in the classroom, including children's voices, speech, and other environmental sounds.

[0099] "Text data" refers to character string information converted from voice data using voice recognition technology.

[0100] A "secure communication protocol" refers to a communication method that includes encryption technology to ensure high security when sending and receiving data. For example, HTTPS is an example of this.

[0101] A "summary" refers to information that extracts important information from collected text data and summarizes it briefly.

[0102] "Report format" refers to a document in which the analysis results are organized visually or in writing and processed into a format that is easy for parents to understand.

[0103] A "generative artificial intelligence model" refers to a machine learning model trained to analyze and summarize text data using natural language processing.

[0104] "Web portal or mobile communication device" means an interface through which parents access generated reports over the internet, including websites and smartphone apps.

[0105] This invention relates to a system that collects and analyzes children's voices and sounds in the classroom and provides parents with information about their children's growth and daily life. This system consists of multiple means for collecting, converting, analyzing, summarizing, and providing voice data.

[0106] System Configuration

[0107] 1. Terminal (sound collection microphone and processing device installed in the classroom)

[0108] The devices are equipped with microphones installed in classrooms that collect children's conversations and comments in real time. This audio data is then automatically converted into text data using the device's built-in voice recognition software. Specifically, the Google Speech Recognition API is used, which provides highly accurate voice recognition and converts the audio collected by the microphones into text.

[0109] Examples:

[0110] The teacher says, "Today we're going to start math class. Are you all ready?" Child A responds, "Yes!" and Child B responds, "I'll do my best!" The audio data of this exchange is captured by a sound-collecting microphone.

[0111] 2. Server (centralized processing system)

[0112] The server receives the text data sent from the device and stores it in a database. The stored text data is analyzed using a generative AI model (e.g., Hugging Face's T5 model) to summarize important information. This summary text becomes the basis for a report and is provided to parents.

[0113] Examples:

[0114] The server receives text data saying, "Today we will begin math class. Are you all ready? Yes! Let's do our best!" and summarizes it as, "In today's class, we learned about math. The children actively participated and worked hard in class."

[0115] 3. User (Parent)

[0116] Parents can access the generated reports via a dedicated web portal or mobile app to track their child's daily activities and progress.

[0117] Audio data collection and text conversion

[0118] The devices use microphones installed in the classroom to capture the children's voices, which are then converted into text using speech recognition software (Google Speech Recognition API), resulting in highly accurate speech-to-text data.

[0119] Sending data

[0120] The converted text data is sent to the server using a secure communication protocol (e.g., HTTPS). The data is encrypted during transmission to ensure security.

[0121] Receiving and storing data

[0122] The server stores the received text data in a database for further processing, and the stored data is indexed for efficient access.

[0123] Generative AI summarization

[0124] The server analyzes the stored text data using a generative AI model (Hugging Face's T5 model) to summarize key information. This summarized text is used as the basis for the report.

[0125] Generate and deliver reports

[0126] Based on the summarized data, the server generates detailed reports for parents, which are made available to them via a web portal and mobile app.

[0127] Prompt Sentence Examples

[0128] "Given the following text as input, generate a lesson summary: 'Today we'll start our math lesson. Are you all ready? Yes! Let's do our best!'"

[0129] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0130] Step 1:

[0131] Audio data collection

[0132] The device uses a microphone installed in the classroom to collect children's conversations and comments in real time. Audio data is input into the microphone, converted into a digital signal, and sent to the device. Specifically, the microphone captures the audio signal and stores it as data on the device.

[0133] Input: Audio signal in the classroom, Output: Digital audio data

[0134] Step 2:

[0135] Converting audio data to text

[0136] The device converts the collected voice data into text data using the Google Speech Recognition API. The voice data is input into the API and the corresponding text is output. Specifically, the voice recognition software analyzes the voice data and generates text data.

[0137] Input: Digital audio data, Output: Text data

[0138] Step 3:

[0139] Sending text data

[0140] The terminal transmits the converted text data to the server using a secure communication protocol (e.g., HTTPS). The text data is encrypted, input into the communication protocol, and transmitted to the server. Specifically, the text data is encrypted using the HTTPS protocol.

[0141] Input: Text data, Output: Encrypted text data (received on the server side)

[0142] Step 4:

[0143] Receiving and storing data

[0144] The server stores the received text data in a database. The encrypted data is decrypted and entered into the database for storage. Specifically, the server decrypts the encrypted data and stores it in the database.

[0145] Input: Encrypted text data, Output: Text data stored in the database

[0146] Step 5:

[0147] Generative AI summarization

[0148] The server analyzes the stored text data using a generative AI model (Hugging Face's T5 model) to summarize important information. The text data is input into the AI ​​model, which outputs a summary text. Specifically, the AI ​​model analyzes the text, extracts key points, and generates a summary.

[0149] Input: Text data stored in a database, Output: Summarized text data

[0150] Step 6:

[0151] Generate and deliver reports

[0152] The server uses the summarized data to create a detailed report for parents. The summarized data is input into a reporting tool, which outputs the report in HTML or PDF format. Specifically, the server embeds the summarized data into a template and generates the report.

[0153] The report is then made accessible to parents through a web portal or mobile app, where parents can access the portal, view the generated report, and download it if desired.

[0154] Input: Summarized text data, Output: Parent-readable report

[0155] (Application example 1)

[0156] 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."

[0157] In today's factories, it is difficult to grasp the work situation in real time and manage it efficiently. In particular, there is a lack of means to effectively utilize information obtained from communication between workers and work sounds, which can make it difficult to improve work efficiency or ensure safety. Therefore, there is a need for a system that uses voice data to visualize the work situation in the factory and supports work progress management and identification of areas for improvement.

[0158] 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.

[0159] In this invention, the server includes a voice data collection means, a text conversion means, a summarization means, an analysis result generation means, a report output means, and an alert generation means, which allows the work status to be grasped in real time from the voice data, thereby improving work efficiency and ensuring safety.

[0160] A "factory" is a workplace where goods are manufactured or processed, a facility where machines and equipment operate, and workers perform their work.

[0161] "Audio data" is data that represents audio in a digital format, and is information collected using an audio input device such as a microphone.

[0162] "Collection means" refers to devices or software for collecting specific information or data, and in the case of audio data, includes a microphone.

[0163] "Text data" is digital data expressed in characters or sentences, and is converted from voice data using voice recognition technology.

[0164] "Summarization means" refers to technologies or devices for concisely summarizing large amounts of information or text data, including generative AI models.

[0165] A "worker" is a worker who works in a factory, operating machinery or manufacturing goods.

[0166] A "manager" is a person in charge of factory operations and supervising workers, and is responsible for work efficiency and quality control.

[0167] "Analysis tools" are software or devices used to analyze collected data and extract patterns and important information.

[0168] "Report output means" refers to a device or software for displaying or printing analyzed data and summary results in report format.

[0169] An "alert mechanism" is a device or software that generates a warning or notification when a specified condition is met.

[0170] The present invention is a system for real-time understanding and efficient management of work conditions in a factory. A specific embodiment of this system is described below.

[0171] System Configuration

[0172] 1. Terminal (sound collection microphone and processing device installed in the factory)

[0173] The terminal is a device that processes sound-collecting microphones and data installed in factories. The microphones collect workers' conversations and work sounds in real time. The collected voice data is automatically converted into text data by the terminal's voice recognition software. Specifically, the Google Speech Recognition API is used to convert voice into text with high accuracy.

[0174] 2. Server (centralized processing system)

[0175] The server receives and stores text data sent from the device, extracts important information from the received data, summarizes the text data using generative AI technology, and generates a detailed report based on the analysis results, which is provided to operators and administrators.

[0176] 3. Users (operators, administrators)

[0177] Users can access the generated reports via a dedicated web portal or mobile app to check the status of operations within the factory and receive advice on how to improve efficiency.

[0178] Program processing flow

[0179] Audio data collection and text conversion

[0180] The device uses microphones installed in the factory to capture the voices and sounds of workers. This voice data is converted into text using speech recognition software. For example, by using the Google Speech Recognition API, speech can be converted into text with high accuracy.

[0181] Sending data

[0182] The converted text data is sent to the server using a secure communication protocol (e.g., HTTPS).

[0183] Receiving and storing data

[0184] The server stores the received text data in a database and prepares it for further processing, after which the stored data can be retrieved and used for analysis.

[0185] Generative AI summarization

[0186] On the server, the stored text data is analyzed using generative AI (e.g., Hugging Face's T5 model) to summarize the highlights and important information of the work. This summary forms the basis of the generated report.

[0187] Generate and deliver reports

[0188] Based on the summarized data, the server generates reports for operators, including progress reports and recommendations for improving efficiency, which are then made available to operators and managers via a web portal or mobile app.

[0189] Specific examples

[0190] For example, if the following conversation takes place on a work site:

[0191] Worker A: "Next, I'll assemble part number 1234."

[0192] Worker B: "Got it. Tools are ready."

[0193] The collected audio data is transcribed and summarized as follows:

[0194] Summary: Worker A has started assembling part number 1234, and Worker B has finished preparing the tooling.

[0195] Prompt Sentence Examples

[0196] By prefaced the collected text data with the prompt "Summarize today's work:" as the input to the generative AI model, the data can be made suitable for the T5 model.

[0197] Prompt: Summary of today's tasks: Next we will assemble part number 1234. Got it. Tools are ready.

[0198] This approach makes it possible to visualize the work status within the factory and to make operational improvements quickly and effectively.

[0199] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0200] Step 1:

[0201] The terminal collects audio data using microphones installed in the factory. Specifically, it captures the conversations and work sounds of workers in real time. The input data is audio data, and the output is the collected raw audio data.

[0202] Step 2:

[0203] The device converts the collected voice data into text data using speech recognition software. Specifically, it uses the Google Speech Recognition API to convert the voice data into text with high accuracy. The input data is voice data, and the output is the corresponding text data.

[0204] Step 3:

[0205] The terminal transmits the converted text data to the server using a secure communication protocol (e.g., HTTPS). Specifically, the text data is encoded using the HTTPS protocol and transmitted to the server. The input data is the text data, and the output is a transmission completion status to the server.

[0206] Step 4:

[0207] The server saves the received text data in a database and prepares it for subsequent processing. Specifically, it receives the text data and stores it in a database. The input data is the text data, and the output is a status indicating whether it has been saved to the database.

[0208] Step 5:

[0209] The server analyzes the stored text data using a generative AI model (e.g., Hugging Face's T5 model) to extract and summarize important information. Specifically, the text data is fed as input to the T5 model along with the prompt, and a summary is generated. The input data is the stored text data and the prompt, and the output is the summarized text data.

[0210] Step 6:

[0211] The server creates a report for the operator based on the summarized data. Specifically, it formats the summarized data and composes it into a report document. The input data is summarized text data, and the output is a document in report format.

[0212] Step 7:

[0213] The server provides the generated report to the user (operator, administrator) through a web portal or mobile app. Specifically, it uploads the report document to the database of the web portal or mobile app and makes it accessible to the user. The input data is a report-formatted document, and the output is the report provision status that can be accessed by the user.

[0214] 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.

[0215] This invention is a system that collects and analyzes voice data from children in educational settings and provides information to parents based on that data. Furthermore, this system incorporates an emotion engine that recognizes and analyzes children's emotional states. This system consistently performs all processes, from collecting voice data to converting it to text, summarizing it, recognizing emotions, and generating and providing reports.

[0216] System Configuration

[0217] 1. Terminal (sound collection microphone and processing device installed in the classroom)

[0218] Microphones installed in classrooms collect children's conversations and comments in real time. The microphones are positioned to effectively capture the speech of teachers and students. This audio data is processed within the device.

[0219] 2. Voice recognition and data transmission

[0220] The audio data collected in the classroom is converted into text data using speech recognition software installed on the device, such as the Google Speech Recognition API, and then transmitted to a server via a secure communication protocol (such as HTTPS).

[0221] 3. Server (Centralized Processing System)

[0222] The server receives the text data sent from the device and stores it in a database. The stored text data is then summarized using generative AI technology (such as the T5 model of Hugging Face). At the same time, an emotion engine analyzes the text data and recognizes the child's emotions.

[0223] 4. Emotion Engine

[0224] The emotion engine implemented on the server analyzes the converted text data and identifies the user's emotions, such as joy, sadness, anger, etc. This engine utilizes, for example, natural language processing (NLP) techniques and machine learning algorithms.

[0225] 5. Report Generation

[0226] Based on the summary data and emotion recognition results, the server generates a detailed report for parents, which includes highlights of their child's daily learning progress and emotional state, and is provided to parents via a web portal and mobile app.

[0227] Program Processing Details

[0228] Audio data collection and text conversion

[0229] The device collects voice data from within the classroom and converts it into text data using voice recognition software. For example, using voice recognition technology, a voice saying, "Today is math class. Are you all ready?" can be converted into text as, "Today is math class. Are you all ready?"

[0230] Sending data

[0231] Text data from the device is sent to the server using a secure communication protocol, which receives the data and stores it in a database.

[0232] Summarizing text data

[0233] The server uses generative AI technology to summarize the received text data, for example generating an overall summary of the day's lessons, such as "Today we had math class. The children asked questions enthusiastically and achieved many results."

[0234] emotion recognition

[0235] The emotion engine implemented on the server analyzes the text data and identifies the emotional state of the children. For example, it recognizes the emotion of "joy" from the text "I had a lot of fun today."

[0236] Report Generation

[0237] Based on the summarized data and emotion recognition results, a detailed report is generated for parents, such as, "Today we had math class and the children actively participated. They seemed to be having fun."

[0238] Providing reports

[0239] The generated reports are provided to parents via a web portal or mobile application, allowing them to understand their child's growth, learning progress, and emotional state.

[0240] Specific examples

[0241] For example, consider the following conversation taking place during a classroom lesson:

[0242] Teacher: "We're starting math today. Are you all ready?"

[0243] Child A: "Yes!"

[0244] Child B: "I'll do my best!"

[0245] This audio is collected and transcribed by speech recognition software as follows:

[0246] "Today we will begin our math lesson. Are you all ready? Yes! Let's do our best!"

[0247] The server receives this text data and summarizes it as follows:

[0248] "We had a math lesson today. The children came prepared and engaged in the lesson."

[0249] At the same time, the emotional data analyzed by the emotion engine indicates "joy" and "high motivation," which are incorporated into the report.

[0250] When parents access this report, they can see things like, "Today we had math class, and the children were actively engaged. They seemed to be particularly enjoying themselves." This will enable parents to get a detailed understanding of their children's daily learning and emotional changes.

[0251] The processing flow will be explained below.

[0252] Step 1:

[0253] Device:

[0254] Microphones installed in classrooms collect children's conversations and comments in real time. The microphones are placed in the center of the classroom or in key locations to capture all surrounding sounds, allowing the entire situation in the classroom to be understood.

[0255] Step 2:

[0256] Device:

[0257] The collected voice data is converted into text data using voice recognition software (e.g., Google Speech Recognition API) installed on the device. Voice recognition software has the ability to process natural language and can convert voice into text with high accuracy.

[0258] Step 3:

[0259] Device:

[0260] The converted text data is sent to the server using a secure communication protocol (e.g., HTTPS), which is important to maintain the confidentiality and integrity of the data.

[0261] Step 4:

[0262] server:

[0263] The server receives text data sent from the terminal via the endpoint, and stores the received text data in a database for subsequent analysis and processing.

[0264] Step 5:

[0265] server:

[0266] The stored text data is analyzed using generative AI technology (e.g., Hugging Face's T5 model), which extracts important information and generates a summary. The generative AI combines multiple summarization techniques to provide a summary that contains the most useful information.

[0267] Step 6:

[0268] server:

[0269] At the same time, an emotion engine implemented on the server analyzes the text data and recognizes the children's emotional state. The emotion engine uses natural language processing (NLP) technology to extract emotional nuances from the text and identify emotions such as "joy," "sadness," and "anger."

[0270] Step 7:

[0271] server:

[0272] The summarized data and emotion recognition results are used to generate a detailed report for parents, including lesson highlights, children's engagement, and observed emotional states.

[0273] Step 8:

[0274] server:

[0275] The generated reports are uploaded to a web portal or mobile application for parental access, and an authentication system ensures that only parents can access and review the reports.

[0276] Step 9:

[0277] User (Parent):

[0278] Parents can log in to a dedicated web portal or mobile application and view the provided reports, which provide detailed insight into their child's academic progress, engagement and emotional state.

[0279] Step 10:

[0280] server:

[0281] The system detects specific keywords in real time from collected voice and text data, and uses an emotion engine to identify signs of negative emotions or bullying. If any are identified, the server automatically generates an alert and notifies teachers and administrators, enabling a rapid response.

[0282] Example 2

[0283] 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."

[0284] In conventional educational systems, teachers and parents spend a lot of time and effort trying to understand the situation of children in the classroom. Furthermore, there are insufficient means to effectively monitor children's emotional state and learning status, making it difficult for parents to understand their children's daily learning and emotional changes in detail. Therefore, there is a need for a system that can effectively and efficiently collect and analyze classroom voice data and provide information to parents.

[0285] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0286] In this invention, the server includes means for collecting voice data in the classroom, means for converting the collected voice data into text data, means for summarizing the converted text data and generating summary data, means for analyzing the text data and recognizing emotional states, means for generating a report for parents based on the generated summary data and emotional states, and means for providing the generated report to parents. This makes it possible to effectively collect and analyze voice data in the classroom and monitor in detail the learning status and emotional states of children.

[0287] Below are definitions of important words.

[0288] "Means for collecting audio data in the classroom" refers to a series of processes for collecting audio generated in the classroom using a sound collection device such as a microphone.

[0289] The "means for converting collected voice data into text data" refers to a process for converting collected voice data into text data as character information using voice recognition technology.

[0290] "Means for summarizing the converted text data and generating summary data" refers to the process of using generative AI technology to concisely summarize the content of the converted text data and generate summary data.

[0291] The "means for analyzing text data to recognize emotional states" refers to a process of identifying emotions in text data using natural language processing techniques and recognizing the emotional states.

[0292] The "means for generating a report for parents based on the generated summary data and emotional state" is a process of integrating the summary data and the results of the emotion analysis to generate a report in a format that is easy for parents to understand.

[0293] "Means for providing generated reports to parents" refers to the process by which generated reports are sent to parents and made available for viewing through a web portal or mobile application.

[0294] "Means for receiving and storing voice data" refers to the process of receiving voice data and converted text data sent from the terminal to the server and storing them in a database.

[0295] The "means for analyzing and generating summary data and emotional states" refers to a series of processes for analyzing the converted text data and generating summary data and emotional states.

[0296] The "means for detecting specific keywords from collected voice data" is a process for identifying and detecting specific keywords from text data that has been speech-recognized.

[0297] The "means for generating alerts based on keywords" is a process for generating alerts and notifying users when certain conditions are met based on detected keywords.

[0298] The present invention is a system that collects and analyzes speech data from children in educational settings and provides information to parents based on the collected data. In particular, this system performs a comprehensive process from collecting speech data to converting it into text, summarizing it, recognizing emotions, and generating and providing reports. Specific embodiments for implementing this system are described below.

[0299] 1. Collection of audio data

[0300] The device collects audio from within the classroom

[0301] Microphones installed in classrooms collect children's conversations and teacher comments in real time. These microphones are positioned to effectively capture what the teacher and students are saying. For example, if a teacher says, "Today's math class. Are you all ready?", that voice will be collected by the microphones.

[0302] 2. Speech-to-text

[0303] The device converts the voice data into text data.

[0304] Using speech recognition software installed on the device (such as Google Speech Recognition API), the collected voice data is converted into text data in real time. For example, the aforementioned speech "Today is math class. Are you all ready?" is converted directly into text data.

[0305] 3. Data transmission and storage

[0306] The device sends text data to the server.

[0307] The generated text data is sent to a server using a secure communication protocol (e.g., HTTPS). This secure communication prevents data leakage and tampering.

[0308] The server receives and stores the text data.

[0309] The server receives the text data sent from the device and stores it in a database. For example, the text "Today is math class. Are you all ready?" is stored in the database as is.

[0310] 4. Summarizing Text Data

[0311] The server summarizes the text data

[0312] The server uses generative AI technology (e.g., Hugging Face's T5 model) to summarize the received text data. For example, a summary of the day's lessons might be generated, such as, "Today we had math class. The children asked questions enthusiastically and achieved many results."

[0313] 5. Emotion recognition

[0314] The server analyzes the text data and recognizes the emotional state.

[0315] The emotion engine installed on the server uses natural language processing technology to analyze the text data and identify the emotional state of the children. For example, the emotion of "joy" can be recognized from the text "I had a lot of fun today."

[0316] 6. Report Generation

[0317] The server generates a report that integrates the summary data and the sentiment results.

[0318] The server generates a detailed report for parents based on the summary data and emotion recognition results, such as, "Today, we had math class, and the children actively participated. They seemed to be having fun."

[0319] 7. Report provision

[0320] The server provides the generated report to the parent.

[0321] The generated reports are provided to parents via a web portal or mobile application, allowing them to gain detailed insight into their child's academic progress and emotional state.

[0322] Examples of prompt statements

[0323] Example 1: "Please transcribe what is said in class. Input speech: 'Today is math class. Are you all ready?'"

[0324] Example 2: "Summarize the following text. Input text: 'Today is math class. Are you all ready? Yes! Let's do our best!'"

[0325] Example 3: "Recognize the emotion in the following text. Input text: 'I had a lot of fun today.'"

[0326] In this way, the system of the present invention allows parents to easily and in detail understand their children's learning situation and emotional state through a series of processes: collecting voice data in the classroom, converting it into text data, summarizing it, recognizing emotions, and generating and providing reports.

[0327] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0328] Processing Steps

[0329] Step 1: Collecting audio data

[0330] The device collects audio from within the classroom

[0331] A microphone installed on each device collects speech in the classroom in real time. This microphone is positioned to effectively capture speech from the teacher and students. For example, the input collected is the voice of a teacher saying, "Today's math class. Are you all ready?" Real-time audio data is generated as the output.

[0332] Step 2: Speech to text

[0333] The device converts the voice data into text data.

[0334] Using speech recognition software installed on the device, the collected voice data is converted into text data in real time. For example, the input voice is "Today is math class. Are you all ready?", and this voice data is converted and output as text data saying "Today is math class. Are you all ready?"

[0335] Step 3: Sending data

[0336] Send text data from the device to the server

[0337] The generated text data is sent to the server using a secure communication protocol (e.g., HTTPS). For example, the text data converted on the terminal, "Today is math class. Are you all ready?", is sent to the server as input. The server receives the text data as output.

[0338] Step 4: Save your data

[0339] The server receives and stores the text data.

[0340] The server receives the text data sent from the terminal and stores it in a database. As input, it receives the text data "Today is math class. Are you all ready?" and stores it in the database as output. The data is stored in the database along with the collection time and sender information.

[0341] Step 5: Summarizing the text data

[0342] The server summarizes the text data

[0343] The server uses generative AI technology (e.g., a text summarization model) to concisely summarize the received text data. The input is the received text data, "Today is math class. Are you all ready?". The output is the summary data, "Today we had math class. The children participated enthusiastically."

[0344] Step 6: Emotion Recognition

[0345] The server analyzes the text data and recognizes the emotional state.

[0346] The emotion engine implemented on the server analyzes the text data using natural language processing technology to identify the children's emotional state. The input is the text data to be analyzed: "I had a lot of fun today." The emotional state "joy" is recognized as the output.

[0347] Step 7: Generate reports

[0348] The server generates a report that integrates the summary data and the sentiment results.

[0349] The server generates a detailed report for parents based on the summary data and emotion recognition results. The input is the summary data "Today we had a math class. The children participated enthusiastically" and the emotion data "joy." The output is a report stating, "Today we had a math class. The children participated enthusiastically. They seemed to be having a particularly good time."

[0350] Step 8: Reporting

[0351] The server provides the generated report to the parent.

[0352] The generated report is provided to parents through a web portal or mobile application. The input is the generated report: "Today we had math class and the children participated actively. They seemed to enjoy it especially." As an output, the report is sent to the parents, who can access and view it.

[0353] Through these steps, this system can efficiently collect and analyze classroom voice data and provide useful information to parents.

[0354] (Application example 2)

[0355] 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."

[0356] Traditional customer feedback systems rely on collecting opinions directly from customers or answering surveys, making it difficult to provide real-time feedback or perform detailed sentiment analysis. As a result, restaurants and food delivery companies continue to struggle to obtain effective data for improving customer satisfaction and employee training. Furthermore, improving employee response and speedy service improvements are difficult challenges.

[0357] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting voice data in the classroom, means for converting the collected voice data into text data, means for summarizing the converted text data, means for analyzing the text data and recognizing the emotional state, and means for providing the summarized data and the recognition result of the emotional state to the guardian. This makes it possible to obtain customer feedback in real time, analyze the emotional state, and quickly improve responses and train employees.

[0358] "Audio data" refers to audio information collected within a restaurant or a specific space, including conversations between customers and employees and environmental sounds.

[0359] "Text data" is digital data that has been converted from collected voice data into text information using voice recognition technology.

[0360] A "summary" is digital information that extracts important parts from text data and summarizes them in a concise form.

[0361] "Emotional state" is information that identifies a person's emotions (for example, joy, anger, sadness, etc.) obtained by analyzing text data.

[0362] "Parent" refers to the guardian or guardian of the child of the system user in an educational setting, but in this application example, it refers to the manager or person in charge of the restaurant to which the report is provided.

[0363] "Analysis results" are the information obtained by analyzing the collected text data and emotional state.

[0364] "Report" means a detailed report generated based on the Analysis Results and Emotion Recognition Results.

[0365] "Employee training" means using the collected and analyzed information to provide training and guidance to restaurant staff to improve the quality of their service.

[0366] "Improving customer service" means optimizing service content and delivery methods to improve customer satisfaction based on analyzed data and reports.

[0367] An "alert" is a warning message that is used to quickly notify an administrator of a specific situation based on collected voice data and key information.

[0368] To implement this invention, the following system and processing steps are required: First, a microphone is installed in the restaurant to collect sound data. This microphone collects conversations and environmental sounds in the restaurant in real time.

[0369] The device processes the voice data received from the microphone and converts it into text data. This conversion is performed using voice recognition software. For example, the Google Speech Recognition API can be used. The device then transmits the converted text data to a server using a secure communication protocol (e.g., HTTPS).

[0370] The server stores the received text data in a database and summarizes it using generative AI technology, such as the Hugging Face T5 model. At the same time, an emotion engine implemented on the server analyzes the text data and identifies the customer's emotional state. This emotion engine utilizes natural language processing technology and machine learning algorithms.

[0371] Based on the summarized data and emotion recognition results, the server generates a detailed report, which includes information for employee training and customer service improvement, and is provided to managers via a web portal or mobile application.

[0372] Specific examples

[0373] For example, consider the following conversation taking place in a restaurant:

[0374] Customer: "The roast duck was delicious today. It's just a shame that the service was a little slow."

[0375] This audio is collected and transcribed by speech recognition software as follows:

[0376] "The roast duck was delicious today. It's just a shame that the service was a little late."

[0377] The server receives this text data and summarizes it as follows:

[0378] "A customer who had roast duck today was pleased with the taste of the food, but was unhappy with the slow delivery."

[0379] At the same time, the emotional data analyzed by the emotion engine indicates "satisfaction" and "dissatisfaction," which are incorporated into the report.

[0380] When parents access this report, they can see that "the customer was satisfied with the taste of the food, but was dissatisfied with the slow delivery time." Based on this information, the restaurant can review the way staff respond and the time it takes to provide service.

[0381] Prompt Sentence Examples

[0382] "The roast duck was delicious today. It's just a shame that the service was a little late."

[0383] This system allows restaurants to understand customer satisfaction in real time and quickly improve their responses, making it easy to obtain data that can be used for employee training and service improvement.

[0384] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0385] Step 1:

[0386] The device collects audio data through a microphone installed in the restaurant. The input data includes conversations between customers and employees, as well as the surrounding environmental sounds. The collected audio data is temporarily stored in the device.

[0387] Step 2:

[0388] The device converts the collected voice data into text data using voice recognition software. Specifically, the voice recognition software (e.g., Google Speech Recognition API) analyzes the input voice data and converts it into corresponding text data. The text data is generated within the device.

[0389] Step 3:

[0390] The terminal transmits the converted text data to the server using a secure communication protocol (e.g., HTTPS), where the input is the converted text data and the output is the data transmission to the server.

[0391] Step 4:

[0392] The server stores the received text data in a database. The stored text data is used in subsequent processing steps. The input here is the text data sent from the terminal, and the output is the data stored in the database.

[0393] Step 5:

[0394] The server uses generative AI technology to summarize the stored text data. For example, the Hugging Face T5 model is used in this summarization process. The input is the stored text data, and the output is the summarized text data. Specifically, the important parts of the text data are extracted and summarized in a concise form.

[0395] Step 6:

[0396] The emotion engine installed on the server analyzes the summarized text data and identifies the customer's emotional state. The emotion engine utilizes natural language processing technology and machine learning algorithms. The input is the summarized text data, and the output is the identification result of the emotional state. Specifically, emotions such as joy, anger, and sadness are identified from the text content.

[0397] Step 7:

[0398] The server generates a detailed report based on the summarized data and emotion recognition results. The generated report contains information useful for employee training and improving customer service. The input is the summarized data and emotion recognition results, and the output is a report document.

[0399] Step 8:

[0400] The server provides the generated report to the administrator via a web portal or mobile application. The input here is the generated report, and the output is the report provided to the administrator. The administrator can access this report and check and implement improvements.

[0401] Through these processing steps, the system can collect and analyze customer feedback in real time, providing specific data that can be used to train employees and improve customer service.

[0402] 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.

[0403] 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.

[0404] 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.

[0405] [Second embodiment]

[0406] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0407] 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.

[0408] 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).

[0409] 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.

[0410] 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.

[0411] 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).

[0412] 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. 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.

[0413] 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.

[0414] 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.

[0415] 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.

[0416] 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.

[0417] 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."

[0418] This invention relates to a system that collects and analyzes children's voices and sounds in the classroom and provides parents with information about their children's growth and daily life. This system consists of multiple means for collecting, converting, analyzing, summarizing, and providing voice data.

[0419] System Configuration

[0420] 1. Terminal (sound collection microphone and processing device installed in the classroom)

[0421] Microphones installed in the classroom collect the children's conversations and comments in real time, and this audio data is automatically converted into text data by voice recognition software installed on the device.

[0422] 2. Server (centralized processing system)

[0423] The system receives and stores text data sent from the device. The server extracts important information from the received data and summarizes the text data using generative AI technology. It also generates a detailed report based on the analysis results and provides it to parents.

[0424] 3. User (Parent)

[0425] Parents can access the generated reports through a dedicated web portal or mobile app to view their child's daily activities and development.

[0426] Program processing flow

[0427] Audio data collection and text conversion

[0428] The devices use microphones installed in the classroom to capture the children's voices. This voice data is then converted into text using speech recognition software. For example, using the Google Speech Recognition API, speech can be converted into text with high accuracy.

[0429] Sending data

[0430] The converted text data is sent to the server using a secure communication protocol (e.g., HTTPS).

[0431] Receiving and storing data

[0432] The server stores the received text data in a database and prepares it for further processing, after which the stored data can be retrieved and used for analysis.

[0433] Generative AI summarization

[0434] The server analyzes the stored text data using generative AI (e.g., Hugging Face's T5 model) to summarize the highlights and important information from the lesson. This summary forms the basis of the generated report.

[0435] Generate and deliver reports

[0436] Based on the summarized data, the server generates reports for parents, detailing their child's engagement and classroom behavior, and provides these reports to parents via a web portal or mobile app.

[0437] Specific examples

[0438] For example, consider the following conversation taking place in a classroom one day:

[0439] Teacher: "We're starting math today. Are you all ready?"

[0440] Child A: "Yes!"

[0441] Child B: "I'll do my best!"

[0442] This voice data is collected by a microphone and converted into text data by the device's voice recognition software:

[0443] "Today we will begin our math lesson. Are you all ready? Yes! Let's do our best!"

[0444] The server receives this text data and summarizes it as follows:

[0445] "Today's lesson was about math. The children participated actively and worked hard in the lesson."

[0446] Based on this summary, the server generates a report for parents and provides it to them via a web portal or mobile app, allowing them to understand their child's learning progress and daily progress.

[0447] The processing flow will be explained below.

[0448] Step 1:

[0449] Device:

[0450] Microphones installed in classrooms collect children's voices and sounds in real time. The microphones are placed in positions suitable for the classroom environment to effectively capture children's conversations and comments.

[0451] Step 2:

[0452] Device:

[0453] The collected voice data is converted into text data using voice recognition software installed on the device. This voice recognition software can convert voice data into text with high accuracy using, for example, the Google Speech Recognition API.

[0454] Step 3:

[0455] Device:

[0456] The converted text data is sent to the server using a secure communication protocol (e.g., HTTPS), which is used to ensure data integrity and security.

[0457] Step 4:

[0458] server:

[0459] The server receives text data sent from the device via the endpoint, processes the received data in real time, and stores it in a database.

[0460] Step 5:

[0461] server:

[0462] Generative AI technology (such as Hugging Face's T5 model) is used to analyze the stored text data, extracting important highlights and key points from the data and summarizing the text data.

[0463] Step 6:

[0464] server:

[0465] The summarized data is used to generate a report for parents, which includes lesson highlights, children's engagement, and any interesting behaviors observed.

[0466] Step 7:

[0467] server:

[0468] The generated reports are uploaded to a web portal or mobile application for parents to log in through a dedicated authentication system and view reports on their child's daily life and development.

[0469] Step 8:

[0470] User (Parent):

[0471] Parents can access the web portal or mobile application and view the reports provided, giving them detailed insight into their child's progress and classroom activities.

[0472] Step 9:

[0473] server:

[0474] Furthermore, the server continuously analyzes collected voice data and detects specific keywords in the text data (e.g., signs of bullying or inappropriate language) in real time. If detected, an alert is generated and relevant parties are notified, allowing for a prompt response.

[0475] Example 1

[0476] 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."

[0477] In conventional educational environments, it has been difficult to record children's comments and activities in detail in the classroom and provide appropriate and timely feedback to parents. Furthermore, converting audio data into text and summarizing it is time-consuming, making it difficult to operate efficiently. Furthermore, there has been a lack of means to quickly detect abnormalities or important information in specific situations and provide appropriate alerts.

[0478] 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.

[0479] In this invention, the server includes means for receiving and storing collected voice data, means for transmitting converted text data using a secure communication protocol, and means for summarizing the converted text data, thereby enabling efficient analysis of the activities and comments of children in the classroom and timely provision of the summary results to parents.

[0480] "Audio data" refers to electrical signals collected in the classroom, including children's voices, speech, and other environmental sounds.

[0481] "Text data" refers to character string information converted from voice data using voice recognition technology.

[0482] A "secure communication protocol" refers to a communication method that includes encryption technology to ensure high security when sending and receiving data. For example, HTTPS is an example of this.

[0483] A "summary" refers to information that extracts important information from collected text data and summarizes it briefly.

[0484] "Report format" refers to a document in which the analysis results are organized visually or in writing and processed into a format that is easy for parents to understand.

[0485] A "generative artificial intelligence model" refers to a machine learning model trained to analyze and summarize text data using natural language processing.

[0486] "Web portal or mobile communication device" means an interface through which parents access generated reports over the internet, including websites and smartphone apps.

[0487] This invention relates to a system that collects and analyzes children's voices and sounds in the classroom and provides parents with information about their children's growth and daily life. This system consists of multiple means for collecting, converting, analyzing, summarizing, and providing voice data.

[0488] System Configuration

[0489] 1. Terminal (sound collection microphone and processing device installed in the classroom)

[0490] The devices are equipped with microphones installed in classrooms that collect children's conversations and comments in real time. This audio data is then automatically converted into text data using the device's built-in voice recognition software. Specifically, the Google Speech Recognition API is used, which provides highly accurate voice recognition and converts the audio collected by the microphones into text.

[0491] Examples:

[0492] The teacher says, "Today we're going to start math class. Are you all ready?" Child A responds, "Yes!" and Child B responds, "I'll do my best!" The audio data of this exchange is captured by a sound-collecting microphone.

[0493] 2. Server (centralized processing system)

[0494] The server receives the text data sent from the device and stores it in a database. The stored text data is analyzed using a generative AI model (e.g., Hugging Face's T5 model) to summarize important information. This summary text becomes the basis for a report and is provided to parents.

[0495] Examples:

[0496] The server receives text data saying, "Today we will begin math class. Are you all ready? Yes! Let's do our best!" and summarizes it as, "In today's class, we learned about math. The children actively participated and worked hard in class."

[0497] 3. User (Parent)

[0498] Parents can access the generated reports via a dedicated web portal or mobile app to track their child's daily activities and progress.

[0499] Audio data collection and text conversion

[0500] The devices use microphones installed in the classroom to capture the children's voices, which are then converted into text using speech recognition software (Google Speech Recognition API), resulting in highly accurate speech-to-text data.

[0501] Sending data

[0502] The converted text data is sent to the server using a secure communication protocol (e.g., HTTPS). The data is encrypted during transmission to ensure security.

[0503] Receiving and storing data

[0504] The server stores the received text data in a database for further processing, and the stored data is indexed for efficient access.

[0505] Generative AI summarization

[0506] The server analyzes the stored text data using a generative AI model (Hugging Face's T5 model) to summarize key information. This summarized text is used as the basis for the report.

[0507] Generate and deliver reports

[0508] Based on the summarized data, the server generates detailed reports for parents, which are made available to them via a web portal and mobile app.

[0509] Prompt Sentence Examples

[0510] "Given the following text as input, generate a lesson summary: 'Today we'll start our math lesson. Are you all ready? Yes! Let's do our best!'"

[0511] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0512] Step 1:

[0513] Audio data collection

[0514] The device uses a microphone installed in the classroom to collect children's conversations and comments in real time. Audio data is input into the microphone, converted into a digital signal, and sent to the device. Specifically, the microphone captures the audio signal and stores it as data on the device.

[0515] Input: Audio signal in the classroom, Output: Digital audio data

[0516] Step 2:

[0517] Converting audio data to text

[0518] The device converts the collected voice data into text data using the Google Speech Recognition API. The voice data is input into the API and the corresponding text is output. Specifically, the voice recognition software analyzes the voice data and generates text data.

[0519] Input: Digital audio data, Output: Text data

[0520] Step 3:

[0521] Sending text data

[0522] The terminal transmits the converted text data to the server using a secure communication protocol (e.g., HTTPS). The text data is encrypted, input into the communication protocol, and transmitted to the server. Specifically, the text data is encrypted using the HTTPS protocol.

[0523] Input: Text data, Output: Encrypted text data (received on the server side)

[0524] Step 4:

[0525] Receiving and storing data

[0526] The server stores the received text data in a database. The encrypted data is decrypted and entered into the database for storage. Specifically, the server decrypts the encrypted data and stores it in the database.

[0527] Input: Encrypted text data, Output: Text data stored in the database

[0528] Step 5:

[0529] Generative AI summarization

[0530] The server analyzes the stored text data using a generative AI model (Hugging Face's T5 model) to summarize important information. The text data is input into the AI ​​model, which outputs a summary text. Specifically, the AI ​​model analyzes the text, extracts key points, and generates a summary.

[0531] Input: Text data stored in a database, Output: Summarized text data

[0532] Step 6:

[0533] Generate and deliver reports

[0534] The server uses the summarized data to create a detailed report for parents. The summarized data is input into a reporting tool, which outputs the report in HTML or PDF format. Specifically, the server embeds the summarized data into a template and generates the report.

[0535] The report is then made accessible to parents through a web portal or mobile app, where parents can access the portal, view the generated report, and download it if desired.

[0536] Input: Summarized text data, Output: Parent-readable report

[0537] (Application example 1)

[0538] 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."

[0539] In today's factories, it is difficult to grasp the work situation in real time and manage it efficiently. In particular, there is a lack of means to effectively utilize information obtained from communication between workers and work sounds, which can make it difficult to improve work efficiency or ensure safety. Therefore, there is a need for a system that uses voice data to visualize the work situation in the factory and supports work progress management and identification of areas for improvement.

[0540] 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.

[0541] In this invention, the server includes a voice data collection means, a text conversion means, a summarization means, an analysis result generation means, a report output means, and an alert generation means, which allows the work status to be grasped in real time from the voice data, thereby improving work efficiency and ensuring safety.

[0542] A "factory" is a workplace where goods are manufactured or processed, a facility where machines and equipment operate, and workers perform their work.

[0543] "Audio data" is data that represents audio in a digital format, and is information collected using an audio input device such as a microphone.

[0544] "Collection means" refers to devices or software for collecting specific information or data, and in the case of audio data, includes a microphone.

[0545] "Text data" is digital data expressed in characters or sentences, and is converted from voice data using voice recognition technology.

[0546] "Summarization means" refers to technologies or devices for concisely summarizing large amounts of information or text data, including generative AI models.

[0547] A "worker" is a worker who works in a factory, operating machinery or manufacturing goods.

[0548] A "manager" is a person in charge of factory operations and supervising workers, and is responsible for work efficiency and quality control.

[0549] "Analysis tools" are software or devices used to analyze collected data and extract patterns and important information.

[0550] "Report output means" refers to a device or software for displaying or printing analyzed data and summary results in report format.

[0551] An "alert mechanism" is a device or software that generates a warning or notification when a specified condition is met.

[0552] The present invention is a system for real-time understanding and efficient management of work conditions in a factory. A specific embodiment of this system is described below.

[0553] System Configuration

[0554] 1. Terminal (sound collection microphone and processing device installed in the factory)

[0555] The terminal is a device that processes sound-collecting microphones and data installed in factories. The microphones collect workers' conversations and work sounds in real time. The collected voice data is automatically converted into text data by the terminal's voice recognition software. Specifically, the Google Speech Recognition API is used to convert voice into text with high accuracy.

[0556] 2. Server (centralized processing system)

[0557] The server receives and stores text data sent from the device, extracts important information from the received data, summarizes the text data using generative AI technology, and generates a detailed report based on the analysis results, which is provided to operators and administrators.

[0558] 3. Users (operators, administrators)

[0559] Users can access the generated reports via a dedicated web portal or mobile app to check the status of operations within the factory and receive advice on how to improve efficiency.

[0560] Program processing flow

[0561] Audio data collection and text conversion

[0562] The device uses microphones installed in the factory to capture the voices and sounds of workers. This voice data is converted into text using speech recognition software. For example, by using the Google Speech Recognition API, speech can be converted into text with high accuracy.

[0563] Sending data

[0564] The converted text data is sent to the server using a secure communication protocol (e.g., HTTPS).

[0565] Receiving and storing data

[0566] The server stores the received text data in a database and prepares it for further processing, after which the stored data can be retrieved and used for analysis.

[0567] Generative AI summarization

[0568] On the server, the stored text data is analyzed using generative AI (e.g., Hugging Face's T5 model) to summarize the highlights and important information of the work. This summary forms the basis of the generated report.

[0569] Generate and deliver reports

[0570] Based on the summarized data, the server generates reports for operators, including progress reports and recommendations for improving efficiency, which are then made available to operators and managers via a web portal or mobile app.

[0571] Specific examples

[0572] For example, if the following conversation takes place on a work site:

[0573] Worker A: "Next, I'll assemble part number 1234."

[0574] Worker B: "Got it. Tools are ready."

[0575] The collected audio data is transcribed and summarized as follows:

[0576] Summary: Worker A has started assembling part number 1234, and Worker B has finished preparing the tooling.

[0577] Prompt Sentence Examples

[0578] By prefaced the collected text data with the prompt "Summarize today's work:" as the input to the generative AI model, the data can be made suitable for the T5 model.

[0579] Prompt: Summary of today's tasks: Next we will assemble part number 1234. Got it. Tools are ready.

[0580] This approach makes it possible to visualize the work status within the factory and to make operational improvements quickly and effectively.

[0581] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0582] Step 1:

[0583] The terminal collects audio data using microphones installed in the factory. Specifically, it captures the conversations and work sounds of workers in real time. The input data is audio data, and the output is the collected raw audio data.

[0584] Step 2:

[0585] The device converts the collected voice data into text data using speech recognition software. Specifically, it uses the Google Speech Recognition API to convert the voice data into text with high accuracy. The input data is voice data, and the output is the corresponding text data.

[0586] Step 3:

[0587] The terminal transmits the converted text data to the server using a secure communication protocol (e.g., HTTPS). Specifically, the text data is encoded using the HTTPS protocol and transmitted to the server. The input data is the text data, and the output is a transmission completion status to the server.

[0588] Step 4:

[0589] The server saves the received text data in a database and prepares it for subsequent processing. Specifically, it receives the text data and stores it in a database. The input data is the text data, and the output is a status indicating whether it has been saved to the database.

[0590] Step 5:

[0591] The server analyzes the stored text data using a generative AI model (e.g., Hugging Face's T5 model) to extract and summarize important information. Specifically, the text data is fed as input to the T5 model along with the prompt, and a summary is generated. The input data is the stored text data and the prompt, and the output is the summarized text data.

[0592] Step 6:

[0593] The server creates a report for the operator based on the summarized data. Specifically, it formats the summarized data and composes it into a report document. The input data is summarized text data, and the output is a document in report format.

[0594] Step 7:

[0595] The server provides the generated report to the user (operator, administrator) through a web portal or mobile app. Specifically, it uploads the report document to the database of the web portal or mobile app and makes it accessible to the user. The input data is a report-formatted document, and the output is the report provision status that can be accessed by the user.

[0596] 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.

[0597] This invention is a system that collects and analyzes voice data from children in educational settings and provides information to parents based on that data. Furthermore, this system incorporates an emotion engine that recognizes and analyzes children's emotional states. This system consistently performs all processes, from collecting voice data to converting it to text, summarizing it, recognizing emotions, and generating and providing reports.

[0598] System Configuration

[0599] 1. Terminal (sound collection microphone and processing device installed in the classroom)

[0600] Microphones installed in classrooms collect children's conversations and comments in real time. The microphones are positioned to effectively capture the speech of teachers and students. This audio data is processed within the device.

[0601] 2. Voice recognition and data transmission

[0602] The audio data collected in the classroom is converted into text data using speech recognition software installed on the device, such as the Google Speech Recognition API, and then transmitted to a server via a secure communication protocol (such as HTTPS).

[0603] 3. Server (Centralized Processing System)

[0604] The server receives the text data sent from the device and stores it in a database. The stored text data is then summarized using generative AI technology (such as the T5 model of Hugging Face). At the same time, an emotion engine analyzes the text data and recognizes the child's emotions.

[0605] 4. Emotion Engine

[0606] The emotion engine implemented on the server analyzes the converted text data and identifies the user's emotions, such as joy, sadness, anger, etc. This engine utilizes, for example, natural language processing (NLP) techniques and machine learning algorithms.

[0607] 5. Report Generation

[0608] Based on the summary data and emotion recognition results, the server generates a detailed report for parents, which includes highlights of their child's daily learning progress and emotional state, and is provided to parents via a web portal and mobile app.

[0609] Program Processing Details

[0610] Audio data collection and text conversion

[0611] The device collects voice data from within the classroom and converts it into text data using voice recognition software. For example, using voice recognition technology, a voice saying, "Today is math class. Are you all ready?" can be converted into text as, "Today is math class. Are you all ready?"

[0612] Sending data

[0613] Text data from the device is sent to the server using a secure communication protocol, which receives the data and stores it in a database.

[0614] Summarizing text data

[0615] The server uses generative AI technology to summarize the received text data, for example generating an overall summary of the day's lessons, such as "Today we had math class. The children asked questions enthusiastically and achieved many results."

[0616] emotion recognition

[0617] The emotion engine implemented on the server analyzes the text data and identifies the emotional state of the children. For example, it recognizes the emotion of "joy" from the text "I had a lot of fun today."

[0618] Report Generation

[0619] Based on the summarized data and emotion recognition results, a detailed report is generated for parents, such as, "Today we had math class and the children actively participated. They seemed to be having fun."

[0620] Providing reports

[0621] The generated reports are provided to parents via a web portal or mobile application, allowing them to understand their child's growth, learning progress, and emotional state.

[0622] Specific examples

[0623] For example, consider the following conversation taking place during a classroom lesson:

[0624] Teacher: "We're starting math today. Are you all ready?"

[0625] Child A: "Yes!"

[0626] Child B: "I'll do my best!"

[0627] This audio is collected and transcribed by speech recognition software as follows:

[0628] "Today we will begin our math lesson. Are you all ready? Yes! Let's do our best!"

[0629] The server receives this text data and summarizes it as follows:

[0630] "We had a math lesson today. The children came prepared and engaged in the lesson."

[0631] At the same time, the emotional data analyzed by the emotion engine indicates "joy" and "high motivation," which are incorporated into the report.

[0632] When parents access this report, they can see things like, "Today we had math class, and the children were actively engaged. They seemed to be particularly enjoying themselves." This will enable parents to get a detailed understanding of their children's daily learning and emotional changes.

[0633] The processing flow will be explained below.

[0634] Step 1:

[0635] Device:

[0636] Microphones installed in classrooms collect children's conversations and comments in real time. The microphones are placed in the center of the classroom or in key locations to capture all surrounding sounds, allowing the entire situation in the classroom to be understood.

[0637] Step 2:

[0638] Device:

[0639] The collected voice data is converted into text data using voice recognition software (e.g., Google Speech Recognition API) installed on the device. Voice recognition software has the ability to process natural language and can convert voice into text with high accuracy.

[0640] Step 3:

[0641] Device:

[0642] The converted text data is sent to the server using a secure communication protocol (e.g., HTTPS), which is important to maintain the confidentiality and integrity of the data.

[0643] Step 4:

[0644] server:

[0645] The server receives text data sent from the terminal via the endpoint, and stores the received text data in a database for subsequent analysis and processing.

[0646] Step 5:

[0647] server:

[0648] The stored text data is analyzed using generative AI technology (e.g., Hugging Face's T5 model), which extracts important information and generates a summary. The generative AI combines multiple summarization techniques to provide a summary that contains the most useful information.

[0649] Step 6:

[0650] server:

[0651] At the same time, an emotion engine implemented on the server analyzes the text data and recognizes the children's emotional state. The emotion engine uses natural language processing (NLP) technology to extract emotional nuances from the text and identify emotions such as "joy," "sadness," and "anger."

[0652] Step 7:

[0653] server:

[0654] The summarized data and emotion recognition results are used to generate a detailed report for parents, including lesson highlights, children's engagement, and observed emotional states.

[0655] Step 8:

[0656] server:

[0657] The generated reports are uploaded to a web portal or mobile application for parental access, and an authentication system ensures that only parents can access and review the reports.

[0658] Step 9:

[0659] User (Parent):

[0660] Parents can log in to a dedicated web portal or mobile application and view the provided reports, which provide detailed insight into their child's academic progress, engagement and emotional state.

[0661] Step 10:

[0662] server:

[0663] The system detects specific keywords in real time from collected voice and text data, and uses an emotion engine to identify signs of negative emotions or bullying. If any are identified, the server automatically generates an alert and notifies teachers and administrators, enabling a rapid response.

[0664] Example 2

[0665] 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."

[0666] In conventional educational systems, teachers and parents spend a lot of time and effort trying to understand the situation of children in the classroom. Furthermore, there are insufficient means to effectively monitor children's emotional state and learning status, making it difficult for parents to understand their children's daily learning and emotional changes in detail. Therefore, there is a need for a system that can effectively and efficiently collect and analyze classroom voice data and provide information to parents.

[0667] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0668] In this invention, the server includes means for collecting voice data in the classroom, means for converting the collected voice data into text data, means for summarizing the converted text data and generating summary data, means for analyzing the text data and recognizing emotional states, means for generating a report for parents based on the generated summary data and emotional states, and means for providing the generated report to parents. This makes it possible to effectively collect and analyze voice data in the classroom and monitor in detail the learning status and emotional states of children.

[0669] Below are definitions of important words.

[0670] "Means for collecting audio data in the classroom" refers to a series of processes for collecting audio generated in the classroom using a sound collection device such as a microphone.

[0671] The "means for converting collected voice data into text data" refers to a process for converting collected voice data into text data as character information using voice recognition technology.

[0672] "Means for summarizing the converted text data and generating summary data" refers to the process of using generative AI technology to concisely summarize the content of the converted text data and generate summary data.

[0673] The "means for analyzing text data to recognize emotional states" refers to a process of identifying emotions in text data using natural language processing techniques and recognizing the emotional states.

[0674] The "means for generating a report for parents based on the generated summary data and emotional state" is a process of integrating the summary data and the results of the emotion analysis to generate a report in a format that is easy for parents to understand.

[0675] "Means for providing generated reports to parents" refers to the process by which generated reports are sent to parents and made available for viewing through a web portal or mobile application.

[0676] "Means for receiving and storing voice data" refers to the process of receiving voice data and converted text data sent from the terminal to the server and storing them in a database.

[0677] The "means for analyzing and generating summary data and emotional states" refers to a series of processes for analyzing the converted text data and generating summary data and emotional states.

[0678] The "means for detecting specific keywords from collected voice data" is a process for identifying and detecting specific keywords from text data that has been speech-recognized.

[0679] The "means for generating alerts based on keywords" is a process for generating alerts and notifying users when certain conditions are met based on detected keywords.

[0680] The present invention is a system that collects and analyzes speech data from children in educational settings and provides information to parents based on the collected data. In particular, this system performs a comprehensive process from collecting speech data to converting it into text, summarizing it, recognizing emotions, and generating and providing reports. Specific embodiments for implementing this system are described below.

[0681] 1. Collection of audio data

[0682] The device collects audio from within the classroom

[0683] Microphones installed in classrooms collect children's conversations and teacher comments in real time. These microphones are positioned to effectively capture what the teacher and students are saying. For example, if a teacher says, "Today's math class. Are you all ready?", that voice will be collected by the microphones.

[0684] 2. Speech-to-text

[0685] The device converts the voice data into text data.

[0686] Using speech recognition software installed on the device (such as Google Speech Recognition API), the collected voice data is converted into text data in real time. For example, the aforementioned speech "Today is math class. Are you all ready?" is converted directly into text data.

[0687] 3. Data transmission and storage

[0688] The device sends text data to the server.

[0689] The generated text data is sent to a server using a secure communication protocol (e.g., HTTPS). This secure communication prevents data leakage and tampering.

[0690] The server receives and stores the text data.

[0691] The server receives the text data sent from the device and stores it in a database. For example, the text "Today is math class. Are you all ready?" is stored in the database as is.

[0692] 4. Summarizing Text Data

[0693] The server summarizes the text data

[0694] The server uses generative AI technology (e.g., Hugging Face's T5 model) to summarize the received text data. For example, a summary of the day's lessons might be generated, such as, "Today we had math class. The children asked questions enthusiastically and achieved many results."

[0695] 5. Emotion recognition

[0696] The server analyzes the text data and recognizes the emotional state.

[0697] The emotion engine installed on the server uses natural language processing technology to analyze the text data and identify the emotional state of the children. For example, the emotion of "joy" can be recognized from the text "I had a lot of fun today."

[0698] 6. Report Generation

[0699] The server generates a report that integrates the summary data and the sentiment results.

[0700] The server generates a detailed report for parents based on the summary data and emotion recognition results, such as, "Today, we had math class, and the children actively participated. They seemed to be having fun."

[0701] 7. Report provision

[0702] The server provides the generated report to the parent.

[0703] The generated reports are provided to parents via a web portal or mobile application, allowing them to gain detailed insight into their child's academic progress and emotional state.

[0704] Examples of prompt statements

[0705] Example 1: "Please transcribe what is said in class. Input speech: 'Today is math class. Are you all ready?'"

[0706] Example 2: "Summarize the following text. Input text: 'Today is math class. Are you all ready? Yes! Let's do our best!'"

[0707] Example 3: "Recognize the emotion in the following text. Input text: 'I had a lot of fun today.'"

[0708] In this way, the system of the present invention allows parents to easily and in detail understand their children's learning situation and emotional state through a series of processes: collecting voice data in the classroom, converting it into text data, summarizing it, recognizing emotions, and generating and providing reports.

[0709] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0710] Processing Steps

[0711] Step 1: Collecting audio data

[0712] The device collects audio from within the classroom

[0713] A microphone installed on each device collects speech in the classroom in real time. This microphone is positioned to effectively capture speech from the teacher and students. For example, the input collected is the voice of a teacher saying, "Today's math class. Are you all ready?" Real-time audio data is generated as the output.

[0714] Step 2: Speech to text

[0715] The device converts the voice data into text data.

[0716] Using speech recognition software installed on the device, the collected voice data is converted into text data in real time. For example, the input voice is "Today is math class. Are you all ready?", and this voice data is converted and output as text data saying "Today is math class. Are you all ready?"

[0717] Step 3: Sending data

[0718] Send text data from the device to the server

[0719] The generated text data is sent to the server using a secure communication protocol (e.g., HTTPS). For example, the text data converted on the terminal, "Today is math class. Are you all ready?", is sent to the server as input. The server receives the text data as output.

[0720] Step 4: Save your data

[0721] The server receives and stores the text data.

[0722] The server receives the text data sent from the terminal and stores it in a database. As input, it receives the text data "Today is math class. Are you all ready?" and stores it in the database as output. The data is stored in the database along with the collection time and sender information.

[0723] Step 5: Summarizing the text data

[0724] The server summarizes the text data

[0725] The server uses generative AI technology (e.g., a text summarization model) to concisely summarize the received text data. The input is the received text data, "Today is math class. Are you all ready?". The output is the summary data, "Today we had math class. The children participated enthusiastically."

[0726] Step 6: Emotion Recognition

[0727] The server analyzes the text data and recognizes the emotional state.

[0728] The emotion engine implemented on the server analyzes the text data using natural language processing technology to identify the children's emotional state. The input is the text data to be analyzed: "I had a lot of fun today." The emotional state "joy" is recognized as the output.

[0729] Step 7: Generate reports

[0730] The server generates a report that integrates the summary data and the sentiment results.

[0731] The server generates a detailed report for parents based on the summary data and emotion recognition results. The input is the summary data "Today we had a math class. The children participated enthusiastically" and the emotion data "joy." The output is a report stating, "Today we had a math class. The children participated enthusiastically. They seemed to be having a particularly good time."

[0732] Step 8: Reporting

[0733] The server provides the generated report to the parent.

[0734] The generated report is provided to parents through a web portal or mobile application. The input is the generated report: "Today we had math class and the children participated actively. They seemed to enjoy it especially." As an output, the report is sent to the parents, who can access and view it.

[0735] Through these steps, this system can efficiently collect and analyze classroom voice data and provide useful information to parents.

[0736] (Application example 2)

[0737] 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."

[0738] Traditional customer feedback systems rely on collecting opinions directly from customers or answering surveys, making it difficult to provide real-time feedback or perform detailed sentiment analysis. As a result, restaurants and food delivery companies continue to struggle to obtain effective data for improving customer satisfaction and employee training. Furthermore, improving employee response and speedy service improvements are difficult challenges.

[0739] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting voice data in the classroom, means for converting the collected voice data into text data, means for summarizing the converted text data, means for analyzing the text data and recognizing the emotional state, and means for providing the summarized data and the recognition result of the emotional state to the guardian. This makes it possible to obtain customer feedback in real time, analyze the emotional state, and quickly improve responses and train employees.

[0740] "Audio data" refers to audio information collected within a restaurant or a specific space, including conversations between customers and employees and environmental sounds.

[0741] "Text data" is digital data that has been converted from collected voice data into text information using voice recognition technology.

[0742] A "summary" is digital information that extracts important parts from text data and summarizes them in a concise form.

[0743] "Emotional state" is information that identifies a person's emotions (for example, joy, anger, sadness, etc.) obtained by analyzing text data.

[0744] "Parent" refers to the guardian or guardian of the child of the system user in an educational setting, but in this application example, it refers to the manager or person in charge of the restaurant to which the report is provided.

[0745] "Analysis results" are the information obtained by analyzing the collected text data and emotional state.

[0746] "Report" means a detailed report generated based on the Analysis Results and Emotion Recognition Results.

[0747] "Employee training" means using the collected and analyzed information to provide training and guidance to restaurant staff to improve the quality of their service.

[0748] "Improving customer service" means optimizing service content and delivery methods to improve customer satisfaction based on analyzed data and reports.

[0749] An "alert" is a warning message that is used to quickly notify an administrator of a specific situation based on collected voice data and key information.

[0750] To implement this invention, the following system and processing steps are required: First, a microphone is installed in the restaurant to collect sound data. This microphone collects conversations and environmental sounds in the restaurant in real time.

[0751] The device processes the voice data received from the microphone and converts it into text data. This conversion is performed using voice recognition software. For example, the Google Speech Recognition API can be used. The device then transmits the converted text data to a server using a secure communication protocol (e.g., HTTPS).

[0752] The server stores the received text data in a database and summarizes it using generative AI technology, such as the Hugging Face T5 model. At the same time, an emotion engine implemented on the server analyzes the text data and identifies the customer's emotional state. This emotion engine utilizes natural language processing technology and machine learning algorithms.

[0753] Based on the summarized data and emotion recognition results, the server generates a detailed report, which includes information for employee training and customer service improvement, and is provided to managers via a web portal or mobile application.

[0754] Specific examples

[0755] For example, consider the following conversation taking place in a restaurant:

[0756] Customer: "The roast duck was delicious today. It's just a shame that the service was a little slow."

[0757] This audio is collected and transcribed by speech recognition software as follows:

[0758] "The roast duck was delicious today. It's just a shame that the service was a little late."

[0759] The server receives this text data and summarizes it as follows:

[0760] "A customer who had roast duck today was pleased with the taste of the food, but was unhappy with the slow delivery."

[0761] At the same time, the emotional data analyzed by the emotion engine indicates "satisfaction" and "dissatisfaction," which are incorporated into the report.

[0762] When parents access this report, they can see that "the customer was satisfied with the taste of the food, but was dissatisfied with the slow delivery time." Based on this information, the restaurant can review the way staff respond and the time it takes to provide service.

[0763] Prompt Sentence Examples

[0764] "The roast duck was delicious today. It's just a shame that the service was a little late."

[0765] This system allows restaurants to understand customer satisfaction in real time and quickly improve their responses, making it easy to obtain data that can be used for employee training and service improvement.

[0766] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0767] Step 1:

[0768] The device collects audio data through a microphone installed in the restaurant. The input data includes conversations between customers and employees, as well as the surrounding environmental sounds. The collected audio data is temporarily stored in the device.

[0769] Step 2:

[0770] The device converts the collected voice data into text data using voice recognition software. Specifically, the voice recognition software (e.g., Google Speech Recognition API) analyzes the input voice data and converts it into corresponding text data. The text data is generated within the device.

[0771] Step 3:

[0772] The terminal transmits the converted text data to the server using a secure communication protocol (e.g., HTTPS), where the input is the converted text data and the output is the data transmission to the server.

[0773] Step 4:

[0774] The server stores the received text data in a database. The stored text data is used in subsequent processing steps. The input here is the text data sent from the terminal, and the output is the data stored in the database.

[0775] Step 5:

[0776] The server uses generative AI technology to summarize the stored text data. For example, the Hugging Face T5 model is used in this summarization process. The input is the stored text data, and the output is the summarized text data. Specifically, the important parts of the text data are extracted and summarized in a concise form.

[0777] Step 6:

[0778] The emotion engine installed on the server analyzes the summarized text data and identifies the customer's emotional state. The emotion engine utilizes natural language processing technology and machine learning algorithms. The input is the summarized text data, and the output is the identification result of the emotional state. Specifically, emotions such as joy, anger, and sadness are identified from the text content.

[0779] Step 7:

[0780] The server generates a detailed report based on the summarized data and emotion recognition results. The generated report contains information useful for employee training and improving customer service. The input is the summarized data and emotion recognition results, and the output is a report document.

[0781] Step 8:

[0782] The server provides the generated report to the administrator via a web portal or mobile application. The input here is the generated report, and the output is the report provided to the administrator. The administrator can access this report and check and implement improvements.

[0783] Through these processing steps, the system can collect and analyze customer feedback in real time, providing specific data that can be used to train employees and improve customer service.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] [Third embodiment]

[0788] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0789] 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.

[0790] 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).

[0791] 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.

[0792] 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.

[0793] 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).

[0794] 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. 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.

[0795] 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.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] 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."

[0800] This invention relates to a system that collects and analyzes children's voices and sounds in the classroom and provides parents with information about their children's growth and daily life. This system consists of multiple means for collecting, converting, analyzing, summarizing, and providing voice data.

[0801] System Configuration

[0802] 1. Terminal (sound collection microphone and processing device installed in the classroom)

[0803] Microphones installed in the classroom collect the children's conversations and comments in real time, and this audio data is automatically converted into text data by voice recognition software installed on the device.

[0804] 2. Server (centralized processing system)

[0805] The system receives and stores text data sent from the device. The server extracts important information from the received data and summarizes the text data using generative AI technology. It also generates a detailed report based on the analysis results and provides it to parents.

[0806] 3. User (Parent)

[0807] Parents can access the generated reports through a dedicated web portal or mobile app to view their child's daily activities and development.

[0808] Program processing flow

[0809] Audio data collection and text conversion

[0810] The devices use microphones installed in the classroom to capture the children's voices. This voice data is then converted into text using speech recognition software. For example, using the Google Speech Recognition API, speech can be converted into text with high accuracy.

[0811] Sending data

[0812] The converted text data is sent to the server using a secure communication protocol (e.g., HTTPS).

[0813] Receiving and storing data

[0814] The server stores the received text data in a database and prepares it for further processing, after which the stored data can be retrieved and used for analysis.

[0815] Generative AI summarization

[0816] The server analyzes the stored text data using generative AI (e.g., Hugging Face's T5 model) to summarize the highlights and important information from the lesson. This summary forms the basis of the generated report.

[0817] Generate and deliver reports

[0818] Based on the summarized data, the server generates reports for parents, detailing their child's engagement and classroom behavior, and provides these reports to parents via a web portal or mobile app.

[0819] Specific examples

[0820] For example, consider the following conversation taking place in a classroom one day:

[0821] Teacher: "We're starting math today. Are you all ready?"

[0822] Child A: "Yes!"

[0823] Child B: "I'll do my best!"

[0824] This voice data is collected by a microphone and converted into text data by the device's voice recognition software:

[0825] "Today we will begin our math lesson. Are you all ready? Yes! Let's do our best!"

[0826] The server receives this text data and summarizes it as follows:

[0827] "Today's lesson was about math. The children participated actively and worked hard in the lesson."

[0828] Based on this summary, the server generates a report for parents and provides it to them via a web portal or mobile app, allowing them to understand their child's learning progress and daily progress.

[0829] The processing flow will be explained below.

[0830] Step 1:

[0831] Device:

[0832] Microphones installed in classrooms collect children's voices and sounds in real time. The microphones are placed in positions suitable for the classroom environment to effectively capture children's conversations and comments.

[0833] Step 2:

[0834] Device:

[0835] The collected voice data is converted into text data using voice recognition software installed on the device. This voice recognition software can convert voice data into text with high accuracy using, for example, the Google Speech Recognition API.

[0836] Step 3:

[0837] Device:

[0838] The converted text data is sent to the server using a secure communication protocol (e.g., HTTPS), which is used to ensure data integrity and security.

[0839] Step 4:

[0840] server:

[0841] The server receives text data sent from the device via the endpoint, processes the received data in real time, and stores it in a database.

[0842] Step 5:

[0843] server:

[0844] Generative AI technology (such as Hugging Face's T5 model) is used to analyze the stored text data, extracting important highlights and key points from the data and summarizing the text data.

[0845] Step 6:

[0846] server:

[0847] The summarized data is used to generate a report for parents, which includes lesson highlights, children's engagement, and any interesting behaviors observed.

[0848] Step 7:

[0849] server:

[0850] The generated reports are uploaded to a web portal or mobile application for parents to log in through a dedicated authentication system and view reports on their child's daily life and development.

[0851] Step 8:

[0852] User (Parent):

[0853] Parents can access the web portal or mobile application and view the reports provided, giving them detailed insight into their child's progress and classroom activities.

[0854] Step 9:

[0855] server:

[0856] Furthermore, the server continuously analyzes collected voice data and detects specific keywords in the text data (e.g., signs of bullying or inappropriate language) in real time. If detected, an alert is generated and relevant parties are notified, allowing for a prompt response.

[0857] Example 1

[0858] 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."

[0859] In conventional educational environments, it has been difficult to record children's comments and activities in detail in the classroom and provide appropriate and timely feedback to parents. Furthermore, converting audio data into text and summarizing it is time-consuming, making it difficult to operate efficiently. Furthermore, there has been a lack of means to quickly detect abnormalities or important information in specific situations and provide appropriate alerts.

[0860] 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.

[0861] In this invention, the server includes means for receiving and storing collected voice data, means for transmitting converted text data using a secure communication protocol, and means for summarizing the converted text data, thereby enabling efficient analysis of the activities and comments of children in the classroom and timely provision of the summary results to parents.

[0862] "Audio data" refers to electrical signals collected in the classroom, including children's voices, speech, and other environmental sounds.

[0863] "Text data" refers to character string information converted from voice data using voice recognition technology.

[0864] A "secure communication protocol" refers to a communication method that includes encryption technology to ensure high security when sending and receiving data. For example, HTTPS is an example of this.

[0865] A "summary" refers to information that extracts important information from collected text data and summarizes it briefly.

[0866] "Report format" refers to a document in which the analysis results are organized visually or in writing and processed into a format that is easy for parents to understand.

[0867] A "generative artificial intelligence model" refers to a machine learning model trained to analyze and summarize text data using natural language processing.

[0868] "Web portal or mobile communication device" means an interface through which parents access generated reports over the internet, including websites and smartphone apps.

[0869] This invention relates to a system that collects and analyzes children's voices and sounds in the classroom and provides parents with information about their children's growth and daily life. This system consists of multiple means for collecting, converting, analyzing, summarizing, and providing voice data.

[0870] System Configuration

[0871] 1. Terminal (sound collection microphone and processing device installed in the classroom)

[0872] The devices are equipped with microphones installed in classrooms that collect children's conversations and comments in real time. This audio data is then automatically converted into text data using the device's built-in voice recognition software. Specifically, the Google Speech Recognition API is used, which provides highly accurate voice recognition and converts the audio collected by the microphones into text.

[0873] Examples:

[0874] The teacher says, "Today we're going to start math class. Are you all ready?" Child A responds, "Yes!" and Child B responds, "I'll do my best!" The audio data of this exchange is captured by a sound-collecting microphone.

[0875] 2. Server (centralized processing system)

[0876] The server receives the text data sent from the device and stores it in a database. The stored text data is analyzed using a generative AI model (e.g., Hugging Face's T5 model) to summarize important information. This summary text becomes the basis for a report and is provided to parents.

[0877] Examples:

[0878] The server receives text data saying, "Today we will begin math class. Are you all ready? Yes! Let's do our best!" and summarizes it as, "In today's class, we learned about math. The children actively participated and worked hard in class."

[0879] 3. User (Parent)

[0880] Parents can access the generated reports via a dedicated web portal or mobile app to track their child's daily activities and progress.

[0881] Audio data collection and text conversion

[0882] The devices use microphones installed in the classroom to capture the children's voices, which are then converted into text using speech recognition software (Google Speech Recognition API), resulting in highly accurate speech-to-text data.

[0883] Sending data

[0884] The converted text data is sent to the server using a secure communication protocol (e.g., HTTPS). The data is encrypted during transmission to ensure security.

[0885] Receiving and storing data

[0886] The server stores the received text data in a database for further processing, and the stored data is indexed for efficient access.

[0887] Generative AI summarization

[0888] The server analyzes the stored text data using a generative AI model (Hugging Face's T5 model) to summarize key information. This summarized text is used as the basis for the report.

[0889] Generate and deliver reports

[0890] Based on the summarized data, the server generates detailed reports for parents, which are made available to them via a web portal and mobile app.

[0891] Prompt Sentence Examples

[0892] "Given the following text as input, generate a lesson summary: 'Today we'll start our math lesson. Are you all ready? Yes! Let's do our best!'"

[0893] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0894] Step 1:

[0895] Audio data collection

[0896] The device uses a microphone installed in the classroom to collect children's conversations and comments in real time. Audio data is input into the microphone, converted into a digital signal, and sent to the device. Specifically, the microphone captures the audio signal and stores it as data on the device.

[0897] Input: Audio signal in the classroom, Output: Digital audio data

[0898] Step 2:

[0899] Converting audio data to text

[0900] The device converts the collected voice data into text data using the Google Speech Recognition API. The voice data is input into the API and the corresponding text is output. Specifically, the voice recognition software analyzes the voice data and generates text data.

[0901] Input: Digital audio data, Output: Text data

[0902] Step 3:

[0903] Sending text data

[0904] The terminal transmits the converted text data to the server using a secure communication protocol (e.g., HTTPS). The text data is encrypted, input into the communication protocol, and transmitted to the server. Specifically, the text data is encrypted using the HTTPS protocol.

[0905] Input: Text data, Output: Encrypted text data (received on the server side)

[0906] Step 4:

[0907] Receiving and storing data

[0908] The server stores the received text data in a database. The encrypted data is decrypted and entered into the database for storage. Specifically, the server decrypts the encrypted data and stores it in the database.

[0909] Input: Encrypted text data, Output: Text data stored in the database

[0910] Step 5:

[0911] Generative AI summarization

[0912] The server analyzes the stored text data using a generative AI model (Hugging Face's T5 model) to summarize important information. The text data is input into the AI ​​model, which outputs a summary text. Specifically, the AI ​​model analyzes the text, extracts key points, and generates a summary.

[0913] Input: Text data stored in a database, Output: Summarized text data

[0914] Step 6:

[0915] Generate and deliver reports

[0916] The server uses the summarized data to create a detailed report for parents. The summarized data is input into a reporting tool, which outputs the report in HTML or PDF format. Specifically, the server embeds the summarized data into a template and generates the report.

[0917] The report is then made accessible to parents through a web portal or mobile app, where parents can access the portal, view the generated report, and download it if desired.

[0918] Input: Summarized text data, Output: Parent-readable report

[0919] (Application example 1)

[0920] 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."

[0921] In today's factories, it is difficult to grasp the work situation in real time and manage it efficiently. In particular, there is a lack of means to effectively utilize information obtained from communication between workers and work sounds, which can make it difficult to improve work efficiency or ensure safety. Therefore, there is a need for a system that uses voice data to visualize the work situation in the factory and supports work progress management and identification of areas for improvement.

[0922] 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.

[0923] In this invention, the server includes a voice data collection means, a text conversion means, a summarization means, an analysis result generation means, a report output means, and an alert generation means, which allows the work status to be grasped in real time from the voice data, thereby improving work efficiency and ensuring safety.

[0924] A "factory" is a workplace where goods are manufactured or processed, a facility where machines and equipment operate, and workers perform their work.

[0925] "Audio data" is data that represents audio in a digital format, and is information collected using an audio input device such as a microphone.

[0926] "Collection means" refers to devices or software for collecting specific information or data, and in the case of audio data, includes a microphone.

[0927] "Text data" is digital data expressed in characters or sentences, and is converted from voice data using voice recognition technology.

[0928] "Summarization means" refers to technologies or devices for concisely summarizing large amounts of information or text data, including generative AI models.

[0929] A "worker" is a worker who works in a factory, operating machinery or manufacturing goods.

[0930] A "manager" is a person in charge of factory operations and supervising workers, and is responsible for work efficiency and quality control.

[0931] "Analysis tools" are software or devices used to analyze collected data and extract patterns and important information.

[0932] "Report output means" refers to a device or software for displaying or printing analyzed data and summary results in report format.

[0933] An "alert mechanism" is a device or software that generates a warning or notification when a specified condition is met.

[0934] The present invention is a system for real-time understanding and efficient management of work conditions in a factory. A specific embodiment of this system is described below.

[0935] System Configuration

[0936] 1. Terminal (sound collection microphone and processing device installed in the factory)

[0937] The terminal is a device that processes sound-collecting microphones and data installed in factories. The microphones collect workers' conversations and work sounds in real time. The collected voice data is automatically converted into text data by the terminal's voice recognition software. Specifically, the Google Speech Recognition API is used to convert voice into text with high accuracy.

[0938] 2. Server (centralized processing system)

[0939] The server receives and stores text data sent from the device, extracts important information from the received data, summarizes the text data using generative AI technology, and generates a detailed report based on the analysis results, which is provided to operators and administrators.

[0940] 3. Users (operators, administrators)

[0941] Users can access the generated reports via a dedicated web portal or mobile app to check the status of operations within the factory and receive advice on how to improve efficiency.

[0942] Program processing flow

[0943] Audio data collection and text conversion

[0944] The device uses microphones installed in the factory to capture the voices and sounds of workers. This voice data is converted into text using speech recognition software. For example, by using the Google Speech Recognition API, speech can be converted into text with high accuracy.

[0945] Sending data

[0946] The converted text data is sent to the server using a secure communication protocol (e.g., HTTPS).

[0947] Receiving and storing data

[0948] The server stores the received text data in a database and prepares it for further processing, after which the stored data can be retrieved and used for analysis.

[0949] Generative AI summarization

[0950] On the server, the stored text data is analyzed using generative AI (e.g., Hugging Face's T5 model) to summarize the highlights and important information of the work. This summary forms the basis of the generated report.

[0951] Generate and deliver reports

[0952] Based on the summarized data, the server generates reports for operators, including progress reports and recommendations for improving efficiency, which are then made available to operators and managers via a web portal or mobile app.

[0953] Specific examples

[0954] For example, if the following conversation takes place on a work site:

[0955] Worker A: "Next, I'll assemble part number 1234."

[0956] Worker B: "Got it. Tools are ready."

[0957] The collected audio data is transcribed and summarized as follows:

[0958] Summary: Worker A has started assembling part number 1234, and Worker B has finished preparing the tooling.

[0959] Prompt Sentence Examples

[0960] By prefaced the collected text data with the prompt "Summarize today's work:" as the input to the generative AI model, the data can be made suitable for the T5 model.

[0961] Prompt: Summary of today's tasks: Next we will assemble part number 1234. Got it. Tools are ready.

[0962] This approach makes it possible to visualize the work status within the factory and to make operational improvements quickly and effectively.

[0963] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0964] Step 1:

[0965] The terminal collects audio data using microphones installed in the factory. Specifically, it captures the conversations and work sounds of workers in real time. The input data is audio data, and the output is the collected raw audio data.

[0966] Step 2:

[0967] The device converts the collected voice data into text data using speech recognition software. Specifically, it uses the Google Speech Recognition API to convert the voice data into text with high accuracy. The input data is voice data, and the output is the corresponding text data.

[0968] Step 3:

[0969] The terminal transmits the converted text data to the server using a secure communication protocol (e.g., HTTPS). Specifically, the text data is encoded using the HTTPS protocol and transmitted to the server. The input data is the text data, and the output is a transmission completion status to the server.

[0970] Step 4:

[0971] The server saves the received text data in a database and prepares it for subsequent processing. Specifically, it receives the text data and stores it in a database. The input data is the text data, and the output is a status indicating whether it has been saved to the database.

[0972] Step 5:

[0973] The server analyzes the stored text data using a generative AI model (e.g., Hugging Face's T5 model) to extract and summarize important information. Specifically, the text data is fed as input to the T5 model along with the prompt, and a summary is generated. The input data is the stored text data and the prompt, and the output is the summarized text data.

[0974] Step 6:

[0975] The server creates a report for the operator based on the summarized data. Specifically, it formats the summarized data and composes it into a report document. The input data is summarized text data, and the output is a document in report format.

[0976] Step 7:

[0977] The server provides the generated report to the user (operator, administrator) through a web portal or mobile app. Specifically, it uploads the report document to the database of the web portal or mobile app and makes it accessible to the user. The input data is a report-formatted document, and the output is the report provision status that can be accessed by the user.

[0978] 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.

[0979] This invention is a system that collects and analyzes voice data from children in educational settings and provides information to parents based on that data. Furthermore, this system incorporates an emotion engine that recognizes and analyzes children's emotional states. This system consistently performs all processes, from collecting voice data to converting it to text, summarizing it, recognizing emotions, and generating and providing reports.

[0980] System Configuration

[0981] 1. Terminal (sound collection microphone and processing device installed in the classroom)

[0982] Microphones installed in classrooms collect children's conversations and comments in real time. The microphones are positioned to effectively capture the speech of teachers and students. This audio data is processed within the device.

[0983] 2. Voice recognition and data transmission

[0984] The audio data collected in the classroom is converted into text data using speech recognition software installed on the device, such as the Google Speech Recognition API, and then transmitted to a server via a secure communication protocol (such as HTTPS).

[0985] 3. Server (Centralized Processing System)

[0986] The server receives the text data sent from the device and stores it in a database. The stored text data is then summarized using generative AI technology (such as the T5 model of Hugging Face). At the same time, an emotion engine analyzes the text data and recognizes the child's emotions.

[0987] 4. Emotion Engine

[0988] The emotion engine implemented on the server analyzes the converted text data and identifies the user's emotions, such as joy, sadness, anger, etc. This engine utilizes, for example, natural language processing (NLP) techniques and machine learning algorithms.

[0989] 5. Report Generation

[0990] Based on the summary data and emotion recognition results, the server generates a detailed report for parents, which includes highlights of their child's daily learning progress and emotional state, and is provided to parents via a web portal and mobile app.

[0991] Program Processing Details

[0992] Audio data collection and text conversion

[0993] The device collects voice data from within the classroom and converts it into text data using voice recognition software. For example, using voice recognition technology, a voice saying, "Today is math class. Are you all ready?" can be converted into text as, "Today is math class. Are you all ready?"

[0994] Sending data

[0995] Text data from the device is sent to the server using a secure communication protocol, which receives the data and stores it in a database.

[0996] Summarizing text data

[0997] The server uses generative AI technology to summarize the received text data, for example generating an overall summary of the day's lessons, such as "Today we had math class. The children asked questions enthusiastically and achieved many results."

[0998] emotion recognition

[0999] The emotion engine implemented on the server analyzes the text data and identifies the emotional state of the children. For example, it recognizes the emotion of "joy" from the text "I had a lot of fun today."

[1000] Report Generation

[1001] Based on the summarized data and emotion recognition results, a detailed report is generated for parents, such as, "Today we had math class and the children actively participated. They seemed to be having fun."

[1002] Providing reports

[1003] The generated reports are provided to parents via a web portal or mobile application, allowing them to understand their child's growth, learning progress, and emotional state.

[1004] Specific examples

[1005] For example, consider the following conversation taking place during a classroom lesson:

[1006] Teacher: "We're starting math today. Are you all ready?"

[1007] Child A: "Yes!"

[1008] Child B: "I'll do my best!"

[1009] This audio is collected and transcribed by speech recognition software as follows:

[1010] "Today we will begin our math lesson. Are you all ready? Yes! Let's do our best!"

[1011] The server receives this text data and summarizes it as follows:

[1012] "We had a math lesson today. The children came prepared and engaged in the lesson."

[1013] At the same time, the emotional data analyzed by the emotion engine indicates "joy" and "high motivation," which are incorporated into the report.

[1014] When parents access this report, they can see things like, "Today we had math class, and the children were actively engaged. They seemed to be particularly enjoying themselves." This will enable parents to get a detailed understanding of their children's daily learning and emotional changes.

[1015] The processing flow will be explained below.

[1016] Step 1:

[1017] Device:

[1018] Microphones installed in classrooms collect children's conversations and comments in real time. The microphones are placed in the center of the classroom or in key locations to capture all surrounding sounds, allowing the entire situation in the classroom to be understood.

[1019] Step 2:

[1020] Device:

[1021] The collected voice data is converted into text data using voice recognition software (e.g., Google Speech Recognition API) installed on the device. Voice recognition software has the ability to process natural language and can convert voice into text with high accuracy.

[1022] Step 3:

[1023] Device:

[1024] The converted text data is sent to the server using a secure communication protocol (e.g., HTTPS), which is important to maintain the confidentiality and integrity of the data.

[1025] Step 4:

[1026] server:

[1027] The server receives text data sent from the terminal via the endpoint, and stores the received text data in a database for subsequent analysis and processing.

[1028] Step 5:

[1029] server:

[1030] The stored text data is analyzed using generative AI technology (e.g., Hugging Face's T5 model), which extracts important information and generates a summary. The generative AI combines multiple summarization techniques to provide a summary that contains the most useful information.

[1031] Step 6:

[1032] server:

[1033] At the same time, an emotion engine implemented on the server analyzes the text data and recognizes the children's emotional state. The emotion engine uses natural language processing (NLP) technology to extract emotional nuances from the text and identify emotions such as "joy," "sadness," and "anger."

[1034] Step 7:

[1035] server:

[1036] The summarized data and emotion recognition results are used to generate a detailed report for parents, including lesson highlights, children's engagement, and observed emotional states.

[1037] Step 8:

[1038] server:

[1039] The generated reports are uploaded to a web portal or mobile application for parental access, and an authentication system ensures that only parents can access and review the reports.

[1040] Step 9:

[1041] User (Parent):

[1042] Parents can log in to a dedicated web portal or mobile application and view the provided reports, which provide detailed insight into their child's academic progress, engagement and emotional state.

[1043] Step 10:

[1044] server:

[1045] The system detects specific keywords in real time from collected voice and text data, and uses an emotion engine to identify signs of negative emotions or bullying. If any are identified, the server automatically generates an alert and notifies teachers and administrators, enabling a rapid response.

[1046] Example 2

[1047] 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."

[1048] In conventional educational systems, teachers and parents spend a lot of time and effort trying to understand the situation of children in the classroom. Furthermore, there are insufficient means to effectively monitor children's emotional state and learning status, making it difficult for parents to understand their children's daily learning and emotional changes in detail. Therefore, there is a need for a system that can effectively and efficiently collect and analyze classroom voice data and provide information to parents.

[1049] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1050] In this invention, the server includes means for collecting voice data in the classroom, means for converting the collected voice data into text data, means for summarizing the converted text data and generating summary data, means for analyzing the text data and recognizing emotional states, means for generating a report for parents based on the generated summary data and emotional states, and means for providing the generated report to parents. This makes it possible to effectively collect and analyze voice data in the classroom and monitor in detail the learning status and emotional states of children.

[1051] Below are definitions of important words.

[1052] "Means for collecting audio data in the classroom" refers to a series of processes for collecting audio generated in the classroom using a sound collection device such as a microphone.

[1053] The "means for converting collected voice data into text data" refers to a process for converting collected voice data into text data as character information using voice recognition technology.

[1054] "Means for summarizing the converted text data and generating summary data" refers to the process of using generative AI technology to concisely summarize the content of the converted text data and generate summary data.

[1055] The "means for analyzing text data to recognize emotional states" refers to a process of identifying emotions in text data using natural language processing techniques and recognizing the emotional states.

[1056] The "means for generating a report for parents based on the generated summary data and emotional state" is a process of integrating the summary data and the results of the emotion analysis to generate a report in a format that is easy for parents to understand.

[1057] "Means for providing generated reports to parents" refers to the process by which generated reports are sent to parents and made available for viewing through a web portal or mobile application.

[1058] "Means for receiving and storing voice data" refers to the process of receiving voice data and converted text data sent from the terminal to the server and storing them in a database.

[1059] The "means for analyzing and generating summary data and emotional states" refers to a series of processes for analyzing the converted text data and generating summary data and emotional states.

[1060] The "means for detecting specific keywords from collected voice data" is a process for identifying and detecting specific keywords from text data that has been speech-recognized.

[1061] The "means for generating alerts based on keywords" is a process for generating alerts and notifying users when certain conditions are met based on detected keywords.

[1062] The present invention is a system that collects and analyzes speech data from children in educational settings and provides information to parents based on the collected data. In particular, this system performs a comprehensive process from collecting speech data to converting it into text, summarizing it, recognizing emotions, and generating and providing reports. Specific embodiments for implementing this system are described below.

[1063] 1. Collection of audio data

[1064] The device collects audio from within the classroom

[1065] Microphones installed in classrooms collect children's conversations and teacher comments in real time. These microphones are positioned to effectively capture what the teacher and students are saying. For example, if a teacher says, "Today's math class. Are you all ready?", that voice will be collected by the microphones.

[1066] 2. Speech-to-text

[1067] The device converts the voice data into text data.

[1068] Using speech recognition software installed on the device (such as Google Speech Recognition API), the collected voice data is converted into text data in real time. For example, the aforementioned speech "Today is math class. Are you all ready?" is converted directly into text data.

[1069] 3. Data transmission and storage

[1070] The device sends text data to the server.

[1071] The generated text data is sent to a server using a secure communication protocol (e.g., HTTPS). This secure communication prevents data leakage and tampering.

[1072] The server receives and stores the text data.

[1073] The server receives the text data sent from the device and stores it in a database. For example, the text "Today is math class. Are you all ready?" is stored in the database as is.

[1074] 4. Summarizing Text Data

[1075] The server summarizes the text data

[1076] The server uses generative AI technology (e.g., Hugging Face's T5 model) to summarize the received text data. For example, a summary of the day's lessons might be generated, such as, "Today we had math class. The children asked questions enthusiastically and achieved many results."

[1077] 5. Emotion recognition

[1078] The server analyzes the text data and recognizes the emotional state.

[1079] The emotion engine installed on the server uses natural language processing technology to analyze the text data and identify the emotional state of the children. For example, the emotion of "joy" can be recognized from the text "I had a lot of fun today."

[1080] 6. Report Generation

[1081] The server generates a report that integrates the summary data and the sentiment results.

[1082] The server generates a detailed report for parents based on the summary data and emotion recognition results, such as, "Today, we had math class, and the children actively participated. They seemed to be having fun."

[1083] 7. Report provision

[1084] The server provides the generated report to the parent.

[1085] The generated reports are provided to parents via a web portal or mobile application, allowing them to gain detailed insight into their child's academic progress and emotional state.

[1086] Examples of prompt statements

[1087] Example 1: "Please transcribe what is said in class. Input speech: 'Today is math class. Are you all ready?'"

[1088] Example 2: "Summarize the following text. Input text: 'Today is math class. Are you all ready? Yes! Let's do our best!'"

[1089] Example 3: "Recognize the emotion in the following text. Input text: 'I had a lot of fun today.'"

[1090] In this way, the system of the present invention allows parents to easily and in detail understand their children's learning situation and emotional state through a series of processes: collecting voice data in the classroom, converting it into text data, summarizing it, recognizing emotions, and generating and providing reports.

[1091] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1092] Processing Steps

[1093] Step 1: Collecting audio data

[1094] The device collects audio from within the classroom

[1095] A microphone installed on each device collects speech in the classroom in real time. This microphone is positioned to effectively capture speech from the teacher and students. For example, the input collected is the voice of a teacher saying, "Today's math class. Are you all ready?" Real-time audio data is generated as the output.

[1096] Step 2: Speech to text

[1097] The device converts the voice data into text data.

[1098] Using speech recognition software installed on the device, the collected voice data is converted into text data in real time. For example, the input voice is "Today is math class. Are you all ready?", and this voice data is converted and output as text data saying "Today is math class. Are you all ready?"

[1099] Step 3: Sending data

[1100] Send text data from the device to the server

[1101] The generated text data is sent to the server using a secure communication protocol (e.g., HTTPS). For example, the text data converted on the terminal, "Today is math class. Are you all ready?", is sent to the server as input. The server receives the text data as output.

[1102] Step 4: Save your data

[1103] The server receives and stores the text data.

[1104] The server receives the text data sent from the terminal and stores it in a database. As input, it receives the text data "Today is math class. Are you all ready?" and stores it in the database as output. The data is stored in the database along with the collection time and sender information.

[1105] Step 5: Summarizing the text data

[1106] The server summarizes the text data

[1107] The server uses generative AI technology (e.g., a text summarization model) to concisely summarize the received text data. The input is the received text data, "Today is math class. Are you all ready?". The output is the summary data, "Today we had math class. The children participated enthusiastically."

[1108] Step 6: Emotion Recognition

[1109] The server analyzes the text data and recognizes the emotional state.

[1110] The emotion engine implemented on the server analyzes the text data using natural language processing technology to identify the children's emotional state. The input is the text data to be analyzed: "I had a lot of fun today." The emotional state "joy" is recognized as the output.

[1111] Step 7: Generate reports

[1112] The server generates a report that integrates the summary data and the sentiment results.

[1113] The server generates a detailed report for parents based on the summary data and emotion recognition results. The input is the summary data "Today we had a math class. The children participated enthusiastically" and the emotion data "joy." The output is a report stating, "Today we had a math class. The children participated enthusiastically. They seemed to be having a particularly good time."

[1114] Step 8: Reporting

[1115] The server provides the generated report to the parent.

[1116] The generated report is provided to parents through a web portal or mobile application. The input is the generated report: "Today we had math class and the children participated actively. They seemed to enjoy it especially." As an output, the report is sent to the parents, who can access and view it.

[1117] Through these steps, this system can efficiently collect and analyze classroom voice data and provide useful information to parents.

[1118] (Application example 2)

[1119] 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."

[1120] Traditional customer feedback systems rely on collecting opinions directly from customers or answering surveys, making it difficult to provide real-time feedback or perform detailed sentiment analysis. As a result, restaurants and food delivery companies continue to struggle to obtain effective data for improving customer satisfaction and employee training. Furthermore, improving employee response and speedy service improvements are difficult challenges.

[1121] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting voice data in the classroom, means for converting the collected voice data into text data, means for summarizing the converted text data, means for analyzing the text data and recognizing the emotional state, and means for providing the summarized data and the recognition result of the emotional state to the guardian. This makes it possible to obtain customer feedback in real time, analyze the emotional state, and quickly improve responses and train employees.

[1122] "Audio data" refers to audio information collected within a restaurant or a specific space, including conversations between customers and employees and environmental sounds.

[1123] "Text data" is digital data that has been converted from collected voice data into text information using voice recognition technology.

[1124] A "summary" is digital information that extracts important parts from text data and summarizes them in a concise form.

[1125] "Emotional state" is information that identifies a person's emotions (for example, joy, anger, sadness, etc.) obtained by analyzing text data.

[1126] "Parent" refers to the guardian or guardian of the child of the system user in an educational setting, but in this application example, it refers to the manager or person in charge of the restaurant to which the report is provided.

[1127] "Analysis results" are the information obtained by analyzing the collected text data and emotional state.

[1128] "Report" means a detailed report generated based on the Analysis Results and Emotion Recognition Results.

[1129] "Employee training" means using the collected and analyzed information to provide training and guidance to restaurant staff to improve the quality of their service.

[1130] "Improving customer service" means optimizing service content and delivery methods to improve customer satisfaction based on analyzed data and reports.

[1131] An "alert" is a warning message that is used to quickly notify an administrator of a specific situation based on collected voice data and key information.

[1132] To implement this invention, the following system and processing steps are required: First, a microphone is installed in the restaurant to collect sound data. This microphone collects conversations and environmental sounds in the restaurant in real time.

[1133] The device processes the voice data received from the microphone and converts it into text data. This conversion is performed using voice recognition software. For example, the Google Speech Recognition API can be used. The device then transmits the converted text data to a server using a secure communication protocol (e.g., HTTPS).

[1134] The server stores the received text data in a database and summarizes it using generative AI technology, such as the Hugging Face T5 model. At the same time, an emotion engine implemented on the server analyzes the text data and identifies the customer's emotional state. This emotion engine utilizes natural language processing technology and machine learning algorithms.

[1135] Based on the summarized data and emotion recognition results, the server generates a detailed report, which includes information for employee training and customer service improvement, and is provided to managers via a web portal or mobile application.

[1136] Specific examples

[1137] For example, consider the following conversation taking place in a restaurant:

[1138] Customer: "The roast duck was delicious today. It's just a shame that the service was a little slow."

[1139] This audio is collected and transcribed by speech recognition software as follows:

[1140] "The roast duck was delicious today. It's just a shame that the service was a little late."

[1141] The server receives this text data and summarizes it as follows:

[1142] "A customer who had roast duck today was pleased with the taste of the food, but was unhappy with the slow delivery."

[1143] At the same time, the emotional data analyzed by the emotion engine indicates "satisfaction" and "dissatisfaction," which are incorporated into the report.

[1144] When parents access this report, they can see that "the customer was satisfied with the taste of the food, but was dissatisfied with the slow delivery time." Based on this information, the restaurant can review the way staff respond and the time it takes to provide service.

[1145] Prompt Sentence Examples

[1146] "The roast duck was delicious today. It's just a shame that the service was a little late."

[1147] This system allows restaurants to understand customer satisfaction in real time and quickly improve their responses, making it easy to obtain data that can be used for employee training and service improvement.

[1148] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1149] Step 1:

[1150] The device collects audio data through a microphone installed in the restaurant. The input data includes conversations between customers and employees, as well as the surrounding environmental sounds. The collected audio data is temporarily stored in the device.

[1151] Step 2:

[1152] The device converts the collected voice data into text data using voice recognition software. Specifically, the voice recognition software (e.g., Google Speech Recognition API) analyzes the input voice data and converts it into corresponding text data. The text data is generated within the device.

[1153] Step 3:

[1154] The terminal transmits the converted text data to the server using a secure communication protocol (e.g., HTTPS), where the input is the converted text data and the output is the data transmission to the server.

[1155] Step 4:

[1156] The server stores the received text data in a database. The stored text data is used in subsequent processing steps. The input here is the text data sent from the terminal, and the output is the data stored in the database.

[1157] Step 5:

[1158] The server uses generative AI technology to summarize the stored text data. For example, the Hugging Face T5 model is used in this summarization process. The input is the stored text data, and the output is the summarized text data. Specifically, the important parts of the text data are extracted and summarized in a concise form.

[1159] Step 6:

[1160] The emotion engine installed on the server analyzes the summarized text data and identifies the customer's emotional state. The emotion engine utilizes natural language processing technology and machine learning algorithms. The input is the summarized text data, and the output is the identification result of the emotional state. Specifically, emotions such as joy, anger, and sadness are identified from the text content.

[1161] Step 7:

[1162] The server generates a detailed report based on the summarized data and emotion recognition results. The generated report contains information useful for employee training and improving customer service. The input is the summarized data and emotion recognition results, and the output is a report document.

[1163] Step 8:

[1164] The server provides the generated report to the administrator via a web portal or mobile application. The input here is the generated report, and the output is the report provided to the administrator. The administrator can access this report and check and implement improvements.

[1165] Through these processing steps, the system can collect and analyze customer feedback in real time, providing specific data that can be used to train employees and improve customer service.

[1166] 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.

[1167] 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.

[1168] 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.

[1169] [Fourth embodiment]

[1170] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1171] 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.

[1172] 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).

[1173] 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.

[1174] 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.

[1175] 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).

[1176] 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. 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.

[1177] 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.

[1178] 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.

[1179] 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.

[1180] 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.

[1181] 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.

[1182] 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."

[1183] This invention relates to a system that collects and analyzes children's voices and sounds in the classroom and provides parents with information about their children's growth and daily life. This system consists of multiple means for collecting, converting, analyzing, summarizing, and providing voice data.

[1184] System Configuration

[1185] 1. Terminal (sound collection microphone and processing device installed in the classroom)

[1186] Microphones installed in the classroom collect the children's conversations and comments in real time, and this audio data is automatically converted into text data by voice recognition software installed on the device.

[1187] 2. Server (centralized processing system)

[1188] The system receives and stores text data sent from the device. The server extracts important information from the received data and summarizes the text data using generative AI technology. It also generates a detailed report based on the analysis results and provides it to parents.

[1189] 3. User (Parent)

[1190] Parents can access the generated reports through a dedicated web portal or mobile app to view their child's daily activities and development.

[1191] Program processing flow

[1192] Audio data collection and text conversion

[1193] The devices use microphones installed in the classroom to capture the children's voices. This voice data is then converted into text using speech recognition software. For example, using the Google Speech Recognition API, speech can be converted into text with high accuracy.

[1194] Sending data

[1195] The converted text data is sent to the server using a secure communication protocol (e.g., HTTPS).

[1196] Receiving and storing data

[1197] The server stores the received text data in a database and prepares it for further processing, after which the stored data can be retrieved and used for analysis.

[1198] Generative AI summarization

[1199] The server analyzes the stored text data using generative AI (e.g., Hugging Face's T5 model) to summarize the highlights and important information from the lesson. This summary forms the basis of the generated report.

[1200] Generate and deliver reports

[1201] Based on the summarized data, the server generates reports for parents, detailing their child's engagement and classroom behavior, and provides these reports to parents via a web portal or mobile app.

[1202] Specific examples

[1203] For example, consider the following conversation taking place in a classroom one day:

[1204] Teacher: "We're starting math today. Are you all ready?"

[1205] Child A: "Yes!"

[1206] Child B: "I'll do my best!"

[1207] This voice data is collected by a microphone and converted into text data by the device's voice recognition software:

[1208] "Today we will begin our math lesson. Are you all ready? Yes! Let's do our best!"

[1209] The server receives this text data and summarizes it as follows:

[1210] "Today's lesson was about math. The children participated actively and worked hard in the lesson."

[1211] Based on this summary, the server generates a report for parents and provides it to them via a web portal or mobile app, allowing them to understand their child's learning progress and daily progress.

[1212] The processing flow will be explained below.

[1213] Step 1:

[1214] Device:

[1215] Microphones installed in classrooms collect children's voices and sounds in real time. The microphones are placed in positions suitable for the classroom environment to effectively capture children's conversations and comments.

[1216] Step 2:

[1217] Device:

[1218] The collected voice data is converted into text data using voice recognition software installed on the device. This voice recognition software can convert voice data into text with high accuracy using, for example, the Google Speech Recognition API.

[1219] Step 3:

[1220] Device:

[1221] The converted text data is sent to the server using a secure communication protocol (e.g., HTTPS), which is used to ensure data integrity and security.

[1222] Step 4:

[1223] server:

[1224] The server receives text data sent from the device via the endpoint, processes the received data in real time, and stores it in a database.

[1225] Step 5:

[1226] server:

[1227] Generative AI technology (such as Hugging Face's T5 model) is used to analyze the stored text data, extracting important highlights and key points from the data and summarizing the text data.

[1228] Step 6:

[1229] server:

[1230] The summarized data is used to generate a report for parents, which includes lesson highlights, children's engagement, and any interesting behaviors observed.

[1231] Step 7:

[1232] server:

[1233] The generated reports are uploaded to a web portal or mobile application for parents to log in through a dedicated authentication system and view reports on their child's daily life and development.

[1234] Step 8:

[1235] User (Parent):

[1236] Parents can access the web portal or mobile application and view the reports provided, giving them detailed insight into their child's progress and classroom activities.

[1237] Step 9:

[1238] server:

[1239] Furthermore, the server continuously analyzes collected voice data and detects specific keywords in the text data (e.g., signs of bullying or inappropriate language) in real time. If detected, an alert is generated and relevant parties are notified, allowing for a prompt response.

[1240] Example 1

[1241] 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."

[1242] In conventional educational environments, it has been difficult to record children's comments and activities in detail in the classroom and provide appropriate and timely feedback to parents. Furthermore, converting audio data into text and summarizing it is time-consuming, making it difficult to operate efficiently. Furthermore, there has been a lack of means to quickly detect abnormalities or important information in specific situations and provide appropriate alerts.

[1243] 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.

[1244] In this invention, the server includes means for receiving and storing collected voice data, means for transmitting converted text data using a secure communication protocol, and means for summarizing the converted text data, thereby enabling efficient analysis of the activities and comments of children in the classroom and timely provision of the summary results to parents.

[1245] "Audio data" refers to electrical signals collected in the classroom, including children's voices, speech, and other environmental sounds.

[1246] "Text data" refers to character string information converted from voice data using voice recognition technology.

[1247] A "secure communication protocol" refers to a communication method that includes encryption technology to ensure high security when sending and receiving data. For example, HTTPS is an example of this.

[1248] A "summary" refers to information that extracts important information from collected text data and summarizes it briefly.

[1249] "Report format" refers to a document in which the analysis results are organized visually or in writing and processed into a format that is easy for parents to understand.

[1250] A "generative artificial intelligence model" refers to a machine learning model trained to analyze and summarize text data using natural language processing.

[1251] "Web portal or mobile communication device" means an interface through which parents access generated reports over the internet, including websites and smartphone apps.

[1252] This invention relates to a system that collects and analyzes children's voices and sounds in the classroom and provides parents with information about their children's growth and daily life. This system consists of multiple means for collecting, converting, analyzing, summarizing, and providing voice data.

[1253] System Configuration

[1254] 1. Terminal (sound collection microphone and processing device installed in the classroom)

[1255] The devices are equipped with microphones installed in classrooms that collect children's conversations and comments in real time. This audio data is then automatically converted into text data using the device's built-in voice recognition software. Specifically, the Google Speech Recognition API is used, which provides highly accurate voice recognition and converts the audio collected by the microphones into text.

[1256] Examples:

[1257] The teacher says, "Today we're going to start math class. Are you all ready?" Child A responds, "Yes!" and Child B responds, "I'll do my best!" The audio data of this exchange is captured by a sound-collecting microphone.

[1258] 2. Server (centralized processing system)

[1259] The server receives the text data sent from the device and stores it in a database. The stored text data is analyzed using a generative AI model (e.g., Hugging Face's T5 model) to summarize important information. This summary text becomes the basis for a report and is provided to parents.

[1260] Examples:

[1261] The server receives text data saying, "Today we will begin math class. Are you all ready? Yes! Let's do our best!" and summarizes it as, "In today's class, we learned about math. The children actively participated and worked hard in class."

[1262] 3. User (Parent)

[1263] Parents can access the generated reports via a dedicated web portal or mobile app to track their child's daily activities and progress.

[1264] Audio data collection and text conversion

[1265] The devices use microphones installed in the classroom to capture the children's voices, which are then converted into text using speech recognition software (Google Speech Recognition API), resulting in highly accurate speech-to-text data.

[1266] Sending data

[1267] The converted text data is sent to the server using a secure communication protocol (e.g., HTTPS). The data is encrypted during transmission to ensure security.

[1268] Receiving and storing data

[1269] The server stores the received text data in a database for further processing, and the stored data is indexed for efficient access.

[1270] Generative AI summarization

[1271] The server analyzes the stored text data using a generative AI model (Hugging Face's T5 model) to summarize key information. This summarized text is used as the basis for the report.

[1272] Generate and deliver reports

[1273] Based on the summarized data, the server generates detailed reports for parents, which are made available to them via a web portal and mobile app.

[1274] Prompt Sentence Examples

[1275] "Given the following text as input, generate a lesson summary: 'Today we'll start our math lesson. Are you all ready? Yes! Let's do our best!'"

[1276] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1277] Step 1:

[1278] Audio data collection

[1279] The device uses a microphone installed in the classroom to collect children's conversations and comments in real time. Audio data is input into the microphone, converted into a digital signal, and sent to the device. Specifically, the microphone captures the audio signal and stores it as data on the device.

[1280] Input: Audio signal in the classroom, Output: Digital audio data

[1281] Step 2:

[1282] Converting audio data to text

[1283] The device converts the collected voice data into text data using the Google Speech Recognition API. The voice data is input into the API and the corresponding text is output. Specifically, the voice recognition software analyzes the voice data and generates text data.

[1284] Input: Digital audio data, Output: Text data

[1285] Step 3:

[1286] Sending text data

[1287] The terminal transmits the converted text data to the server using a secure communication protocol (e.g., HTTPS). The text data is encrypted, input into the communication protocol, and transmitted to the server. Specifically, the text data is encrypted using the HTTPS protocol.

[1288] Input: Text data, Output: Encrypted text data (received on the server side)

[1289] Step 4:

[1290] Receiving and storing data

[1291] The server stores the received text data in a database. The encrypted data is decrypted and entered into the database for storage. Specifically, the server decrypts the encrypted data and stores it in the database.

[1292] Input: Encrypted text data, Output: Text data stored in the database

[1293] Step 5:

[1294] Generative AI summarization

[1295] The server analyzes the stored text data using a generative AI model (Hugging Face's T5 model) to summarize important information. The text data is input into the AI ​​model, which outputs a summary text. Specifically, the AI ​​model analyzes the text, extracts key points, and generates a summary.

[1296] Input: Text data stored in a database, Output: Summarized text data

[1297] Step 6:

[1298] Generate and deliver reports

[1299] The server uses the summarized data to create a detailed report for parents. The summarized data is input into a reporting tool, which outputs the report in HTML or PDF format. Specifically, the server embeds the summarized data into a template and generates the report.

[1300] The report is then made accessible to parents through a web portal or mobile app, where parents can access the portal, view the generated report, and download it if desired.

[1301] Input: Summarized text data, Output: Parent-readable report

[1302] (Application example 1)

[1303] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1304] In today's factories, it is difficult to grasp the work situation in real time and manage it efficiently. In particular, there is a lack of means to effectively utilize information obtained from communication between workers and work sounds, which can make it difficult to improve work efficiency or ensure safety. Therefore, there is a need for a system that uses voice data to visualize the work situation in the factory and supports work progress management and identification of areas for improvement.

[1305] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1306] In this invention, the server includes a voice data collection means, a text conversion means, a summarization means, an analysis result generation means, a report output means, and an alert generation means, which allows the work status to be grasped in real time from the voice data, thereby improving work efficiency and ensuring safety.

[1307] A "factory" is a workplace where goods are manufactured or processed, a facility where machines and equipment operate, and workers perform their work.

[1308] "Audio data" is data that represents audio in a digital format, and is information collected using an audio input device such as a microphone.

[1309] "Collection means" refers to devices or software for collecting specific information or data, and in the case of audio data, includes a microphone.

[1310] "Text data" is digital data expressed in characters or sentences, and is converted from voice data using voice recognition technology.

[1311] "Summarization means" refers to technologies or devices for concisely summarizing large amounts of information or text data, including generative AI models.

[1312] A "worker" is a worker who works in a factory, operating machinery or manufacturing goods.

[1313] A "manager" is a person in charge of factory operations and supervising workers, and is responsible for work efficiency and quality control.

[1314] "Analysis tools" are software or devices used to analyze collected data and extract patterns and important information.

[1315] "Report output means" refers to a device or software for displaying or printing analyzed data and summary results in report format.

[1316] An "alert mechanism" is a device or software that generates a warning or notification when a specified condition is met.

[1317] The present invention is a system for real-time understanding and efficient management of work conditions in a factory. A specific embodiment of this system is described below.

[1318] System Configuration

[1319] 1. Terminal (sound collection microphone and processing device installed in the factory)

[1320] The terminal is a device that processes sound-collecting microphones and data installed in factories. The microphones collect workers' conversations and work sounds in real time. The collected voice data is automatically converted into text data by the terminal's voice recognition software. Specifically, the Google Speech Recognition API is used to convert voice into text with high accuracy.

[1321] 2. Server (centralized processing system)

[1322] The server receives and stores text data sent from the device, extracts important information from the received data, summarizes the text data using generative AI technology, and generates a detailed report based on the analysis results, which is provided to operators and administrators.

[1323] 3. Users (operators, administrators)

[1324] Users can access the generated reports via a dedicated web portal or mobile app to check the status of operations within the factory and receive advice on how to improve efficiency.

[1325] Program processing flow

[1326] Audio data collection and text conversion

[1327] The device uses microphones installed in the factory to capture the voices and sounds of workers. This voice data is converted into text using speech recognition software. For example, by using the Google Speech Recognition API, speech can be converted into text with high accuracy.

[1328] Sending data

[1329] The converted text data is sent to the server using a secure communication protocol (e.g., HTTPS).

[1330] Receiving and storing data

[1331] The server stores the received text data in a database and prepares it for further processing, after which the stored data can be retrieved and used for analysis.

[1332] Generative AI summarization

[1333] On the server, the stored text data is analyzed using generative AI (e.g., Hugging Face's T5 model) to summarize the highlights and important information of the work. This summary forms the basis of the generated report.

[1334] Generate and deliver reports

[1335] Based on the summarized data, the server generates reports for operators, including progress reports and recommendations for improving efficiency, which are then made available to operators and managers via a web portal or mobile app.

[1336] Specific examples

[1337] For example, if the following conversation takes place on a work site:

[1338] Worker A: "Next, I'll assemble part number 1234."

[1339] Worker B: "Got it. Tools are ready."

[1340] The collected audio data is transcribed and summarized as follows:

[1341] Summary: Worker A has started assembling part number 1234, and Worker B has finished preparing the tooling.

[1342] Prompt Sentence Examples

[1343] By prefaced the collected text data with the prompt "Summarize today's work:" as the input to the generative AI model, the data can be made suitable for the T5 model.

[1344] Prompt: Summary of today's tasks: Next we will assemble part number 1234. Got it. Tools are ready.

[1345] This approach makes it possible to visualize the work status within the factory and to make operational improvements quickly and effectively.

[1346] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1347] Step 1:

[1348] The terminal collects audio data using microphones installed in the factory. Specifically, it captures the conversations and work sounds of workers in real time. The input data is audio data, and the output is the collected raw audio data.

[1349] Step 2:

[1350] The device converts the collected voice data into text data using speech recognition software. Specifically, it uses the Google Speech Recognition API to convert the voice data into text with high accuracy. The input data is voice data, and the output is the corresponding text data.

[1351] Step 3:

[1352] The terminal transmits the converted text data to the server using a secure communication protocol (e.g., HTTPS). Specifically, the text data is encoded using the HTTPS protocol and transmitted to the server. The input data is the text data, and the output is a transmission completion status to the server.

[1353] Step 4:

[1354] The server saves the received text data in a database and prepares it for subsequent processing. Specifically, it receives the text data and stores it in a database. The input data is the text data, and the output is a status indicating whether it has been saved to the database.

[1355] Step 5:

[1356] The server analyzes the stored text data using a generative AI model (e.g., Hugging Face's T5 model) to extract and summarize important information. Specifically, the text data is fed as input to the T5 model along with the prompt, and a summary is generated. The input data is the stored text data and the prompt, and the output is the summarized text data.

[1357] Step 6:

[1358] The server creates a report for the operator based on the summarized data. Specifically, it formats the summarized data and composes it into a report document. The input data is summarized text data, and the output is a document in report format.

[1359] Step 7:

[1360] The server provides the generated report to the user (operator, administrator) through a web portal or mobile app. Specifically, it uploads the report document to the database of the web portal or mobile app and makes it accessible to the user. The input data is a report-formatted document, and the output is the report provision status that can be accessed by the user.

[1361] 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.

[1362] This invention is a system that collects and analyzes voice data from children in educational settings and provides information to parents based on that data. Furthermore, this system incorporates an emotion engine that recognizes and analyzes children's emotional states. This system consistently performs all processes, from collecting voice data to converting it to text, summarizing it, recognizing emotions, and generating and providing reports.

[1363] System Configuration

[1364] 1. Terminal (sound collection microphone and processing device installed in the classroom)

[1365] Microphones installed in classrooms collect children's conversations and comments in real time. The microphones are positioned to effectively capture the speech of teachers and students. This audio data is processed within the device.

[1366] 2. Voice recognition and data transmission

[1367] The audio data collected in the classroom is converted into text data using speech recognition software installed on the device, such as the Google Speech Recognition API, and then transmitted to a server via a secure communication protocol (such as HTTPS).

[1368] 3. Server (Centralized Processing System)

[1369] The server receives the text data sent from the device and stores it in a database. The stored text data is then summarized using generative AI technology (such as the T5 model of Hugging Face). At the same time, an emotion engine analyzes the text data and recognizes the child's emotions.

[1370] 4. Emotion Engine

[1371] The emotion engine implemented on the server analyzes the converted text data and identifies the user's emotions, such as joy, sadness, anger, etc. This engine utilizes, for example, natural language processing (NLP) techniques and machine learning algorithms.

[1372] 5. Report Generation

[1373] Based on the summary data and emotion recognition results, the server generates a detailed report for parents, which includes highlights of their child's daily learning progress and emotional state, and is provided to parents via a web portal and mobile app.

[1374] Program Processing Details

[1375] Audio data collection and text conversion

[1376] The device collects voice data from within the classroom and converts it into text data using voice recognition software. For example, using voice recognition technology, a voice saying, "Today is math class. Are you all ready?" can be converted into text as, "Today is math class. Are you all ready?"

[1377] Sending data

[1378] Text data from the device is sent to the server using a secure communication protocol, which receives the data and stores it in a database.

[1379] Summarizing text data

[1380] The server uses generative AI technology to summarize the received text data, for example generating an overall summary of the day's lessons, such as "Today we had math class. The children asked questions enthusiastically and achieved many results."

[1381] emotion recognition

[1382] The emotion engine implemented on the server analyzes the text data and identifies the emotional state of the children. For example, it recognizes the emotion of "joy" from the text "I had a lot of fun today."

[1383] Report Generation

[1384] Based on the summarized data and emotion recognition results, a detailed report is generated for parents, such as, "Today we had math class and the children actively participated. They seemed to be having fun."

[1385] Providing reports

[1386] The generated reports are provided to parents via a web portal or mobile application, allowing them to understand their child's growth, learning progress, and emotional state.

[1387] Specific examples

[1388] For example, consider the following conversation taking place during a classroom lesson:

[1389] Teacher: "We're starting math today. Are you all ready?"

[1390] Child A: "Yes!"

[1391] Child B: "I'll do my best!"

[1392] This audio is collected and transcribed by speech recognition software as follows:

[1393] "Today we will begin our math lesson. Are you all ready? Yes! Let's do our best!"

[1394] The server receives this text data and summarizes it as follows:

[1395] "We had a math lesson today. The children came prepared and engaged in the lesson."

[1396] At the same time, the emotional data analyzed by the emotion engine indicates "joy" and "high motivation," which are incorporated into the report.

[1397] When parents access this report, they can see things like, "Today we had math class, and the children were actively engaged. They seemed to be particularly enjoying themselves." This will enable parents to get a detailed understanding of their children's daily learning and emotional changes.

[1398] The processing flow will be explained below.

[1399] Step 1:

[1400] Device:

[1401] Microphones installed in classrooms collect children's conversations and comments in real time. The microphones are placed in the center of the classroom or in key locations to capture all surrounding sounds, allowing the entire situation in the classroom to be understood.

[1402] Step 2:

[1403] Device:

[1404] The collected voice data is converted into text data using voice recognition software (e.g., Google Speech Recognition API) installed on the device. Voice recognition software has the ability to process natural language and can convert voice into text with high accuracy.

[1405] Step 3:

[1406] Device:

[1407] The converted text data is sent to the server using a secure communication protocol (e.g., HTTPS), which is important to maintain the confidentiality and integrity of the data.

[1408] Step 4:

[1409] server:

[1410] The server receives text data sent from the terminal via the endpoint, and stores the received text data in a database for subsequent analysis and processing.

[1411] Step 5:

[1412] server:

[1413] The stored text data is analyzed using generative AI technology (e.g., Hugging Face's T5 model), which extracts important information and generates a summary. The generative AI combines multiple summarization techniques to provide a summary that contains the most useful information.

[1414] Step 6:

[1415] server:

[1416] At the same time, an emotion engine implemented on the server analyzes the text data and recognizes the children's emotional state. The emotion engine uses natural language processing (NLP) technology to extract emotional nuances from the text and identify emotions such as "joy," "sadness," and "anger."

[1417] Step 7:

[1418] server:

[1419] The summarized data and emotion recognition results are used to generate a detailed report for parents, including lesson highlights, children's engagement, and observed emotional states.

[1420] Step 8:

[1421] server:

[1422] The generated reports are uploaded to a web portal or mobile application for parental access, and an authentication system ensures that only parents can access and review the reports.

[1423] Step 9:

[1424] User (Parent):

[1425] Parents can log in to a dedicated web portal or mobile application and view the provided reports, which provide detailed insight into their child's academic progress, engagement and emotional state.

[1426] Step 10:

[1427] server:

[1428] The system detects specific keywords in real time from collected voice and text data, and uses an emotion engine to identify signs of negative emotions or bullying. If any are identified, the server automatically generates an alert and notifies teachers and administrators, enabling a rapid response.

[1429] Example 2

[1430] 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."

[1431] In conventional educational systems, teachers and parents spend a lot of time and effort trying to understand the situation of children in the classroom. Furthermore, there are insufficient means to effectively monitor children's emotional state and learning status, making it difficult for parents to understand their children's daily learning and emotional changes in detail. Therefore, there is a need for a system that can effectively and efficiently collect and analyze classroom voice data and provide information to parents.

[1432] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1433] In this invention, the server includes means for collecting voice data in the classroom, means for converting the collected voice data into text data, means for summarizing the converted text data and generating summary data, means for analyzing the text data and recognizing emotional states, means for generating a report for parents based on the generated summary data and emotional states, and means for providing the generated report to parents. This makes it possible to effectively collect and analyze voice data in the classroom and monitor in detail the learning status and emotional states of children.

[1434] Below are definitions of important words.

[1435] "Means for collecting audio data in the classroom" refers to a series of processes for collecting audio generated in the classroom using a sound collection device such as a microphone.

[1436] The "means for converting collected voice data into text data" refers to a process for converting collected voice data into text data as character information using voice recognition technology.

[1437] "Means for summarizing the converted text data and generating summary data" refers to the process of using generative AI technology to concisely summarize the content of the converted text data and generate summary data.

[1438] The "means for analyzing text data to recognize emotional states" refers to a process of identifying emotions in text data using natural language processing techniques and recognizing the emotional states.

[1439] The "means for generating a report for parents based on the generated summary data and emotional state" is a process of integrating the summary data and the results of the emotion analysis to generate a report in a format that is easy for parents to understand.

[1440] "Means for providing generated reports to parents" refers to the process by which generated reports are sent to parents and made available for viewing through a web portal or mobile application.

[1441] "Means for receiving and storing voice data" refers to the process of receiving voice data and converted text data sent from the terminal to the server and storing them in a database.

[1442] The "means for analyzing and generating summary data and emotional states" refers to a series of processes for analyzing the converted text data and generating summary data and emotional states.

[1443] The "means for detecting specific keywords from collected voice data" is a process for identifying and detecting specific keywords from text data that has been speech-recognized.

[1444] The "means for generating alerts based on keywords" is a process for generating alerts and notifying users when certain conditions are met based on detected keywords.

[1445] The present invention is a system that collects and analyzes speech data from children in educational settings and provides information to parents based on the collected data. In particular, this system performs a comprehensive process from collecting speech data to converting it into text, summarizing it, recognizing emotions, and generating and providing reports. Specific embodiments for implementing this system are described below.

[1446] 1. Collection of audio data

[1447] The device collects audio from within the classroom

[1448] Microphones installed in classrooms collect children's conversations and teacher comments in real time. These microphones are positioned to effectively capture what the teacher and students are saying. For example, if a teacher says, "Today's math class. Are you all ready?", that voice will be collected by the microphones.

[1449] 2. Speech-to-text

[1450] The device converts the voice data into text data.

[1451] Using speech recognition software installed on the device (such as Google Speech Recognition API), the collected voice data is converted into text data in real time. For example, the aforementioned speech "Today is math class. Are you all ready?" is converted directly into text data.

[1452] 3. Data transmission and storage

[1453] The device sends text data to the server

[1454] The generated text data is sent to a server using a secure communication protocol (e.g., HTTPS). This secure communication prevents data leakage and tampering.

[1455] The server receives and stores the text data.

[1456] The server receives the text data sent from the device and stores it in a database. For example, the text "Today is math class. Are you all ready?" is stored in the database as is.

[1457] 4. Summarizing Text Data

[1458] The server summarizes the text data

[1459] The server uses generative AI technology (e.g., Hugging Face's T5 model) to summarize the received text data. For example, a summary of the day's lessons might be generated, such as, "Today we had math class. The children asked questions enthusiastically and achieved many results."

[1460] 5. Emotion recognition

[1461] The server analyzes the text data and recognizes the emotional state.

[1462] The emotion engine installed on the server uses natural language processing technology to analyze the text data and identify the emotional state of the children. For example, the emotion of "joy" can be recognized from the text "I had a lot of fun today."

[1463] 6. Report Generation

[1464] The server generates a report that integrates the summary data and the sentiment results.

[1465] The server generates a detailed report for parents based on the summary data and emotion recognition results, such as, "Today, we had math class, and the children actively participated. They seemed to be having fun."

[1466] 7. Report provision

[1467] The server provides the generated report to the parent.

[1468] The generated reports are provided to parents via a web portal or mobile application, allowing them to gain detailed insight into their child's academic progress and emotional state.

[1469] Examples of prompt statements

[1470] Example 1: "Please transcribe what is said in class. Input speech: 'Today is math class. Are you all ready?'"

[1471] Example 2: "Summarize the following text. Input text: 'Today is math class. Are you all ready? Yes! Let's do our best!'"

[1472] Example 3: "Recognize the emotion in the following text. Input text: 'I had a lot of fun today.'"

[1473] In this way, the system of the present invention allows parents to easily and in detail understand their children's learning situation and emotional state through a series of processes: collecting voice data in the classroom, converting it into text data, summarizing it, recognizing emotions, and generating and providing reports.

[1474] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1475] Processing Steps

[1476] Step 1: Collecting audio data

[1477] The device collects audio from within the classroom

[1478] A microphone installed on each device collects speech in the classroom in real time. This microphone is positioned to effectively capture speech from the teacher and students. For example, the input collected is the voice of a teacher saying, "Today's math class. Are you all ready?" Real-time audio data is generated as the output.

[1479] Step 2: Speech to text

[1480] The device converts the voice data into text data.

[1481] Using speech recognition software installed on the device, the collected voice data is converted into text data in real time. For example, the input voice is "Today is math class. Are you all ready?", and this voice data is converted and output as text data saying "Today is math class. Are you all ready?"

[1482] Step 3: Sending data

[1483] Send text data from the device to the server

[1484] The generated text data is sent to the server using a secure communication protocol (e.g., HTTPS). For example, the text data converted on the terminal, "Today is math class. Are you all ready?", is sent to the server as input. The server receives the text data as output.

[1485] Step 4: Save your data

[1486] The server receives and stores the text data.

[1487] The server receives the text data sent from the terminal and stores it in a database. As input, it receives the text data "Today is math class. Are you all ready?" and stores it in the database as output. The data is stored in the database along with the collection time and sender information.

[1488] Step 5: Summarizing the text data

[1489] The server summarizes the text data

[1490] The server uses generative AI technology (e.g., a text summarization model) to concisely summarize the received text data. The input is the received text data, "Today is math class. Are you all ready?". The output is the summary data, "Today we had math class. The children participated enthusiastically."

[1491] Step 6: Emotion Recognition

[1492] The server analyzes the text data and recognizes the emotional state.

[1493] The emotion engine implemented on the server analyzes the text data using natural language processing technology to identify the children's emotional state. The input is the text data to be analyzed: "I had a lot of fun today." The emotional state "joy" is recognized as the output.

[1494] Step 7: Generate reports

[1495] The server generates a report that integrates the summary data and the sentiment results.

[1496] The server generates a detailed report for parents based on the summary data and emotion recognition results. The input is the summary data "Today we had a math class. The children participated enthusiastically" and the emotion data "joy." The output is a report stating, "Today we had a math class. The children participated enthusiastically. They seemed to be having a particularly good time."

[1497] Step 8: Reporting

[1498] The server provides the generated report to the parent.

[1499] The generated report is provided to parents through a web portal or mobile application. The input is the generated report: "Today we had math class and the children participated actively. They seemed to enjoy it especially." As an output, the report is sent to the parents, who can access and view it.

[1500] Through these steps, this system can efficiently collect and analyze classroom voice data and provide useful information to parents.

[1501] (Application example 2)

[1502] 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."

[1503] Traditional customer feedback systems rely on collecting opinions directly from customers or answering surveys, making it difficult to provide real-time feedback or perform detailed sentiment analysis. As a result, restaurants and food delivery companies continue to struggle to obtain effective data for improving customer satisfaction and employee training. Furthermore, improving employee response and speedy service improvements are difficult challenges.

[1504] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting voice data in the classroom, means for converting the collected voice data into text data, means for summarizing the converted text data, means for analyzing the text data and recognizing the emotional state, and means for providing the summarized data and the recognition result of the emotional state to the guardian. This makes it possible to obtain customer feedback in real time, analyze the emotional state, and quickly improve responses and train employees.

[1505] "Audio data" refers to audio information collected within a restaurant or a specific space, including conversations between customers and employees and environmental sounds.

[1506] "Text data" is digital data that has been converted from collected voice data into text information using voice recognition technology.

[1507] A "summary" is digital information that extracts important parts from text data and summarizes them in a concise form.

[1508] "Emotional state" is information that identifies a person's emotions (for example, joy, anger, sadness, etc.) obtained by analyzing text data.

[1509] "Parent" refers to the guardian or guardian of the child of the system user in an educational setting, but in this application example, it refers to the manager or person in charge of the restaurant to which the report is provided.

[1510] "Analysis results" are the information obtained by analyzing the collected text data and emotional state.

[1511] "Report" means a detailed report generated based on the Analysis Results and Emotion Recognition Results.

[1512] "Employee training" means using the collected and analyzed information to provide training and guidance to restaurant staff to improve the quality of their service.

[1513] "Improving customer service" means optimizing service content and delivery methods to improve customer satisfaction based on analyzed data and reports.

[1514] An "alert" is a warning message that is used to quickly notify an administrator of a specific situation based on collected voice data and key information.

[1515] To implement this invention, the following system and processing steps are required: First, a microphone is installed in the restaurant to collect sound data. This microphone collects conversations and environmental sounds in the restaurant in real time.

[1516] The device processes the voice data received from the microphone and converts it into text data. This conversion is performed using voice recognition software. For example, the Google Speech Recognition API can be used. The device then transmits the converted text data to a server using a secure communication protocol (e.g., HTTPS).

[1517] The server stores the received text data in a database and summarizes it using generative AI technology, such as the Hugging Face T5 model. At the same time, an emotion engine implemented on the server analyzes the text data and identifies the customer's emotional state. This emotion engine utilizes natural language processing technology and machine learning algorithms.

[1518] Based on the summarized data and emotion recognition results, the server generates a detailed report, which includes information for employee training and customer service improvement, and is provided to managers via a web portal or mobile application.

[1519] Specific examples

[1520] For example, consider the following conversation taking place in a restaurant:

[1521] Customer: "The roast duck was delicious today. It's just a shame that the service was a little slow."

[1522] This audio is collected and transcribed by speech recognition software as follows:

[1523] "The roast duck was delicious today. It's just a shame that the service was a little late."

[1524] The server receives this text data and summarizes it as follows:

[1525] "A customer who had roast duck today was pleased with the taste of the food, but was unhappy with the slow delivery."

[1526] At the same time, the emotional data analyzed by the emotion engine indicates "satisfaction" and "dissatisfaction," which are incorporated into the report.

[1527] When parents access this report, they can see that "the customer was satisfied with the taste of the food, but was dissatisfied with the slow delivery time." Based on this information, the restaurant can review the way staff respond and the time it takes to provide service.

[1528] Prompt Sentence Examples

[1529] "The roast duck was delicious today. It's just a shame that the service was a little late."

[1530] This system allows restaurants to understand customer satisfaction in real time and quickly improve their responses, making it easy to obtain data that can be used for employee training and service improvement.

[1531] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1532] Step 1:

[1533] The device collects audio data through a microphone installed in the restaurant. The input data includes conversations between customers and employees, as well as the surrounding environmental sounds. The collected audio data is temporarily stored in the device.

[1534] Step 2:

[1535] The device converts the collected voice data into text data using voice recognition software. Specifically, the voice recognition software (e.g., Google Speech Recognition API) analyzes the input voice data and converts it into corresponding text data. The text data is generated within the device.

[1536] Step 3:

[1537] The terminal transmits the converted text data to the server using a secure communication protocol (e.g., HTTPS), where the input is the converted text data and the output is the data transmission to the server.

[1538] Step 4:

[1539] The server stores the received text data in a database. The stored text data is used in subsequent processing steps. The input here is the text data sent from the terminal, and the output is the data stored in the database.

[1540] Step 5:

[1541] The server uses generative AI technology to summarize the stored text data. For example, the Hugging Face T5 model is used in this summarization process. The input is the stored text data, and the output is the summarized text data. Specifically, the important parts of the text data are extracted and summarized in a concise form.

[1542] Step 6:

[1543] The emotion engine installed on the server analyzes the summarized text data and identifies the customer's emotional state. The emotion engine utilizes natural language processing technology and machine learning algorithms. The input is the summarized text data, and the output is the identification result of the emotional state. Specifically, emotions such as joy, anger, and sadness are identified from the text content.

[1544] Step 7:

[1545] The server generates a detailed report based on the summarized data and emotion recognition results. The generated report contains information useful for employee training and improving customer service. The input is the summarized data and emotion recognition results, and the output is a report document.

[1546] Step 8:

[1547] The server provides the generated report to the administrator via a web portal or mobile application. The input here is the generated report, and the output is the report provided to the administrator. The administrator can access this report and check and implement improvements.

[1548] Through these processing steps, the system can collect and analyze customer feedback in real time, providing specific data that can be used to train employees and improve customer service.

[1549] 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.

[1550] 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.

[1551] 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.

[1552] 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.

[1553] 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.

[1554] 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.

[1555] 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).

[1556] 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.

[1557] 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."

[1558] 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.

[1559] 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).

[1560] 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.

[1561] 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.

[1562] 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.

[1563] 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.

[1564] 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.

[1565] 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.

[1566] 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.

[1567] 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.

[1568] 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.

[1569] 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.

[1570] The following is further disclosed regarding the above embodiment.

[1571] (Claim 1)

[1572] A means of collecting classroom audio data;

[1573] A means for converting the collected voice data into text data;

[1574] means for summarizing the converted text data;

[1575] a means of providing summarized data to parents;

[1576] A system including:

[1577] (Claim 2)

[1578] means for receiving and storing the collected voice data;

[1579] means for analyzing the converted text data and generating an analysis result;

[1580] a means for outputting the generated analysis results in a report format;

[1581] 10. The system of claim 1, further comprising:

[1582] (Claim 3)

[1583] Detect specific keywords from the collected voice data,

[1584] means for generating alerts based on keywords;

[1585] 10. The system of claim 1.

[1586] "Example 1"

[1587] (Claim 1)

[1588] A means of collecting classroom audio data;

[1589] A means for converting the collected voice data into text data;

[1590] means for transmitting the converted text data using a secure communication protocol;

[1591] means for summarizing the converted text data;

[1592] a means of providing summarized data in the form of a report;

[1593] A system including:

[1594] (Claim 2)

[1595] means for receiving and storing the collected voice data;

[1596] means for analyzing the converted text data and summarizing the analysis results using a generative artificial intelligence model;

[1597] means for storing the generated summary results and outputting a report for parents;

[1598] 10. The system of claim 1, further comprising:

[1599] (Claim 3)

[1600] Detect specific keywords from the collected voice data,

[1601] a means for generating alerts based on keywords;

[1602] means for providing the report via a web portal or a mobile communication device;

[1603] 10. The system of claim 1.

[1604] "Application Example 1"

[1605] (Claim 1)

[1606] A means for collecting voice data within the factory;

[1607] A means for converting the collected voice data into text data;

[1608] means for summarizing the converted text data;

[1609] A means of providing summarized data to workers and managers;

[1610] A system including:

[1611] (Claim 2)

[1612] means for receiving and storing the collected voice data;

[1613] means for analyzing the converted text data and generating an analysis result;

[1614] a means for outputting the generated analysis results in a report format;

[1615] 10. The system of claim 1, further comprising:

[1616] (Claim 3)

[1617] Detect specific keywords from the collected voice data,

[1618] means for generating alerts based on keywords;

[1619] 10. The system of claim 1.

[1620] "Example 2: Combining Emotion Engines"

[1621] (Claim 1)

[1622] A means of collecting classroom audio data;

[1623] A means for converting the collected voice data into text data;

[1624] means for summarizing the converted text data to generate summary data;

[1625] means for analyzing text data to recognize emotional states;

[1626] a means for generating a report for the parent based on the generated summary data and emotional state;

[1627] a means for providing the generated report to the parent;

[1628] A system including:

[1629] (Claim 2)

[1630] means for receiving and storing the collected voice data;

[1631] means for analyzing the converted text data and generating summary data and emotional states;

[1632] means for outputting the generated emotional state in a report format;

[1633] 10. The system of claim 1, further comprising:

[1634] (Claim 3)

[1635] Detect specific keywords from the collected voice data,

[1636] a means for generating alerts based on keywords;

[1637] 10. The system of claim 1, comprising:

[1638] "Application example 2 when combining emotion engines"

[1639] (Claim 1)

[1640] A means of collecting classroom audio data;

[1641] A means for converting the collected voice data into text data;

[1642] means for summarizing the converted text data;

[1643] means for analyzing text data and recognizing emotional states;

[1644] a means for providing the parent with summarized data and emotional state recognition results;

[1645] A system including:

[1646] (Claim 2)

[1647] means for receiving and storing the collected voice data;

[1648] means for analyzing the converted text data and generating an analysis result;

[1649] a means for outputting the generated analysis results in a report format;

[1650] a means for providing the generated report to the parent;

[1651] 10. The system of claim 1, further comprising:

[1652] (Claim 3)

[1653] Detect specific keywords from the collected voice data,

[1654] means for generating alerts based on keywords;

[1655] It includes a means to generate reports for employee training and customer service improvement based on the generated analysis results and emotion recognition results.

[1656] 10. The system of claim 1. [Explanation of symbols]

[1657] 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 of collecting classroom audio data; A means for converting the collected voice data into text data; means for summarizing the converted text data; a means of providing summarized data to parents; A system including:

2. means for receiving and storing the collected voice data; means for analyzing the converted text data and generating an analysis result; a means for outputting the generated analysis results in a report format; The system of claim 1 further comprising:

3. Detect specific keywords from the collected voice data, means for generating alerts based on keywords; The system of claim 1 .

Images